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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: jdqqjr/Qwen2.5-0.5B-Open-R1-Distill
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-0.5B-Open-R1-Distill-FactThink-SFT
+  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. -->
+
+# Qwen2.5-0.5B-Open-R1-Distill-FactThink-SFT
+
+This model is a fine-tuned version of [jdqqjr/Qwen2.5-0.5B-Open-R1-Distill](https://huggingface.co/jdqqjr/Qwen2.5-0.5B-Open-R1-Distill) on the cot_fact_think_sft_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: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- 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
+- num_epochs: 6.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- 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": 5.970666666666666,
+    "total_flos": 6.092825392526131e+16,
+    "train_loss": 3.2993942699436625,
+    "train_runtime": 2130.8581,
+    "train_samples_per_second": 16.892,
+    "train_steps_per_second": 0.527
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "jdqqjr/Qwen2.5-0.5B-Open-R1-Distill",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2b3bb82c38dbb80b2fdfd7bdcd898060984bbd67d38cbc2fe38517b1790e23
+size 1976163472

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": "<|im_end|>",
+    "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": "{% set system_message = 'Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution. In the Thought section, detail your reasoning process using the specified format: <think> {thought with steps separated with \\'\\n\\n\\'} </think> Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The solution should remain a logical, accurate, concise expression style and detail necessary step needed to reach the conclusion, formatted as follows: <answer> {final formatted, precise, and clear solution} </answer> Now, try to solve the following question through the above guidelines:' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>\\n' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.970666666666666,
+    "total_flos": 6.092825392526131e+16,
+    "train_loss": 3.2993942699436625,
+    "train_runtime": 2130.8581,
+    "train_samples_per_second": 16.892,
+    "train_steps_per_second": 0.527
+}

trainer_state.json

@@ -0,0 +1,826 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.970666666666666,
+  "eval_steps": 500,
+  "global_step": 1122,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 24.72922706604004,
+      "learning_rate": 9.999039635236575e-05,
+      "loss": 9.3592,
+      "step": 10
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 15.090938568115234,
+      "learning_rate": 9.99433669591504e-05,
+      "loss": 8.1951,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.75036334991455,
+      "learning_rate": 9.985718470743917e-05,
+      "loss": 8.0486,
+      "step": 30
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": Infinity,
+      "learning_rate": 9.974620019358045e-05,
+      "loss": 7.9758,
+      "step": 40
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 11.149462699890137,
+      "learning_rate": 9.958583897050699e-05,
+      "loss": 8.0914,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.258933067321777,
+      "learning_rate": 9.93866051712574e-05,
+      "loss": 8.068,
+      "step": 60
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 11.847441673278809,
+      "learning_rate": 9.91486549841951e-05,
+      "loss": 8.0715,
+      "step": 70
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 10.42148208618164,
+      "learning_rate": 9.887217494920655e-05,
+      "loss": 8.0495,
+      "step": 80
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 9.987250328063965,
+      "learning_rate": 9.855738181146428e-05,
+      "loss": 8.15,
+      "step": 90
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 10.14989948272705,
+      "learning_rate": 9.820452235151049e-05,
+      "loss": 7.9533,
+      "step": 100
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 10.510122299194336,
+      "learning_rate": 9.781387319179466e-05,
+      "loss": 8.0125,
+      "step": 110
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 10.167430877685547,
+      "learning_rate": 9.738574057981678e-05,
+      "loss": 7.867,
+      "step": 120
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 10.005114555358887,
+      "learning_rate": 9.69204601480461e-05,
+      "loss": 8.0841,
+      "step": 130
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 9.920500755310059,
+      "learning_rate": 9.641839665080363e-05,
+      "loss": 7.8963,
+      "step": 140
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 10.194422721862793,
+      "learning_rate": 9.58799436783149e-05,
+      "loss": 7.9465,
+      "step": 150
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 9.244508743286133,
+      "learning_rate": 9.53055233481567e-05,
+      "loss": 7.8268,
+      "step": 160
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 9.413444519042969,
+      "learning_rate": 9.469558597434018e-05,
+      "loss": 7.9496,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.113428115844727,
+      "learning_rate": 9.405060971428923e-05,
+      "loss": 7.8761,
+      "step": 180
+    },
+    {
+      "epoch": 1.0106666666666666,
+      "grad_norm": 10.662834167480469,
+      "learning_rate": 9.337110019399149e-05,
+      "loss": 7.0447,
+      "step": 190
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 9.262643814086914,
+      "learning_rate": 9.265759011161519e-05,
+      "loss": 5.604,
+      "step": 200
+    },
+    {
+      "epoch": 1.1173333333333333,
+      "grad_norm": 10.475074768066406,
+      "learning_rate": 9.191063881990308e-05,
+      "loss": 5.5011,
+      "step": 210
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 9.422979354858398,
+      "learning_rate": 9.113083188767057e-05,
+      "loss": 5.6094,
+      "step": 220
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 9.824627876281738,
+      "learning_rate": 9.03187806407519e-05,
+      "loss": 5.5714,
+      "step": 230
+    },
+    {
+      "epoch": 1.2773333333333334,
+      "grad_norm": 9.943827629089355,
+      "learning_rate": 8.947512168275429e-05,
+      "loss": 5.6587,
+      "step": 240
+    },
+    {
+      "epoch": 1.3306666666666667,
+      "grad_norm": 8.791569709777832,
+      "learning_rate": 8.86005163959956e-05,
+      "loss": 5.7327,
+      "step": 250
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 9.47322940826416,
+      "learning_rate": 8.769565042301691e-05,
+      "loss": 5.6468,
+      "step": 260
+    },
+    {
+      "epoch": 1.4373333333333334,
+      "grad_norm": 9.704258918762207,
+      "learning_rate": 8.676123312907642e-05,
+      "loss": 5.7799,
+      "step": 270
+    },
+    {
+      "epoch": 1.4906666666666666,
+      "grad_norm": 9.217696189880371,
+      "learning_rate": 8.579799704604596e-05,
+      "loss": 5.7282,
+      "step": 280
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 9.473422050476074,
+      "learning_rate": 8.480669729814635e-05,
+      "loss": 5.7854,
+      "step": 290
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "grad_norm": 9.128384590148926,
+      "learning_rate": 8.378811100997123e-05,
+      "loss": 5.824,
+      "step": 300
+    },
+    {
+      "epoch": 1.6506666666666665,
+      "grad_norm": 9.525070190429688,
+      "learning_rate": 8.274303669726426e-05,
+      "loss": 5.8272,
+      "step": 310
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 9.38967227935791,
+      "learning_rate": 8.167229364092647e-05,
+      "loss": 5.8388,
+      "step": 320
+    },
+    {
+      "epoch": 1.7573333333333334,
+      "grad_norm": 9.629057884216309,
+      "learning_rate": 8.057672124474508e-05,
+      "loss": 5.834,
+      "step": 330
+    },
+    {
+      "epoch": 1.8106666666666666,
+      "grad_norm": 9.649420738220215,
+      "learning_rate": 7.945717837734688e-05,
+      "loss": 5.7878,
+      "step": 340
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 10.08434009552002,
+      "learning_rate": 7.831454269889251e-05,
+      "loss": 5.7565,
+      "step": 350
+    },
+    {
+      "epoch": 1.9173333333333333,
+      "grad_norm": 8.834407806396484,
+      "learning_rate": 7.714970997303898e-05,
+      "loss": 5.805,
+      "step": 360
+    },
+    {
+      "epoch": 1.9706666666666668,
+      "grad_norm": 8.648845672607422,
+      "learning_rate": 7.596359336471015e-05,
+      "loss": 5.7674,
+      "step": 370
+    },
+    {
+      "epoch": 2.021333333333333,
+      "grad_norm": 9.286345481872559,
+      "learning_rate": 7.475712272422557e-05,
+      "loss": 4.6739,
+      "step": 380
+    },
+    {
+      "epoch": 2.074666666666667,
+      "grad_norm": 9.184532165527344,
+      "learning_rate": 7.35312438583488e-05,
+      "loss": 3.4263,
+      "step": 390
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 9.793543815612793,
+      "learning_rate": 7.228691778882693e-05,
+      "loss": 3.3865,
+      "step": 400
+    },
+    {
+      "epoch": 2.1813333333333333,
+      "grad_norm": 9.974711418151855,
+      "learning_rate": 7.102511999900213e-05,
+      "loss": 3.4448,
+      "step": 410
+    },
+    {
+      "epoch": 2.2346666666666666,
+      "grad_norm": 9.690023422241211,
+      "learning_rate": 6.974683966908641e-05,
+      "loss": 3.4652,
+      "step": 420
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 10.495637893676758,
+      "learning_rate": 6.84530789006985e-05,
+      "loss": 3.4585,
+      "step": 430
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 9.875127792358398,
+      "learning_rate": 6.714485193127126e-05,
+      "loss": 3.4596,
+      "step": 440
+    },
+    {
+      "epoch": 2.3946666666666667,
+      "grad_norm": 9.386152267456055,
+      "learning_rate": 6.582318433894513e-05,
+      "loss": 3.4094,
+      "step": 450
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 9.699738502502441,
+      "learning_rate": 6.448911223857123e-05,
+      "loss": 3.5483,
+      "step": 460
+    },
+    {
+      "epoch": 2.501333333333333,
+      "grad_norm": 9.54281234741211,
+      "learning_rate": 6.314368146945418e-05,
+      "loss": 3.4739,
+      "step": 470
+    },
+    {
+      "epoch": 2.554666666666667,
+      "grad_norm": 10.121294975280762,
+      "learning_rate": 6.178794677547137e-05,
+      "loss": 3.5686,
+      "step": 480
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 10.000744819641113,
+      "learning_rate": 6.0422970978211834e-05,
+      "loss": 3.4778,
+      "step": 490
+    },
+    {
+      "epoch": 2.6613333333333333,
+      "grad_norm": 9.480353355407715,
+      "learning_rate": 5.904982414378233e-05,
+      "loss": 3.5983,
+      "step": 500
+    },
+    {
+      "epoch": 2.7146666666666666,
+      "grad_norm": 10.401140213012695,
+      "learning_rate": 5.7669582743934284e-05,
+      "loss": 3.6008,
+      "step": 510
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 9.911478042602539,
+      "learning_rate": 5.628332881216899e-05,
+      "loss": 3.5318,
+      "step": 520
+    },
+    {
+      "epoch": 2.8213333333333335,
+      "grad_norm": 9.741485595703125,
+      "learning_rate": 5.4892149095482815e-05,
+      "loss": 3.5949,
+      "step": 530
+    },
+    {
+      "epoch": 2.8746666666666667,
+      "grad_norm": 9.522744178771973,
+      "learning_rate": 5.3497134202417096e-05,
+      "loss": 3.5776,
+      "step": 540
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 9.862764358520508,
+      "learning_rate": 5.209937774808098e-05,
+      "loss": 3.5341,
+      "step": 550
+    },
+    {
+      "epoch": 2.981333333333333,
+      "grad_norm": 9.565387725830078,
+      "learning_rate": 5.069997549681718e-05,
+      "loss": 3.4962,
+      "step": 560
+    },
+    {
+      "epoch": 3.032,
+      "grad_norm": 8.7464599609375,
+      "learning_rate": 4.930002450318282e-05,
+      "loss": 2.2876,
+      "step": 570
+    },
+    {
+      "epoch": 3.0853333333333333,
+      "grad_norm": 7.954220294952393,
+      "learning_rate": 4.790062225191902e-05,
+      "loss": 1.6802,
+      "step": 580
+    },
+    {
+      "epoch": 3.1386666666666665,
+      "grad_norm": 9.074536323547363,
+      "learning_rate": 4.650286579758291e-05,
+      "loss": 1.6187,
+      "step": 590
+    },
+    {
+      "epoch": 3.192,
+      "grad_norm": 8.827848434448242,
+      "learning_rate": 4.510785090451719e-05,
+      "loss": 1.6036,
+      "step": 600
+    },
+    {
+      "epoch": 3.2453333333333334,
+      "grad_norm": 8.552383422851562,
+      "learning_rate": 4.371667118783101e-05,
+      "loss": 1.6022,
+      "step": 610
+    },
+    {
+      "epoch": 3.2986666666666666,
+      "grad_norm": 8.28974437713623,
+      "learning_rate": 4.233041725606572e-05,
+      "loss": 1.6742,
+      "step": 620
+    },
+    {
+      "epoch": 3.352,
+      "grad_norm": 10.971680641174316,
+      "learning_rate": 4.095017585621767e-05,
+      "loss": 1.5802,
+      "step": 630
+    },
+    {
+      "epoch": 3.405333333333333,
+      "grad_norm": 8.309553146362305,
+      "learning_rate": 3.9577029021788164e-05,
+      "loss": 1.6889,
+      "step": 640
+    },
+    {
+      "epoch": 3.458666666666667,
+      "grad_norm": 8.555489540100098,
+      "learning_rate": 3.821205322452863e-05,
+      "loss": 1.6509,
+      "step": 650
+    },
+    {
+      "epoch": 3.512,
+      "grad_norm": 9.02466869354248,
+      "learning_rate": 3.685631853054583e-05,
+      "loss": 1.6118,
+      "step": 660
+    },
+    {
+      "epoch": 3.5653333333333332,
+      "grad_norm": 8.728509902954102,
+      "learning_rate": 3.5510887761428765e-05,
+      "loss": 1.6266,
+      "step": 670
+    },
+    {
+      "epoch": 3.618666666666667,
+      "grad_norm": 8.970052719116211,
+      "learning_rate": 3.4176815661054885e-05,
+      "loss": 1.6069,
+      "step": 680
+    },
+    {
+      "epoch": 3.672,
+      "grad_norm": 8.516586303710938,
+      "learning_rate": 3.2855148068728756e-05,
+      "loss": 1.6659,
+      "step": 690
+    },
+    {
+      "epoch": 3.7253333333333334,
+      "grad_norm": 8.919830322265625,
+      "learning_rate": 3.1546921099301506e-05,
+      "loss": 1.6846,
+      "step": 700
+    },
+    {
+      "epoch": 3.7786666666666666,
+      "grad_norm": 8.541778564453125,
+      "learning_rate": 3.0253160330913598e-05,
+      "loss": 1.6181,
+      "step": 710
+    },
+    {
+      "epoch": 3.832,
+      "grad_norm": 8.83139419555664,
+      "learning_rate": 2.8974880000997877e-05,
+      "loss": 1.5836,
+      "step": 720
+    },
+    {
+      "epoch": 3.8853333333333335,
+      "grad_norm": 8.658729553222656,
+      "learning_rate": 2.771308221117309e-05,
+      "loss": 1.7024,
+      "step": 730
+    },
+    {
+      "epoch": 3.9386666666666668,
+      "grad_norm": 8.480195999145508,
+      "learning_rate": 2.6468756141651206e-05,
+      "loss": 1.6222,
+      "step": 740
+    },
+    {
+      "epoch": 3.992,
+      "grad_norm": 8.250679016113281,
+      "learning_rate": 2.5242877275774445e-05,
+      "loss": 1.6467,
+      "step": 750
+    },
+    {
+      "epoch": 4.042666666666666,
+      "grad_norm": 5.594525337219238,
+      "learning_rate": 2.403640663528986e-05,
+      "loss": 0.7207,
+      "step": 760
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 5.844119071960449,
+      "learning_rate": 2.285029002696103e-05,
+      "loss": 0.6291,
+      "step": 770
+    },
+    {
+      "epoch": 4.149333333333334,
+      "grad_norm": 6.574643135070801,
+      "learning_rate": 2.1685457301107504e-05,
+      "loss": 0.5735,
+      "step": 780
+    },
+    {
+      "epoch": 4.2026666666666666,
+      "grad_norm": 5.774216651916504,
+      "learning_rate": 2.054282162265313e-05,
+      "loss": 0.5888,
+      "step": 790
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 5.600583553314209,
+      "learning_rate": 1.9423278755254932e-05,
+      "loss": 0.5797,
+      "step": 800
+    },
+    {
+      "epoch": 4.309333333333333,
+      "grad_norm": 6.131619453430176,
+      "learning_rate": 1.8327706359073526e-05,
+      "loss": 0.6167,
+      "step": 810
+    },
+    {
+      "epoch": 4.362666666666667,
+      "grad_norm": 5.416571140289307,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.5787,
+      "step": 820
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 5.745408058166504,
+      "learning_rate": 1.6211888990028785e-05,
+      "loss": 0.5982,
+      "step": 830
+    },
+    {
+      "epoch": 4.469333333333333,
+      "grad_norm": 6.464406967163086,
+      "learning_rate": 1.5193302701853673e-05,
+      "loss": 0.5994,
+      "step": 840
+    },
+    {
+      "epoch": 4.522666666666667,
+      "grad_norm": 5.810715198516846,
+      "learning_rate": 1.4202002953954041e-05,
+      "loss": 0.5936,
+      "step": 850
+    },
+    {
+      "epoch": 4.576,
+      "grad_norm": 5.5798516273498535,
+      "learning_rate": 1.323876687092359e-05,
+      "loss": 0.5807,
+      "step": 860
+    },
+    {
+      "epoch": 4.629333333333333,
+      "grad_norm": 6.70074462890625,
+      "learning_rate": 1.2304349576983093e-05,
+      "loss": 0.5784,
+      "step": 870
+    },
+    {
+      "epoch": 4.682666666666667,
+      "grad_norm": 6.038529396057129,
+      "learning_rate": 1.1399483604004402e-05,
+      "loss": 0.572,
+      "step": 880
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 5.514012813568115,
+      "learning_rate": 1.0524878317245712e-05,
+      "loss": 0.5582,
+      "step": 890
+    },
+    {
+      "epoch": 4.789333333333333,
+      "grad_norm": 5.5417680740356445,
+      "learning_rate": 9.681219359248106e-06,
+      "loss": 0.5343,
+      "step": 900
+    },
+    {
+      "epoch": 4.842666666666666,
+      "grad_norm": 5.650195121765137,
+      "learning_rate": 8.869168112329441e-06,
+      "loss": 0.5305,
+      "step": 910
+    },
+    {
+      "epoch": 4.896,
+      "grad_norm": 5.692509174346924,
+      "learning_rate": 8.089361180096927e-06,
+      "loss": 0.5936,
+      "step": 920
+    },
+    {
+      "epoch": 4.949333333333334,
+      "grad_norm": 5.946127891540527,
+      "learning_rate": 7.342409888384816e-06,
+      "loss": 0.5516,
+      "step": 930
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.735246419906616,
+      "learning_rate": 6.628899806008515e-06,
+      "loss": 0.5143,
+      "step": 940
+    },
+    {
+      "epoch": 5.053333333333334,
+      "grad_norm": 3.113004207611084,
+      "learning_rate": 5.949390285710776e-06,
+      "loss": 0.2498,
+      "step": 950
+    },
+    {
+      "epoch": 5.1066666666666665,
+      "grad_norm": 4.239569664001465,
+      "learning_rate": 5.304414025659832e-06,
+      "loss": 0.2392,
+      "step": 960
+    },
+    {
+      "epoch": 5.16,
+      "grad_norm": 3.16518497467041,
+      "learning_rate": 4.694476651843294e-06,
+      "loss": 0.2241,
+      "step": 970
+    },
+    {
+      "epoch": 5.213333333333333,
+      "grad_norm": 3.297945499420166,
+      "learning_rate": 4.120056321685101e-06,
+      "loss": 0.2332,
+      "step": 980
+    },
+    {
+      "epoch": 5.266666666666667,
+      "grad_norm": 3.4214251041412354,
+      "learning_rate": 3.581603349196372e-06,
+      "loss": 0.22,
+      "step": 990
+    },
+    {
+      "epoch": 5.32,
+      "grad_norm": 2.959951162338257,
+      "learning_rate": 3.079539851953911e-06,
+      "loss": 0.2192,
+      "step": 1000
+    },
+    {
+      "epoch": 5.373333333333333,
+      "grad_norm": 2.8886938095092773,
+      "learning_rate": 2.614259420183218e-06,
+      "loss": 0.2244,
+      "step": 1010
+    },
+    {
+      "epoch": 5.426666666666667,
+      "grad_norm": 3.0144460201263428,
+      "learning_rate": 2.1861268082053466e-06,
+      "loss": 0.2234,
+      "step": 1020
+    },
+    {
+      "epoch": 5.48,
+      "grad_norm": 3.1671485900878906,
+      "learning_rate": 1.7954776484895186e-06,
+      "loss": 0.2178,
+      "step": 1030
+    },
+    {
+      "epoch": 5.533333333333333,
+      "grad_norm": 2.926842451095581,
+      "learning_rate": 1.4426181885357215e-06,
+      "loss": 0.2222,
+      "step": 1040
+    },
+    {
+      "epoch": 5.586666666666667,
+      "grad_norm": 3.4401443004608154,
+      "learning_rate": 1.1278250507934518e-06,
+      "loss": 0.2276,
+      "step": 1050
+    },
+    {
+      "epoch": 5.64,
+      "grad_norm": 3.664684295654297,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 0.2316,
+      "step": 1060
+    },
+    {
+      "epoch": 5.693333333333333,
+      "grad_norm": 3.684296131134033,
+      "learning_rate": 6.133948287426028e-07,
+      "loss": 0.2237,
+      "step": 1070
+    },
+    {
+      "epoch": 5.746666666666667,
+      "grad_norm": 3.4764082431793213,
+      "learning_rate": 4.141610294930043e-07,
+      "loss": 0.2227,
+      "step": 1080
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 2.9150614738464355,
+      "learning_rate": 2.537998064195579e-07,
+      "loss": 0.2257,
+      "step": 1090
+    },
+    {
+      "epoch": 5.8533333333333335,
+      "grad_norm": 3.013000011444092,
+      "learning_rate": 1.324368739195281e-07,
+      "loss": 0.2226,
+      "step": 1100
+    },
+    {
+      "epoch": 5.906666666666666,
+      "grad_norm": 3.105398654937744,
+      "learning_rate": 5.016737387085191e-08,
+      "loss": 0.2171,
+      "step": 1110
+    },
+    {
+      "epoch": 5.96,
+      "grad_norm": 3.3148136138916016,
+      "learning_rate": 7.055801046113031e-09,
+      "loss": 0.2126,
+      "step": 1120
+    },
+    {
+      "epoch": 5.970666666666666,
+      "step": 1122,
+      "total_flos": 6.092825392526131e+16,
+      "train_loss": 3.2993942699436625,
+      "train_runtime": 2130.8581,
+      "train_samples_per_second": 16.892,
+      "train_steps_per_second": 0.527
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1122,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.092825392526131e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc812bdee3802bdc46f1df3b47b8a934fcf5137c939503e203b3959a393f3bfd
+size 5560