Upload folder using huggingface_hub

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1724227694

README.md

@@ -0,0 +1,7 @@
+---
+license: other
+base_model: qwen/Qwen2-7B
+
+<!-- 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. -->
+

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9999310202110782,
+    "eval_loss": 0.7303591966629028,
+    "eval_runtime": 11440.2897,
+    "eval_samples_per_second": 2.253,
+    "eval_steps_per_second": 0.282,
+    "total_flos": 3799534094254080.0,
+    "train_loss": 0.7359120230011592,
+    "train_runtime": 173906.7289,
+    "train_samples_per_second": 1.334,
+    "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/nas/data/yanxin/qwen/Qwen2-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9999310202110782,
+    "eval_loss": 0.7303591966629028,
+    "eval_runtime": 11440.2897,
+    "eval_samples_per_second": 2.253,
+    "eval_steps_per_second": 0.282
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.43.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e571ff72455f89c26f5c8467f6cd533b1614848a15e07461bb93d83623be4a0a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907aa4322e50352321099cdcae98bc35d6bd2dd0504ca6bb3d76f28d9ddab5d7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d79f5181ab07caa873a032c72a4e01d385048bb1ad4128ae81fd51b26c97891
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df26126620e17af6dc5c370ffaf56eec9f5b677b0c050c64847dcfc0007a190
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999310202110782,
+    "total_flos": 3799534094254080.0,
+    "train_loss": 0.7359120230011592,
+    "train_runtime": 173906.7289,
+    "train_samples_per_second": 1.334,
+    "train_steps_per_second": 0.003
+}

trainer_log.jsonl

@@ -0,0 +1,46 @@
+{"current_steps": 10, "total_steps": 453, "loss": 0.8555, "learning_rate": 1.0869565217391305e-05, "epoch": 0.022073532454990687, "percentage": 2.21, "elapsed_time": "1:05:25", "remaining_time": "2 days, 0:18:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 453, "loss": 0.7997, "learning_rate": 2.173913043478261e-05, "epoch": 0.044147064909981375, "percentage": 4.42, "elapsed_time": "2:10:47", "remaining_time": "1 day, 23:11:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 453, "loss": 0.7758, "learning_rate": 3.260869565217392e-05, "epoch": 0.06622059736497206, "percentage": 6.62, "elapsed_time": "3:15:43", "remaining_time": "1 day, 21:59:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 453, "loss": 0.7616, "learning_rate": 4.347826086956522e-05, "epoch": 0.08829412981996275, "percentage": 8.83, "elapsed_time": "4:20:42", "remaining_time": "1 day, 20:51:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 453, "loss": 0.7609, "learning_rate": 4.9988084660498037e-05, "epoch": 0.11036766227495344, "percentage": 11.04, "elapsed_time": "5:26:38", "remaining_time": "1 day, 19:52:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 453, "loss": 0.7677, "learning_rate": 4.985416749673074e-05, "epoch": 0.13244119472994412, "percentage": 13.25, "elapsed_time": "6:30:27", "remaining_time": "1 day, 18:37:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 453, "loss": 0.7558, "learning_rate": 4.957223915853709e-05, "epoch": 0.1545147271849348, "percentage": 15.45, "elapsed_time": "7:34:03", "remaining_time": "1 day, 17:24:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 453, "loss": 0.7492, "learning_rate": 4.9143978581429445e-05, "epoch": 0.1765882596399255, "percentage": 17.66, "elapsed_time": "8:37:31", "remaining_time": "1 day, 16:12:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 453, "loss": 0.7497, "learning_rate": 4.857193613652711e-05, "epoch": 0.1986617920949162, "percentage": 19.87, "elapsed_time": "9:40:39", "remaining_time": "1 day, 15:01:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 453, "loss": 0.7433, "learning_rate": 4.78595184426236e-05, "epoch": 0.22073532454990688, "percentage": 22.08, "elapsed_time": "10:43:40", "remaining_time": "1 day, 13:52:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 453, "loss": 0.744, "learning_rate": 4.7010968079140294e-05, "epoch": 0.24280885700489757, "percentage": 24.28, "elapsed_time": "11:46:44", "remaining_time": "1 day, 12:43:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 120, "total_steps": 453, "loss": 0.7378, "learning_rate": 4.6031338320779534e-05, "epoch": 0.26488238945988823, "percentage": 26.49, "elapsed_time": "12:49:47", "remaining_time": "1 day, 11:36:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 130, "total_steps": 453, "loss": 0.7388, "learning_rate": 4.492646304433711e-05, "epoch": 0.28695592191487895, "percentage": 28.7, "elapsed_time": "13:52:49", "remaining_time": "1 day, 10:29:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 140, "total_steps": 453, "loss": 0.7301, "learning_rate": 4.3702921986884574e-05, "epoch": 0.3090294543698696, "percentage": 30.91, "elapsed_time": "14:55:49", "remaining_time": "1 day, 9:22:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 150, "total_steps": 453, "loss": 0.7407, "learning_rate": 4.236800156221536e-05, "epoch": 0.33110298682486033, "percentage": 33.11, "elapsed_time": "15:58:47", "remaining_time": "1 day, 8:16:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 453, "loss": 0.7319, "learning_rate": 4.092965146890002e-05, "epoch": 0.353176519279851, "percentage": 35.32, "elapsed_time": "17:01:45", "remaining_time": "1 day, 7:11:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 453, "loss": 0.7292, "learning_rate": 3.9396437348357684e-05, "epoch": 0.3752500517348417, "percentage": 37.53, "elapsed_time": "18:04:38", "remaining_time": "1 day, 6:05:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 453, "loss": 0.7488, "learning_rate": 3.777748977487366e-05, "epoch": 0.3973235841898324, "percentage": 39.74, "elapsed_time": "19:07:38", "remaining_time": "1 day, 5:00:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 453, "loss": 0.7305, "learning_rate": 3.608244988133713e-05, "epoch": 0.41939711664482304, "percentage": 41.94, "elapsed_time": "20:10:54", "remaining_time": "1 day, 3:56:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 453, "loss": 0.7329, "learning_rate": 3.432141194450772e-05, "epoch": 0.44147064909981376, "percentage": 44.15, "elapsed_time": "21:14:40", "remaining_time": "1 day, 2:52:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 453, "loss": 0.729, "learning_rate": 3.2504863271726286e-05, "epoch": 0.4635441815548044, "percentage": 46.36, "elapsed_time": "22:17:56", "remaining_time": "1 day, 1:48:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 453, "loss": 0.7392, "learning_rate": 3.064362174705578e-05, "epoch": 0.48561771400979514, "percentage": 48.57, "elapsed_time": "23:21:26", "remaining_time": "1 day, 0:44:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 453, "loss": 0.7323, "learning_rate": 2.8748771408776466e-05, "epoch": 0.5076912464647858, "percentage": 50.77, "elapsed_time": "1 day, 0:27:42", "remaining_time": "23:43:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 453, "loss": 0.7391, "learning_rate": 2.683159644188339e-05, "epoch": 0.5297647789197765, "percentage": 52.98, "elapsed_time": "1 day, 1:35:35", "remaining_time": "22:42:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 453, "loss": 0.7304, "learning_rate": 2.4903513978673077e-05, "epoch": 0.5518383113747672, "percentage": 55.19, "elapsed_time": "1 day, 2:43:22", "remaining_time": "21:41:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 260, "total_steps": 453, "loss": 0.7248, "learning_rate": 2.2976006107604482e-05, "epoch": 0.5739118438297579, "percentage": 57.4, "elapsed_time": "1 day, 3:47:40", "remaining_time": "20:37:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 270, "total_steps": 453, "loss": 0.7361, "learning_rate": 2.1060551495333818e-05, "epoch": 0.5959853762847486, "percentage": 59.6, "elapsed_time": "1 day, 4:51:30", "remaining_time": "19:33:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 280, "total_steps": 453, "loss": 0.7205, "learning_rate": 1.9168557029126963e-05, "epoch": 0.6180589087397392, "percentage": 61.81, "elapsed_time": "1 day, 5:55:20", "remaining_time": "18:29:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 290, "total_steps": 453, "loss": 0.7215, "learning_rate": 1.7311289886731408e-05, "epoch": 0.6401324411947299, "percentage": 64.02, "elapsed_time": "1 day, 6:59:03", "remaining_time": "17:24:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 300, "total_steps": 453, "loss": 0.7204, "learning_rate": 1.549981043824425e-05, "epoch": 0.6622059736497207, "percentage": 66.23, "elapsed_time": "1 day, 8:02:33", "remaining_time": "16:20:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 310, "total_steps": 453, "loss": 0.7217, "learning_rate": 1.3744906379558165e-05, "epoch": 0.6842795061047113, "percentage": 68.43, "elapsed_time": "1 day, 9:05:54", "remaining_time": "15:16:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 320, "total_steps": 453, "loss": 0.7288, "learning_rate": 1.2057028489632682e-05, "epoch": 0.706353038559702, "percentage": 70.64, "elapsed_time": "1 day, 10:09:19", "remaining_time": "14:11:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 330, "total_steps": 453, "loss": 0.7128, "learning_rate": 1.0446228394168356e-05, "epoch": 0.7284265710146927, "percentage": 72.85, "elapsed_time": "1 day, 11:12:40", "remaining_time": "13:07:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 340, "total_steps": 453, "loss": 0.7212, "learning_rate": 8.922098706312548e-06, "epoch": 0.7505001034696834, "percentage": 75.06, "elapsed_time": "1 day, 12:16:03", "remaining_time": "12:03:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 350, "total_steps": 453, "loss": 0.7109, "learning_rate": 7.493715900870027e-06, "epoch": 0.7725736359246741, "percentage": 77.26, "elapsed_time": "1 day, 13:19:26", "remaining_time": "10:59:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 360, "total_steps": 453, "loss": 0.7206, "learning_rate": 6.169586262213081e-06, "epoch": 0.7946471683796648, "percentage": 79.47, "elapsed_time": "1 day, 14:22:50", "remaining_time": "9:54:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 370, "total_steps": 453, "loss": 0.7166, "learning_rate": 4.957595227781395e-06, "epoch": 0.8167207008346554, "percentage": 81.68, "elapsed_time": "1 day, 15:26:17", "remaining_time": "8:50:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 380, "total_steps": 453, "loss": 0.7095, "learning_rate": 3.864960428840375e-06, "epoch": 0.8387942332896461, "percentage": 83.89, "elapsed_time": "1 day, 16:29:44", "remaining_time": "7:46:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 390, "total_steps": 453, "loss": 0.7088, "learning_rate": 2.8981887081491576e-06, "epoch": 0.8608677657446369, "percentage": 86.09, "elapsed_time": "1 day, 17:33:28", "remaining_time": "6:42:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 400, "total_steps": 453, "loss": 0.7189, "learning_rate": 2.0630373705058407e-06, "epoch": 0.8829412981996275, "percentage": 88.3, "elapsed_time": "1 day, 18:36:48", "remaining_time": "5:38:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 453, "loss": 0.7215, "learning_rate": 1.3644798969302403e-06, "epoch": 0.9050148306546182, "percentage": 90.51, "elapsed_time": "1 day, 19:40:02", "remaining_time": "4:34:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 453, "loss": 0.7155, "learning_rate": 8.066763266625282e-07, "epoch": 0.9270883631096088, "percentage": 92.72, "elapsed_time": "1 day, 20:43:43", "remaining_time": "3:30:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 453, "loss": 0.7076, "learning_rate": 3.929484833584546e-07, "epoch": 0.9491618955645996, "percentage": 94.92, "elapsed_time": "1 day, 21:47:27", "remaining_time": "2:26:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 453, "loss": 0.7176, "learning_rate": 1.2576019301373532e-07, "epoch": 0.9712354280195903, "percentage": 97.13, "elapsed_time": "1 day, 22:51:11", "remaining_time": "1:23:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 453, "loss": 0.7082, "learning_rate": 6.702611423550775e-09, "epoch": 0.993308960474581, "percentage": 99.34, "elapsed_time": "1 day, 23:54:56", "remaining_time": "0:19:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 453, "total_steps": 453, "epoch": 0.9999310202110782, "percentage": 100.0, "elapsed_time": "2 days, 0:18:26", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,357 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999310202110782,
+  "eval_steps": 500,
+  "global_step": 453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022073532454990687,
+      "grad_norm": 1.114385199189024,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.8555,
+      "step": 10
+    },
+    {
+      "epoch": 0.044147064909981375,
+      "grad_norm": 0.4068262714558307,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.7997,
+      "step": 20
+    },
+    {
+      "epoch": 0.06622059736497206,
+      "grad_norm": 0.38632787233483873,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.7758,
+      "step": 30
+    },
+    {
+      "epoch": 0.08829412981996275,
+      "grad_norm": 0.33047790751954587,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.7616,
+      "step": 40
+    },
+    {
+      "epoch": 0.11036766227495344,
+      "grad_norm": 1.0326147215252546,
+      "learning_rate": 4.9988084660498037e-05,
+      "loss": 0.7609,
+      "step": 50
+    },
+    {
+      "epoch": 0.13244119472994412,
+      "grad_norm": 0.36413735150639703,
+      "learning_rate": 4.985416749673074e-05,
+      "loss": 0.7677,
+      "step": 60
+    },
+    {
+      "epoch": 0.1545147271849348,
+      "grad_norm": 0.23884890145764054,
+      "learning_rate": 4.957223915853709e-05,
+      "loss": 0.7558,
+      "step": 70
+    },
+    {
+      "epoch": 0.1765882596399255,
+      "grad_norm": 0.35792840187365693,
+      "learning_rate": 4.9143978581429445e-05,
+      "loss": 0.7492,
+      "step": 80
+    },
+    {
+      "epoch": 0.1986617920949162,
+      "grad_norm": 0.24556724333359267,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 0.7497,
+      "step": 90
+    },
+    {
+      "epoch": 0.22073532454990688,
+      "grad_norm": 0.2087162197069783,
+      "learning_rate": 4.78595184426236e-05,
+      "loss": 0.7433,
+      "step": 100
+    },
+    {
+      "epoch": 0.24280885700489757,
+      "grad_norm": 0.30705087020634647,
+      "learning_rate": 4.7010968079140294e-05,
+      "loss": 0.744,
+      "step": 110
+    },
+    {
+      "epoch": 0.26488238945988823,
+      "grad_norm": 0.2021404929324958,
+      "learning_rate": 4.6031338320779534e-05,
+      "loss": 0.7378,
+      "step": 120
+    },
+    {
+      "epoch": 0.28695592191487895,
+      "grad_norm": 0.3679260523738371,
+      "learning_rate": 4.492646304433711e-05,
+      "loss": 0.7388,
+      "step": 130
+    },
+    {
+      "epoch": 0.3090294543698696,
+      "grad_norm": 0.2575945484350903,
+      "learning_rate": 4.3702921986884574e-05,
+      "loss": 0.7301,
+      "step": 140
+    },
+    {
+      "epoch": 0.33110298682486033,
+      "grad_norm": 0.1987923782298564,
+      "learning_rate": 4.236800156221536e-05,
+      "loss": 0.7407,
+      "step": 150
+    },
+    {
+      "epoch": 0.353176519279851,
+      "grad_norm": 0.22541496226647023,
+      "learning_rate": 4.092965146890002e-05,
+      "loss": 0.7319,
+      "step": 160
+    },
+    {
+      "epoch": 0.3752500517348417,
+      "grad_norm": 0.1903443234063274,
+      "learning_rate": 3.9396437348357684e-05,
+      "loss": 0.7292,
+      "step": 170
+    },
+    {
+      "epoch": 0.3973235841898324,
+      "grad_norm": 0.2786630443541303,
+      "learning_rate": 3.777748977487366e-05,
+      "loss": 0.7488,
+      "step": 180
+    },
+    {
+      "epoch": 0.41939711664482304,
+      "grad_norm": 0.22941720588230605,
+      "learning_rate": 3.608244988133713e-05,
+      "loss": 0.7305,
+      "step": 190
+    },
+    {
+      "epoch": 0.44147064909981376,
+      "grad_norm": 0.2244920841625261,
+      "learning_rate": 3.432141194450772e-05,
+      "loss": 0.7329,
+      "step": 200
+    },
+    {
+      "epoch": 0.4635441815548044,
+      "grad_norm": 0.20271098423902761,
+      "learning_rate": 3.2504863271726286e-05,
+      "loss": 0.729,
+      "step": 210
+    },
+    {
+      "epoch": 0.48561771400979514,
+      "grad_norm": 0.21017591515648715,
+      "learning_rate": 3.064362174705578e-05,
+      "loss": 0.7392,
+      "step": 220
+    },
+    {
+      "epoch": 0.5076912464647858,
+      "grad_norm": 0.16688378969283219,
+      "learning_rate": 2.8748771408776466e-05,
+      "loss": 0.7323,
+      "step": 230
+    },
+    {
+      "epoch": 0.5297647789197765,
+      "grad_norm": 0.18531081231895546,
+      "learning_rate": 2.683159644188339e-05,
+      "loss": 0.7391,
+      "step": 240
+    },
+    {
+      "epoch": 0.5518383113747672,
+      "grad_norm": 0.1949891552768074,
+      "learning_rate": 2.4903513978673077e-05,
+      "loss": 0.7304,
+      "step": 250
+    },
+    {
+      "epoch": 0.5739118438297579,
+      "grad_norm": 0.1847538114841563,
+      "learning_rate": 2.2976006107604482e-05,
+      "loss": 0.7248,
+      "step": 260
+    },
+    {
+      "epoch": 0.5959853762847486,
+      "grad_norm": 0.17808591988598846,
+      "learning_rate": 2.1060551495333818e-05,
+      "loss": 0.7361,
+      "step": 270
+    },
+    {
+      "epoch": 0.6180589087397392,
+      "grad_norm": 0.15634167603442348,
+      "learning_rate": 1.9168557029126963e-05,
+      "loss": 0.7205,
+      "step": 280
+    },
+    {
+      "epoch": 0.6401324411947299,
+      "grad_norm": 0.16800926021112392,
+      "learning_rate": 1.7311289886731408e-05,
+      "loss": 0.7215,
+      "step": 290
+    },
+    {
+      "epoch": 0.6622059736497207,
+      "grad_norm": 0.15374716011431305,
+      "learning_rate": 1.549981043824425e-05,
+      "loss": 0.7204,
+      "step": 300
+    },
+    {
+      "epoch": 0.6842795061047113,
+      "grad_norm": 0.1358494068080939,
+      "learning_rate": 1.3744906379558165e-05,
+      "loss": 0.7217,
+      "step": 310
+    },
+    {
+      "epoch": 0.706353038559702,
+      "grad_norm": 0.1598338460219363,
+      "learning_rate": 1.2057028489632682e-05,
+      "loss": 0.7288,
+      "step": 320
+    },
+    {
+      "epoch": 0.7284265710146927,
+      "grad_norm": 0.1552517836620765,
+      "learning_rate": 1.0446228394168356e-05,
+      "loss": 0.7128,
+      "step": 330
+    },
+    {
+      "epoch": 0.7505001034696834,
+      "grad_norm": 0.1363267921768715,
+      "learning_rate": 8.922098706312548e-06,
+      "loss": 0.7212,
+      "step": 340
+    },
+    {
+      "epoch": 0.7725736359246741,
+      "grad_norm": 0.1417947472753852,
+      "learning_rate": 7.493715900870027e-06,
+      "loss": 0.7109,
+      "step": 350
+    },
+    {
+      "epoch": 0.7946471683796648,
+      "grad_norm": 0.13261081741759453,
+      "learning_rate": 6.169586262213081e-06,
+      "loss": 0.7206,
+      "step": 360
+    },
+    {
+      "epoch": 0.8167207008346554,
+      "grad_norm": 0.13329678652766908,
+      "learning_rate": 4.957595227781395e-06,
+      "loss": 0.7166,
+      "step": 370
+    },
+    {
+      "epoch": 0.8387942332896461,
+      "grad_norm": 0.13079371602746745,
+      "learning_rate": 3.864960428840375e-06,
+      "loss": 0.7095,
+      "step": 380
+    },
+    {
+      "epoch": 0.8608677657446369,
+      "grad_norm": 0.12980162903604736,
+      "learning_rate": 2.8981887081491576e-06,
+      "loss": 0.7088,
+      "step": 390
+    },
+    {
+      "epoch": 0.8829412981996275,
+      "grad_norm": 0.12204737322722421,
+      "learning_rate": 2.0630373705058407e-06,
+      "loss": 0.7189,
+      "step": 400
+    },
+    {
+      "epoch": 0.9050148306546182,
+      "grad_norm": 0.12227603852992606,
+      "learning_rate": 1.3644798969302403e-06,
+      "loss": 0.7215,
+      "step": 410
+    },
+    {
+      "epoch": 0.9270883631096088,
+      "grad_norm": 0.12433131124525597,
+      "learning_rate": 8.066763266625282e-07,
+      "loss": 0.7155,
+      "step": 420
+    },
+    {
+      "epoch": 0.9491618955645996,
+      "grad_norm": 0.12167710585090329,
+      "learning_rate": 3.929484833584546e-07,
+      "loss": 0.7076,
+      "step": 430
+    },
+    {
+      "epoch": 0.9712354280195903,
+      "grad_norm": 0.12190898417393506,
+      "learning_rate": 1.2576019301373532e-07,
+      "loss": 0.7176,
+      "step": 440
+    },
+    {
+      "epoch": 0.993308960474581,
+      "grad_norm": 0.1232187443009331,
+      "learning_rate": 6.702611423550775e-09,
+      "loss": 0.7082,
+      "step": 450
+    },
+    {
+      "epoch": 0.9999310202110782,
+      "step": 453,
+      "total_flos": 3799534094254080.0,
+      "train_loss": 0.7359120230011592,
+      "train_runtime": 173906.7289,
+      "train_samples_per_second": 1.334,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 453,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3799534094254080.0,
+  "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:acc8abfaec2c2ea4783e8a6e7e3eabb388d4ce5c44b7e6cb3256dbf71c0ba490
+size 7032