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: 6
+- total_train_batch_size: 48
+- 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: 4.0
+- 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": 4.0,
+    "total_flos": 4.036279852125389e+16,
+    "train_loss": 7.3980213584899905,
+    "train_runtime": 1227.9067,
+    "train_samples_per_second": 19.542,
+    "train_steps_per_second": 0.407
+}

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:dc2713383ea3d47c46b4bca480cd6c813a9808286819fd333cdf0df2ef94b722
+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": 4.0,
+    "total_flos": 4.036279852125389e+16,
+    "train_loss": 7.3980213584899905,
+    "train_runtime": 1227.9067,
+    "train_samples_per_second": 19.542,
+    "train_steps_per_second": 0.407
+}

trainer_log.jsonl

@@ -0,0 +1,51 @@
+{"current_steps": 10, "total_steps": 500, "loss": 16.6271, "learning_rate": 9.996447363202946e-05, "epoch": 0.08, "percentage": 2.0, "elapsed_time": "0:00:24", "remaining_time": "0:19:39"}
+{"current_steps": 20, "total_steps": 500, "loss": 13.6217, "learning_rate": 9.977809823015401e-05, "epoch": 0.16, "percentage": 4.0, "elapsed_time": "0:00:47", "remaining_time": "0:19:02"}
+{"current_steps": 30, "total_steps": 500, "loss": 12.3656, "learning_rate": 9.938441702975689e-05, "epoch": 0.24, "percentage": 6.0, "elapsed_time": "0:01:11", "remaining_time": "0:18:33"}
+{"current_steps": 40, "total_steps": 500, "loss": 12.2646, "learning_rate": 9.879583809693738e-05, "epoch": 0.32, "percentage": 8.0, "elapsed_time": "0:01:35", "remaining_time": "0:18:12"}
+{"current_steps": 50, "total_steps": 500, "loss": 12.1808, "learning_rate": 9.801468428384716e-05, "epoch": 0.4, "percentage": 10.0, "elapsed_time": "0:01:58", "remaining_time": "0:17:49"}
+{"current_steps": 60, "total_steps": 500, "loss": 12.1502, "learning_rate": 9.704403844771128e-05, "epoch": 0.48, "percentage": 12.0, "elapsed_time": "0:02:22", "remaining_time": "0:17:26"}
+{"current_steps": 70, "total_steps": 500, "loss": 11.9683, "learning_rate": 9.588773128419906e-05, "epoch": 0.56, "percentage": 14.0, "elapsed_time": "0:02:46", "remaining_time": "0:17:05"}
+{"current_steps": 80, "total_steps": 500, "loss": 11.8564, "learning_rate": 9.45503262094184e-05, "epoch": 0.64, "percentage": 16.0, "elapsed_time": "0:03:10", "remaining_time": "0:16:41"}
+{"current_steps": 90, "total_steps": 500, "loss": 12.0212, "learning_rate": 9.30371013501972e-05, "epoch": 0.72, "percentage": 18.0, "elapsed_time": "0:03:35", "remaining_time": "0:16:20"}
+{"current_steps": 100, "total_steps": 500, "loss": 11.8631, "learning_rate": 9.135402871372808e-05, "epoch": 0.8, "percentage": 20.0, "elapsed_time": "0:03:59", "remaining_time": "0:15:56"}
+{"current_steps": 110, "total_steps": 500, "loss": 11.6954, "learning_rate": 8.950775061878453e-05, "epoch": 0.88, "percentage": 22.0, "elapsed_time": "0:04:23", "remaining_time": "0:15:33"}
+{"current_steps": 120, "total_steps": 500, "loss": 11.7669, "learning_rate": 8.750555348152298e-05, "epoch": 0.96, "percentage": 24.0, "elapsed_time": "0:04:47", "remaining_time": "0:15:10"}
+{"current_steps": 130, "total_steps": 500, "loss": 10.3003, "learning_rate": 8.535533905932738e-05, "epoch": 1.04, "percentage": 26.0, "elapsed_time": "0:05:11", "remaining_time": "0:14:46"}
+{"current_steps": 140, "total_steps": 500, "loss": 8.5731, "learning_rate": 8.306559326618259e-05, "epoch": 1.12, "percentage": 28.0, "elapsed_time": "0:05:35", "remaining_time": "0:14:23"}
+{"current_steps": 150, "total_steps": 500, "loss": 8.5948, "learning_rate": 8.064535268264883e-05, "epoch": 1.2, "percentage": 30.0, "elapsed_time": "0:06:00", "remaining_time": "0:14:00"}
+{"current_steps": 160, "total_steps": 500, "loss": 8.656, "learning_rate": 7.810416889260653e-05, "epoch": 1.28, "percentage": 32.0, "elapsed_time": "0:06:24", "remaining_time": "0:13:37"}
+{"current_steps": 170, "total_steps": 500, "loss": 8.7269, "learning_rate": 7.545207078751857e-05, "epoch": 1.3599999999999999, "percentage": 34.0, "elapsed_time": "0:06:49", "remaining_time": "0:13:14"}
+{"current_steps": 180, "total_steps": 500, "loss": 8.6868, "learning_rate": 7.269952498697734e-05, "epoch": 1.44, "percentage": 36.0, "elapsed_time": "0:07:13", "remaining_time": "0:12:50"}
+{"current_steps": 190, "total_steps": 500, "loss": 8.7702, "learning_rate": 6.985739453173903e-05, "epoch": 1.52, "percentage": 38.0, "elapsed_time": "0:07:37", "remaining_time": "0:12:26"}
+{"current_steps": 200, "total_steps": 500, "loss": 8.7521, "learning_rate": 6.693689601226458e-05, "epoch": 1.6, "percentage": 40.0, "elapsed_time": "0:08:01", "remaining_time": "0:12:02"}
+{"current_steps": 210, "total_steps": 500, "loss": 8.8742, "learning_rate": 6.394955530196147e-05, "epoch": 1.6800000000000002, "percentage": 42.0, "elapsed_time": "0:08:25", "remaining_time": "0:11:38"}
+{"current_steps": 220, "total_steps": 500, "loss": 8.7707, "learning_rate": 6.090716206982714e-05, "epoch": 1.76, "percentage": 44.0, "elapsed_time": "0:08:49", "remaining_time": "0:11:14"}
+{"current_steps": 230, "total_steps": 500, "loss": 8.7433, "learning_rate": 5.782172325201155e-05, "epoch": 1.8399999999999999, "percentage": 46.0, "elapsed_time": "0:09:13", "remaining_time": "0:10:50"}
+{"current_steps": 240, "total_steps": 500, "loss": 8.7179, "learning_rate": 5.470541566592573e-05, "epoch": 1.92, "percentage": 48.0, "elapsed_time": "0:09:38", "remaining_time": "0:10:26"}
+{"current_steps": 250, "total_steps": 500, "loss": 8.6486, "learning_rate": 5.157053795390642e-05, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:10:02", "remaining_time": "0:10:02"}
+{"current_steps": 260, "total_steps": 500, "loss": 5.591, "learning_rate": 4.8429462046093585e-05, "epoch": 2.08, "percentage": 52.0, "elapsed_time": "0:10:26", "remaining_time": "0:09:38"}
+{"current_steps": 270, "total_steps": 500, "loss": 5.4084, "learning_rate": 4.529458433407429e-05, "epoch": 2.16, "percentage": 54.0, "elapsed_time": "0:10:50", "remaining_time": "0:09:14"}
+{"current_steps": 280, "total_steps": 500, "loss": 5.3605, "learning_rate": 4.2178276747988446e-05, "epoch": 2.24, "percentage": 56.0, "elapsed_time": "0:11:14", "remaining_time": "0:08:50"}
+{"current_steps": 290, "total_steps": 500, "loss": 5.3401, "learning_rate": 3.9092837930172884e-05, "epoch": 2.32, "percentage": 58.0, "elapsed_time": "0:11:39", "remaining_time": "0:08:26"}
+{"current_steps": 300, "total_steps": 500, "loss": 5.3064, "learning_rate": 3.605044469803854e-05, "epoch": 2.4, "percentage": 60.0, "elapsed_time": "0:12:03", "remaining_time": "0:08:02"}
+{"current_steps": 310, "total_steps": 500, "loss": 5.3187, "learning_rate": 3.3063103987735433e-05, "epoch": 2.48, "percentage": 62.0, "elapsed_time": "0:12:27", "remaining_time": "0:07:38"}
+{"current_steps": 320, "total_steps": 500, "loss": 5.413, "learning_rate": 3.0142605468260978e-05, "epoch": 2.56, "percentage": 64.0, "elapsed_time": "0:12:52", "remaining_time": "0:07:14"}
+{"current_steps": 330, "total_steps": 500, "loss": 5.2867, "learning_rate": 2.7300475013022663e-05, "epoch": 2.64, "percentage": 66.0, "elapsed_time": "0:13:16", "remaining_time": "0:06:50"}
+{"current_steps": 340, "total_steps": 500, "loss": 5.3684, "learning_rate": 2.4547929212481435e-05, "epoch": 2.7199999999999998, "percentage": 68.0, "elapsed_time": "0:13:40", "remaining_time": "0:06:26"}
+{"current_steps": 350, "total_steps": 500, "loss": 5.3484, "learning_rate": 2.1895831107393484e-05, "epoch": 2.8, "percentage": 70.0, "elapsed_time": "0:14:05", "remaining_time": "0:06:02"}
+{"current_steps": 360, "total_steps": 500, "loss": 5.2971, "learning_rate": 1.9354647317351188e-05, "epoch": 2.88, "percentage": 72.0, "elapsed_time": "0:14:29", "remaining_time": "0:05:38"}
+{"current_steps": 370, "total_steps": 500, "loss": 5.2595, "learning_rate": 1.6934406733817414e-05, "epoch": 2.96, "percentage": 74.0, "elapsed_time": "0:14:53", "remaining_time": "0:05:14"}
+{"current_steps": 380, "total_steps": 500, "loss": 4.2182, "learning_rate": 1.4644660940672627e-05, "epoch": 3.04, "percentage": 76.0, "elapsed_time": "0:15:18", "remaining_time": "0:04:50"}
+{"current_steps": 390, "total_steps": 500, "loss": 3.1071, "learning_rate": 1.2494446518477022e-05, "epoch": 3.12, "percentage": 78.0, "elapsed_time": "0:15:43", "remaining_time": "0:04:25"}
+{"current_steps": 400, "total_steps": 500, "loss": 3.068, "learning_rate": 1.049224938121548e-05, "epoch": 3.2, "percentage": 80.0, "elapsed_time": "0:16:07", "remaining_time": "0:04:01"}
+{"current_steps": 410, "total_steps": 500, "loss": 2.9727, "learning_rate": 8.645971286271904e-06, "epoch": 3.2800000000000002, "percentage": 82.0, "elapsed_time": "0:16:31", "remaining_time": "0:03:37"}
+{"current_steps": 420, "total_steps": 500, "loss": 2.9938, "learning_rate": 6.962898649802823e-06, "epoch": 3.36, "percentage": 84.0, "elapsed_time": "0:16:55", "remaining_time": "0:03:13"}
+{"current_steps": 430, "total_steps": 500, "loss": 3.0744, "learning_rate": 5.449673790581611e-06, "epoch": 3.44, "percentage": 86.0, "elapsed_time": "0:17:20", "remaining_time": "0:02:49"}
+{"current_steps": 440, "total_steps": 500, "loss": 2.9339, "learning_rate": 4.112268715800943e-06, "epoch": 3.52, "percentage": 88.0, "elapsed_time": "0:17:44", "remaining_time": "0:02:25"}
+{"current_steps": 450, "total_steps": 500, "loss": 2.9912, "learning_rate": 2.9559615522887273e-06, "epoch": 3.6, "percentage": 90.0, "elapsed_time": "0:18:09", "remaining_time": "0:02:01"}
+{"current_steps": 460, "total_steps": 500, "loss": 2.9679, "learning_rate": 1.985315716152847e-06, "epoch": 3.68, "percentage": 92.0, "elapsed_time": "0:18:33", "remaining_time": "0:01:36"}
+{"current_steps": 470, "total_steps": 500, "loss": 3.0297, "learning_rate": 1.2041619030626284e-06, "epoch": 3.76, "percentage": 94.0, "elapsed_time": "0:18:57", "remaining_time": "0:01:12"}
+{"current_steps": 480, "total_steps": 500, "loss": 2.9479, "learning_rate": 6.15582970243117e-07, "epoch": 3.84, "percentage": 96.0, "elapsed_time": "0:19:22", "remaining_time": "0:00:48"}
+{"current_steps": 490, "total_steps": 500, "loss": 3.0567, "learning_rate": 2.219017698460002e-07, "epoch": 3.92, "percentage": 98.0, "elapsed_time": "0:19:46", "remaining_time": "0:00:24"}
+{"current_steps": 500, "total_steps": 500, "loss": 3.0452, "learning_rate": 2.467198171342e-08, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:20:10", "remaining_time": "0:00:00"}
+{"current_steps": 500, "total_steps": 500, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:20:20", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 114.14533233642578,
+      "learning_rate": 9.996447363202946e-05,
+      "loss": 16.6271,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 19.26224136352539,
+      "learning_rate": 9.977809823015401e-05,
+      "loss": 13.6217,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 16.628232955932617,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 12.3656,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 13.531852722167969,
+      "learning_rate": 9.879583809693738e-05,
+      "loss": 12.2646,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 14.354416847229004,
+      "learning_rate": 9.801468428384716e-05,
+      "loss": 12.1808,
+      "step": 50
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 13.167389869689941,
+      "learning_rate": 9.704403844771128e-05,
+      "loss": 12.1502,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 12.674458503723145,
+      "learning_rate": 9.588773128419906e-05,
+      "loss": 11.9683,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 13.783093452453613,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 11.8564,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 17.22150993347168,
+      "learning_rate": 9.30371013501972e-05,
+      "loss": 12.0212,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.618257522583008,
+      "learning_rate": 9.135402871372808e-05,
+      "loss": 11.8631,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 13.423781394958496,
+      "learning_rate": 8.950775061878453e-05,
+      "loss": 11.6954,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 12.201665878295898,
+      "learning_rate": 8.750555348152298e-05,
+      "loss": 11.7669,
+      "step": 120
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 14.449649810791016,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3003,
+      "step": 130
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 14.11440658569336,
+      "learning_rate": 8.306559326618259e-05,
+      "loss": 8.5731,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 12.817862510681152,
+      "learning_rate": 8.064535268264883e-05,
+      "loss": 8.5948,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 12.568441390991211,
+      "learning_rate": 7.810416889260653e-05,
+      "loss": 8.656,
+      "step": 160
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 13.24677848815918,
+      "learning_rate": 7.545207078751857e-05,
+      "loss": 8.7269,
+      "step": 170
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 12.547300338745117,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 8.6868,
+      "step": 180
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 12.896221160888672,
+      "learning_rate": 6.985739453173903e-05,
+      "loss": 8.7702,
+      "step": 190
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 12.103998184204102,
+      "learning_rate": 6.693689601226458e-05,
+      "loss": 8.7521,
+      "step": 200
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 12.651740074157715,
+      "learning_rate": 6.394955530196147e-05,
+      "loss": 8.8742,
+      "step": 210
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 12.18869400024414,
+      "learning_rate": 6.090716206982714e-05,
+      "loss": 8.7707,
+      "step": 220
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 12.143824577331543,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 8.7433,
+      "step": 230
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 11.785919189453125,
+      "learning_rate": 5.470541566592573e-05,
+      "loss": 8.7179,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.037582397460938,
+      "learning_rate": 5.157053795390642e-05,
+      "loss": 8.6486,
+      "step": 250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 12.652670860290527,
+      "learning_rate": 4.8429462046093585e-05,
+      "loss": 5.591,
+      "step": 260
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 14.214653015136719,
+      "learning_rate": 4.529458433407429e-05,
+      "loss": 5.4084,
+      "step": 270
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 12.59438419342041,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 5.3605,
+      "step": 280
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 12.09847354888916,
+      "learning_rate": 3.9092837930172884e-05,
+      "loss": 5.3401,
+      "step": 290
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.492688179016113,
+      "learning_rate": 3.605044469803854e-05,
+      "loss": 5.3064,
+      "step": 300
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 12.142609596252441,
+      "learning_rate": 3.3063103987735433e-05,
+      "loss": 5.3187,
+      "step": 310
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 12.719853401184082,
+      "learning_rate": 3.0142605468260978e-05,
+      "loss": 5.413,
+      "step": 320
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 12.052017211914062,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 5.2867,
+      "step": 330
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 12.2785062789917,
+      "learning_rate": 2.4547929212481435e-05,
+      "loss": 5.3684,
+      "step": 340
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 11.52890396118164,
+      "learning_rate": 2.1895831107393484e-05,
+      "loss": 5.3484,
+      "step": 350
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 12.041983604431152,
+      "learning_rate": 1.9354647317351188e-05,
+      "loss": 5.2971,
+      "step": 360
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 12.474526405334473,
+      "learning_rate": 1.6934406733817414e-05,
+      "loss": 5.2595,
+      "step": 370
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 10.717528343200684,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.2182,
+      "step": 380
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 11.499459266662598,
+      "learning_rate": 1.2494446518477022e-05,
+      "loss": 3.1071,
+      "step": 390
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 11.054661750793457,
+      "learning_rate": 1.049224938121548e-05,
+      "loss": 3.068,
+      "step": 400
+    },
+    {
+      "epoch": 3.2800000000000002,
+      "grad_norm": 11.394171714782715,
+      "learning_rate": 8.645971286271904e-06,
+      "loss": 2.9727,
+      "step": 410
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 10.573503494262695,
+      "learning_rate": 6.962898649802823e-06,
+      "loss": 2.9938,
+      "step": 420
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 11.186671257019043,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.0744,
+      "step": 430
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 10.377039909362793,
+      "learning_rate": 4.112268715800943e-06,
+      "loss": 2.9339,
+      "step": 440
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 10.85782527923584,
+      "learning_rate": 2.9559615522887273e-06,
+      "loss": 2.9912,
+      "step": 450
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 11.210704803466797,
+      "learning_rate": 1.985315716152847e-06,
+      "loss": 2.9679,
+      "step": 460
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 11.051790237426758,
+      "learning_rate": 1.2041619030626284e-06,
+      "loss": 3.0297,
+      "step": 470
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 10.918357849121094,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.9479,
+      "step": 480
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 10.786859512329102,
+      "learning_rate": 2.219017698460002e-07,
+      "loss": 3.0567,
+      "step": 490
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.881739616394043,
+      "learning_rate": 2.467198171342e-08,
+      "loss": 3.0452,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "step": 500,
+      "total_flos": 4.036279852125389e+16,
+      "train_loss": 7.3980213584899905,
+      "train_runtime": 1227.9067,
+      "train_samples_per_second": 19.542,
+      "train_steps_per_second": 0.407
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 4.036279852125389e+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:be8e15e7ee5c54fefa3a3ec8ddf285112e954bc3f80498cf81f01aa3c0e48ec1
+size 5560