Upload 15 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

@@ -1,3 +1,59 @@
----
-license: mit
----
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: models
+  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. -->
+
+# models
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the question_finetune_train 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- 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: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "up_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 sha256:77bf0adf2dc5814cdf195502da727dc2d3c37381e8c96fcf3aee1b17af9b109a
+size 295488936

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 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_question_finetune_val_loss": 0.21022072434425354,
+    "eval_question_finetune_val_runtime": 147.8928,
+    "eval_question_finetune_val_samples_per_second": 1.149,
+    "eval_question_finetune_val_steps_per_second": 1.149,
+    "total_flos": 2.11652989949952e+16,
+    "train_loss": 0.1360657389201815,
+    "train_runtime": 7264.9105,
+    "train_samples_per_second": 0.347,
+    "train_steps_per_second": 0.087
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_question_finetune_val_loss": 0.21022072434425354,
+    "eval_question_finetune_val_runtime": 147.8928,
+    "eval_question_finetune_val_samples_per_second": 1.149,
+    "eval_question_finetune_val_steps_per_second": 1.149
+}

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        {{- '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",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.11652989949952e+16,
+    "train_loss": 0.1360657389201815,
+    "train_runtime": 7264.9105,
+    "train_samples_per_second": 0.347,
+    "train_steps_per_second": 0.087
+}

trainer_log.jsonl

@@ -0,0 +1,70 @@
+{"current_steps": 10, "total_steps": 630, "loss": 0.2872, "lr": 1.5873015873015872e-05, "epoch": 0.047619047619047616, "percentage": 1.59, "elapsed_time": "0:01:35", "remaining_time": "1:38:45"}
+{"current_steps": 20, "total_steps": 630, "loss": 0.2256, "lr": 3.1746031746031745e-05, "epoch": 0.09523809523809523, "percentage": 3.17, "elapsed_time": "0:03:24", "remaining_time": "1:44:07"}
+{"current_steps": 30, "total_steps": 630, "loss": 0.2407, "lr": 4.761904761904762e-05, "epoch": 0.14285714285714285, "percentage": 4.76, "elapsed_time": "0:05:08", "remaining_time": "1:42:53"}
+{"current_steps": 40, "total_steps": 630, "loss": 0.24, "lr": 6.349206349206349e-05, "epoch": 0.19047619047619047, "percentage": 6.35, "elapsed_time": "0:06:47", "remaining_time": "1:40:11"}
+{"current_steps": 50, "total_steps": 630, "loss": 0.253, "lr": 7.936507936507937e-05, "epoch": 0.23809523809523808, "percentage": 7.94, "elapsed_time": "0:08:19", "remaining_time": "1:36:33"}
+{"current_steps": 60, "total_steps": 630, "loss": 0.244, "lr": 9.523809523809524e-05, "epoch": 0.2857142857142857, "percentage": 9.52, "elapsed_time": "0:09:56", "remaining_time": "1:34:31"}
+{"current_steps": 70, "total_steps": 630, "loss": 0.201, "lr": 9.996239762521151e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:11:35", "remaining_time": "1:32:40"}
+{"current_steps": 80, "total_steps": 630, "loss": 0.215, "lr": 9.977835886801848e-05, "epoch": 0.38095238095238093, "percentage": 12.7, "elapsed_time": "0:13:22", "remaining_time": "1:31:57"}
+{"current_steps": 90, "total_steps": 630, "loss": 0.2332, "lr": 9.944154131125642e-05, "epoch": 0.42857142857142855, "percentage": 14.29, "elapsed_time": "0:14:54", "remaining_time": "1:29:29"}
+{"current_steps": 100, "total_steps": 630, "loss": 0.2197, "lr": 9.895297870901379e-05, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "0:16:38", "remaining_time": "1:28:09"}
+{"current_steps": 100, "total_steps": 630, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "0:19:05", "remaining_time": "1:41:13"}
+{"current_steps": 110, "total_steps": 630, "loss": 0.2104, "lr": 9.83141705484087e-05, "epoch": 0.5238095238095238, "percentage": 17.46, "elapsed_time": "0:20:54", "remaining_time": "1:38:49"}
+{"current_steps": 120, "total_steps": 630, "loss": 0.23, "lr": 9.752707744739145e-05, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:22:25", "remaining_time": "1:35:17"}
+{"current_steps": 130, "total_steps": 630, "loss": 0.2026, "lr": 9.659411513725284e-05, "epoch": 0.6190476190476191, "percentage": 20.63, "elapsed_time": "0:24:03", "remaining_time": "1:32:32"}
+{"current_steps": 140, "total_steps": 630, "loss": 0.2058, "lr": 9.551814704830734e-05, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:25:47", "remaining_time": "1:30:14"}
+{"current_steps": 150, "total_steps": 630, "loss": 0.2148, "lr": 9.430247552150673e-05, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "0:27:22", "remaining_time": "1:27:35"}
+{"current_steps": 160, "total_steps": 630, "loss": 0.1923, "lr": 9.295083167295766e-05, "epoch": 0.7619047619047619, "percentage": 25.4, "elapsed_time": "0:29:12", "remaining_time": "1:25:48"}
+{"current_steps": 170, "total_steps": 630, "loss": 0.2044, "lr": 9.146736394245047e-05, "epoch": 0.8095238095238095, "percentage": 26.98, "elapsed_time": "0:30:54", "remaining_time": "1:23:38"}
+{"current_steps": 180, "total_steps": 630, "loss": 0.1983, "lr": 8.985662536114613e-05, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:32:38", "remaining_time": "1:21:37"}
+{"current_steps": 190, "total_steps": 630, "loss": 0.1601, "lr": 8.812355957749882e-05, "epoch": 0.9047619047619048, "percentage": 30.16, "elapsed_time": "0:34:27", "remaining_time": "1:19:47"}
+{"current_steps": 200, "total_steps": 630, "loss": 0.21, "lr": 8.627348568430352e-05, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "0:36:02", "remaining_time": "1:17:29"}
+{"current_steps": 200, "total_steps": 630, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "0:38:30", "remaining_time": "1:22:47"}
+{"current_steps": 210, "total_steps": 630, "loss": 0.191, "lr": 8.43120818934367e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:40:20", "remaining_time": "1:20:40"}
+{"current_steps": 220, "total_steps": 630, "loss": 0.1219, "lr": 8.224536810839564e-05, "epoch": 1.0476190476190477, "percentage": 34.92, "elapsed_time": "0:41:59", "remaining_time": "1:18:15"}
+{"current_steps": 230, "total_steps": 630, "loss": 0.1382, "lr": 8.007968744812424e-05, "epoch": 1.0952380952380953, "percentage": 36.51, "elapsed_time": "0:43:38", "remaining_time": "1:15:54"}
+{"current_steps": 240, "total_steps": 630, "loss": 0.1216, "lr": 7.782168677883206e-05, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:45:18", "remaining_time": "1:13:37"}
+{"current_steps": 250, "total_steps": 630, "loss": 0.1294, "lr": 7.547829631355794e-05, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "0:47:00", "remaining_time": "1:11:27"}
+{"current_steps": 260, "total_steps": 630, "loss": 0.1235, "lr": 7.3056708342091e-05, "epoch": 1.2380952380952381, "percentage": 41.27, "elapsed_time": "0:48:47", "remaining_time": "1:09:25"}
+{"current_steps": 270, "total_steps": 630, "loss": 0.1144, "lr": 7.056435515653059e-05, "epoch": 1.2857142857142856, "percentage": 42.86, "elapsed_time": "0:50:19", "remaining_time": "1:07:05"}
+{"current_steps": 280, "total_steps": 630, "loss": 0.1182, "lr": 6.800888624023553e-05, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:52:09", "remaining_time": "1:05:11"}
+{"current_steps": 290, "total_steps": 630, "loss": 0.1161, "lr": 6.539814479017428e-05, "epoch": 1.380952380952381, "percentage": 46.03, "elapsed_time": "0:53:54", "remaining_time": "1:03:11"}
+{"current_steps": 300, "total_steps": 630, "loss": 0.1284, "lr": 6.274014364473274e-05, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:55:34", "remaining_time": "1:01:08"}
+{"current_steps": 300, "total_steps": 630, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:58:02", "remaining_time": "1:03:50"}
+{"current_steps": 310, "total_steps": 630, "loss": 0.1174, "lr": 6.004304069086196e-05, "epoch": 1.4761904761904763, "percentage": 49.21, "elapsed_time": "0:59:48", "remaining_time": "1:01:43"}
+{"current_steps": 320, "total_steps": 630, "loss": 0.1203, "lr": 5.731511382604544e-05, "epoch": 1.5238095238095237, "percentage": 50.79, "elapsed_time": "1:01:27", "remaining_time": "0:59:32"}
+{"current_steps": 330, "total_steps": 630, "loss": 0.1267, "lr": 5.456473555193242e-05, "epoch": 1.5714285714285714, "percentage": 52.38, "elapsed_time": "1:03:13", "remaining_time": "0:57:29"}
+{"current_steps": 340, "total_steps": 630, "loss": 0.1295, "lr": 5.180034727761382e-05, "epoch": 1.619047619047619, "percentage": 53.97, "elapsed_time": "1:04:54", "remaining_time": "0:55:21"}
+{"current_steps": 350, "total_steps": 630, "loss": 0.1275, "lr": 4.903043341140879e-05, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:06:32", "remaining_time": "0:53:14"}
+{"current_steps": 360, "total_steps": 630, "loss": 0.131, "lr": 4.626349532067879e-05, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "1:08:09", "remaining_time": "0:51:07"}
+{"current_steps": 370, "total_steps": 630, "loss": 0.1259, "lr": 4.350802523959138e-05, "epoch": 1.7619047619047619, "percentage": 58.73, "elapsed_time": "1:09:46", "remaining_time": "0:49:01"}
+{"current_steps": 380, "total_steps": 630, "loss": 0.1361, "lr": 4.0772480204915364e-05, "epoch": 1.8095238095238095, "percentage": 60.32, "elapsed_time": "1:11:24", "remaining_time": "0:46:58"}
+{"current_steps": 390, "total_steps": 630, "loss": 0.0992, "lr": 3.806525609984312e-05, "epoch": 1.8571428571428572, "percentage": 61.9, "elapsed_time": "1:13:12", "remaining_time": "0:45:02"}
+{"current_steps": 400, "total_steps": 630, "loss": 0.1388, "lr": 3.5394661885504386e-05, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "1:14:54", "remaining_time": "0:43:04"}
+{"current_steps": 400, "total_steps": 630, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "1:17:22", "remaining_time": "0:44:29"}
+{"current_steps": 410, "total_steps": 630, "loss": 0.1227, "lr": 3.276889409925963e-05, "epoch": 1.9523809523809523, "percentage": 65.08, "elapsed_time": "1:19:01", "remaining_time": "0:42:23"}
+{"current_steps": 420, "total_steps": 630, "loss": 0.124, "lr": 3.019601169804216e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:20:41", "remaining_time": "0:40:20"}
+{"current_steps": 430, "total_steps": 630, "loss": 0.0804, "lr": 2.7683911323959712e-05, "epoch": 2.0476190476190474, "percentage": 68.25, "elapsed_time": "1:22:18", "remaining_time": "0:38:17"}
+{"current_steps": 440, "total_steps": 630, "loss": 0.0834, "lr": 2.524030306806944e-05, "epoch": 2.0952380952380953, "percentage": 69.84, "elapsed_time": "1:23:58", "remaining_time": "0:36:15"}
+{"current_steps": 450, "total_steps": 630, "loss": 0.0664, "lr": 2.2872686806712035e-05, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "1:25:37", "remaining_time": "0:34:15"}
+{"current_steps": 460, "total_steps": 630, "loss": 0.0637, "lr": 2.0588329183032744e-05, "epoch": 2.1904761904761907, "percentage": 73.02, "elapsed_time": "1:27:16", "remaining_time": "0:32:15"}
+{"current_steps": 470, "total_steps": 630, "loss": 0.0694, "lr": 1.8394241304337413e-05, "epoch": 2.238095238095238, "percentage": 74.6, "elapsed_time": "1:28:51", "remaining_time": "0:30:15"}
+{"current_steps": 480, "total_steps": 630, "loss": 0.0586, "lr": 1.629715722373423e-05, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "1:30:38", "remaining_time": "0:28:19"}
+{"current_steps": 490, "total_steps": 630, "loss": 0.0653, "lr": 1.4303513272105057e-05, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "1:32:21", "remaining_time": "0:26:23"}
+{"current_steps": 500, "total_steps": 630, "loss": 0.0639, "lr": 1.2419428303840091e-05, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "1:34:10", "remaining_time": "0:24:29"}
+{"current_steps": 500, "total_steps": 630, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "1:36:38", "remaining_time": "0:25:07"}
+{"current_steps": 510, "total_steps": 630, "loss": 0.0655, "lr": 1.0650684916965559e-05, "epoch": 2.4285714285714284, "percentage": 80.95, "elapsed_time": "1:38:19", "remaining_time": "0:23:08"}
+{"current_steps": 520, "total_steps": 630, "loss": 0.0664, "lr": 9.002711705302886e-06, "epoch": 2.4761904761904763, "percentage": 82.54, "elapsed_time": "1:39:57", "remaining_time": "0:21:08"}
+{"current_steps": 530, "total_steps": 630, "loss": 0.0618, "lr": 7.48056659713105e-06, "epoch": 2.5238095238095237, "percentage": 84.13, "elapsed_time": "1:41:44", "remaining_time": "0:19:11"}
+{"current_steps": 540, "total_steps": 630, "loss": 0.0614, "lr": 6.088921331488568e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "1:43:27", "remaining_time": "0:17:14"}
+{"current_steps": 550, "total_steps": 630, "loss": 0.0579, "lr": 4.832047119760186e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "1:45:18", "remaining_time": "0:15:19"}
+{"current_steps": 560, "total_steps": 630, "loss": 0.0657, "lr": 3.7138015365554833e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "1:47:00", "remaining_time": "0:13:22"}
+{"current_steps": 570, "total_steps": 630, "loss": 0.0655, "lr": 2.737616680113758e-06, "epoch": 2.7142857142857144, "percentage": 90.48, "elapsed_time": "1:48:38", "remaining_time": "0:11:26"}
+{"current_steps": 580, "total_steps": 630, "loss": 0.0646, "lr": 1.9064886385728399e-06, "epoch": 2.761904761904762, "percentage": 92.06, "elapsed_time": "1:50:17", "remaining_time": "0:09:30"}
+{"current_steps": 590, "total_steps": 630, "loss": 0.0618, "lr": 1.2229682944319031e-06, "epoch": 2.8095238095238093, "percentage": 93.65, "elapsed_time": "1:51:57", "remaining_time": "0:07:35"}
+{"current_steps": 600, "total_steps": 630, "loss": 0.0709, "lr": 6.891534954310885e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:53:28", "remaining_time": "0:05:40"}
+{"current_steps": 600, "total_steps": 630, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:55:56", "remaining_time": "0:05:47"}
+{"current_steps": 610, "total_steps": 630, "loss": 0.0658, "lr": 3.066826158767855e-07, "epoch": 2.9047619047619047, "percentage": 96.83, "elapsed_time": "1:57:34", "remaining_time": "0:03:51"}
+{"current_steps": 620, "total_steps": 630, "loss": 0.0632, "lr": 7.672952817413537e-08, "epoch": 2.9523809523809526, "percentage": 98.41, "elapsed_time": "1:59:21", "remaining_time": "0:01:55"}
+{"current_steps": 630, "total_steps": 630, "loss": 0.0606, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:01:01", "remaining_time": "0:00:00"}
+{"current_steps": 630, "total_steps": 630, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:01:03", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,531 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 630,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.6868933439254761,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.2872,
+      "step": 10
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.7597203850746155,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.2256,
+      "step": 20
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.5019340515136719,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.2407,
+      "step": 30
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.7778149247169495,
+      "learning_rate": 6.349206349206349e-05,
+      "loss": 0.24,
+      "step": 40
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.5550121665000916,
+      "learning_rate": 7.936507936507937e-05,
+      "loss": 0.253,
+      "step": 50
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.5827834606170654,
+      "learning_rate": 9.523809523809524e-05,
+      "loss": 0.244,
+      "step": 60
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.3167480230331421,
+      "learning_rate": 9.996239762521151e-05,
+      "loss": 0.201,
+      "step": 70
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.4390418827533722,
+      "learning_rate": 9.977835886801848e-05,
+      "loss": 0.215,
+      "step": 80
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.4620651304721832,
+      "learning_rate": 9.944154131125642e-05,
+      "loss": 0.2332,
+      "step": 90
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.6008896231651306,
+      "learning_rate": 9.895297870901379e-05,
+      "loss": 0.2197,
+      "step": 100
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "eval_question_finetune_val_loss": 0.22019629180431366,
+      "eval_question_finetune_val_runtime": 147.8155,
+      "eval_question_finetune_val_samples_per_second": 1.15,
+      "eval_question_finetune_val_steps_per_second": 1.15,
+      "step": 100
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.41202816367149353,
+      "learning_rate": 9.83141705484087e-05,
+      "loss": 0.2104,
+      "step": 110
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.5663377046585083,
+      "learning_rate": 9.752707744739145e-05,
+      "loss": 0.23,
+      "step": 120
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.3894096910953522,
+      "learning_rate": 9.659411513725284e-05,
+      "loss": 0.2026,
+      "step": 130
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5098657608032227,
+      "learning_rate": 9.551814704830734e-05,
+      "loss": 0.2058,
+      "step": 140
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.6123200058937073,
+      "learning_rate": 9.430247552150673e-05,
+      "loss": 0.2148,
+      "step": 150
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.3542161285877228,
+      "learning_rate": 9.295083167295766e-05,
+      "loss": 0.1923,
+      "step": 160
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.5978957414627075,
+      "learning_rate": 9.146736394245047e-05,
+      "loss": 0.2044,
+      "step": 170
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.5118722915649414,
+      "learning_rate": 8.985662536114613e-05,
+      "loss": 0.1983,
+      "step": 180
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.3764272630214691,
+      "learning_rate": 8.812355957749882e-05,
+      "loss": 0.1601,
+      "step": 190
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.3428772985935211,
+      "learning_rate": 8.627348568430352e-05,
+      "loss": 0.21,
+      "step": 200
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "eval_question_finetune_val_loss": 0.2040266990661621,
+      "eval_question_finetune_val_runtime": 147.8548,
+      "eval_question_finetune_val_samples_per_second": 1.15,
+      "eval_question_finetune_val_steps_per_second": 1.15,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3707384169101715,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 0.191,
+      "step": 210
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.32814162969589233,
+      "learning_rate": 8.224536810839564e-05,
+      "loss": 0.1219,
+      "step": 220
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.3846438527107239,
+      "learning_rate": 8.007968744812424e-05,
+      "loss": 0.1382,
+      "step": 230
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.600942075252533,
+      "learning_rate": 7.782168677883206e-05,
+      "loss": 0.1216,
+      "step": 240
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.3708088994026184,
+      "learning_rate": 7.547829631355794e-05,
+      "loss": 0.1294,
+      "step": 250
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.45602136850357056,
+      "learning_rate": 7.3056708342091e-05,
+      "loss": 0.1235,
+      "step": 260
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.4373123347759247,
+      "learning_rate": 7.056435515653059e-05,
+      "loss": 0.1144,
+      "step": 270
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.3915819227695465,
+      "learning_rate": 6.800888624023553e-05,
+      "loss": 0.1182,
+      "step": 280
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.3638611435890198,
+      "learning_rate": 6.539814479017428e-05,
+      "loss": 0.1161,
+      "step": 290
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.4916077256202698,
+      "learning_rate": 6.274014364473274e-05,
+      "loss": 0.1284,
+      "step": 300
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "eval_question_finetune_val_loss": 0.20424266159534454,
+      "eval_question_finetune_val_runtime": 147.8685,
+      "eval_question_finetune_val_samples_per_second": 1.15,
+      "eval_question_finetune_val_steps_per_second": 1.15,
+      "step": 300
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.32184702157974243,
+      "learning_rate": 6.004304069086196e-05,
+      "loss": 0.1174,
+      "step": 310
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.3934004306793213,
+      "learning_rate": 5.731511382604544e-05,
+      "loss": 0.1203,
+      "step": 320
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.32937076687812805,
+      "learning_rate": 5.456473555193242e-05,
+      "loss": 0.1267,
+      "step": 330
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.44530630111694336,
+      "learning_rate": 5.180034727761382e-05,
+      "loss": 0.1295,
+      "step": 340
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5469300746917725,
+      "learning_rate": 4.903043341140879e-05,
+      "loss": 0.1275,
+      "step": 350
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.42091014981269836,
+      "learning_rate": 4.626349532067879e-05,
+      "loss": 0.131,
+      "step": 360
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.5508981943130493,
+      "learning_rate": 4.350802523959138e-05,
+      "loss": 0.1259,
+      "step": 370
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.536870539188385,
+      "learning_rate": 4.0772480204915364e-05,
+      "loss": 0.1361,
+      "step": 380
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.39201387763023376,
+      "learning_rate": 3.806525609984312e-05,
+      "loss": 0.0992,
+      "step": 390
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.4120243191719055,
+      "learning_rate": 3.5394661885504386e-05,
+      "loss": 0.1388,
+      "step": 400
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "eval_question_finetune_val_loss": 0.19780363142490387,
+      "eval_question_finetune_val_runtime": 147.8694,
+      "eval_question_finetune_val_samples_per_second": 1.15,
+      "eval_question_finetune_val_steps_per_second": 1.15,
+      "step": 400
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 0.6459566354751587,
+      "learning_rate": 3.276889409925963e-05,
+      "loss": 0.1227,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5514885187149048,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 0.124,
+      "step": 420
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 0.29513123631477356,
+      "learning_rate": 2.7683911323959712e-05,
+      "loss": 0.0804,
+      "step": 430
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.4728158116340637,
+      "learning_rate": 2.524030306806944e-05,
+      "loss": 0.0834,
+      "step": 440
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.35146838426589966,
+      "learning_rate": 2.2872686806712035e-05,
+      "loss": 0.0664,
+      "step": 450
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.3647899627685547,
+      "learning_rate": 2.0588329183032744e-05,
+      "loss": 0.0637,
+      "step": 460
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 0.3702828884124756,
+      "learning_rate": 1.8394241304337413e-05,
+      "loss": 0.0694,
+      "step": 470
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.27304157614707947,
+      "learning_rate": 1.629715722373423e-05,
+      "loss": 0.0586,
+      "step": 480
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.3929966688156128,
+      "learning_rate": 1.4303513272105057e-05,
+      "loss": 0.0653,
+      "step": 490
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.3267512619495392,
+      "learning_rate": 1.2419428303840091e-05,
+      "loss": 0.0639,
+      "step": 500
+    },
+    {
+      "epoch": 2.380952380952381,
+      "eval_question_finetune_val_loss": 0.2098911553621292,
+      "eval_question_finetune_val_runtime": 147.8662,
+      "eval_question_finetune_val_samples_per_second": 1.15,
+      "eval_question_finetune_val_steps_per_second": 1.15,
+      "step": 500
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.3743651211261749,
+      "learning_rate": 1.0650684916965559e-05,
+      "loss": 0.0655,
+      "step": 510
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.6065438389778137,
+      "learning_rate": 9.002711705302886e-06,
+      "loss": 0.0664,
+      "step": 520
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 0.38518133759498596,
+      "learning_rate": 7.48056659713105e-06,
+      "loss": 0.0618,
+      "step": 530
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.2961275279521942,
+      "learning_rate": 6.088921331488568e-06,
+      "loss": 0.0614,
+      "step": 540
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.3589339554309845,
+      "learning_rate": 4.832047119760186e-06,
+      "loss": 0.0579,
+      "step": 550
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.4137968122959137,
+      "learning_rate": 3.7138015365554833e-06,
+      "loss": 0.0657,
+      "step": 560
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.5474274158477783,
+      "learning_rate": 2.737616680113758e-06,
+      "loss": 0.0655,
+      "step": 570
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.6094250679016113,
+      "learning_rate": 1.9064886385728399e-06,
+      "loss": 0.0646,
+      "step": 580
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 0.3034960925579071,
+      "learning_rate": 1.2229682944319031e-06,
+      "loss": 0.0618,
+      "step": 590
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.4673740863800049,
+      "learning_rate": 6.891534954310885e-07,
+      "loss": 0.0709,
+      "step": 600
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_question_finetune_val_loss": 0.21026459336280823,
+      "eval_question_finetune_val_runtime": 147.9364,
+      "eval_question_finetune_val_samples_per_second": 1.149,
+      "eval_question_finetune_val_steps_per_second": 1.149,
+      "step": 600
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 0.43377596139907837,
+      "learning_rate": 3.066826158767855e-07,
+      "loss": 0.0658,
+      "step": 610
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.4616926312446594,
+      "learning_rate": 7.672952817413537e-08,
+      "loss": 0.0632,
+      "step": 620
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3746221959590912,
+      "learning_rate": 0.0,
+      "loss": 0.0606,
+      "step": 630
+    },
+    {
+      "epoch": 3.0,
+      "step": 630,
+      "total_flos": 2.11652989949952e+16,
+      "train_loss": 0.1360657389201815,
+      "train_runtime": 7264.9105,
+      "train_samples_per_second": 0.347,
+      "train_steps_per_second": 0.087
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 630,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.11652989949952e+16,
+  "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:caed176bd9191174086db79b59956bd85dabb16ff5b4ec7616aa2616f84f7000
+size 5752