Upload folder using huggingface_hub

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- princeton-nlp/llama3-ultrafeedback-armorm
+model-index:
+- name: llama-3-8b-instruct-gapo-v2-jaccard_score-beta10-gamma0.3-lr1.0e-6-he_scale-rerun
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-3-8b-instruct-gapo-v2-jaccard_score-beta10-gamma0.3-lr1.0e-6-he_scale-rerun
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the princeton-nlp/llama3-ultrafeedback-armorm dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3838
+- Rewards/chosen: -14.6828
+- Rewards/rejected: -19.8328
+- Rewards/accuracies: 0.8232
+- Rewards/margins: 5.1500
+- Logps/rejected: -1.9833
+- Logps/chosen: -1.4683
+- Logits/rejected: -1.3238
+- Logits/chosen: -1.3154
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 1.353         | 0.8550 | 400  | 1.3838          | -14.6828       | -19.8328         | 0.8232             | 5.1500          | -1.9833        | -1.4683      | -1.3238         | -1.3154       |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.2.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 0.9982631930527722,
+    "eval_logits/chosen": -1.319807767868042,
+    "eval_logits/rejected": -1.328245759010315,
+    "eval_logps/chosen": -1.4769620895385742,
+    "eval_logps/rejected": -1.9949750900268555,
+    "eval_loss": 1.3845703601837158,
+    "eval_rewards/accuracies": 0.8231707215309143,
+    "eval_rewards/chosen": -14.769620895385742,
+    "eval_rewards/margins": 5.180131435394287,
+    "eval_rewards/rejected": -19.949752807617188,
+    "eval_runtime": 87.8371,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 22.325,
+    "eval_steps_per_second": 1.4,
+    "total_flos": 0.0,
+    "train_loss": 1.957533876696797,
+    "train_runtime": 11480.123,
+    "train_samples": 59876,
+    "train_samples_per_second": 5.216,
+    "train_steps_per_second": 0.041
+}

checkpoint-467/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-467/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

checkpoint-467/global_step467/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e7f3fa357528a9395e826cd10a8b39074f67354258797eaa26f658679e9900
+size 24090789950

checkpoint-467/global_step467/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ad690ba6ccb1c41937ac8bb7f067f40da93ef6aef3833e04776f5515c7a281
+size 24090789950

checkpoint-467/global_step467/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef376895d5bec9ae31478db03d04d06fd1638017a127cd97102e7f513bfc6d7
+size 24090789950

checkpoint-467/global_step467/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c5651e321ed408ab1db4b96a0b0d4b9c060495e17e71bfd9bbda8f4574c2e7
+size 24090789950

checkpoint-467/global_step467/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca97cd3bc44aef4837bbcab5ce33ea35cf7a96cb568bae18f29db404b0b0a5b
+size 150693

checkpoint-467/global_step467/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed747b44ace193a514249241429f7027bb1960e8c41207993750102c24811702
+size 150693

checkpoint-467/global_step467/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3dc6efc7836ac52a44c13fe9e807b9f98334c8ad10c9016b42415fe4ac73393
+size 150693

checkpoint-467/global_step467/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83932751abcf5800e0a3e129b2800fba699e4bcece54d9b7be9726cc7360c05
+size 150693

checkpoint-467/latest

@@ -0,0 +1 @@
+global_step467

checkpoint-467/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4d02f89ee587dfa885a25c30e44d063677e16f453c463a54bafc90ea1cdf9a
+size 4976698672

checkpoint-467/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d38a3529eaf96c27321ef1669f21a739743104249072a85e8b5b4557ee5407
+size 4999802720

checkpoint-467/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c070b7aea29214412ec41afb6e3bbfa6bba53ef0d5487f3fc17ff630de9237
+size 4915916176

checkpoint-467/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcf7552dca049a441a7bd173f737520ca7ceadf16ba931b5deab4f65cac276a
+size 1168138808

checkpoint-467/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-467/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe0d720c4c75a6a04213fa3b64bacbe794718a53e2b56ebb67a1a795014dfad
+size 15024

checkpoint-467/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72452d3138d0ca2ff89429e3294a834ae7a68e8596fc757735ca56ae52509d57
+size 15024

checkpoint-467/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36e306fb8ebcf53a167bfd6c9af74db410a269ada1e619e3e816f5269543b9d
+size 15024

checkpoint-467/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb47ce0c6f815a6f8302b0e3819b4c2315ca71dae3138d97fdceb765cdd0a039
+size 15024

checkpoint-467/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9102e77a2cc8c7ee284edfad042168479d3805191c01ddc8892608349dec22
+size 1064

checkpoint-467/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-467/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-467/trainer_state.json

@@ -0,0 +1,1444 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9982631930527722,
+  "eval_steps": 400,
+  "global_step": 467,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01068804275217101,
+      "grad_norm": 51.9219704867916,
+      "learning_rate": 1.0638297872340425e-07,
+      "logits/chosen": -1.0090945959091187,
+      "logits/rejected": -0.9798948168754578,
+      "logps/chosen": -0.2737821936607361,
+      "logps/rejected": -0.2714875340461731,
+      "loss": 2.9624,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -2.7378220558166504,
+      "rewards/margins": -0.02294684387743473,
+      "rewards/rejected": -2.7148749828338623,
+      "step": 5
+    },
+    {
+      "epoch": 0.02137608550434202,
+      "grad_norm": 44.19632899404353,
+      "learning_rate": 2.127659574468085e-07,
+      "logits/chosen": -1.0468437671661377,
+      "logits/rejected": -0.9794818758964539,
+      "logps/chosen": -0.2943094074726105,
+      "logps/rejected": -0.2997472286224365,
+      "loss": 3.2285,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -2.943093776702881,
+      "rewards/margins": 0.054378531873226166,
+      "rewards/rejected": -2.9974725246429443,
+      "step": 10
+    },
+    {
+      "epoch": 0.03206412825651302,
+      "grad_norm": 51.06549177485018,
+      "learning_rate": 3.1914893617021275e-07,
+      "logits/chosen": -0.9672244191169739,
+      "logits/rejected": -0.9858204126358032,
+      "logps/chosen": -0.2640294134616852,
+      "logps/rejected": -0.30089089274406433,
+      "loss": 3.2949,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -2.640293836593628,
+      "rewards/margins": 0.3686152398586273,
+      "rewards/rejected": -3.008909225463867,
+      "step": 15
+    },
+    {
+      "epoch": 0.04275217100868404,
+      "grad_norm": 74.83681858154256,
+      "learning_rate": 4.25531914893617e-07,
+      "logits/chosen": -0.9596344232559204,
+      "logits/rejected": -0.933236300945282,
+      "logps/chosen": -0.2778920531272888,
+      "logps/rejected": -0.29140567779541016,
+      "loss": 3.0107,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -2.7789206504821777,
+      "rewards/margins": 0.13513638079166412,
+      "rewards/rejected": -2.9140570163726807,
+      "step": 20
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 53.488412779583946,
+      "learning_rate": 5.319148936170212e-07,
+      "logits/chosen": -1.0089600086212158,
+      "logits/rejected": -0.9799430966377258,
+      "logps/chosen": -0.27165931463241577,
+      "logps/rejected": -0.2783976197242737,
+      "loss": 3.2847,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -2.7165932655334473,
+      "rewards/margins": 0.06738300621509552,
+      "rewards/rejected": -2.7839760780334473,
+      "step": 25
+    },
+    {
+      "epoch": 0.06412825651302605,
+      "grad_norm": 49.467165701102346,
+      "learning_rate": 6.382978723404255e-07,
+      "logits/chosen": -0.9974703788757324,
+      "logits/rejected": -0.952576756477356,
+      "logps/chosen": -0.2734770178794861,
+      "logps/rejected": -0.27953463792800903,
+      "loss": 3.0768,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -2.734769821166992,
+      "rewards/margins": 0.06057664006948471,
+      "rewards/rejected": -2.795346736907959,
+      "step": 30
+    },
+    {
+      "epoch": 0.07481629926519706,
+      "grad_norm": 62.938723083055315,
+      "learning_rate": 7.446808510638297e-07,
+      "logits/chosen": -1.055626630783081,
+      "logits/rejected": -0.9798073768615723,
+      "logps/chosen": -0.29555463790893555,
+      "logps/rejected": -0.3219638466835022,
+      "loss": 3.0274,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -2.9555466175079346,
+      "rewards/margins": 0.26409202814102173,
+      "rewards/rejected": -3.2196388244628906,
+      "step": 35
+    },
+    {
+      "epoch": 0.08550434201736808,
+      "grad_norm": 60.78411434363956,
+      "learning_rate": 8.51063829787234e-07,
+      "logits/chosen": -0.9993880987167358,
+      "logits/rejected": -0.9557031393051147,
+      "logps/chosen": -0.2811431288719177,
+      "logps/rejected": -0.3281245231628418,
+      "loss": 2.953,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -2.8114311695098877,
+      "rewards/margins": 0.469813734292984,
+      "rewards/rejected": -3.281245470046997,
+      "step": 40
+    },
+    {
+      "epoch": 0.09619238476953908,
+      "grad_norm": 37.98461592095763,
+      "learning_rate": 9.574468085106384e-07,
+      "logits/chosen": -1.0411790609359741,
+      "logits/rejected": -0.9992967844009399,
+      "logps/chosen": -0.30747953057289124,
+      "logps/rejected": -0.3615890145301819,
+      "loss": 3.0174,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -3.0747952461242676,
+      "rewards/margins": 0.5410946607589722,
+      "rewards/rejected": -3.6158900260925293,
+      "step": 45
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 117.4214402638359,
+      "learning_rate": 9.998741174712533e-07,
+      "logits/chosen": -1.0310847759246826,
+      "logits/rejected": -0.9821462631225586,
+      "logps/chosen": -0.31808674335479736,
+      "logps/rejected": -0.3582245707511902,
+      "loss": 3.0624,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -3.1808676719665527,
+      "rewards/margins": 0.4013778567314148,
+      "rewards/rejected": -3.5822455883026123,
+      "step": 50
+    },
+    {
+      "epoch": 0.11756847027388109,
+      "grad_norm": 170.90804995599427,
+      "learning_rate": 9.991050648838675e-07,
+      "logits/chosen": -1.0685880184173584,
+      "logits/rejected": -1.0338609218597412,
+      "logps/chosen": -0.310200572013855,
+      "logps/rejected": -0.37700629234313965,
+      "loss": 2.7117,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -3.10200572013855,
+      "rewards/margins": 0.6680572628974915,
+      "rewards/rejected": -3.770063877105713,
+      "step": 55
+    },
+    {
+      "epoch": 0.1282565130260521,
+      "grad_norm": 134.13615502558548,
+      "learning_rate": 9.97637968732563e-07,
+      "logits/chosen": -1.109356164932251,
+      "logits/rejected": -1.0756348371505737,
+      "logps/chosen": -0.37418466806411743,
+      "logps/rejected": -0.3752634525299072,
+      "loss": 2.9555,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -3.7418465614318848,
+      "rewards/margins": 0.010788190178573132,
+      "rewards/rejected": -3.7526347637176514,
+      "step": 60
+    },
+    {
+      "epoch": 0.13894455577822312,
+      "grad_norm": 62.988442946717754,
+      "learning_rate": 9.954748808839674e-07,
+      "logits/chosen": -1.0235508680343628,
+      "logits/rejected": -0.9943636059761047,
+      "logps/chosen": -0.3913114666938782,
+      "logps/rejected": -0.4661448001861572,
+      "loss": 2.8601,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -3.9131150245666504,
+      "rewards/margins": 0.7483334541320801,
+      "rewards/rejected": -4.6614484786987305,
+      "step": 65
+    },
+    {
+      "epoch": 0.14963259853039412,
+      "grad_norm": 43.4379227945051,
+      "learning_rate": 9.926188266120295e-07,
+      "logits/chosen": -1.0352689027786255,
+      "logits/rejected": -1.0102473497390747,
+      "logps/chosen": -0.353306382894516,
+      "logps/rejected": -0.4401523172855377,
+      "loss": 2.8751,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -3.5330634117126465,
+      "rewards/margins": 0.8684590458869934,
+      "rewards/rejected": -4.401522636413574,
+      "step": 70
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 83.11781382244568,
+      "learning_rate": 9.890738003669027e-07,
+      "logits/chosen": -0.996098518371582,
+      "logits/rejected": -0.9254637956619263,
+      "logps/chosen": -0.34757333993911743,
+      "logps/rejected": -0.413855642080307,
+      "loss": 2.8749,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -3.475733518600464,
+      "rewards/margins": 0.6628231406211853,
+      "rewards/rejected": -4.138556480407715,
+      "step": 75
+    },
+    {
+      "epoch": 0.17100868403473615,
+      "grad_norm": 51.202568906876266,
+      "learning_rate": 9.848447601883433e-07,
+      "logits/chosen": -0.9647027850151062,
+      "logits/rejected": -0.950391411781311,
+      "logps/chosen": -0.3513404130935669,
+      "logps/rejected": -0.46568623185157776,
+      "loss": 2.6436,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -3.513404369354248,
+      "rewards/margins": 1.1434578895568848,
+      "rewards/rejected": -4.656861782073975,
+      "step": 80
+    },
+    {
+      "epoch": 0.18169672678690715,
+      "grad_norm": 70.97672847293224,
+      "learning_rate": 9.799376207714444e-07,
+      "logits/chosen": -0.9941811561584473,
+      "logits/rejected": -0.9714711308479309,
+      "logps/chosen": -0.3401820659637451,
+      "logps/rejected": -0.40950268507003784,
+      "loss": 2.6659,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -3.401820659637451,
+      "rewards/margins": 0.6932064890861511,
+      "rewards/rejected": -4.095026969909668,
+      "step": 85
+    },
+    {
+      "epoch": 0.19238476953907815,
+      "grad_norm": 152.3633388876466,
+      "learning_rate": 9.743592451943998e-07,
+      "logits/chosen": -1.0390641689300537,
+      "logits/rejected": -1.002964735031128,
+      "logps/chosen": -0.4347335696220398,
+      "logps/rejected": -0.5336366891860962,
+      "loss": 2.8761,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -4.347336769104004,
+      "rewards/margins": 0.9890311360359192,
+      "rewards/rejected": -5.336367130279541,
+      "step": 90
+    },
+    {
+      "epoch": 0.20307281229124916,
+      "grad_norm": 48.723602234021136,
+      "learning_rate": 9.681174353198686e-07,
+      "logits/chosen": -1.112140417098999,
+      "logits/rejected": -1.0275517702102661,
+      "logps/chosen": -0.4523504674434662,
+      "logps/rejected": -0.5077233910560608,
+      "loss": 2.653,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -4.523504734039307,
+      "rewards/margins": 0.5537286996841431,
+      "rewards/rejected": -5.077233791351318,
+      "step": 95
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 67.84801804788158,
+      "learning_rate": 9.612209208833646e-07,
+      "logits/chosen": -1.000867486000061,
+      "logits/rejected": -0.9747543334960938,
+      "logps/chosen": -0.4416694641113281,
+      "logps/rejected": -0.5102046728134155,
+      "loss": 2.8531,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -4.4166951179504395,
+      "rewards/margins": 0.6853527426719666,
+      "rewards/rejected": -5.102047920227051,
+      "step": 100
+    },
+    {
+      "epoch": 0.22444889779559118,
+      "grad_norm": 73.17857628661973,
+      "learning_rate": 9.536793472839324e-07,
+      "logits/chosen": -1.0074902772903442,
+      "logits/rejected": -0.9537180662155151,
+      "logps/chosen": -0.40940943360328674,
+      "logps/rejected": -0.5277153849601746,
+      "loss": 2.9423,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -4.094094276428223,
+      "rewards/margins": 1.1830594539642334,
+      "rewards/rejected": -5.277153968811035,
+      "step": 105
+    },
+    {
+      "epoch": 0.23513694054776219,
+      "grad_norm": 58.188153286610884,
+      "learning_rate": 9.455032620941839e-07,
+      "logits/chosen": -0.9680612683296204,
+      "logits/rejected": -0.9060274362564087,
+      "logps/chosen": -0.4779647886753082,
+      "logps/rejected": -0.6175049543380737,
+      "loss": 2.7583,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -4.7796478271484375,
+      "rewards/margins": 1.3954023122787476,
+      "rewards/rejected": -6.175050258636475,
+      "step": 110
+    },
+    {
+      "epoch": 0.2458249832999332,
+      "grad_norm": 55.673813232077116,
+      "learning_rate": 9.367041003085648e-07,
+      "logits/chosen": -1.0318225622177124,
+      "logits/rejected": -0.9690453410148621,
+      "logps/chosen": -0.5004153251647949,
+      "logps/rejected": -0.564782440662384,
+      "loss": 2.6268,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": -5.004153251647949,
+      "rewards/margins": 0.643670916557312,
+      "rewards/rejected": -5.647824287414551,
+      "step": 115
+    },
+    {
+      "epoch": 0.2565130260521042,
+      "grad_norm": 93.24909470705533,
+      "learning_rate": 9.272941683504808e-07,
+      "logits/chosen": -0.9859496355056763,
+      "logits/rejected": -0.892734169960022,
+      "logps/chosen": -0.5100774168968201,
+      "logps/rejected": -0.7314041256904602,
+      "loss": 2.6175,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -5.100773811340332,
+      "rewards/margins": 2.213266372680664,
+      "rewards/rejected": -7.314040184020996,
+      "step": 120
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 62.49186315009438,
+      "learning_rate": 9.172866268606513e-07,
+      "logits/chosen": -1.0501500368118286,
+      "logits/rejected": -1.0046356916427612,
+      "logps/chosen": -0.568703293800354,
+      "logps/rejected": -0.6640041470527649,
+      "loss": 2.4292,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -5.687033176422119,
+      "rewards/margins": 0.9530088305473328,
+      "rewards/rejected": -6.640041351318359,
+      "step": 125
+    },
+    {
+      "epoch": 0.27788911155644624,
+      "grad_norm": 94.37106722966159,
+      "learning_rate": 9.066954722907638e-07,
+      "logits/chosen": -1.0626311302185059,
+      "logits/rejected": -1.0533256530761719,
+      "logps/chosen": -0.5523235201835632,
+      "logps/rejected": -0.8242877125740051,
+      "loss": 2.3709,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -5.5232343673706055,
+      "rewards/margins": 2.719642162322998,
+      "rewards/rejected": -8.242877006530762,
+      "step": 130
+    },
+    {
+      "epoch": 0.28857715430861725,
+      "grad_norm": 78.14100135139738,
+      "learning_rate": 8.955355173281707e-07,
+      "logits/chosen": -1.0362498760223389,
+      "logits/rejected": -0.9840585589408875,
+      "logps/chosen": -0.5984936952590942,
+      "logps/rejected": -0.7128698825836182,
+      "loss": 2.355,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -5.984936714172363,
+      "rewards/margins": 1.1437618732452393,
+      "rewards/rejected": -7.128698825836182,
+      "step": 135
+    },
+    {
+      "epoch": 0.29926519706078825,
+      "grad_norm": 80.07356057826689,
+      "learning_rate": 8.838223701790055e-07,
+      "logits/chosen": -1.0999033451080322,
+      "logits/rejected": -1.0737004280090332,
+      "logps/chosen": -0.719946026802063,
+      "logps/rejected": -0.8201924562454224,
+      "loss": 2.4387,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -7.199460029602051,
+      "rewards/margins": 1.0024646520614624,
+      "rewards/rejected": -8.201925277709961,
+      "step": 140
+    },
+    {
+      "epoch": 0.30995323981295925,
+      "grad_norm": 90.63467648251373,
+      "learning_rate": 8.71572412738697e-07,
+      "logits/chosen": -1.0016281604766846,
+      "logits/rejected": -0.9718937873840332,
+      "logps/chosen": -0.6957625150680542,
+      "logps/rejected": -0.89495849609375,
+      "loss": 2.3174,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -6.957624912261963,
+      "rewards/margins": 1.991959810256958,
+      "rewards/rejected": -8.9495849609375,
+      "step": 145
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 73.56126608282666,
+      "learning_rate": 8.588027776804058e-07,
+      "logits/chosen": -1.0221322774887085,
+      "logits/rejected": -0.9965847134590149,
+      "logps/chosen": -0.7128551006317139,
+      "logps/rejected": -0.896537184715271,
+      "loss": 2.3663,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -7.128551483154297,
+      "rewards/margins": 1.8368213176727295,
+      "rewards/rejected": -8.965372085571289,
+      "step": 150
+    },
+    {
+      "epoch": 0.33132932531730125,
+      "grad_norm": 81.6804828395219,
+      "learning_rate": 8.455313244934324e-07,
+      "logits/chosen": -1.016101598739624,
+      "logits/rejected": -0.9916119575500488,
+      "logps/chosen": -0.7570836544036865,
+      "logps/rejected": -1.0055702924728394,
+      "loss": 2.1714,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -7.570836544036865,
+      "rewards/margins": 2.4848668575286865,
+      "rewards/rejected": -10.055703163146973,
+      "step": 155
+    },
+    {
+      "epoch": 0.3420173680694723,
+      "grad_norm": 99.4901399654396,
+      "learning_rate": 8.317766145051057e-07,
+      "logits/chosen": -1.0358034372329712,
+      "logits/rejected": -1.015195608139038,
+      "logps/chosen": -0.8496212959289551,
+      "logps/rejected": -1.2102388143539429,
+      "loss": 2.1439,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -8.49621295928955,
+      "rewards/margins": 3.606174945831299,
+      "rewards/rejected": -12.102388381958008,
+      "step": 160
+    },
+    {
+      "epoch": 0.3527054108216433,
+      "grad_norm": 70.81537442159531,
+      "learning_rate": 8.175578849210894e-07,
+      "logits/chosen": -1.025247573852539,
+      "logits/rejected": -0.9949723482131958,
+      "logps/chosen": -0.9383013844490051,
+      "logps/rejected": -1.2926217317581177,
+      "loss": 2.1748,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -9.383014678955078,
+      "rewards/margins": 3.5432026386260986,
+      "rewards/rejected": -12.926218032836914,
+      "step": 165
+    },
+    {
+      "epoch": 0.3633934535738143,
+      "grad_norm": 87.64514196797495,
+      "learning_rate": 8.028950219204099e-07,
+      "logits/chosen": -1.0285688638687134,
+      "logits/rejected": -1.003366470336914,
+      "logps/chosen": -0.8483174443244934,
+      "logps/rejected": -1.227891445159912,
+      "loss": 1.9588,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -8.483174324035645,
+      "rewards/margins": 3.7957394123077393,
+      "rewards/rejected": -12.278913497924805,
+      "step": 170
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 112.86629209538306,
+      "learning_rate": 7.878085328428368e-07,
+      "logits/chosen": -1.0398296117782593,
+      "logits/rejected": -0.9856590032577515,
+      "logps/chosen": -0.975140392780304,
+      "logps/rejected": -1.1828876733779907,
+      "loss": 1.8418,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -9.75140380859375,
+      "rewards/margins": 2.07747220993042,
+      "rewards/rejected": -11.828875541687012,
+      "step": 175
+    },
+    {
+      "epoch": 0.3847695390781563,
+      "grad_norm": 78.96808907768161,
+      "learning_rate": 7.723195175075135e-07,
+      "logits/chosen": -0.9896231889724731,
+      "logits/rejected": -0.9649994969367981,
+      "logps/chosen": -0.9527977108955383,
+      "logps/rejected": -1.2905272245407104,
+      "loss": 1.8762,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -9.527976036071777,
+      "rewards/margins": 3.377295732498169,
+      "rewards/rejected": -12.9052734375,
+      "step": 180
+    },
+    {
+      "epoch": 0.3954575818303273,
+      "grad_norm": 108.85803981934055,
+      "learning_rate": 7.564496387029531e-07,
+      "logits/chosen": -1.0348621606826782,
+      "logits/rejected": -0.9732630848884583,
+      "logps/chosen": -1.0269982814788818,
+      "logps/rejected": -1.4066517353057861,
+      "loss": 1.7941,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -10.269983291625977,
+      "rewards/margins": 3.7965340614318848,
+      "rewards/rejected": -14.06651782989502,
+      "step": 185
+    },
+    {
+      "epoch": 0.4061456245824983,
+      "grad_norm": 88.17963395634109,
+      "learning_rate": 7.402210918896689e-07,
+      "logits/chosen": -1.0109108686447144,
+      "logits/rejected": -1.016540765762329,
+      "logps/chosen": -1.1914116144180298,
+      "logps/rejected": -1.6932926177978516,
+      "loss": 1.7838,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -11.914116859436035,
+      "rewards/margins": 5.018809795379639,
+      "rewards/rejected": -16.932926177978516,
+      "step": 190
+    },
+    {
+      "epoch": 0.4168336673346693,
+      "grad_norm": 93.26710505616924,
+      "learning_rate": 7.236565741578162e-07,
+      "logits/chosen": -0.9588305354118347,
+      "logits/rejected": -0.9351094961166382,
+      "logps/chosen": -1.1738094091415405,
+      "logps/rejected": -1.507836103439331,
+      "loss": 1.7312,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -11.738093376159668,
+      "rewards/margins": 3.340266704559326,
+      "rewards/rejected": -15.078363418579102,
+      "step": 195
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 148.12833430588864,
+      "learning_rate": 7.067792524832603e-07,
+      "logits/chosen": -0.962164044380188,
+      "logits/rejected": -0.946324348449707,
+      "logps/chosen": -1.190048098564148,
+      "logps/rejected": -1.5737119913101196,
+      "loss": 1.8488,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -11.900480270385742,
+      "rewards/margins": 3.8366382122039795,
+      "rewards/rejected": -15.737119674682617,
+      "step": 200
+    },
+    {
+      "epoch": 0.43820975283901137,
+      "grad_norm": 88.33539547998033,
+      "learning_rate": 6.896127313264642e-07,
+      "logits/chosen": -0.9857925176620483,
+      "logits/rejected": -0.9326913952827454,
+      "logps/chosen": -1.2696114778518677,
+      "logps/rejected": -1.6608413457870483,
+      "loss": 1.844,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -12.696113586425781,
+      "rewards/margins": 3.9123005867004395,
+      "rewards/rejected": -16.608415603637695,
+      "step": 205
+    },
+    {
+      "epoch": 0.44889779559118237,
+      "grad_norm": 96.6188335214616,
+      "learning_rate": 6.721810196195174e-07,
+      "logits/chosen": -1.0050965547561646,
+      "logits/rejected": -0.9934624433517456,
+      "logps/chosen": -1.2922513484954834,
+      "logps/rejected": -1.710461974143982,
+      "loss": 1.6898,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -12.922513961791992,
+      "rewards/margins": 4.182106018066406,
+      "rewards/rejected": -17.10462188720703,
+      "step": 210
+    },
+    {
+      "epoch": 0.45958583834335337,
+      "grad_norm": 96.68880124766956,
+      "learning_rate": 6.545084971874736e-07,
+      "logits/chosen": -0.9563829302787781,
+      "logits/rejected": -0.9366313815116882,
+      "logps/chosen": -1.364743947982788,
+      "logps/rejected": -1.8573719263076782,
+      "loss": 1.5133,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -13.647438049316406,
+      "rewards/margins": 4.926279067993164,
+      "rewards/rejected": -18.573719024658203,
+      "step": 215
+    },
+    {
+      "epoch": 0.47027388109552437,
+      "grad_norm": 150.34366732566772,
+      "learning_rate": 6.3661988065096e-07,
+      "logits/chosen": -1.0227452516555786,
+      "logits/rejected": -1.0000264644622803,
+      "logps/chosen": -1.4215940237045288,
+      "logps/rejected": -1.926209807395935,
+      "loss": 1.6503,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -14.21593952178955,
+      "rewards/margins": 5.0461578369140625,
+      "rewards/rejected": -19.262096405029297,
+      "step": 220
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 118.50430730198147,
+      "learning_rate": 6.185401888577487e-07,
+      "logits/chosen": -0.9958481788635254,
+      "logits/rejected": -0.9570272564888,
+      "logps/chosen": -1.4551509618759155,
+      "logps/rejected": -1.8940250873565674,
+      "loss": 1.4789,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -14.551508903503418,
+      "rewards/margins": 4.388740062713623,
+      "rewards/rejected": -18.940250396728516,
+      "step": 225
+    },
+    {
+      "epoch": 0.4916499665998664,
+      "grad_norm": 97.94256873991337,
+      "learning_rate": 6.002947078916364e-07,
+      "logits/chosen": -1.0675132274627686,
+      "logits/rejected": -1.012401819229126,
+      "logps/chosen": -1.4190456867218018,
+      "logps/rejected": -1.884321928024292,
+      "loss": 1.5692,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -14.190455436706543,
+      "rewards/margins": 4.652764320373535,
+      "rewards/rejected": -18.843217849731445,
+      "step": 230
+    },
+    {
+      "epoch": 0.5023380093520374,
+      "grad_norm": 97.69525089331223,
+      "learning_rate": 5.819089557075688e-07,
+      "logits/chosen": -1.0891209840774536,
+      "logits/rejected": -1.0585644245147705,
+      "logps/chosen": -1.4393976926803589,
+      "logps/rejected": -1.9622634649276733,
+      "loss": 1.625,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -14.393977165222168,
+      "rewards/margins": 5.228659152984619,
+      "rewards/rejected": -19.622636795043945,
+      "step": 235
+    },
+    {
+      "epoch": 0.5130260521042084,
+      "grad_norm": 75.47943033357323,
+      "learning_rate": 5.634086464424742e-07,
+      "logits/chosen": -1.0535987615585327,
+      "logits/rejected": -1.051977276802063,
+      "logps/chosen": -1.3285123109817505,
+      "logps/rejected": -1.7905857563018799,
+      "loss": 1.559,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -13.285120964050293,
+      "rewards/margins": 4.620734691619873,
+      "rewards/rejected": -17.90585708618164,
+      "step": 240
+    },
+    {
+      "epoch": 0.5237140948563794,
+      "grad_norm": 100.04007765445822,
+      "learning_rate": 5.448196544517167e-07,
+      "logits/chosen": -1.1635222434997559,
+      "logits/rejected": -1.0964869260787964,
+      "logps/chosen": -1.320629358291626,
+      "logps/rejected": -1.8691266775131226,
+      "loss": 1.4185,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -13.206293106079102,
+      "rewards/margins": 5.484975337982178,
+      "rewards/rejected": -18.691268920898438,
+      "step": 245
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 90.6563420202814,
+      "learning_rate": 5.26167978121472e-07,
+      "logits/chosen": -1.084279179573059,
+      "logits/rejected": -1.0659908056259155,
+      "logps/chosen": -1.389957308769226,
+      "logps/rejected": -1.9566434621810913,
+      "loss": 1.481,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -13.899574279785156,
+      "rewards/margins": 5.666860580444336,
+      "rewards/rejected": -19.56643295288086,
+      "step": 250
+    },
+    {
+      "epoch": 0.5450901803607214,
+      "grad_norm": 182.74327675067556,
+      "learning_rate": 5.074797035076318e-07,
+      "logits/chosen": -1.1342357397079468,
+      "logits/rejected": -1.1009563207626343,
+      "logps/chosen": -1.4785124063491821,
+      "logps/rejected": -1.9460515975952148,
+      "loss": 1.5455,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.785125732421875,
+      "rewards/margins": 4.67539119720459,
+      "rewards/rejected": -19.460514068603516,
+      "step": 255
+    },
+    {
+      "epoch": 0.5557782231128925,
+      "grad_norm": 107.72294875535913,
+      "learning_rate": 4.887809678520975e-07,
+      "logits/chosen": -1.0977184772491455,
+      "logits/rejected": -1.0647294521331787,
+      "logps/chosen": -1.377906322479248,
+      "logps/rejected": -1.8358585834503174,
+      "loss": 1.4211,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -13.779062271118164,
+      "rewards/margins": 4.579524040222168,
+      "rewards/rejected": -18.358585357666016,
+      "step": 260
+    },
+    {
+      "epoch": 0.5664662658650634,
+      "grad_norm": 75.63967900485645,
+      "learning_rate": 4.700979230274829e-07,
+      "logits/chosen": -1.046972393989563,
+      "logits/rejected": -1.027153730392456,
+      "logps/chosen": -1.4691593647003174,
+      "logps/rejected": -1.9394676685333252,
+      "loss": 1.4695,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -14.6915922164917,
+      "rewards/margins": 4.703083038330078,
+      "rewards/rejected": -19.394678115844727,
+      "step": 265
+    },
+    {
+      "epoch": 0.5771543086172345,
+      "grad_norm": 193.81178663729204,
+      "learning_rate": 4.514566989613559e-07,
+      "logits/chosen": -1.0509687662124634,
+      "logits/rejected": -1.0184508562088013,
+      "logps/chosen": -1.3223508596420288,
+      "logps/rejected": -1.8159472942352295,
+      "loss": 1.5709,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -13.22350788116455,
+      "rewards/margins": 4.935965061187744,
+      "rewards/rejected": -18.159473419189453,
+      "step": 270
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 93.1736953697589,
+      "learning_rate": 4.328833670911724e-07,
+      "logits/chosen": -1.0397508144378662,
+      "logits/rejected": -0.9964058995246887,
+      "logps/chosen": -1.2974085807800293,
+      "logps/rejected": -1.7082370519638062,
+      "loss": 1.551,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -12.974085807800293,
+      "rewards/margins": 4.108286380767822,
+      "rewards/rejected": -17.08237075805664,
+      "step": 275
+    },
+    {
+      "epoch": 0.5985303941215765,
+      "grad_norm": 76.2073903395276,
+      "learning_rate": 4.144039039010124e-07,
+      "logits/chosen": -1.1180676221847534,
+      "logits/rejected": -1.09043550491333,
+      "logps/chosen": -1.346557378768921,
+      "logps/rejected": -1.8500111103057861,
+      "loss": 1.4682,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -13.46557331085205,
+      "rewards/margins": 5.034535884857178,
+      "rewards/rejected": -18.500110626220703,
+      "step": 280
+    },
+    {
+      "epoch": 0.6092184368737475,
+      "grad_norm": 94.07989298570106,
+      "learning_rate": 3.960441545911204e-07,
+      "logits/chosen": -1.0859159231185913,
+      "logits/rejected": -1.0468647480010986,
+      "logps/chosen": -1.399982213973999,
+      "logps/rejected": -1.926845908164978,
+      "loss": 1.2667,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -13.999821662902832,
+      "rewards/margins": 5.268637657165527,
+      "rewards/rejected": -19.26845932006836,
+      "step": 285
+    },
+    {
+      "epoch": 0.6199064796259185,
+      "grad_norm": 89.07279022649925,
+      "learning_rate": 3.778297969310529e-07,
+      "logits/chosen": -1.110459327697754,
+      "logits/rejected": -1.0649018287658691,
+      "logps/chosen": -1.3886842727661133,
+      "logps/rejected": -1.8522567749023438,
+      "loss": 1.5307,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -13.886842727661133,
+      "rewards/margins": 4.635725975036621,
+      "rewards/rejected": -18.522567749023438,
+      "step": 290
+    },
+    {
+      "epoch": 0.6305945223780896,
+      "grad_norm": 104.92194222567683,
+      "learning_rate": 3.5978630534699865e-07,
+      "logits/chosen": -1.0469499826431274,
+      "logits/rejected": -1.0278840065002441,
+      "logps/chosen": -1.4743906259536743,
+      "logps/rejected": -1.9389221668243408,
+      "loss": 1.3919,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -14.743906021118164,
+      "rewards/margins": 4.645317077636719,
+      "rewards/rejected": -19.38922119140625,
+      "step": 295
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 115.157031251591,
+      "learning_rate": 3.4193891529348795e-07,
+      "logits/chosen": -0.9734314680099487,
+      "logits/rejected": -0.9448921084403992,
+      "logps/chosen": -1.4543259143829346,
+      "logps/rejected": -1.8318170309066772,
+      "loss": 1.7971,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -14.543258666992188,
+      "rewards/margins": 3.7749099731445312,
+      "rewards/rejected": -18.31817054748535,
+      "step": 300
+    },
+    {
+      "epoch": 0.6519706078824316,
+      "grad_norm": 87.78878822591881,
+      "learning_rate": 3.243125879593286e-07,
+      "logits/chosen": -1.0921169519424438,
+      "logits/rejected": -1.041258692741394,
+      "logps/chosen": -1.3990426063537598,
+      "logps/rejected": -1.7868198156356812,
+      "loss": 1.4931,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -13.990427017211914,
+      "rewards/margins": 3.877769947052002,
+      "rewards/rejected": -17.86819839477539,
+      "step": 305
+    },
+    {
+      "epoch": 0.6626586506346025,
+      "grad_norm": 105.06509533230586,
+      "learning_rate": 3.069319753571269e-07,
+      "logits/chosen": -1.1367733478546143,
+      "logits/rejected": -1.1123126745224,
+      "logps/chosen": -1.4809437990188599,
+      "logps/rejected": -1.9527852535247803,
+      "loss": 1.6001,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -14.80943775177002,
+      "rewards/margins": 4.718415260314941,
+      "rewards/rejected": -19.52785301208496,
+      "step": 310
+    },
+    {
+      "epoch": 0.6733466933867736,
+      "grad_norm": 100.34303754111261,
+      "learning_rate": 2.898213858452173e-07,
+      "logits/chosen": -1.1173804998397827,
+      "logits/rejected": -1.0558984279632568,
+      "logps/chosen": -1.3943215608596802,
+      "logps/rejected": -1.851544976234436,
+      "loss": 1.4087,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -13.943216323852539,
+      "rewards/margins": 4.572234153747559,
+      "rewards/rejected": -18.51544761657715,
+      "step": 315
+    },
+    {
+      "epoch": 0.6840347361389446,
+      "grad_norm": 113.86543674722715,
+      "learning_rate": 2.730047501302266e-07,
+      "logits/chosen": -1.0984666347503662,
+      "logits/rejected": -1.0932129621505737,
+      "logps/chosen": -1.4517738819122314,
+      "logps/rejected": -2.008024215698242,
+      "loss": 1.4795,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -14.517735481262207,
+      "rewards/margins": 5.562503814697266,
+      "rewards/rejected": -20.080242156982422,
+      "step": 320
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 99.61197741979623,
+      "learning_rate": 2.5650558779781635e-07,
+      "logits/chosen": -1.116877794265747,
+      "logits/rejected": -1.0635037422180176,
+      "logps/chosen": -1.6024644374847412,
+      "logps/rejected": -2.2202725410461426,
+      "loss": 1.4448,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -16.02464485168457,
+      "rewards/margins": 6.178084373474121,
+      "rewards/rejected": -22.202730178833008,
+      "step": 325
+    },
+    {
+      "epoch": 0.7054108216432866,
+      "grad_norm": 77.71480741385236,
+      "learning_rate": 2.403469744184154e-07,
+      "logits/chosen": -1.0377768278121948,
+      "logits/rejected": -0.9935773611068726,
+      "logps/chosen": -1.4898747205734253,
+      "logps/rejected": -1.9272472858428955,
+      "loss": 1.4709,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -14.898748397827148,
+      "rewards/margins": 4.37372350692749,
+      "rewards/rejected": -19.272472381591797,
+      "step": 330
+    },
+    {
+      "epoch": 0.7160988643954576,
+      "grad_norm": 89.73568696356142,
+      "learning_rate": 2.2455150927394878e-07,
+      "logits/chosen": -1.0675146579742432,
+      "logits/rejected": -1.0462026596069336,
+      "logps/chosen": -1.4130958318710327,
+      "logps/rejected": -1.9325294494628906,
+      "loss": 1.39,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.130956649780273,
+      "rewards/margins": 5.194336891174316,
+      "rewards/rejected": -19.32529640197754,
+      "step": 335
+    },
+    {
+      "epoch": 0.7267869071476286,
+      "grad_norm": 110.68879818809171,
+      "learning_rate": 2.0914128375069722e-07,
+      "logits/chosen": -1.0806689262390137,
+      "logits/rejected": -1.042923927307129,
+      "logps/chosen": -1.4482777118682861,
+      "logps/rejected": -1.9667714834213257,
+      "loss": 1.4947,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -14.48277759552002,
+      "rewards/margins": 5.184937000274658,
+      "rewards/rejected": -19.667715072631836,
+      "step": 340
+    },
+    {
+      "epoch": 0.7374749498997996,
+      "grad_norm": 118.37607191091168,
+      "learning_rate": 1.9413785044249676e-07,
+      "logits/chosen": -1.1191717386245728,
+      "logits/rejected": -1.0921493768692017,
+      "logps/chosen": -1.5390311479568481,
+      "logps/rejected": -2.1164662837982178,
+      "loss": 1.6411,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -15.390310287475586,
+      "rewards/margins": 5.774353981018066,
+      "rewards/rejected": -21.164663314819336,
+      "step": 345
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 177.61167476414326,
+      "learning_rate": 1.7956219300748792e-07,
+      "logits/chosen": -1.1068302392959595,
+      "logits/rejected": -1.1092784404754639,
+      "logps/chosen": -1.4487911462783813,
+      "logps/rejected": -1.9363235235214233,
+      "loss": 1.5257,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -14.487910270690918,
+      "rewards/margins": 4.875324726104736,
+      "rewards/rejected": -19.363237380981445,
+      "step": 350
+    },
+    {
+      "epoch": 0.7588510354041417,
+      "grad_norm": 93.0216947858328,
+      "learning_rate": 1.6543469682057104e-07,
+      "logits/chosen": -1.0323774814605713,
+      "logits/rejected": -1.0446354150772095,
+      "logps/chosen": -1.3830714225769043,
+      "logps/rejected": -1.8855358362197876,
+      "loss": 1.352,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -13.830714225769043,
+      "rewards/margins": 5.02464485168457,
+      "rewards/rejected": -18.855358123779297,
+      "step": 355
+    },
+    {
+      "epoch": 0.7695390781563126,
+      "grad_norm": 94.72973814318713,
+      "learning_rate": 1.5177512046261666e-07,
+      "logits/chosen": -1.0865602493286133,
+      "logits/rejected": -1.0826921463012695,
+      "logps/chosen": -1.4152530431747437,
+      "logps/rejected": -2.0346670150756836,
+      "loss": 1.4234,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -14.1525297164917,
+      "rewards/margins": 6.1941399574279785,
+      "rewards/rejected": -20.346668243408203,
+      "step": 360
+    },
+    {
+      "epoch": 0.7802271209084837,
+      "grad_norm": 68.4731130261061,
+      "learning_rate": 1.3860256808630427e-07,
+      "logits/chosen": -1.135087490081787,
+      "logits/rejected": -1.059451937675476,
+      "logps/chosen": -1.4586212635040283,
+      "logps/rejected": -2.061830997467041,
+      "loss": 1.4973,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -14.586212158203125,
+      "rewards/margins": 6.0320963859558105,
+      "rewards/rejected": -20.618310928344727,
+      "step": 365
+    },
+    {
+      "epoch": 0.7909151636606546,
+      "grad_norm": 121.84202884529543,
+      "learning_rate": 1.2593546269723647e-07,
+      "logits/chosen": -1.0569720268249512,
+      "logits/rejected": -1.040205717086792,
+      "logps/chosen": -1.4913088083267212,
+      "logps/rejected": -1.9543384313583374,
+      "loss": 1.5364,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -14.913087844848633,
+      "rewards/margins": 4.630299091339111,
+      "rewards/rejected": -19.543384552001953,
+      "step": 370
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 132.37754504186287,
+      "learning_rate": 1.1379152038770029e-07,
+      "logits/chosen": -1.0853582620620728,
+      "logits/rejected": -1.0880931615829468,
+      "logps/chosen": -1.561675786972046,
+      "logps/rejected": -2.0865683555603027,
+      "loss": 1.4922,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -15.6167573928833,
+      "rewards/margins": 5.24892520904541,
+      "rewards/rejected": -20.86568260192871,
+      "step": 375
+    },
+    {
+      "epoch": 0.8122912491649966,
+      "grad_norm": 146.30353813707708,
+      "learning_rate": 1.0218772555910954e-07,
+      "logits/chosen": -1.1082967519760132,
+      "logits/rejected": -1.084113359451294,
+      "logps/chosen": -1.449220895767212,
+      "logps/rejected": -1.9152443408966064,
+      "loss": 1.6124,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -14.492208480834961,
+      "rewards/margins": 4.660233974456787,
+      "rewards/rejected": -19.15244483947754,
+      "step": 380
+    },
+    {
+      "epoch": 0.8229792919171677,
+      "grad_norm": 77.25479077025736,
+      "learning_rate": 9.114030716778432e-08,
+      "logits/chosen": -1.0906922817230225,
+      "logits/rejected": -1.0660183429718018,
+      "logps/chosen": -1.457859992980957,
+      "logps/rejected": -2.104210138320923,
+      "loss": 1.2879,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -14.578600883483887,
+      "rewards/margins": 6.4635009765625,
+      "rewards/rejected": -21.042102813720703,
+      "step": 385
+    },
+    {
+      "epoch": 0.8336673346693386,
+      "grad_norm": 93.07916389497416,
+      "learning_rate": 8.066471602728803e-08,
+      "logits/chosen": -1.1058779954910278,
+      "logits/rejected": -1.0853393077850342,
+      "logps/chosen": -1.526141881942749,
+      "logps/rejected": -2.099813461303711,
+      "loss": 1.3994,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -15.261419296264648,
+      "rewards/margins": 5.736716270446777,
+      "rewards/rejected": -20.99813461303711,
+      "step": 390
+    },
+    {
+      "epoch": 0.8443553774215097,
+      "grad_norm": 101.69355206701071,
+      "learning_rate": 7.077560319906694e-08,
+      "logits/chosen": -1.1104137897491455,
+      "logits/rejected": -1.0867125988006592,
+      "logps/chosen": -1.461976408958435,
+      "logps/rejected": -2.0008349418640137,
+      "loss": 1.5022,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.61976432800293,
+      "rewards/margins": 5.388585090637207,
+      "rewards/rejected": -20.008350372314453,
+      "step": 395
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 78.27794611977339,
+      "learning_rate": 6.148679950161672e-08,
+      "logits/chosen": -1.1054575443267822,
+      "logits/rejected": -1.086721658706665,
+      "logps/chosen": -1.4834736585617065,
+      "logps/rejected": -1.9632450342178345,
+      "loss": 1.353,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -14.834736824035645,
+      "rewards/margins": 4.797713756561279,
+      "rewards/rejected": -19.6324520111084,
+      "step": 400
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "eval_logits/chosen": -1.3153965473175049,
+      "eval_logits/rejected": -1.323797345161438,
+      "eval_logps/chosen": -1.4682824611663818,
+      "eval_logps/rejected": -1.983279824256897,
+      "eval_loss": 1.3837593793869019,
+      "eval_rewards/accuracies": 0.8231707215309143,
+      "eval_rewards/chosen": -14.68282413482666,
+      "eval_rewards/margins": 5.149974822998047,
+      "eval_rewards/rejected": -19.83279800415039,
+      "eval_runtime": 89.1693,
+      "eval_samples_per_second": 21.992,
+      "eval_steps_per_second": 1.379,
+      "step": 400
+    },
+    {
+      "epoch": 0.8657314629258517,
+      "grad_norm": 123.22959345953065,
+      "learning_rate": 5.2811296166831666e-08,
+      "logits/chosen": -1.072684645652771,
+      "logits/rejected": -1.0882729291915894,
+      "logps/chosen": -1.541043996810913,
+      "logps/rejected": -1.9995849132537842,
+      "loss": 1.3185,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -15.410443305969238,
+      "rewards/margins": 4.585409641265869,
+      "rewards/rejected": -19.995851516723633,
+      "step": 405
+    },
+    {
+      "epoch": 0.8764195056780227,
+      "grad_norm": 147.91474233820844,
+      "learning_rate": 4.4761226670592066e-08,
+      "logits/chosen": -1.0857017040252686,
+      "logits/rejected": -1.0723140239715576,
+      "logps/chosen": -1.4827214479446411,
+      "logps/rejected": -1.9837812185287476,
+      "loss": 1.4599,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.827215194702148,
+      "rewards/margins": 5.010597229003906,
+      "rewards/rejected": -19.837810516357422,
+      "step": 410
+    },
+    {
+      "epoch": 0.8871075484301937,
+      "grad_norm": 91.16953725496764,
+      "learning_rate": 3.734784976300165e-08,
+      "logits/chosen": -1.08389413356781,
+      "logits/rejected": -1.025193691253662,
+      "logps/chosen": -1.436957597732544,
+      "logps/rejected": -2.0282580852508545,
+      "loss": 1.5869,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -14.369573593139648,
+      "rewards/margins": 5.913008213043213,
+      "rewards/rejected": -20.282581329345703,
+      "step": 415
+    },
+    {
+      "epoch": 0.8977955911823647,
+      "grad_norm": 107.28232680425738,
+      "learning_rate": 3.058153372200695e-08,
+      "logits/chosen": -1.1248770952224731,
+      "logits/rejected": -1.0667715072631836,
+      "logps/chosen": -1.3739981651306152,
+      "logps/rejected": -1.912716269493103,
+      "loss": 1.4124,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -13.739982604980469,
+      "rewards/margins": 5.387181282043457,
+      "rewards/rejected": -19.12716293334961,
+      "step": 420
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 120.49009743628018,
+      "learning_rate": 2.4471741852423233e-08,
+      "logits/chosen": -1.1182382106781006,
+      "logits/rejected": -1.1063783168792725,
+      "logps/chosen": -1.5358679294586182,
+      "logps/rejected": -1.9908769130706787,
+      "loss": 1.6669,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -15.358678817749023,
+      "rewards/margins": 4.5500898361206055,
+      "rewards/rejected": -19.908771514892578,
+      "step": 425
+    },
+    {
+      "epoch": 0.9191716766867067,
+      "grad_norm": 121.92864479159549,
+      "learning_rate": 1.9027019250647036e-08,
+      "logits/chosen": -1.0952109098434448,
+      "logits/rejected": -1.0773556232452393,
+      "logps/chosen": -1.5638394355773926,
+      "logps/rejected": -2.070910930633545,
+      "loss": 1.4596,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -15.638395309448242,
+      "rewards/margins": 5.070715427398682,
+      "rewards/rejected": -20.709110260009766,
+      "step": 430
+    },
+    {
+      "epoch": 0.9298597194388778,
+      "grad_norm": 105.14729635844223,
+      "learning_rate": 1.4254980853566246e-08,
+      "logits/chosen": -1.0598957538604736,
+      "logits/rejected": -1.0141620635986328,
+      "logps/chosen": -1.4233707189559937,
+      "logps/rejected": -1.9325555562973022,
+      "loss": 1.4575,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -14.233708381652832,
+      "rewards/margins": 5.091846466064453,
+      "rewards/rejected": -19.3255558013916,
+      "step": 435
+    },
+    {
+      "epoch": 0.9405477621910487,
+      "grad_norm": 84.89716957923389,
+      "learning_rate": 1.016230078838226e-08,
+      "logits/chosen": -1.0672032833099365,
+      "logits/rejected": -1.004197359085083,
+      "logps/chosen": -1.4600632190704346,
+      "logps/rejected": -1.9247214794158936,
+      "loss": 1.3976,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.60063362121582,
+      "rewards/margins": 4.646584510803223,
+      "rewards/rejected": -19.24721908569336,
+      "step": 440
+    },
+    {
+      "epoch": 0.9512358049432198,
+      "grad_norm": 100.8050659107904,
+      "learning_rate": 6.754703038239329e-09,
+      "logits/chosen": -1.0271015167236328,
+      "logits/rejected": -1.0067023038864136,
+      "logps/chosen": -1.479617953300476,
+      "logps/rejected": -2.0660512447357178,
+      "loss": 1.1916,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -14.796180725097656,
+      "rewards/margins": 5.86433219909668,
+      "rewards/rejected": -20.660511016845703,
+      "step": 445
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 108.38487580301923,
+      "learning_rate": 4.036953436716895e-09,
+      "logits/chosen": -1.1366522312164307,
+      "logits/rejected": -1.1128257513046265,
+      "logps/chosen": -1.4388145208358765,
+      "logps/rejected": -1.9377214908599854,
+      "loss": 1.5938,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -14.388147354125977,
+      "rewards/margins": 4.989068031311035,
+      "rewards/rejected": -19.377216339111328,
+      "step": 450
+    },
+    {
+      "epoch": 0.9726118904475618,
+      "grad_norm": 103.77485773787681,
+      "learning_rate": 2.0128530023804656e-09,
+      "logits/chosen": -1.1026852130889893,
+      "logits/rejected": -1.0658283233642578,
+      "logps/chosen": -1.4252578020095825,
+      "logps/rejected": -2.0259361267089844,
+      "loss": 1.0798,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -14.25257682800293,
+      "rewards/margins": 6.006783485412598,
+      "rewards/rejected": -20.259363174438477,
+      "step": 455
+    },
+    {
+      "epoch": 0.9832999331997327,
+      "grad_norm": 94.49790728355107,
+      "learning_rate": 6.852326227130833e-10,
+      "logits/chosen": -1.1023436784744263,
+      "logits/rejected": -1.0878626108169556,
+      "logps/chosen": -1.5501340627670288,
+      "logps/rejected": -2.1030094623565674,
+      "loss": 1.389,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -15.50133991241455,
+      "rewards/margins": 5.528753757476807,
+      "rewards/rejected": -21.030094146728516,
+      "step": 460
+    },
+    {
+      "epoch": 0.9939879759519038,
+      "grad_norm": 98.7777667397615,
+      "learning_rate": 5.594909486328348e-11,
+      "logits/chosen": -1.0701709985733032,
+      "logits/rejected": -1.0728482007980347,
+      "logps/chosen": -1.511604905128479,
+      "logps/rejected": -2.0450565814971924,
+      "loss": 1.5678,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -15.116047859191895,
+      "rewards/margins": 5.334519863128662,
+      "rewards/rejected": -20.4505672454834,
+      "step": 465
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 467,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-467/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990c8c5b8001cd51e3e89a7606a50e1bdf23c328f1a714b8e03c87972f974da2
+size 7352

checkpoint-467/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9982631930527722,
+    "eval_logits/chosen": -1.319807767868042,
+    "eval_logits/rejected": -1.328245759010315,
+    "eval_logps/chosen": -1.4769620895385742,
+    "eval_logps/rejected": -1.9949750900268555,
+    "eval_loss": 1.3845703601837158,
+    "eval_rewards/accuracies": 0.8231707215309143,
+    "eval_rewards/chosen": -14.769620895385742,
+    "eval_rewards/margins": 5.180131435394287,
+    "eval_rewards/rejected": -19.949752807617188,
+    "eval_runtime": 87.8371,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 22.325,
+    "eval_steps_per_second": 1.4
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4d02f89ee587dfa885a25c30e44d063677e16f453c463a54bafc90ea1cdf9a
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d38a3529eaf96c27321ef1669f21a739743104249072a85e8b5b4557ee5407
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c070b7aea29214412ec41afb6e3bbfa6bba53ef0d5487f3fc17ff630de9237
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcf7552dca049a441a7bd173f737520ca7ceadf16ba931b5deab4f65cac276a
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9982631930527722,
+    "total_flos": 0.0,
+    "train_loss": 1.957533876696797,
+    "train_runtime": 11480.123,
+    "train_samples": 59876,
+    "train_samples_per_second": 5.216,
+    "train_steps_per_second": 0.041
+}

trainer_state.json

@@ -0,0 +1,1453 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9982631930527722,
+  "eval_steps": 400,
+  "global_step": 467,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01068804275217101,
+      "grad_norm": 51.9219704867916,
+      "learning_rate": 1.0638297872340425e-07,
+      "logits/chosen": -1.0090945959091187,
+      "logits/rejected": -0.9798948168754578,
+      "logps/chosen": -0.2737821936607361,
+      "logps/rejected": -0.2714875340461731,
+      "loss": 2.9624,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -2.7378220558166504,
+      "rewards/margins": -0.02294684387743473,
+      "rewards/rejected": -2.7148749828338623,
+      "step": 5
+    },
+    {
+      "epoch": 0.02137608550434202,
+      "grad_norm": 44.19632899404353,
+      "learning_rate": 2.127659574468085e-07,
+      "logits/chosen": -1.0468437671661377,
+      "logits/rejected": -0.9794818758964539,
+      "logps/chosen": -0.2943094074726105,
+      "logps/rejected": -0.2997472286224365,
+      "loss": 3.2285,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -2.943093776702881,
+      "rewards/margins": 0.054378531873226166,
+      "rewards/rejected": -2.9974725246429443,
+      "step": 10
+    },
+    {
+      "epoch": 0.03206412825651302,
+      "grad_norm": 51.06549177485018,
+      "learning_rate": 3.1914893617021275e-07,
+      "logits/chosen": -0.9672244191169739,
+      "logits/rejected": -0.9858204126358032,
+      "logps/chosen": -0.2640294134616852,
+      "logps/rejected": -0.30089089274406433,
+      "loss": 3.2949,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -2.640293836593628,
+      "rewards/margins": 0.3686152398586273,
+      "rewards/rejected": -3.008909225463867,
+      "step": 15
+    },
+    {
+      "epoch": 0.04275217100868404,
+      "grad_norm": 74.83681858154256,
+      "learning_rate": 4.25531914893617e-07,
+      "logits/chosen": -0.9596344232559204,
+      "logits/rejected": -0.933236300945282,
+      "logps/chosen": -0.2778920531272888,
+      "logps/rejected": -0.29140567779541016,
+      "loss": 3.0107,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -2.7789206504821777,
+      "rewards/margins": 0.13513638079166412,
+      "rewards/rejected": -2.9140570163726807,
+      "step": 20
+    },
+    {
+      "epoch": 0.053440213760855046,
+      "grad_norm": 53.488412779583946,
+      "learning_rate": 5.319148936170212e-07,
+      "logits/chosen": -1.0089600086212158,
+      "logits/rejected": -0.9799430966377258,
+      "logps/chosen": -0.27165931463241577,
+      "logps/rejected": -0.2783976197242737,
+      "loss": 3.2847,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -2.7165932655334473,
+      "rewards/margins": 0.06738300621509552,
+      "rewards/rejected": -2.7839760780334473,
+      "step": 25
+    },
+    {
+      "epoch": 0.06412825651302605,
+      "grad_norm": 49.467165701102346,
+      "learning_rate": 6.382978723404255e-07,
+      "logits/chosen": -0.9974703788757324,
+      "logits/rejected": -0.952576756477356,
+      "logps/chosen": -0.2734770178794861,
+      "logps/rejected": -0.27953463792800903,
+      "loss": 3.0768,
+      "rewards/accuracies": 0.42500001192092896,
+      "rewards/chosen": -2.734769821166992,
+      "rewards/margins": 0.06057664006948471,
+      "rewards/rejected": -2.795346736907959,
+      "step": 30
+    },
+    {
+      "epoch": 0.07481629926519706,
+      "grad_norm": 62.938723083055315,
+      "learning_rate": 7.446808510638297e-07,
+      "logits/chosen": -1.055626630783081,
+      "logits/rejected": -0.9798073768615723,
+      "logps/chosen": -0.29555463790893555,
+      "logps/rejected": -0.3219638466835022,
+      "loss": 3.0274,
+      "rewards/accuracies": 0.512499988079071,
+      "rewards/chosen": -2.9555466175079346,
+      "rewards/margins": 0.26409202814102173,
+      "rewards/rejected": -3.2196388244628906,
+      "step": 35
+    },
+    {
+      "epoch": 0.08550434201736808,
+      "grad_norm": 60.78411434363956,
+      "learning_rate": 8.51063829787234e-07,
+      "logits/chosen": -0.9993880987167358,
+      "logits/rejected": -0.9557031393051147,
+      "logps/chosen": -0.2811431288719177,
+      "logps/rejected": -0.3281245231628418,
+      "loss": 2.953,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -2.8114311695098877,
+      "rewards/margins": 0.469813734292984,
+      "rewards/rejected": -3.281245470046997,
+      "step": 40
+    },
+    {
+      "epoch": 0.09619238476953908,
+      "grad_norm": 37.98461592095763,
+      "learning_rate": 9.574468085106384e-07,
+      "logits/chosen": -1.0411790609359741,
+      "logits/rejected": -0.9992967844009399,
+      "logps/chosen": -0.30747953057289124,
+      "logps/rejected": -0.3615890145301819,
+      "loss": 3.0174,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -3.0747952461242676,
+      "rewards/margins": 0.5410946607589722,
+      "rewards/rejected": -3.6158900260925293,
+      "step": 45
+    },
+    {
+      "epoch": 0.10688042752171009,
+      "grad_norm": 117.4214402638359,
+      "learning_rate": 9.998741174712533e-07,
+      "logits/chosen": -1.0310847759246826,
+      "logits/rejected": -0.9821462631225586,
+      "logps/chosen": -0.31808674335479736,
+      "logps/rejected": -0.3582245707511902,
+      "loss": 3.0624,
+      "rewards/accuracies": 0.4937500059604645,
+      "rewards/chosen": -3.1808676719665527,
+      "rewards/margins": 0.4013778567314148,
+      "rewards/rejected": -3.5822455883026123,
+      "step": 50
+    },
+    {
+      "epoch": 0.11756847027388109,
+      "grad_norm": 170.90804995599427,
+      "learning_rate": 9.991050648838675e-07,
+      "logits/chosen": -1.0685880184173584,
+      "logits/rejected": -1.0338609218597412,
+      "logps/chosen": -0.310200572013855,
+      "logps/rejected": -0.37700629234313965,
+      "loss": 2.7117,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -3.10200572013855,
+      "rewards/margins": 0.6680572628974915,
+      "rewards/rejected": -3.770063877105713,
+      "step": 55
+    },
+    {
+      "epoch": 0.1282565130260521,
+      "grad_norm": 134.13615502558548,
+      "learning_rate": 9.97637968732563e-07,
+      "logits/chosen": -1.109356164932251,
+      "logits/rejected": -1.0756348371505737,
+      "logps/chosen": -0.37418466806411743,
+      "logps/rejected": -0.3752634525299072,
+      "loss": 2.9555,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -3.7418465614318848,
+      "rewards/margins": 0.010788190178573132,
+      "rewards/rejected": -3.7526347637176514,
+      "step": 60
+    },
+    {
+      "epoch": 0.13894455577822312,
+      "grad_norm": 62.988442946717754,
+      "learning_rate": 9.954748808839674e-07,
+      "logits/chosen": -1.0235508680343628,
+      "logits/rejected": -0.9943636059761047,
+      "logps/chosen": -0.3913114666938782,
+      "logps/rejected": -0.4661448001861572,
+      "loss": 2.8601,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -3.9131150245666504,
+      "rewards/margins": 0.7483334541320801,
+      "rewards/rejected": -4.6614484786987305,
+      "step": 65
+    },
+    {
+      "epoch": 0.14963259853039412,
+      "grad_norm": 43.4379227945051,
+      "learning_rate": 9.926188266120295e-07,
+      "logits/chosen": -1.0352689027786255,
+      "logits/rejected": -1.0102473497390747,
+      "logps/chosen": -0.353306382894516,
+      "logps/rejected": -0.4401523172855377,
+      "loss": 2.8751,
+      "rewards/accuracies": 0.5562499761581421,
+      "rewards/chosen": -3.5330634117126465,
+      "rewards/margins": 0.8684590458869934,
+      "rewards/rejected": -4.401522636413574,
+      "step": 70
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 83.11781382244568,
+      "learning_rate": 9.890738003669027e-07,
+      "logits/chosen": -0.996098518371582,
+      "logits/rejected": -0.9254637956619263,
+      "logps/chosen": -0.34757333993911743,
+      "logps/rejected": -0.413855642080307,
+      "loss": 2.8749,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -3.475733518600464,
+      "rewards/margins": 0.6628231406211853,
+      "rewards/rejected": -4.138556480407715,
+      "step": 75
+    },
+    {
+      "epoch": 0.17100868403473615,
+      "grad_norm": 51.202568906876266,
+      "learning_rate": 9.848447601883433e-07,
+      "logits/chosen": -0.9647027850151062,
+      "logits/rejected": -0.950391411781311,
+      "logps/chosen": -0.3513404130935669,
+      "logps/rejected": -0.46568623185157776,
+      "loss": 2.6436,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -3.513404369354248,
+      "rewards/margins": 1.1434578895568848,
+      "rewards/rejected": -4.656861782073975,
+      "step": 80
+    },
+    {
+      "epoch": 0.18169672678690715,
+      "grad_norm": 70.97672847293224,
+      "learning_rate": 9.799376207714444e-07,
+      "logits/chosen": -0.9941811561584473,
+      "logits/rejected": -0.9714711308479309,
+      "logps/chosen": -0.3401820659637451,
+      "logps/rejected": -0.40950268507003784,
+      "loss": 2.6659,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": -3.401820659637451,
+      "rewards/margins": 0.6932064890861511,
+      "rewards/rejected": -4.095026969909668,
+      "step": 85
+    },
+    {
+      "epoch": 0.19238476953907815,
+      "grad_norm": 152.3633388876466,
+      "learning_rate": 9.743592451943998e-07,
+      "logits/chosen": -1.0390641689300537,
+      "logits/rejected": -1.002964735031128,
+      "logps/chosen": -0.4347335696220398,
+      "logps/rejected": -0.5336366891860962,
+      "loss": 2.8761,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -4.347336769104004,
+      "rewards/margins": 0.9890311360359192,
+      "rewards/rejected": -5.336367130279541,
+      "step": 90
+    },
+    {
+      "epoch": 0.20307281229124916,
+      "grad_norm": 48.723602234021136,
+      "learning_rate": 9.681174353198686e-07,
+      "logits/chosen": -1.112140417098999,
+      "logits/rejected": -1.0275517702102661,
+      "logps/chosen": -0.4523504674434662,
+      "logps/rejected": -0.5077233910560608,
+      "loss": 2.653,
+      "rewards/accuracies": 0.543749988079071,
+      "rewards/chosen": -4.523504734039307,
+      "rewards/margins": 0.5537286996841431,
+      "rewards/rejected": -5.077233791351318,
+      "step": 95
+    },
+    {
+      "epoch": 0.21376085504342018,
+      "grad_norm": 67.84801804788158,
+      "learning_rate": 9.612209208833646e-07,
+      "logits/chosen": -1.000867486000061,
+      "logits/rejected": -0.9747543334960938,
+      "logps/chosen": -0.4416694641113281,
+      "logps/rejected": -0.5102046728134155,
+      "loss": 2.8531,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -4.4166951179504395,
+      "rewards/margins": 0.6853527426719666,
+      "rewards/rejected": -5.102047920227051,
+      "step": 100
+    },
+    {
+      "epoch": 0.22444889779559118,
+      "grad_norm": 73.17857628661973,
+      "learning_rate": 9.536793472839324e-07,
+      "logits/chosen": -1.0074902772903442,
+      "logits/rejected": -0.9537180662155151,
+      "logps/chosen": -0.40940943360328674,
+      "logps/rejected": -0.5277153849601746,
+      "loss": 2.9423,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -4.094094276428223,
+      "rewards/margins": 1.1830594539642334,
+      "rewards/rejected": -5.277153968811035,
+      "step": 105
+    },
+    {
+      "epoch": 0.23513694054776219,
+      "grad_norm": 58.188153286610884,
+      "learning_rate": 9.455032620941839e-07,
+      "logits/chosen": -0.9680612683296204,
+      "logits/rejected": -0.9060274362564087,
+      "logps/chosen": -0.4779647886753082,
+      "logps/rejected": -0.6175049543380737,
+      "loss": 2.7583,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -4.7796478271484375,
+      "rewards/margins": 1.3954023122787476,
+      "rewards/rejected": -6.175050258636475,
+      "step": 110
+    },
+    {
+      "epoch": 0.2458249832999332,
+      "grad_norm": 55.673813232077116,
+      "learning_rate": 9.367041003085648e-07,
+      "logits/chosen": -1.0318225622177124,
+      "logits/rejected": -0.9690453410148621,
+      "logps/chosen": -0.5004153251647949,
+      "logps/rejected": -0.564782440662384,
+      "loss": 2.6268,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": -5.004153251647949,
+      "rewards/margins": 0.643670916557312,
+      "rewards/rejected": -5.647824287414551,
+      "step": 115
+    },
+    {
+      "epoch": 0.2565130260521042,
+      "grad_norm": 93.24909470705533,
+      "learning_rate": 9.272941683504808e-07,
+      "logits/chosen": -0.9859496355056763,
+      "logits/rejected": -0.892734169960022,
+      "logps/chosen": -0.5100774168968201,
+      "logps/rejected": -0.7314041256904602,
+      "loss": 2.6175,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -5.100773811340332,
+      "rewards/margins": 2.213266372680664,
+      "rewards/rejected": -7.314040184020996,
+      "step": 120
+    },
+    {
+      "epoch": 0.26720106880427524,
+      "grad_norm": 62.49186315009438,
+      "learning_rate": 9.172866268606513e-07,
+      "logits/chosen": -1.0501500368118286,
+      "logits/rejected": -1.0046356916427612,
+      "logps/chosen": -0.568703293800354,
+      "logps/rejected": -0.6640041470527649,
+      "loss": 2.4292,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": -5.687033176422119,
+      "rewards/margins": 0.9530088305473328,
+      "rewards/rejected": -6.640041351318359,
+      "step": 125
+    },
+    {
+      "epoch": 0.27788911155644624,
+      "grad_norm": 94.37106722966159,
+      "learning_rate": 9.066954722907638e-07,
+      "logits/chosen": -1.0626311302185059,
+      "logits/rejected": -1.0533256530761719,
+      "logps/chosen": -0.5523235201835632,
+      "logps/rejected": -0.8242877125740051,
+      "loss": 2.3709,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -5.5232343673706055,
+      "rewards/margins": 2.719642162322998,
+      "rewards/rejected": -8.242877006530762,
+      "step": 130
+    },
+    {
+      "epoch": 0.28857715430861725,
+      "grad_norm": 78.14100135139738,
+      "learning_rate": 8.955355173281707e-07,
+      "logits/chosen": -1.0362498760223389,
+      "logits/rejected": -0.9840585589408875,
+      "logps/chosen": -0.5984936952590942,
+      "logps/rejected": -0.7128698825836182,
+      "loss": 2.355,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -5.984936714172363,
+      "rewards/margins": 1.1437618732452393,
+      "rewards/rejected": -7.128698825836182,
+      "step": 135
+    },
+    {
+      "epoch": 0.29926519706078825,
+      "grad_norm": 80.07356057826689,
+      "learning_rate": 8.838223701790055e-07,
+      "logits/chosen": -1.0999033451080322,
+      "logits/rejected": -1.0737004280090332,
+      "logps/chosen": -0.719946026802063,
+      "logps/rejected": -0.8201924562454224,
+      "loss": 2.4387,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -7.199460029602051,
+      "rewards/margins": 1.0024646520614624,
+      "rewards/rejected": -8.201925277709961,
+      "step": 140
+    },
+    {
+      "epoch": 0.30995323981295925,
+      "grad_norm": 90.63467648251373,
+      "learning_rate": 8.71572412738697e-07,
+      "logits/chosen": -1.0016281604766846,
+      "logits/rejected": -0.9718937873840332,
+      "logps/chosen": -0.6957625150680542,
+      "logps/rejected": -0.89495849609375,
+      "loss": 2.3174,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -6.957624912261963,
+      "rewards/margins": 1.991959810256958,
+      "rewards/rejected": -8.9495849609375,
+      "step": 145
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 73.56126608282666,
+      "learning_rate": 8.588027776804058e-07,
+      "logits/chosen": -1.0221322774887085,
+      "logits/rejected": -0.9965847134590149,
+      "logps/chosen": -0.7128551006317139,
+      "logps/rejected": -0.896537184715271,
+      "loss": 2.3663,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -7.128551483154297,
+      "rewards/margins": 1.8368213176727295,
+      "rewards/rejected": -8.965372085571289,
+      "step": 150
+    },
+    {
+      "epoch": 0.33132932531730125,
+      "grad_norm": 81.6804828395219,
+      "learning_rate": 8.455313244934324e-07,
+      "logits/chosen": -1.016101598739624,
+      "logits/rejected": -0.9916119575500488,
+      "logps/chosen": -0.7570836544036865,
+      "logps/rejected": -1.0055702924728394,
+      "loss": 2.1714,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -7.570836544036865,
+      "rewards/margins": 2.4848668575286865,
+      "rewards/rejected": -10.055703163146973,
+      "step": 155
+    },
+    {
+      "epoch": 0.3420173680694723,
+      "grad_norm": 99.4901399654396,
+      "learning_rate": 8.317766145051057e-07,
+      "logits/chosen": -1.0358034372329712,
+      "logits/rejected": -1.015195608139038,
+      "logps/chosen": -0.8496212959289551,
+      "logps/rejected": -1.2102388143539429,
+      "loss": 2.1439,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -8.49621295928955,
+      "rewards/margins": 3.606174945831299,
+      "rewards/rejected": -12.102388381958008,
+      "step": 160
+    },
+    {
+      "epoch": 0.3527054108216433,
+      "grad_norm": 70.81537442159531,
+      "learning_rate": 8.175578849210894e-07,
+      "logits/chosen": -1.025247573852539,
+      "logits/rejected": -0.9949723482131958,
+      "logps/chosen": -0.9383013844490051,
+      "logps/rejected": -1.2926217317581177,
+      "loss": 2.1748,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -9.383014678955078,
+      "rewards/margins": 3.5432026386260986,
+      "rewards/rejected": -12.926218032836914,
+      "step": 165
+    },
+    {
+      "epoch": 0.3633934535738143,
+      "grad_norm": 87.64514196797495,
+      "learning_rate": 8.028950219204099e-07,
+      "logits/chosen": -1.0285688638687134,
+      "logits/rejected": -1.003366470336914,
+      "logps/chosen": -0.8483174443244934,
+      "logps/rejected": -1.227891445159912,
+      "loss": 1.9588,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -8.483174324035645,
+      "rewards/margins": 3.7957394123077393,
+      "rewards/rejected": -12.278913497924805,
+      "step": 170
+    },
+    {
+      "epoch": 0.3740814963259853,
+      "grad_norm": 112.86629209538306,
+      "learning_rate": 7.878085328428368e-07,
+      "logits/chosen": -1.0398296117782593,
+      "logits/rejected": -0.9856590032577515,
+      "logps/chosen": -0.975140392780304,
+      "logps/rejected": -1.1828876733779907,
+      "loss": 1.8418,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -9.75140380859375,
+      "rewards/margins": 2.07747220993042,
+      "rewards/rejected": -11.828875541687012,
+      "step": 175
+    },
+    {
+      "epoch": 0.3847695390781563,
+      "grad_norm": 78.96808907768161,
+      "learning_rate": 7.723195175075135e-07,
+      "logits/chosen": -0.9896231889724731,
+      "logits/rejected": -0.9649994969367981,
+      "logps/chosen": -0.9527977108955383,
+      "logps/rejected": -1.2905272245407104,
+      "loss": 1.8762,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -9.527976036071777,
+      "rewards/margins": 3.377295732498169,
+      "rewards/rejected": -12.9052734375,
+      "step": 180
+    },
+    {
+      "epoch": 0.3954575818303273,
+      "grad_norm": 108.85803981934055,
+      "learning_rate": 7.564496387029531e-07,
+      "logits/chosen": -1.0348621606826782,
+      "logits/rejected": -0.9732630848884583,
+      "logps/chosen": -1.0269982814788818,
+      "logps/rejected": -1.4066517353057861,
+      "loss": 1.7941,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -10.269983291625977,
+      "rewards/margins": 3.7965340614318848,
+      "rewards/rejected": -14.06651782989502,
+      "step": 185
+    },
+    {
+      "epoch": 0.4061456245824983,
+      "grad_norm": 88.17963395634109,
+      "learning_rate": 7.402210918896689e-07,
+      "logits/chosen": -1.0109108686447144,
+      "logits/rejected": -1.016540765762329,
+      "logps/chosen": -1.1914116144180298,
+      "logps/rejected": -1.6932926177978516,
+      "loss": 1.7838,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -11.914116859436035,
+      "rewards/margins": 5.018809795379639,
+      "rewards/rejected": -16.932926177978516,
+      "step": 190
+    },
+    {
+      "epoch": 0.4168336673346693,
+      "grad_norm": 93.26710505616924,
+      "learning_rate": 7.236565741578162e-07,
+      "logits/chosen": -0.9588305354118347,
+      "logits/rejected": -0.9351094961166382,
+      "logps/chosen": -1.1738094091415405,
+      "logps/rejected": -1.507836103439331,
+      "loss": 1.7312,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -11.738093376159668,
+      "rewards/margins": 3.340266704559326,
+      "rewards/rejected": -15.078363418579102,
+      "step": 195
+    },
+    {
+      "epoch": 0.42752171008684037,
+      "grad_norm": 148.12833430588864,
+      "learning_rate": 7.067792524832603e-07,
+      "logits/chosen": -0.962164044380188,
+      "logits/rejected": -0.946324348449707,
+      "logps/chosen": -1.190048098564148,
+      "logps/rejected": -1.5737119913101196,
+      "loss": 1.8488,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -11.900480270385742,
+      "rewards/margins": 3.8366382122039795,
+      "rewards/rejected": -15.737119674682617,
+      "step": 200
+    },
+    {
+      "epoch": 0.43820975283901137,
+      "grad_norm": 88.33539547998033,
+      "learning_rate": 6.896127313264642e-07,
+      "logits/chosen": -0.9857925176620483,
+      "logits/rejected": -0.9326913952827454,
+      "logps/chosen": -1.2696114778518677,
+      "logps/rejected": -1.6608413457870483,
+      "loss": 1.844,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -12.696113586425781,
+      "rewards/margins": 3.9123005867004395,
+      "rewards/rejected": -16.608415603637695,
+      "step": 205
+    },
+    {
+      "epoch": 0.44889779559118237,
+      "grad_norm": 96.6188335214616,
+      "learning_rate": 6.721810196195174e-07,
+      "logits/chosen": -1.0050965547561646,
+      "logits/rejected": -0.9934624433517456,
+      "logps/chosen": -1.2922513484954834,
+      "logps/rejected": -1.710461974143982,
+      "loss": 1.6898,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -12.922513961791992,
+      "rewards/margins": 4.182106018066406,
+      "rewards/rejected": -17.10462188720703,
+      "step": 210
+    },
+    {
+      "epoch": 0.45958583834335337,
+      "grad_norm": 96.68880124766956,
+      "learning_rate": 6.545084971874736e-07,
+      "logits/chosen": -0.9563829302787781,
+      "logits/rejected": -0.9366313815116882,
+      "logps/chosen": -1.364743947982788,
+      "logps/rejected": -1.8573719263076782,
+      "loss": 1.5133,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -13.647438049316406,
+      "rewards/margins": 4.926279067993164,
+      "rewards/rejected": -18.573719024658203,
+      "step": 215
+    },
+    {
+      "epoch": 0.47027388109552437,
+      "grad_norm": 150.34366732566772,
+      "learning_rate": 6.3661988065096e-07,
+      "logits/chosen": -1.0227452516555786,
+      "logits/rejected": -1.0000264644622803,
+      "logps/chosen": -1.4215940237045288,
+      "logps/rejected": -1.926209807395935,
+      "loss": 1.6503,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -14.21593952178955,
+      "rewards/margins": 5.0461578369140625,
+      "rewards/rejected": -19.262096405029297,
+      "step": 220
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 118.50430730198147,
+      "learning_rate": 6.185401888577487e-07,
+      "logits/chosen": -0.9958481788635254,
+      "logits/rejected": -0.9570272564888,
+      "logps/chosen": -1.4551509618759155,
+      "logps/rejected": -1.8940250873565674,
+      "loss": 1.4789,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -14.551508903503418,
+      "rewards/margins": 4.388740062713623,
+      "rewards/rejected": -18.940250396728516,
+      "step": 225
+    },
+    {
+      "epoch": 0.4916499665998664,
+      "grad_norm": 97.94256873991337,
+      "learning_rate": 6.002947078916364e-07,
+      "logits/chosen": -1.0675132274627686,
+      "logits/rejected": -1.012401819229126,
+      "logps/chosen": -1.4190456867218018,
+      "logps/rejected": -1.884321928024292,
+      "loss": 1.5692,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -14.190455436706543,
+      "rewards/margins": 4.652764320373535,
+      "rewards/rejected": -18.843217849731445,
+      "step": 230
+    },
+    {
+      "epoch": 0.5023380093520374,
+      "grad_norm": 97.69525089331223,
+      "learning_rate": 5.819089557075688e-07,
+      "logits/chosen": -1.0891209840774536,
+      "logits/rejected": -1.0585644245147705,
+      "logps/chosen": -1.4393976926803589,
+      "logps/rejected": -1.9622634649276733,
+      "loss": 1.625,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -14.393977165222168,
+      "rewards/margins": 5.228659152984619,
+      "rewards/rejected": -19.622636795043945,
+      "step": 235
+    },
+    {
+      "epoch": 0.5130260521042084,
+      "grad_norm": 75.47943033357323,
+      "learning_rate": 5.634086464424742e-07,
+      "logits/chosen": -1.0535987615585327,
+      "logits/rejected": -1.051977276802063,
+      "logps/chosen": -1.3285123109817505,
+      "logps/rejected": -1.7905857563018799,
+      "loss": 1.559,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -13.285120964050293,
+      "rewards/margins": 4.620734691619873,
+      "rewards/rejected": -17.90585708618164,
+      "step": 240
+    },
+    {
+      "epoch": 0.5237140948563794,
+      "grad_norm": 100.04007765445822,
+      "learning_rate": 5.448196544517167e-07,
+      "logits/chosen": -1.1635222434997559,
+      "logits/rejected": -1.0964869260787964,
+      "logps/chosen": -1.320629358291626,
+      "logps/rejected": -1.8691266775131226,
+      "loss": 1.4185,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -13.206293106079102,
+      "rewards/margins": 5.484975337982178,
+      "rewards/rejected": -18.691268920898438,
+      "step": 245
+    },
+    {
+      "epoch": 0.5344021376085505,
+      "grad_norm": 90.6563420202814,
+      "learning_rate": 5.26167978121472e-07,
+      "logits/chosen": -1.084279179573059,
+      "logits/rejected": -1.0659908056259155,
+      "logps/chosen": -1.389957308769226,
+      "logps/rejected": -1.9566434621810913,
+      "loss": 1.481,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -13.899574279785156,
+      "rewards/margins": 5.666860580444336,
+      "rewards/rejected": -19.56643295288086,
+      "step": 250
+    },
+    {
+      "epoch": 0.5450901803607214,
+      "grad_norm": 182.74327675067556,
+      "learning_rate": 5.074797035076318e-07,
+      "logits/chosen": -1.1342357397079468,
+      "logits/rejected": -1.1009563207626343,
+      "logps/chosen": -1.4785124063491821,
+      "logps/rejected": -1.9460515975952148,
+      "loss": 1.5455,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.785125732421875,
+      "rewards/margins": 4.67539119720459,
+      "rewards/rejected": -19.460514068603516,
+      "step": 255
+    },
+    {
+      "epoch": 0.5557782231128925,
+      "grad_norm": 107.72294875535913,
+      "learning_rate": 4.887809678520975e-07,
+      "logits/chosen": -1.0977184772491455,
+      "logits/rejected": -1.0647294521331787,
+      "logps/chosen": -1.377906322479248,
+      "logps/rejected": -1.8358585834503174,
+      "loss": 1.4211,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -13.779062271118164,
+      "rewards/margins": 4.579524040222168,
+      "rewards/rejected": -18.358585357666016,
+      "step": 260
+    },
+    {
+      "epoch": 0.5664662658650634,
+      "grad_norm": 75.63967900485645,
+      "learning_rate": 4.700979230274829e-07,
+      "logits/chosen": -1.046972393989563,
+      "logits/rejected": -1.027153730392456,
+      "logps/chosen": -1.4691593647003174,
+      "logps/rejected": -1.9394676685333252,
+      "loss": 1.4695,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -14.6915922164917,
+      "rewards/margins": 4.703083038330078,
+      "rewards/rejected": -19.394678115844727,
+      "step": 265
+    },
+    {
+      "epoch": 0.5771543086172345,
+      "grad_norm": 193.81178663729204,
+      "learning_rate": 4.514566989613559e-07,
+      "logits/chosen": -1.0509687662124634,
+      "logits/rejected": -1.0184508562088013,
+      "logps/chosen": -1.3223508596420288,
+      "logps/rejected": -1.8159472942352295,
+      "loss": 1.5709,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -13.22350788116455,
+      "rewards/margins": 4.935965061187744,
+      "rewards/rejected": -18.159473419189453,
+      "step": 270
+    },
+    {
+      "epoch": 0.5878423513694054,
+      "grad_norm": 93.1736953697589,
+      "learning_rate": 4.328833670911724e-07,
+      "logits/chosen": -1.0397508144378662,
+      "logits/rejected": -0.9964058995246887,
+      "logps/chosen": -1.2974085807800293,
+      "logps/rejected": -1.7082370519638062,
+      "loss": 1.551,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -12.974085807800293,
+      "rewards/margins": 4.108286380767822,
+      "rewards/rejected": -17.08237075805664,
+      "step": 275
+    },
+    {
+      "epoch": 0.5985303941215765,
+      "grad_norm": 76.2073903395276,
+      "learning_rate": 4.144039039010124e-07,
+      "logits/chosen": -1.1180676221847534,
+      "logits/rejected": -1.09043550491333,
+      "logps/chosen": -1.346557378768921,
+      "logps/rejected": -1.8500111103057861,
+      "loss": 1.4682,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -13.46557331085205,
+      "rewards/margins": 5.034535884857178,
+      "rewards/rejected": -18.500110626220703,
+      "step": 280
+    },
+    {
+      "epoch": 0.6092184368737475,
+      "grad_norm": 94.07989298570106,
+      "learning_rate": 3.960441545911204e-07,
+      "logits/chosen": -1.0859159231185913,
+      "logits/rejected": -1.0468647480010986,
+      "logps/chosen": -1.399982213973999,
+      "logps/rejected": -1.926845908164978,
+      "loss": 1.2667,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -13.999821662902832,
+      "rewards/margins": 5.268637657165527,
+      "rewards/rejected": -19.26845932006836,
+      "step": 285
+    },
+    {
+      "epoch": 0.6199064796259185,
+      "grad_norm": 89.07279022649925,
+      "learning_rate": 3.778297969310529e-07,
+      "logits/chosen": -1.110459327697754,
+      "logits/rejected": -1.0649018287658691,
+      "logps/chosen": -1.3886842727661133,
+      "logps/rejected": -1.8522567749023438,
+      "loss": 1.5307,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -13.886842727661133,
+      "rewards/margins": 4.635725975036621,
+      "rewards/rejected": -18.522567749023438,
+      "step": 290
+    },
+    {
+      "epoch": 0.6305945223780896,
+      "grad_norm": 104.92194222567683,
+      "learning_rate": 3.5978630534699865e-07,
+      "logits/chosen": -1.0469499826431274,
+      "logits/rejected": -1.0278840065002441,
+      "logps/chosen": -1.4743906259536743,
+      "logps/rejected": -1.9389221668243408,
+      "loss": 1.3919,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -14.743906021118164,
+      "rewards/margins": 4.645317077636719,
+      "rewards/rejected": -19.38922119140625,
+      "step": 295
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 115.157031251591,
+      "learning_rate": 3.4193891529348795e-07,
+      "logits/chosen": -0.9734314680099487,
+      "logits/rejected": -0.9448921084403992,
+      "logps/chosen": -1.4543259143829346,
+      "logps/rejected": -1.8318170309066772,
+      "loss": 1.7971,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -14.543258666992188,
+      "rewards/margins": 3.7749099731445312,
+      "rewards/rejected": -18.31817054748535,
+      "step": 300
+    },
+    {
+      "epoch": 0.6519706078824316,
+      "grad_norm": 87.78878822591881,
+      "learning_rate": 3.243125879593286e-07,
+      "logits/chosen": -1.0921169519424438,
+      "logits/rejected": -1.041258692741394,
+      "logps/chosen": -1.3990426063537598,
+      "logps/rejected": -1.7868198156356812,
+      "loss": 1.4931,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -13.990427017211914,
+      "rewards/margins": 3.877769947052002,
+      "rewards/rejected": -17.86819839477539,
+      "step": 305
+    },
+    {
+      "epoch": 0.6626586506346025,
+      "grad_norm": 105.06509533230586,
+      "learning_rate": 3.069319753571269e-07,
+      "logits/chosen": -1.1367733478546143,
+      "logits/rejected": -1.1123126745224,
+      "logps/chosen": -1.4809437990188599,
+      "logps/rejected": -1.9527852535247803,
+      "loss": 1.6001,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -14.80943775177002,
+      "rewards/margins": 4.718415260314941,
+      "rewards/rejected": -19.52785301208496,
+      "step": 310
+    },
+    {
+      "epoch": 0.6733466933867736,
+      "grad_norm": 100.34303754111261,
+      "learning_rate": 2.898213858452173e-07,
+      "logits/chosen": -1.1173804998397827,
+      "logits/rejected": -1.0558984279632568,
+      "logps/chosen": -1.3943215608596802,
+      "logps/rejected": -1.851544976234436,
+      "loss": 1.4087,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -13.943216323852539,
+      "rewards/margins": 4.572234153747559,
+      "rewards/rejected": -18.51544761657715,
+      "step": 315
+    },
+    {
+      "epoch": 0.6840347361389446,
+      "grad_norm": 113.86543674722715,
+      "learning_rate": 2.730047501302266e-07,
+      "logits/chosen": -1.0984666347503662,
+      "logits/rejected": -1.0932129621505737,
+      "logps/chosen": -1.4517738819122314,
+      "logps/rejected": -2.008024215698242,
+      "loss": 1.4795,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -14.517735481262207,
+      "rewards/margins": 5.562503814697266,
+      "rewards/rejected": -20.080242156982422,
+      "step": 320
+    },
+    {
+      "epoch": 0.6947227788911156,
+      "grad_norm": 99.61197741979623,
+      "learning_rate": 2.5650558779781635e-07,
+      "logits/chosen": -1.116877794265747,
+      "logits/rejected": -1.0635037422180176,
+      "logps/chosen": -1.6024644374847412,
+      "logps/rejected": -2.2202725410461426,
+      "loss": 1.4448,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -16.02464485168457,
+      "rewards/margins": 6.178084373474121,
+      "rewards/rejected": -22.202730178833008,
+      "step": 325
+    },
+    {
+      "epoch": 0.7054108216432866,
+      "grad_norm": 77.71480741385236,
+      "learning_rate": 2.403469744184154e-07,
+      "logits/chosen": -1.0377768278121948,
+      "logits/rejected": -0.9935773611068726,
+      "logps/chosen": -1.4898747205734253,
+      "logps/rejected": -1.9272472858428955,
+      "loss": 1.4709,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -14.898748397827148,
+      "rewards/margins": 4.37372350692749,
+      "rewards/rejected": -19.272472381591797,
+      "step": 330
+    },
+    {
+      "epoch": 0.7160988643954576,
+      "grad_norm": 89.73568696356142,
+      "learning_rate": 2.2455150927394878e-07,
+      "logits/chosen": -1.0675146579742432,
+      "logits/rejected": -1.0462026596069336,
+      "logps/chosen": -1.4130958318710327,
+      "logps/rejected": -1.9325294494628906,
+      "loss": 1.39,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.130956649780273,
+      "rewards/margins": 5.194336891174316,
+      "rewards/rejected": -19.32529640197754,
+      "step": 335
+    },
+    {
+      "epoch": 0.7267869071476286,
+      "grad_norm": 110.68879818809171,
+      "learning_rate": 2.0914128375069722e-07,
+      "logits/chosen": -1.0806689262390137,
+      "logits/rejected": -1.042923927307129,
+      "logps/chosen": -1.4482777118682861,
+      "logps/rejected": -1.9667714834213257,
+      "loss": 1.4947,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -14.48277759552002,
+      "rewards/margins": 5.184937000274658,
+      "rewards/rejected": -19.667715072631836,
+      "step": 340
+    },
+    {
+      "epoch": 0.7374749498997996,
+      "grad_norm": 118.37607191091168,
+      "learning_rate": 1.9413785044249676e-07,
+      "logits/chosen": -1.1191717386245728,
+      "logits/rejected": -1.0921493768692017,
+      "logps/chosen": -1.5390311479568481,
+      "logps/rejected": -2.1164662837982178,
+      "loss": 1.6411,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -15.390310287475586,
+      "rewards/margins": 5.774353981018066,
+      "rewards/rejected": -21.164663314819336,
+      "step": 345
+    },
+    {
+      "epoch": 0.7481629926519706,
+      "grad_norm": 177.61167476414326,
+      "learning_rate": 1.7956219300748792e-07,
+      "logits/chosen": -1.1068302392959595,
+      "logits/rejected": -1.1092784404754639,
+      "logps/chosen": -1.4487911462783813,
+      "logps/rejected": -1.9363235235214233,
+      "loss": 1.5257,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -14.487910270690918,
+      "rewards/margins": 4.875324726104736,
+      "rewards/rejected": -19.363237380981445,
+      "step": 350
+    },
+    {
+      "epoch": 0.7588510354041417,
+      "grad_norm": 93.0216947858328,
+      "learning_rate": 1.6543469682057104e-07,
+      "logits/chosen": -1.0323774814605713,
+      "logits/rejected": -1.0446354150772095,
+      "logps/chosen": -1.3830714225769043,
+      "logps/rejected": -1.8855358362197876,
+      "loss": 1.352,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -13.830714225769043,
+      "rewards/margins": 5.02464485168457,
+      "rewards/rejected": -18.855358123779297,
+      "step": 355
+    },
+    {
+      "epoch": 0.7695390781563126,
+      "grad_norm": 94.72973814318713,
+      "learning_rate": 1.5177512046261666e-07,
+      "logits/chosen": -1.0865602493286133,
+      "logits/rejected": -1.0826921463012695,
+      "logps/chosen": -1.4152530431747437,
+      "logps/rejected": -2.0346670150756836,
+      "loss": 1.4234,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -14.1525297164917,
+      "rewards/margins": 6.1941399574279785,
+      "rewards/rejected": -20.346668243408203,
+      "step": 360
+    },
+    {
+      "epoch": 0.7802271209084837,
+      "grad_norm": 68.4731130261061,
+      "learning_rate": 1.3860256808630427e-07,
+      "logits/chosen": -1.135087490081787,
+      "logits/rejected": -1.059451937675476,
+      "logps/chosen": -1.4586212635040283,
+      "logps/rejected": -2.061830997467041,
+      "loss": 1.4973,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -14.586212158203125,
+      "rewards/margins": 6.0320963859558105,
+      "rewards/rejected": -20.618310928344727,
+      "step": 365
+    },
+    {
+      "epoch": 0.7909151636606546,
+      "grad_norm": 121.84202884529543,
+      "learning_rate": 1.2593546269723647e-07,
+      "logits/chosen": -1.0569720268249512,
+      "logits/rejected": -1.040205717086792,
+      "logps/chosen": -1.4913088083267212,
+      "logps/rejected": -1.9543384313583374,
+      "loss": 1.5364,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -14.913087844848633,
+      "rewards/margins": 4.630299091339111,
+      "rewards/rejected": -19.543384552001953,
+      "step": 370
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 132.37754504186287,
+      "learning_rate": 1.1379152038770029e-07,
+      "logits/chosen": -1.0853582620620728,
+      "logits/rejected": -1.0880931615829468,
+      "logps/chosen": -1.561675786972046,
+      "logps/rejected": -2.0865683555603027,
+      "loss": 1.4922,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -15.6167573928833,
+      "rewards/margins": 5.24892520904541,
+      "rewards/rejected": -20.86568260192871,
+      "step": 375
+    },
+    {
+      "epoch": 0.8122912491649966,
+      "grad_norm": 146.30353813707708,
+      "learning_rate": 1.0218772555910954e-07,
+      "logits/chosen": -1.1082967519760132,
+      "logits/rejected": -1.084113359451294,
+      "logps/chosen": -1.449220895767212,
+      "logps/rejected": -1.9152443408966064,
+      "loss": 1.6124,
+      "rewards/accuracies": 0.831250011920929,
+      "rewards/chosen": -14.492208480834961,
+      "rewards/margins": 4.660233974456787,
+      "rewards/rejected": -19.15244483947754,
+      "step": 380
+    },
+    {
+      "epoch": 0.8229792919171677,
+      "grad_norm": 77.25479077025736,
+      "learning_rate": 9.114030716778432e-08,
+      "logits/chosen": -1.0906922817230225,
+      "logits/rejected": -1.0660183429718018,
+      "logps/chosen": -1.457859992980957,
+      "logps/rejected": -2.104210138320923,
+      "loss": 1.2879,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -14.578600883483887,
+      "rewards/margins": 6.4635009765625,
+      "rewards/rejected": -21.042102813720703,
+      "step": 385
+    },
+    {
+      "epoch": 0.8336673346693386,
+      "grad_norm": 93.07916389497416,
+      "learning_rate": 8.066471602728803e-08,
+      "logits/chosen": -1.1058779954910278,
+      "logits/rejected": -1.0853393077850342,
+      "logps/chosen": -1.526141881942749,
+      "logps/rejected": -2.099813461303711,
+      "loss": 1.3994,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -15.261419296264648,
+      "rewards/margins": 5.736716270446777,
+      "rewards/rejected": -20.99813461303711,
+      "step": 390
+    },
+    {
+      "epoch": 0.8443553774215097,
+      "grad_norm": 101.69355206701071,
+      "learning_rate": 7.077560319906694e-08,
+      "logits/chosen": -1.1104137897491455,
+      "logits/rejected": -1.0867125988006592,
+      "logps/chosen": -1.461976408958435,
+      "logps/rejected": -2.0008349418640137,
+      "loss": 1.5022,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.61976432800293,
+      "rewards/margins": 5.388585090637207,
+      "rewards/rejected": -20.008350372314453,
+      "step": 395
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "grad_norm": 78.27794611977339,
+      "learning_rate": 6.148679950161672e-08,
+      "logits/chosen": -1.1054575443267822,
+      "logits/rejected": -1.086721658706665,
+      "logps/chosen": -1.4834736585617065,
+      "logps/rejected": -1.9632450342178345,
+      "loss": 1.353,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -14.834736824035645,
+      "rewards/margins": 4.797713756561279,
+      "rewards/rejected": -19.6324520111084,
+      "step": 400
+    },
+    {
+      "epoch": 0.8550434201736807,
+      "eval_logits/chosen": -1.3153965473175049,
+      "eval_logits/rejected": -1.323797345161438,
+      "eval_logps/chosen": -1.4682824611663818,
+      "eval_logps/rejected": -1.983279824256897,
+      "eval_loss": 1.3837593793869019,
+      "eval_rewards/accuracies": 0.8231707215309143,
+      "eval_rewards/chosen": -14.68282413482666,
+      "eval_rewards/margins": 5.149974822998047,
+      "eval_rewards/rejected": -19.83279800415039,
+      "eval_runtime": 89.1693,
+      "eval_samples_per_second": 21.992,
+      "eval_steps_per_second": 1.379,
+      "step": 400
+    },
+    {
+      "epoch": 0.8657314629258517,
+      "grad_norm": 123.22959345953065,
+      "learning_rate": 5.2811296166831666e-08,
+      "logits/chosen": -1.072684645652771,
+      "logits/rejected": -1.0882729291915894,
+      "logps/chosen": -1.541043996810913,
+      "logps/rejected": -1.9995849132537842,
+      "loss": 1.3185,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -15.410443305969238,
+      "rewards/margins": 4.585409641265869,
+      "rewards/rejected": -19.995851516723633,
+      "step": 405
+    },
+    {
+      "epoch": 0.8764195056780227,
+      "grad_norm": 147.91474233820844,
+      "learning_rate": 4.4761226670592066e-08,
+      "logits/chosen": -1.0857017040252686,
+      "logits/rejected": -1.0723140239715576,
+      "logps/chosen": -1.4827214479446411,
+      "logps/rejected": -1.9837812185287476,
+      "loss": 1.4599,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.827215194702148,
+      "rewards/margins": 5.010597229003906,
+      "rewards/rejected": -19.837810516357422,
+      "step": 410
+    },
+    {
+      "epoch": 0.8871075484301937,
+      "grad_norm": 91.16953725496764,
+      "learning_rate": 3.734784976300165e-08,
+      "logits/chosen": -1.08389413356781,
+      "logits/rejected": -1.025193691253662,
+      "logps/chosen": -1.436957597732544,
+      "logps/rejected": -2.0282580852508545,
+      "loss": 1.5869,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -14.369573593139648,
+      "rewards/margins": 5.913008213043213,
+      "rewards/rejected": -20.282581329345703,
+      "step": 415
+    },
+    {
+      "epoch": 0.8977955911823647,
+      "grad_norm": 107.28232680425738,
+      "learning_rate": 3.058153372200695e-08,
+      "logits/chosen": -1.1248770952224731,
+      "logits/rejected": -1.0667715072631836,
+      "logps/chosen": -1.3739981651306152,
+      "logps/rejected": -1.912716269493103,
+      "loss": 1.4124,
+      "rewards/accuracies": 0.8500000238418579,
+      "rewards/chosen": -13.739982604980469,
+      "rewards/margins": 5.387181282043457,
+      "rewards/rejected": -19.12716293334961,
+      "step": 420
+    },
+    {
+      "epoch": 0.9084836339345357,
+      "grad_norm": 120.49009743628018,
+      "learning_rate": 2.4471741852423233e-08,
+      "logits/chosen": -1.1182382106781006,
+      "logits/rejected": -1.1063783168792725,
+      "logps/chosen": -1.5358679294586182,
+      "logps/rejected": -1.9908769130706787,
+      "loss": 1.6669,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -15.358678817749023,
+      "rewards/margins": 4.5500898361206055,
+      "rewards/rejected": -19.908771514892578,
+      "step": 425
+    },
+    {
+      "epoch": 0.9191716766867067,
+      "grad_norm": 121.92864479159549,
+      "learning_rate": 1.9027019250647036e-08,
+      "logits/chosen": -1.0952109098434448,
+      "logits/rejected": -1.0773556232452393,
+      "logps/chosen": -1.5638394355773926,
+      "logps/rejected": -2.070910930633545,
+      "loss": 1.4596,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -15.638395309448242,
+      "rewards/margins": 5.070715427398682,
+      "rewards/rejected": -20.709110260009766,
+      "step": 430
+    },
+    {
+      "epoch": 0.9298597194388778,
+      "grad_norm": 105.14729635844223,
+      "learning_rate": 1.4254980853566246e-08,
+      "logits/chosen": -1.0598957538604736,
+      "logits/rejected": -1.0141620635986328,
+      "logps/chosen": -1.4233707189559937,
+      "logps/rejected": -1.9325555562973022,
+      "loss": 1.4575,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -14.233708381652832,
+      "rewards/margins": 5.091846466064453,
+      "rewards/rejected": -19.3255558013916,
+      "step": 435
+    },
+    {
+      "epoch": 0.9405477621910487,
+      "grad_norm": 84.89716957923389,
+      "learning_rate": 1.016230078838226e-08,
+      "logits/chosen": -1.0672032833099365,
+      "logits/rejected": -1.004197359085083,
+      "logps/chosen": -1.4600632190704346,
+      "logps/rejected": -1.9247214794158936,
+      "loss": 1.3976,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -14.60063362121582,
+      "rewards/margins": 4.646584510803223,
+      "rewards/rejected": -19.24721908569336,
+      "step": 440
+    },
+    {
+      "epoch": 0.9512358049432198,
+      "grad_norm": 100.8050659107904,
+      "learning_rate": 6.754703038239329e-09,
+      "logits/chosen": -1.0271015167236328,
+      "logits/rejected": -1.0067023038864136,
+      "logps/chosen": -1.479617953300476,
+      "logps/rejected": -2.0660512447357178,
+      "loss": 1.1916,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -14.796180725097656,
+      "rewards/margins": 5.86433219909668,
+      "rewards/rejected": -20.660511016845703,
+      "step": 445
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 108.38487580301923,
+      "learning_rate": 4.036953436716895e-09,
+      "logits/chosen": -1.1366522312164307,
+      "logits/rejected": -1.1128257513046265,
+      "logps/chosen": -1.4388145208358765,
+      "logps/rejected": -1.9377214908599854,
+      "loss": 1.5938,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -14.388147354125977,
+      "rewards/margins": 4.989068031311035,
+      "rewards/rejected": -19.377216339111328,
+      "step": 450
+    },
+    {
+      "epoch": 0.9726118904475618,
+      "grad_norm": 103.77485773787681,
+      "learning_rate": 2.0128530023804656e-09,
+      "logits/chosen": -1.1026852130889893,
+      "logits/rejected": -1.0658283233642578,
+      "logps/chosen": -1.4252578020095825,
+      "logps/rejected": -2.0259361267089844,
+      "loss": 1.0798,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -14.25257682800293,
+      "rewards/margins": 6.006783485412598,
+      "rewards/rejected": -20.259363174438477,
+      "step": 455
+    },
+    {
+      "epoch": 0.9832999331997327,
+      "grad_norm": 94.49790728355107,
+      "learning_rate": 6.852326227130833e-10,
+      "logits/chosen": -1.1023436784744263,
+      "logits/rejected": -1.0878626108169556,
+      "logps/chosen": -1.5501340627670288,
+      "logps/rejected": -2.1030094623565674,
+      "loss": 1.389,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -15.50133991241455,
+      "rewards/margins": 5.528753757476807,
+      "rewards/rejected": -21.030094146728516,
+      "step": 460
+    },
+    {
+      "epoch": 0.9939879759519038,
+      "grad_norm": 98.7777667397615,
+      "learning_rate": 5.594909486328348e-11,
+      "logits/chosen": -1.0701709985733032,
+      "logits/rejected": -1.0728482007980347,
+      "logps/chosen": -1.511604905128479,
+      "logps/rejected": -2.0450565814971924,
+      "loss": 1.5678,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -15.116047859191895,
+      "rewards/margins": 5.334519863128662,
+      "rewards/rejected": -20.4505672454834,
+      "step": 465
+    },
+    {
+      "epoch": 0.9982631930527722,
+      "step": 467,
+      "total_flos": 0.0,
+      "train_loss": 1.957533876696797,
+      "train_runtime": 11480.123,
+      "train_samples_per_second": 5.216,
+      "train_steps_per_second": 0.041
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 467,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:990c8c5b8001cd51e3e89a7606a50e1bdf23c328f1a714b8e03c87972f974da2
+size 7352