Upload 16 files

.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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2.5-math-1.5b-instruct-sciqag
+  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. -->
+
+# qwen2.5-math-1.5b-instruct-sciqag
+
+This model is a fine-tuned version of [../models/qwen2.5-math-1.5b-instruct](https://huggingface.co/../models/qwen2.5-math-1.5b-instruct) on the sciqag dataset.
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.98876404494382,
+    "total_flos": 4662359162880.0,
+    "train_loss": 2.0376082160256126,
+    "train_runtime": 1365.9005,
+    "train_samples_per_second": 31.228,
+    "train_steps_per_second": 0.242
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "../models/qwen2.5-math-1.5b-instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552e42816bae6b2728e33f4ba0d21e08862f5d42fba298aa073fe14214444d66
+size 3087467144

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 +1,209 @@
+{
+  "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        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.98876404494382,
+    "total_flos": 4662359162880.0,
+    "train_loss": 2.0376082160256126,
+    "train_runtime": 1365.9005,
+    "train_samples_per_second": 31.228,
+    "train_steps_per_second": 0.242
+}

trainer_log.jsonl

@@ -0,0 +1,34 @@
+{"current_steps": 10, "total_steps": 330, "loss": 3.4296, "lr": 1.1764705882352942e-05, "epoch": 0.149812734082397, "percentage": 3.03, "elapsed_time": "0:00:43", "remaining_time": "0:22:58"}
+{"current_steps": 20, "total_steps": 330, "loss": 3.1559, "lr": 1.9995466947279753e-05, "epoch": 0.299625468164794, "percentage": 6.06, "elapsed_time": "0:01:23", "remaining_time": "0:21:38"}
+{"current_steps": 30, "total_steps": 330, "loss": 3.0083, "lr": 1.9914993620144055e-05, "epoch": 0.449438202247191, "percentage": 9.09, "elapsed_time": "0:02:04", "remaining_time": "0:20:42"}
+{"current_steps": 40, "total_steps": 330, "loss": 2.8453, "lr": 1.9734718376564386e-05, "epoch": 0.599250936329588, "percentage": 12.12, "elapsed_time": "0:02:44", "remaining_time": "0:19:55"}
+{"current_steps": 50, "total_steps": 330, "loss": 2.7226, "lr": 1.945645582333587e-05, "epoch": 0.7490636704119851, "percentage": 15.15, "elapsed_time": "0:03:25", "remaining_time": "0:19:11"}
+{"current_steps": 60, "total_steps": 330, "loss": 2.6656, "lr": 1.9083006883701688e-05, "epoch": 0.898876404494382, "percentage": 18.18, "elapsed_time": "0:04:06", "remaining_time": "0:18:28"}
+{"current_steps": 70, "total_steps": 330, "loss": 2.7955, "lr": 1.8618130603940386e-05, "epoch": 1.0599250936329587, "percentage": 21.21, "elapsed_time": "0:04:48", "remaining_time": "0:17:50"}
+{"current_steps": 80, "total_steps": 330, "loss": 2.3523, "lr": 1.806650631571943e-05, "epoch": 1.2097378277153559, "percentage": 24.24, "elapsed_time": "0:05:28", "remaining_time": "0:17:07"}
+{"current_steps": 90, "total_steps": 330, "loss": 2.2764, "lr": 1.7433686535079736e-05, "epoch": 1.3595505617977528, "percentage": 27.27, "elapsed_time": "0:06:09", "remaining_time": "0:16:24"}
+{"current_steps": 100, "total_steps": 330, "loss": 2.2374, "lr": 1.672604107215848e-05, "epoch": 1.5093632958801497, "percentage": 30.3, "elapsed_time": "0:06:49", "remaining_time": "0:15:42"}
+{"current_steps": 110, "total_steps": 330, "loss": 2.2145, "lr": 1.595069291422807e-05, "epoch": 1.6591760299625467, "percentage": 33.33, "elapsed_time": "0:07:30", "remaining_time": "0:15:01"}
+{"current_steps": 120, "total_steps": 330, "loss": 2.2315, "lr": 1.5115446527437193e-05, "epoch": 1.8089887640449438, "percentage": 36.36, "elapsed_time": "0:08:11", "remaining_time": "0:14:19"}
+{"current_steps": 130, "total_steps": 330, "loss": 2.219, "lr": 1.4228709298950998e-05, "epoch": 1.958801498127341, "percentage": 39.39, "elapsed_time": "0:08:51", "remaining_time": "0:13:38"}
+{"current_steps": 140, "total_steps": 330, "loss": 2.188, "lr": 1.3299406910234917e-05, "epoch": 2.1198501872659175, "percentage": 42.42, "elapsed_time": "0:09:33", "remaining_time": "0:12:58"}
+{"current_steps": 150, "total_steps": 330, "loss": 1.8844, "lr": 1.2336893493313946e-05, "epoch": 2.2696629213483144, "percentage": 45.45, "elapsed_time": "0:10:14", "remaining_time": "0:12:17"}
+{"current_steps": 160, "total_steps": 330, "loss": 1.875, "lr": 1.1350857474352734e-05, "epoch": 2.4194756554307117, "percentage": 48.48, "elapsed_time": "0:10:54", "remaining_time": "0:11:35"}
+{"current_steps": 170, "total_steps": 330, "loss": 1.852, "lr": 1.035122405231209e-05, "epoch": 2.5692883895131087, "percentage": 51.52, "elapsed_time": "0:11:35", "remaining_time": "0:10:54"}
+{"current_steps": 180, "total_steps": 330, "loss": 1.8581, "lr": 9.348055294308074e-06, "epoch": 2.7191011235955056, "percentage": 54.55, "elapsed_time": "0:12:16", "remaining_time": "0:10:13"}
+{"current_steps": 190, "total_steps": 330, "loss": 1.8616, "lr": 8.351448853289448e-06, "epoch": 2.8689138576779025, "percentage": 57.58, "elapsed_time": "0:12:56", "remaining_time": "0:09:32"}
+{"current_steps": 200, "total_steps": 330, "loss": 1.9958, "lr": 7.371436327516854e-06, "epoch": 3.0299625468164795, "percentage": 60.61, "elapsed_time": "0:13:39", "remaining_time": "0:08:52"}
+{"current_steps": 210, "total_steps": 330, "loss": 1.6019, "lr": 6.417882284932373e-06, "epoch": 3.1797752808988764, "percentage": 63.64, "elapsed_time": "0:14:19", "remaining_time": "0:08:11"}
+{"current_steps": 220, "total_steps": 330, "loss": 1.5769, "lr": 5.5003849688157075e-06, "epoch": 3.3295880149812733, "percentage": 66.67, "elapsed_time": "0:15:00", "remaining_time": "0:07:30"}
+{"current_steps": 230, "total_steps": 330, "loss": 1.5771, "lr": 4.628179684199685e-06, "epoch": 3.4794007490636703, "percentage": 69.7, "elapsed_time": "0:15:41", "remaining_time": "0:06:49"}
+{"current_steps": 240, "total_steps": 330, "loss": 1.5697, "lr": 3.81004583753399e-06, "epoch": 3.629213483146067, "percentage": 72.73, "elapsed_time": "0:16:21", "remaining_time": "0:06:08"}
+{"current_steps": 250, "total_steps": 330, "loss": 1.5704, "lr": 3.0542185653132216e-06, "epoch": 3.7790262172284645, "percentage": 75.76, "elapsed_time": "0:17:01", "remaining_time": "0:05:26"}
+{"current_steps": 260, "total_steps": 330, "loss": 1.5622, "lr": 2.3683058411940563e-06, "epoch": 3.9288389513108615, "percentage": 78.79, "elapsed_time": "0:17:42", "remaining_time": "0:04:46"}
+{"current_steps": 270, "total_steps": 330, "loss": 1.6549, "lr": 1.75921189598118e-06, "epoch": 4.089887640449438, "percentage": 81.82, "elapsed_time": "0:18:24", "remaining_time": "0:04:05"}
+{"current_steps": 280, "total_steps": 330, "loss": 1.4349, "lr": 1.2330677213177034e-06, "epoch": 4.239700374531835, "percentage": 84.85, "elapsed_time": "0:19:05", "remaining_time": "0:03:24"}
+{"current_steps": 290, "total_steps": 330, "loss": 1.4191, "lr": 7.951693566131325e-07, "epoch": 4.389513108614232, "percentage": 87.88, "elapsed_time": "0:19:45", "remaining_time": "0:02:43"}
+{"current_steps": 300, "total_steps": 330, "loss": 1.3715, "lr": 4.499245803975927e-07, "epoch": 4.539325842696629, "percentage": 90.91, "elapsed_time": "0:20:26", "remaining_time": "0:02:02"}
+{"current_steps": 310, "total_steps": 330, "loss": 1.4115, "lr": 2.00808542694233e-07, "epoch": 4.689138576779026, "percentage": 93.94, "elapsed_time": "0:21:07", "remaining_time": "0:01:21"}
+{"current_steps": 320, "total_steps": 330, "loss": 1.4175, "lr": 5.032878500355498e-08, "epoch": 4.8389513108614235, "percentage": 96.97, "elapsed_time": "0:21:47", "remaining_time": "0:00:40"}
+{"current_steps": 330, "total_steps": 330, "loss": 1.4049, "lr": 0.0, "epoch": 4.98876404494382, "percentage": 100.0, "elapsed_time": "0:22:28", "remaining_time": "0:00:00"}
+{"current_steps": 330, "total_steps": 330, "epoch": 4.98876404494382, "percentage": 100.0, "elapsed_time": "0:22:44", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.98876404494382,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.149812734082397,
+      "grad_norm": 0.6240223192562641,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 3.4296,
+      "step": 10
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 0.4759039088058634,
+      "learning_rate": 1.9995466947279753e-05,
+      "loss": 3.1559,
+      "step": 20
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.3704142461383357,
+      "learning_rate": 1.9914993620144055e-05,
+      "loss": 3.0083,
+      "step": 30
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.3072287367616599,
+      "learning_rate": 1.9734718376564386e-05,
+      "loss": 2.8453,
+      "step": 40
+    },
+    {
+      "epoch": 0.7490636704119851,
+      "grad_norm": 0.31016408017448077,
+      "learning_rate": 1.945645582333587e-05,
+      "loss": 2.7226,
+      "step": 50
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.30188871160390746,
+      "learning_rate": 1.9083006883701688e-05,
+      "loss": 2.6656,
+      "step": 60
+    },
+    {
+      "epoch": 1.0599250936329587,
+      "grad_norm": 0.24590439921946178,
+      "learning_rate": 1.8618130603940386e-05,
+      "loss": 2.7955,
+      "step": 70
+    },
+    {
+      "epoch": 1.2097378277153559,
+      "grad_norm": 0.2782213231278689,
+      "learning_rate": 1.806650631571943e-05,
+      "loss": 2.3523,
+      "step": 80
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 0.2671277031974292,
+      "learning_rate": 1.7433686535079736e-05,
+      "loss": 2.2764,
+      "step": 90
+    },
+    {
+      "epoch": 1.5093632958801497,
+      "grad_norm": 0.2703437385004914,
+      "learning_rate": 1.672604107215848e-05,
+      "loss": 2.2374,
+      "step": 100
+    },
+    {
+      "epoch": 1.6591760299625467,
+      "grad_norm": 0.27488249330165304,
+      "learning_rate": 1.595069291422807e-05,
+      "loss": 2.2145,
+      "step": 110
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 0.27322654774524974,
+      "learning_rate": 1.5115446527437193e-05,
+      "loss": 2.2315,
+      "step": 120
+    },
+    {
+      "epoch": 1.958801498127341,
+      "grad_norm": 0.2496550941163805,
+      "learning_rate": 1.4228709298950998e-05,
+      "loss": 2.219,
+      "step": 130
+    },
+    {
+      "epoch": 2.1198501872659175,
+      "grad_norm": 0.23748686371621341,
+      "learning_rate": 1.3299406910234917e-05,
+      "loss": 2.188,
+      "step": 140
+    },
+    {
+      "epoch": 2.2696629213483144,
+      "grad_norm": 0.254579126507857,
+      "learning_rate": 1.2336893493313946e-05,
+      "loss": 1.8844,
+      "step": 150
+    },
+    {
+      "epoch": 2.4194756554307117,
+      "grad_norm": 0.2533144202689544,
+      "learning_rate": 1.1350857474352734e-05,
+      "loss": 1.875,
+      "step": 160
+    },
+    {
+      "epoch": 2.5692883895131087,
+      "grad_norm": 0.24718451680051595,
+      "learning_rate": 1.035122405231209e-05,
+      "loss": 1.852,
+      "step": 170
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 0.25305694819263813,
+      "learning_rate": 9.348055294308074e-06,
+      "loss": 1.8581,
+      "step": 180
+    },
+    {
+      "epoch": 2.8689138576779025,
+      "grad_norm": 0.25728520443261826,
+      "learning_rate": 8.351448853289448e-06,
+      "loss": 1.8616,
+      "step": 190
+    },
+    {
+      "epoch": 3.0299625468164795,
+      "grad_norm": 0.264486812241608,
+      "learning_rate": 7.371436327516854e-06,
+      "loss": 1.9958,
+      "step": 200
+    },
+    {
+      "epoch": 3.1797752808988764,
+      "grad_norm": 0.2825888432885122,
+      "learning_rate": 6.417882284932373e-06,
+      "loss": 1.6019,
+      "step": 210
+    },
+    {
+      "epoch": 3.3295880149812733,
+      "grad_norm": 0.312588763374677,
+      "learning_rate": 5.5003849688157075e-06,
+      "loss": 1.5769,
+      "step": 220
+    },
+    {
+      "epoch": 3.4794007490636703,
+      "grad_norm": 0.28888515165506573,
+      "learning_rate": 4.628179684199685e-06,
+      "loss": 1.5771,
+      "step": 230
+    },
+    {
+      "epoch": 3.629213483146067,
+      "grad_norm": 0.2966244683463888,
+      "learning_rate": 3.81004583753399e-06,
+      "loss": 1.5697,
+      "step": 240
+    },
+    {
+      "epoch": 3.7790262172284645,
+      "grad_norm": 0.2894357788177964,
+      "learning_rate": 3.0542185653132216e-06,
+      "loss": 1.5704,
+      "step": 250
+    },
+    {
+      "epoch": 3.9288389513108615,
+      "grad_norm": 0.28773356307664283,
+      "learning_rate": 2.3683058411940563e-06,
+      "loss": 1.5622,
+      "step": 260
+    },
+    {
+      "epoch": 4.089887640449438,
+      "grad_norm": 0.2786673362193353,
+      "learning_rate": 1.75921189598118e-06,
+      "loss": 1.6549,
+      "step": 270
+    },
+    {
+      "epoch": 4.239700374531835,
+      "grad_norm": 0.2699331901599701,
+      "learning_rate": 1.2330677213177034e-06,
+      "loss": 1.4349,
+      "step": 280
+    },
+    {
+      "epoch": 4.389513108614232,
+      "grad_norm": 0.2940053977518716,
+      "learning_rate": 7.951693566131325e-07,
+      "loss": 1.4191,
+      "step": 290
+    },
+    {
+      "epoch": 4.539325842696629,
+      "grad_norm": 0.30293515491434625,
+      "learning_rate": 4.499245803975927e-07,
+      "loss": 1.3715,
+      "step": 300
+    },
+    {
+      "epoch": 4.689138576779026,
+      "grad_norm": 0.30080510867957,
+      "learning_rate": 2.00808542694233e-07,
+      "loss": 1.4115,
+      "step": 310
+    },
+    {
+      "epoch": 4.8389513108614235,
+      "grad_norm": 0.2849664523708078,
+      "learning_rate": 5.032878500355498e-08,
+      "loss": 1.4175,
+      "step": 320
+    },
+    {
+      "epoch": 4.98876404494382,
+      "grad_norm": 0.29196026814035136,
+      "learning_rate": 0.0,
+      "loss": 1.4049,
+      "step": 330
+    },
+    {
+      "epoch": 4.98876404494382,
+      "step": 330,
+      "total_flos": 4662359162880.0,
+      "train_loss": 2.0376082160256126,
+      "train_runtime": 1365.9005,
+      "train_samples_per_second": 31.228,
+      "train_steps_per_second": 0.242
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4662359162880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5175fcbb03a2b2ff5ae69db37206a9aa88931d20955a5e8382dd5042cad6dfed
+size 7480