Training in progress, step 5

autotrain-data/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

autotrain-data/train/data-00000-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcff7033322edc5457a872e7102d5b73008886f82298fd3aa8500e31f0e1898
+size 612540528

autotrain-data/train/data-00001-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d97f6a51a5deffb0ddf7c0df4b6305c829b90728e941d263fab64ad33c82db
+size 582202992

autotrain-data/train/data-00002-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962772a8f12b6f501e35d580958aa39e405034839e107981c2ff0c5af4852a6c
+size 469873904

autotrain-data/train/data-00003-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22969288efa339ddb93f3b0c96cfa6cd495c71696c4468e4c9adfd13bf7228dd
+size 141271728

autotrain-data/train/data-00004-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a151ebc8fb3be6e3969d48d651bfeb648146975ef5be3814f64efe51e6691f
+size 491365808

autotrain-data/train/data-00005-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e416d92cff19f2e316a49d2bf75471f787dfdcf08d35a1bec581d0dbbdebded3
+size 220452656

autotrain-data/train/dataset_info.json

@@ -0,0 +1,12 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

autotrain-data/train/state.json

@@ -0,0 +1,28 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00006.arrow"
+    },
+    {
+      "filename": "data-00001-of-00006.arrow"
+    },
+    {
+      "filename": "data-00002-of-00006.arrow"
+    },
+    {
+      "filename": "data-00003-of-00006.arrow"
+    },
+    {
+      "filename": "data-00004-of-00006.arrow"
+    },
+    {
+      "filename": "data-00005-of-00006.arrow"
+    }
+  ],
+  "_fingerprint": "92455bc5ac963ada",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

autotrain-data/validation/data-00000-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcff7033322edc5457a872e7102d5b73008886f82298fd3aa8500e31f0e1898
+size 612540528

autotrain-data/validation/data-00001-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d97f6a51a5deffb0ddf7c0df4b6305c829b90728e941d263fab64ad33c82db
+size 582202992

autotrain-data/validation/data-00002-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962772a8f12b6f501e35d580958aa39e405034839e107981c2ff0c5af4852a6c
+size 469873904

autotrain-data/validation/data-00003-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22969288efa339ddb93f3b0c96cfa6cd495c71696c4468e4c9adfd13bf7228dd
+size 141271728

autotrain-data/validation/data-00004-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a151ebc8fb3be6e3969d48d651bfeb648146975ef5be3814f64efe51e6691f
+size 491365808

autotrain-data/validation/data-00005-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e416d92cff19f2e316a49d2bf75471f787dfdcf08d35a1bec581d0dbbdebded3
+size 220452656

autotrain-data/validation/dataset_info.json

@@ -0,0 +1,12 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

autotrain-data/validation/state.json

@@ -0,0 +1,28 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00006.arrow"
+    },
+    {
+      "filename": "data-00001-of-00006.arrow"
+    },
+    {
+      "filename": "data-00002-of-00006.arrow"
+    },
+    {
+      "filename": "data-00003-of-00006.arrow"
+    },
+    {
+      "filename": "data-00004-of-00006.arrow"
+    },
+    {
+      "filename": "data-00005-of-00006.arrow"
+    }
+  ],
+  "_fingerprint": "92455bc5ac963ada",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "Wonder-Griffin/TraXLMistral",
+  "architectures": [
+    "TraXLMistralForCausalLM"
+  ],
+  "dropout": 0.1,
+  "dynamic_routing": true,
+  "ff_expansion_factor": 4,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "is_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_computation_steps": 5,
+  "max_len": 256,
+  "memory_size": 256,
+  "model_type": "TraXLMistral",
+  "n_embd": 128,
+  "n_head": 4,
+  "n_layer": 4,
+  "rnn_units": 128,
+  "sparse_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 50257
+}

dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c651e8f83effcdecd7724aba603a9b4c48743ec9ab6ee60fde6cd4e93e08178e
+size 194522976

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train/data-00000-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcff7033322edc5457a872e7102d5b73008886f82298fd3aa8500e31f0e1898
+size 612540528

train/data-00001-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d97f6a51a5deffb0ddf7c0df4b6305c829b90728e941d263fab64ad33c82db
+size 582202992

train/data-00002-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962772a8f12b6f501e35d580958aa39e405034839e107981c2ff0c5af4852a6c
+size 469873904

train/data-00003-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22969288efa339ddb93f3b0c96cfa6cd495c71696c4468e4c9adfd13bf7228dd
+size 141271728

train/data-00004-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a151ebc8fb3be6e3969d48d651bfeb648146975ef5be3814f64efe51e6691f
+size 491365808

train/data-00005-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e416d92cff19f2e316a49d2bf75471f787dfdcf08d35a1bec581d0dbbdebded3
+size 220452656

train/dataset_info.json

@@ -0,0 +1,12 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

train/state.json

@@ -0,0 +1,28 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00006.arrow"
+    },
+    {
+      "filename": "data-00001-of-00006.arrow"
+    },
+    {
+      "filename": "data-00002-of-00006.arrow"
+    },
+    {
+      "filename": "data-00003-of-00006.arrow"
+    },
+    {
+      "filename": "data-00004-of-00006.arrow"
+    },
+    {
+      "filename": "data-00005-of-00006.arrow"
+    }
+  ],
+  "_fingerprint": "92455bc5ac963ada",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458b0eb6720a39b1bb5d10fe01f32483acef761bfe7604e11cca92e3e2cf83d6
+size 5176

training_params (2).json

@@ -0,0 +1,49 @@
+{
+    "model": "Wonder-Griffin/TraXLMistral",
+    "project_name": "TrainTraXLLMistral-1",
+    "data_path": "TrainTraXLLMistral-1/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 512,
+    "model_max_length": 512,
+    "padding": "right",
+    "trainer": "default",
+    "use_flash_attention_2": true,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "eval_strategy": "steps",
+    "save_total_limit": 1,
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3.00003,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": null,
+    "target_modules": "all-linear",
+    "merge_adapter": true,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "max_prompt_length": 128,
+    "max_completion_length": null,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "username": "Wonder-Griffin",
+    "token": "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",
+    "unsloth": false
+}

training_params.json

@@ -0,0 +1,49 @@
+{
+    "model": "Wonder-Griffin/TraXLMistral",
+    "project_name": "trainingTraXLLMistral-2",
+    "data_path": "trainingTraXLLMistral-2/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 512,
+    "model_max_length": 512,
+    "padding": "right",
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "eval_strategy": "epoch",
+    "save_total_limit": 1,
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3.00003,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "max_prompt_length": 128,
+    "max_completion_length": null,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "username": "Wonder-Griffin",
+    "token": "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",
+    "unsloth": false
+}

validation/data-00000-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcff7033322edc5457a872e7102d5b73008886f82298fd3aa8500e31f0e1898
+size 612540528

validation/data-00001-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d97f6a51a5deffb0ddf7c0df4b6305c829b90728e941d263fab64ad33c82db
+size 582202992

validation/data-00002-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962772a8f12b6f501e35d580958aa39e405034839e107981c2ff0c5af4852a6c
+size 469873904

validation/data-00003-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22969288efa339ddb93f3b0c96cfa6cd495c71696c4468e4c9adfd13bf7228dd
+size 141271728

validation/data-00004-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a151ebc8fb3be6e3969d48d651bfeb648146975ef5be3814f64efe51e6691f
+size 491365808

validation/data-00005-of-00006.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e416d92cff19f2e316a49d2bf75471f787dfdcf08d35a1bec581d0dbbdebded3
+size 220452656

validation/dataset_info.json

@@ -0,0 +1,12 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

validation/state.json

@@ -0,0 +1,28 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00006.arrow"
+    },
+    {
+      "filename": "data-00001-of-00006.arrow"
+    },
+    {
+      "filename": "data-00002-of-00006.arrow"
+    },
+    {
+      "filename": "data-00003-of-00006.arrow"
+    },
+    {
+      "filename": "data-00004-of-00006.arrow"
+    },
+    {
+      "filename": "data-00005-of-00006.arrow"
+    }
+  ],
+  "_fingerprint": "92455bc5ac963ada",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}