Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,158 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/lora-out
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.5.0`
+```yaml
+base_model: Qwen/Qwen2.5-14B-Instruct
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: output.jsonl
+    type: alpaca
+
+special_tokens:
+  bos_token:
+  eos_token: "<|im_end|>"
+  pad_token: "<|endoftext|>"
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/lora-out
+
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project: axolotl_gmatrix
+wandb_entity: mssong
+wandb_watch:
+wandb_run_id: 
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 3
+optimizer:
+lr_scheduler: cosine
+learning_rate: 0.00006
+train_on_inputs:
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+gradient_checkpointing: true
+early_stopping_patience: 4
+local_rank:
+logging_steps: 100
+xformers_attention:
+flash_attention: true
+warmup_ratio: 0.05
+#warmup_steps: 100
+eval_steps: 100
+save_steps: 100
+save_total_limit: 2
+eval_sample_packing:
+debug:
+deepspeed:
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+trust_remote_code: true
+```
+
+</details><br>
+
+# outputs/lora-out
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0875
+
+## 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: 6e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 162
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0009 | 1    | 0.4243          |
+| 0.2465        | 0.0923 | 100  | 0.1338          |
+| 0.0425        | 0.1847 | 200  | 0.1110          |
+| 0.0333        | 0.2770 | 300  | 0.1051          |
+| 0.0319        | 0.3693 | 400  | 0.0933          |
+| 0.0257        | 0.4617 | 500  | 0.0886          |
+| 0.0245        | 0.5540 | 600  | 0.0898          |
+| 0.0262        | 0.6464 | 700  | 0.0889          |
+| 0.025         | 0.7387 | 800  | 0.0827          |
+| 0.0221        | 0.8310 | 900  | 0.0813          |
+| 0.0207        | 0.9234 | 1000 | 0.0901          |
+| 0.0219        | 1.0157 | 1100 | 0.0878          |
+| 0.0132        | 1.1080 | 1200 | 0.0890          |
+| 0.0154        | 1.2004 | 1300 | 0.0875          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.1
+- Pytorch 2.3.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.3

README.md

@@ -0,0 +1,158 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/lora-out
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.5.0`
+```yaml
+base_model: Qwen/Qwen2.5-14B-Instruct
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: output.jsonl
+    type: alpaca
+
+special_tokens:
+  bos_token:
+  eos_token: "<|im_end|>"
+  pad_token: "<|endoftext|>"
+
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./outputs/lora-out
+
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project: axolotl_gmatrix
+wandb_entity: mssong
+wandb_watch:
+wandb_run_id: 
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 3
+optimizer:
+lr_scheduler: cosine
+learning_rate: 0.00006
+train_on_inputs:
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+gradient_checkpointing: true
+early_stopping_patience: 4
+local_rank:
+logging_steps: 100
+xformers_attention:
+flash_attention: true
+warmup_ratio: 0.05
+#warmup_steps: 100
+eval_steps: 100
+save_steps: 100
+save_total_limit: 2
+eval_sample_packing:
+debug:
+deepspeed:
+weight_decay: 0.01
+fsdp:
+fsdp_config:
+trust_remote_code: true
+```
+
+</details><br>
+
+# outputs/lora-out
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0875
+
+## 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: 6e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 162
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0009 | 1    | 0.4243          |
+| 0.2465        | 0.0923 | 100  | 0.1338          |
+| 0.0425        | 0.1847 | 200  | 0.1110          |
+| 0.0333        | 0.2770 | 300  | 0.1051          |
+| 0.0319        | 0.3693 | 400  | 0.0933          |
+| 0.0257        | 0.4617 | 500  | 0.0886          |
+| 0.0245        | 0.5540 | 600  | 0.0898          |
+| 0.0262        | 0.6464 | 700  | 0.0889          |
+| 0.025         | 0.7387 | 800  | 0.0827          |
+| 0.0221        | 0.8310 | 900  | 0.0813          |
+| 0.0207        | 0.9234 | 1000 | 0.0901          |
+| 0.0219        | 1.0157 | 1100 | 0.0878          |
+| 0.0132        | 1.1080 | 1200 | 0.0890          |
+| 0.0154        | 1.2004 | 1300 | 0.0875          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.1
+- Pytorch 2.3.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b523102aeb55843ce14795d4a560f0d48fde8f742729373b202014b9f2df8c
+size 137714904

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7210edc61d2a15d50dfcb3cd302a54b72979c0f0f8737ce0883167b27a4527d1
+size 275650130

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b281140bd3bc67e82deebdc7da8a33d100a021dde1ab24c62384134c0901017
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29f4a6d635d5d181ecfeace9305954658575008ee9ccea9fd55f674b85ed2f1
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.08133330941200256,
+  "best_model_checkpoint": "./outputs/lora-out/checkpoint-900",
+  "epoch": 0.8310249307479224,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009233610341643582,
+      "eval_loss": 0.4242709279060364,
+      "eval_runtime": 91.8213,
+      "eval_samples_per_second": 1.252,
+      "eval_steps_per_second": 1.252,
+      "step": 1
+    },
+    {
+      "epoch": 0.09233610341643583,
+      "grad_norm": 0.6968376040458679,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.2465,
+      "step": 100
+    },
+    {
+      "epoch": 0.09233610341643583,
+      "eval_loss": 0.13379718363285065,
+      "eval_runtime": 93.2896,
+      "eval_samples_per_second": 1.233,
+      "eval_steps_per_second": 1.233,
+      "step": 100
+    },
+    {
+      "epoch": 0.18467220683287167,
+      "grad_norm": 0.38504940271377563,
+      "learning_rate": 5.997756992048411e-05,
+      "loss": 0.0425,
+      "step": 200
+    },
+    {
+      "epoch": 0.18467220683287167,
+      "eval_loss": 0.11098360270261765,
+      "eval_runtime": 93.1082,
+      "eval_samples_per_second": 1.235,
+      "eval_steps_per_second": 1.235,
+      "step": 200
+    },
+    {
+      "epoch": 0.2770083102493075,
+      "grad_norm": 0.21793705224990845,
+      "learning_rate": 5.970463299279944e-05,
+      "loss": 0.0333,
+      "step": 300
+    },
+    {
+      "epoch": 0.2770083102493075,
+      "eval_loss": 0.10511630773544312,
+      "eval_runtime": 93.095,
+      "eval_samples_per_second": 1.235,
+      "eval_steps_per_second": 1.235,
+      "step": 300
+    },
+    {
+      "epoch": 0.36934441366574333,
+      "grad_norm": 0.245796799659729,
+      "learning_rate": 5.912431591443999e-05,
+      "loss": 0.0319,
+      "step": 400
+    },
+    {
+      "epoch": 0.36934441366574333,
+      "eval_loss": 0.09326907247304916,
+      "eval_runtime": 93.3684,
+      "eval_samples_per_second": 1.232,
+      "eval_steps_per_second": 1.232,
+      "step": 400
+    },
+    {
+      "epoch": 0.4616805170821791,
+      "grad_norm": 0.2685442864894867,
+      "learning_rate": 5.824262374027476e-05,
+      "loss": 0.0257,
+      "step": 500
+    },
+    {
+      "epoch": 0.4616805170821791,
+      "eval_loss": 0.08864552527666092,
+      "eval_runtime": 93.324,
+      "eval_samples_per_second": 1.232,
+      "eval_steps_per_second": 1.232,
+      "step": 500
+    },
+    {
+      "epoch": 0.554016620498615,
+      "grad_norm": 0.2339438498020172,
+      "learning_rate": 5.706868012025456e-05,
+      "loss": 0.0245,
+      "step": 600
+    },
+    {
+      "epoch": 0.554016620498615,
+      "eval_loss": 0.08980301022529602,
+      "eval_runtime": 93.1142,
+      "eval_samples_per_second": 1.235,
+      "eval_steps_per_second": 1.235,
+      "step": 600
+    },
+    {
+      "epoch": 0.6463527239150508,
+      "grad_norm": 0.17079927027225494,
+      "learning_rate": 5.561463288892402e-05,
+      "loss": 0.0262,
+      "step": 700
+    },
+    {
+      "epoch": 0.6463527239150508,
+      "eval_loss": 0.08885745704174042,
+      "eval_runtime": 93.2779,
+      "eval_samples_per_second": 1.233,
+      "eval_steps_per_second": 1.233,
+      "step": 700
+    },
+    {
+      "epoch": 0.7386888273314867,
+      "grad_norm": 0.18653833866119385,
+      "learning_rate": 5.389552836101671e-05,
+      "loss": 0.025,
+      "step": 800
+    },
+    {
+      "epoch": 0.7386888273314867,
+      "eval_loss": 0.08268226683139801,
+      "eval_runtime": 92.9671,
+      "eval_samples_per_second": 1.237,
+      "eval_steps_per_second": 1.237,
+      "step": 800
+    },
+    {
+      "epoch": 0.8310249307479224,
+      "grad_norm": 0.027869287878274918,
+      "learning_rate": 5.192915563390816e-05,
+      "loss": 0.0221,
+      "step": 900
+    },
+    {
+      "epoch": 0.8310249307479224,
+      "eval_loss": 0.08133330941200256,
+      "eval_runtime": 93.0513,
+      "eval_samples_per_second": 1.236,
+      "eval_steps_per_second": 1.236,
+      "step": 900
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3249,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.204597114765312e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5143b88b46370ca1a5870853b9b004a4400aab88a90c747a71222c07713a9ed3
+size 6200