Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-0.5B-Instruct-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-Instruct-FactThink-SFT
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 6.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

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": 5.984,
+    "total_flos": 6.106743890876826e+16,
+    "train_loss": 0.8316886925774356,
+    "train_runtime": 2204.228,
+    "train_samples_per_second": 16.33,
+    "train_steps_per_second": 0.509
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "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_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "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": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086dfa5989edf9925de28e05056c7b74ea75594cb7b6b2ffb69d15a6ce11b117
+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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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",
+  "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": 5.984,
+    "total_flos": 6.106743890876826e+16,
+    "train_loss": 0.8316886925774356,
+    "train_runtime": 2204.228,
+    "train_samples_per_second": 16.33,
+    "train_steps_per_second": 0.509
+}

trainer_log.jsonl

@@ -0,0 +1,113 @@
+{"current_steps": 10, "total_steps": 1122, "loss": 2.8019, "learning_rate": 9.999686404744783e-05, "epoch": 0.05333333333333334, "percentage": 0.89, "elapsed_time": "0:00:19", "remaining_time": "0:35:56"}
+{"current_steps": 20, "total_steps": 1122, "loss": 2.0956, "learning_rate": 9.996158909866488e-05, "epoch": 0.10666666666666667, "percentage": 1.78, "elapsed_time": "0:00:38", "remaining_time": "0:35:14"}
+{"current_steps": 30, "total_steps": 1122, "loss": 2.0049, "learning_rate": 9.98871470062288e-05, "epoch": 0.16, "percentage": 2.67, "elapsed_time": "0:00:57", "remaining_time": "0:34:42"}
+{"current_steps": 40, "total_steps": 1122, "loss": 1.9912, "learning_rate": 9.977359612865423e-05, "epoch": 0.21333333333333335, "percentage": 3.57, "elapsed_time": "0:01:16", "remaining_time": "0:34:23"}
+{"current_steps": 50, "total_steps": 1122, "loss": 2.0245, "learning_rate": 9.96210254835968e-05, "epoch": 0.26666666666666666, "percentage": 4.46, "elapsed_time": "0:01:35", "remaining_time": "0:34:01"}
+{"current_steps": 60, "total_steps": 1122, "loss": 2.0146, "learning_rate": 9.94295546780682e-05, "epoch": 0.32, "percentage": 5.35, "elapsed_time": "0:01:54", "remaining_time": "0:33:54"}
+{"current_steps": 70, "total_steps": 1122, "loss": 2.0106, "learning_rate": 9.919933381467088e-05, "epoch": 0.37333333333333335, "percentage": 6.24, "elapsed_time": "0:02:14", "remaining_time": "0:33:38"}
+{"current_steps": 80, "total_steps": 1122, "loss": 2.0109, "learning_rate": 9.89305433739258e-05, "epoch": 0.4266666666666667, "percentage": 7.13, "elapsed_time": "0:02:34", "remaining_time": "0:33:30"}
+{"current_steps": 90, "total_steps": 1122, "loss": 2.039, "learning_rate": 9.862339407278564e-05, "epoch": 0.48, "percentage": 8.02, "elapsed_time": "0:02:53", "remaining_time": "0:33:10"}
+{"current_steps": 100, "total_steps": 1122, "loss": 1.9905, "learning_rate": 9.827812669944423e-05, "epoch": 0.5333333333333333, "percentage": 8.91, "elapsed_time": "0:03:13", "remaining_time": "0:32:55"}
+{"current_steps": 110, "total_steps": 1122, "loss": 2.0033, "learning_rate": 9.789501192457188e-05, "epoch": 0.5866666666666667, "percentage": 9.8, "elapsed_time": "0:03:33", "remaining_time": "0:32:43"}
+{"current_steps": 120, "total_steps": 1122, "loss": 1.9661, "learning_rate": 9.747435008912438e-05, "epoch": 0.64, "percentage": 10.7, "elapsed_time": "0:03:53", "remaining_time": "0:32:27"}
+{"current_steps": 130, "total_steps": 1122, "loss": 2.0196, "learning_rate": 9.701647096889219e-05, "epoch": 0.6933333333333334, "percentage": 11.59, "elapsed_time": "0:04:13", "remaining_time": "0:32:18"}
+{"current_steps": 140, "total_steps": 1122, "loss": 1.9727, "learning_rate": 9.652173351597435e-05, "epoch": 0.7466666666666667, "percentage": 12.48, "elapsed_time": "0:04:33", "remaining_time": "0:32:00"}
+{"current_steps": 150, "total_steps": 1122, "loss": 1.985, "learning_rate": 9.599052557737973e-05, "epoch": 0.8, "percentage": 13.37, "elapsed_time": "0:04:53", "remaining_time": "0:31:40"}
+{"current_steps": 160, "total_steps": 1122, "loss": 1.9542, "learning_rate": 9.542326359097619e-05, "epoch": 0.8533333333333334, "percentage": 14.26, "elapsed_time": "0:05:12", "remaining_time": "0:31:20"}
+{"current_steps": 170, "total_steps": 1122, "loss": 1.9835, "learning_rate": 9.482039225902624e-05, "epoch": 0.9066666666666666, "percentage": 15.15, "elapsed_time": "0:05:32", "remaining_time": "0:31:04"}
+{"current_steps": 180, "total_steps": 1122, "loss": 1.9677, "learning_rate": 9.418238419956484e-05, "epoch": 0.96, "percentage": 16.04, "elapsed_time": "0:05:52", "remaining_time": "0:30:45"}
+{"current_steps": 190, "total_steps": 1122, "loss": 1.8294, "learning_rate": 9.350973957589277e-05, "epoch": 1.0133333333333334, "percentage": 16.93, "elapsed_time": "0:06:12", "remaining_time": "0:30:24"}
+{"current_steps": 200, "total_steps": 1122, "loss": 1.42, "learning_rate": 9.280298570447611e-05, "epoch": 1.0666666666666667, "percentage": 17.83, "elapsed_time": "0:06:32", "remaining_time": "0:30:07"}
+{"current_steps": 210, "total_steps": 1122, "loss": 1.381, "learning_rate": 9.206267664155907e-05, "epoch": 1.12, "percentage": 18.72, "elapsed_time": "0:06:52", "remaining_time": "0:29:49"}
+{"current_steps": 220, "total_steps": 1122, "loss": 1.4036, "learning_rate": 9.128939274881421e-05, "epoch": 1.1733333333333333, "percentage": 19.61, "elapsed_time": "0:07:11", "remaining_time": "0:29:31"}
+{"current_steps": 230, "total_steps": 1122, "loss": 1.3998, "learning_rate": 9.048374023837085e-05, "epoch": 1.2266666666666666, "percentage": 20.5, "elapsed_time": "0:07:31", "remaining_time": "0:29:11"}
+{"current_steps": 240, "total_steps": 1122, "loss": 1.421, "learning_rate": 8.964635069757802e-05, "epoch": 1.28, "percentage": 21.39, "elapsed_time": "0:07:51", "remaining_time": "0:28:51"}
+{"current_steps": 250, "total_steps": 1122, "loss": 1.441, "learning_rate": 8.87778805938746e-05, "epoch": 1.3333333333333333, "percentage": 22.28, "elapsed_time": "0:08:10", "remaining_time": "0:28:32"}
+{"current_steps": 260, "total_steps": 1122, "loss": 1.4158, "learning_rate": 8.787901076015486e-05, "epoch": 1.3866666666666667, "percentage": 23.17, "elapsed_time": "0:08:30", "remaining_time": "0:28:13"}
+{"current_steps": 270, "total_steps": 1122, "loss": 1.4436, "learning_rate": 8.695044586103296e-05, "epoch": 1.44, "percentage": 24.06, "elapsed_time": "0:08:50", "remaining_time": "0:27:53"}
+{"current_steps": 280, "total_steps": 1122, "loss": 1.4412, "learning_rate": 8.599291384042442e-05, "epoch": 1.4933333333333334, "percentage": 24.96, "elapsed_time": "0:09:09", "remaining_time": "0:27:33"}
+{"current_steps": 290, "total_steps": 1122, "loss": 1.445, "learning_rate": 8.500716535087814e-05, "epoch": 1.5466666666666666, "percentage": 25.85, "elapsed_time": "0:09:29", "remaining_time": "0:27:13"}
+{"current_steps": 300, "total_steps": 1122, "loss": 1.4719, "learning_rate": 8.399397316510596e-05, "epoch": 1.6, "percentage": 26.74, "elapsed_time": "0:09:48", "remaining_time": "0:26:53"}
+{"current_steps": 310, "total_steps": 1122, "loss": 1.4665, "learning_rate": 8.295413157017127e-05, "epoch": 1.6533333333333333, "percentage": 27.63, "elapsed_time": "0:10:08", "remaining_time": "0:26:34"}
+{"current_steps": 320, "total_steps": 1122, "loss": 1.4728, "learning_rate": 8.188845574481163e-05, "epoch": 1.7066666666666666, "percentage": 28.52, "elapsed_time": "0:10:28", "remaining_time": "0:26:14"}
+{"current_steps": 330, "total_steps": 1122, "loss": 1.4648, "learning_rate": 8.079778112038318e-05, "epoch": 1.76, "percentage": 29.41, "elapsed_time": "0:10:47", "remaining_time": "0:25:54"}
+{"current_steps": 340, "total_steps": 1122, "loss": 1.4525, "learning_rate": 7.968296272592861e-05, "epoch": 1.8133333333333335, "percentage": 30.3, "elapsed_time": "0:11:06", "remaining_time": "0:25:34"}
+{"current_steps": 350, "total_steps": 1122, "loss": 1.4497, "learning_rate": 7.854487451788099e-05, "epoch": 1.8666666666666667, "percentage": 31.19, "elapsed_time": "0:11:26", "remaining_time": "0:25:14"}
+{"current_steps": 360, "total_steps": 1122, "loss": 1.4595, "learning_rate": 7.738440869493018e-05, "epoch": 1.92, "percentage": 32.09, "elapsed_time": "0:11:46", "remaining_time": "0:24:54"}
+{"current_steps": 370, "total_steps": 1122, "loss": 1.4525, "learning_rate": 7.62024749985878e-05, "epoch": 1.9733333333333334, "percentage": 32.98, "elapsed_time": "0:12:06", "remaining_time": "0:24:36"}
+{"current_steps": 380, "total_steps": 1122, "loss": 1.1721, "learning_rate": 7.500000000000001e-05, "epoch": 2.026666666666667, "percentage": 33.87, "elapsed_time": "0:12:26", "remaining_time": "0:24:17"}
+{"current_steps": 390, "total_steps": 1122, "loss": 0.8541, "learning_rate": 7.377792637356645e-05, "epoch": 2.08, "percentage": 34.76, "elapsed_time": "0:12:45", "remaining_time": "0:23:57"}
+{"current_steps": 400, "total_steps": 1122, "loss": 0.855, "learning_rate": 7.253721215793528e-05, "epoch": 2.1333333333333333, "percentage": 35.65, "elapsed_time": "0:13:05", "remaining_time": "0:23:37"}
+{"current_steps": 410, "total_steps": 1122, "loss": 0.861, "learning_rate": 7.127883000495352e-05, "epoch": 2.1866666666666665, "percentage": 36.54, "elapsed_time": "0:13:24", "remaining_time": "0:23:17"}
+{"current_steps": 420, "total_steps": 1122, "loss": 0.8677, "learning_rate": 7.000376641716133e-05, "epoch": 2.24, "percentage": 37.43, "elapsed_time": "0:13:43", "remaining_time": "0:22:56"}
+{"current_steps": 430, "total_steps": 1122, "loss": 0.8831, "learning_rate": 6.87130209744282e-05, "epoch": 2.2933333333333334, "percentage": 38.32, "elapsed_time": "0:14:03", "remaining_time": "0:22:37"}
+{"current_steps": 440, "total_steps": 1122, "loss": 0.8742, "learning_rate": 6.740760555033716e-05, "epoch": 2.3466666666666667, "percentage": 39.22, "elapsed_time": "0:14:23", "remaining_time": "0:22:17"}
+{"current_steps": 450, "total_steps": 1122, "loss": 0.8605, "learning_rate": 6.60885435189314e-05, "epoch": 2.4, "percentage": 40.11, "elapsed_time": "0:14:42", "remaining_time": "0:21:57"}
+{"current_steps": 460, "total_steps": 1122, "loss": 0.8857, "learning_rate": 6.475686895244533e-05, "epoch": 2.453333333333333, "percentage": 41.0, "elapsed_time": "0:15:01", "remaining_time": "0:21:38"}
+{"current_steps": 470, "total_steps": 1122, "loss": 0.8734, "learning_rate": 6.341362581064855e-05, "epoch": 2.506666666666667, "percentage": 41.89, "elapsed_time": "0:15:21", "remaining_time": "0:21:18"}
+{"current_steps": 480, "total_steps": 1122, "loss": 0.9104, "learning_rate": 6.205986712243875e-05, "epoch": 2.56, "percentage": 42.78, "elapsed_time": "0:15:41", "remaining_time": "0:20:58"}
+{"current_steps": 490, "total_steps": 1122, "loss": 0.8724, "learning_rate": 6.069665416032487e-05, "epoch": 2.6133333333333333, "percentage": 43.67, "elapsed_time": "0:16:00", "remaining_time": "0:20:39"}
+{"current_steps": 500, "total_steps": 1122, "loss": 0.9018, "learning_rate": 5.9325055608447655e-05, "epoch": 2.6666666666666665, "percentage": 44.56, "elapsed_time": "0:16:20", "remaining_time": "0:20:19"}
+{"current_steps": 510, "total_steps": 1122, "loss": 0.9018, "learning_rate": 5.7946146724789996e-05, "epoch": 2.7199999999999998, "percentage": 45.45, "elapsed_time": "0:16:39", "remaining_time": "0:19:59"}
+{"current_steps": 520, "total_steps": 1122, "loss": 0.8865, "learning_rate": 5.656100849823366e-05, "epoch": 2.7733333333333334, "percentage": 46.35, "elapsed_time": "0:16:59", "remaining_time": "0:19:39"}
+{"current_steps": 530, "total_steps": 1122, "loss": 0.912, "learning_rate": 5.5170726801123316e-05, "epoch": 2.8266666666666667, "percentage": 47.24, "elapsed_time": "0:17:18", "remaining_time": "0:19:20"}
+{"current_steps": 540, "total_steps": 1122, "loss": 0.8963, "learning_rate": 5.377639153800229e-05, "epoch": 2.88, "percentage": 48.13, "elapsed_time": "0:17:38", "remaining_time": "0:19:00"}
+{"current_steps": 550, "total_steps": 1122, "loss": 0.8931, "learning_rate": 5.2379095791187124e-05, "epoch": 2.9333333333333336, "percentage": 49.02, "elapsed_time": "0:17:57", "remaining_time": "0:18:40"}
+{"current_steps": 560, "total_steps": 1122, "loss": 0.8806, "learning_rate": 5.097993496385112e-05, "epoch": 2.986666666666667, "percentage": 49.91, "elapsed_time": "0:18:17", "remaining_time": "0:18:21"}
+{"current_steps": 570, "total_steps": 1122, "loss": 0.5508, "learning_rate": 4.958000592128834e-05, "epoch": 3.04, "percentage": 50.8, "elapsed_time": "0:18:36", "remaining_time": "0:18:01"}
+{"current_steps": 580, "total_steps": 1122, "loss": 0.4234, "learning_rate": 4.818040613103139e-05, "epoch": 3.0933333333333333, "percentage": 51.69, "elapsed_time": "0:18:56", "remaining_time": "0:17:41"}
+{"current_steps": 590, "total_steps": 1122, "loss": 0.406, "learning_rate": 4.678223280249718e-05, "epoch": 3.1466666666666665, "percentage": 52.58, "elapsed_time": "0:19:16", "remaining_time": "0:17:22"}
+{"current_steps": 600, "total_steps": 1122, "loss": 0.4104, "learning_rate": 4.5386582026834906e-05, "epoch": 3.2, "percentage": 53.48, "elapsed_time": "0:19:35", "remaining_time": "0:17:02"}
+{"current_steps": 610, "total_steps": 1122, "loss": 0.4013, "learning_rate": 4.399454791765075e-05, "epoch": 3.2533333333333334, "percentage": 54.37, "elapsed_time": "0:19:54", "remaining_time": "0:16:43"}
+{"current_steps": 620, "total_steps": 1122, "loss": 0.422, "learning_rate": 4.26072217532829e-05, "epoch": 3.3066666666666666, "percentage": 55.26, "elapsed_time": "0:20:14", "remaining_time": "0:16:23"}
+{"current_steps": 630, "total_steps": 1122, "loss": 0.3986, "learning_rate": 4.122569112129921e-05, "epoch": 3.36, "percentage": 56.15, "elapsed_time": "0:20:34", "remaining_time": "0:16:04"}
+{"current_steps": 640, "total_steps": 1122, "loss": 0.4245, "learning_rate": 3.985103906588821e-05, "epoch": 3.413333333333333, "percentage": 57.04, "elapsed_time": "0:20:53", "remaining_time": "0:15:44"}
+{"current_steps": 650, "total_steps": 1122, "loss": 0.4098, "learning_rate": 3.848434323881197e-05, "epoch": 3.466666666666667, "percentage": 57.93, "elapsed_time": "0:21:13", "remaining_time": "0:15:24"}
+{"current_steps": 660, "total_steps": 1122, "loss": 0.4072, "learning_rate": 3.712667505458622e-05, "epoch": 3.52, "percentage": 58.82, "elapsed_time": "0:21:32", "remaining_time": "0:15:04"}
+{"current_steps": 670, "total_steps": 1122, "loss": 0.4129, "learning_rate": 3.5779098850550186e-05, "epoch": 3.5733333333333333, "percentage": 59.71, "elapsed_time": "0:21:52", "remaining_time": "0:14:45"}
+{"current_steps": 680, "total_steps": 1122, "loss": 0.4029, "learning_rate": 3.444267105248454e-05, "epoch": 3.626666666666667, "percentage": 60.61, "elapsed_time": "0:22:11", "remaining_time": "0:14:25"}
+{"current_steps": 690, "total_steps": 1122, "loss": 0.4154, "learning_rate": 3.311843934643157e-05, "epoch": 3.68, "percentage": 61.5, "elapsed_time": "0:22:30", "remaining_time": "0:14:05"}
+{"current_steps": 700, "total_steps": 1122, "loss": 0.4252, "learning_rate": 3.18074418573668e-05, "epoch": 3.7333333333333334, "percentage": 62.39, "elapsed_time": "0:22:50", "remaining_time": "0:13:46"}
+{"current_steps": 710, "total_steps": 1122, "loss": 0.4042, "learning_rate": 3.0510706335366035e-05, "epoch": 3.7866666666666666, "percentage": 63.28, "elapsed_time": "0:23:09", "remaining_time": "0:13:26"}
+{"current_steps": 720, "total_steps": 1122, "loss": 0.4096, "learning_rate": 2.9229249349905684e-05, "epoch": 3.84, "percentage": 64.17, "elapsed_time": "0:23:29", "remaining_time": "0:13:06"}
+{"current_steps": 730, "total_steps": 1122, "loss": 0.4282, "learning_rate": 2.7964075492928086e-05, "epoch": 3.8933333333333335, "percentage": 65.06, "elapsed_time": "0:23:48", "remaining_time": "0:12:47"}
+{"current_steps": 740, "total_steps": 1122, "loss": 0.4065, "learning_rate": 2.6716176591296548e-05, "epoch": 3.9466666666666668, "percentage": 65.95, "elapsed_time": "0:24:08", "remaining_time": "0:12:27"}
+{"current_steps": 750, "total_steps": 1122, "loss": 0.4176, "learning_rate": 2.5486530929257572e-05, "epoch": 4.0, "percentage": 66.84, "elapsed_time": "0:24:27", "remaining_time": "0:12:07"}
+{"current_steps": 760, "total_steps": 1122, "loss": 0.1568, "learning_rate": 2.4276102481519652e-05, "epoch": 4.053333333333334, "percentage": 67.74, "elapsed_time": "0:24:47", "remaining_time": "0:11:48"}
+{"current_steps": 770, "total_steps": 1122, "loss": 0.1499, "learning_rate": 2.3085840157550037e-05, "epoch": 4.1066666666666665, "percentage": 68.63, "elapsed_time": "0:25:06", "remaining_time": "0:11:28"}
+{"current_steps": 780, "total_steps": 1122, "loss": 0.1465, "learning_rate": 2.1916677057681785e-05, "epoch": 4.16, "percentage": 69.52, "elapsed_time": "0:25:26", "remaining_time": "0:11:09"}
+{"current_steps": 790, "total_steps": 1122, "loss": 0.146, "learning_rate": 2.0769529741614297e-05, "epoch": 4.213333333333333, "percentage": 70.41, "elapsed_time": "0:25:45", "remaining_time": "0:10:49"}
+{"current_steps": 800, "total_steps": 1122, "loss": 0.1455, "learning_rate": 1.9645297509880863e-05, "epoch": 4.266666666666667, "percentage": 71.3, "elapsed_time": "0:26:05", "remaining_time": "0:10:30"}
+{"current_steps": 810, "total_steps": 1122, "loss": 0.1546, "learning_rate": 1.854486169884635e-05, "epoch": 4.32, "percentage": 72.19, "elapsed_time": "0:26:25", "remaining_time": "0:10:10"}
+{"current_steps": 820, "total_steps": 1122, "loss": 0.1432, "learning_rate": 1.746908498978791e-05, "epoch": 4.373333333333333, "percentage": 73.08, "elapsed_time": "0:26:44", "remaining_time": "0:09:51"}
+{"current_steps": 830, "total_steps": 1122, "loss": 0.1508, "learning_rate": 1.6418810732600175e-05, "epoch": 4.426666666666667, "percentage": 73.98, "elapsed_time": "0:27:04", "remaining_time": "0:09:31"}
+{"current_steps": 840, "total_steps": 1122, "loss": 0.1468, "learning_rate": 1.5394862284655264e-05, "epoch": 4.48, "percentage": 74.87, "elapsed_time": "0:27:23", "remaining_time": "0:09:11"}
+{"current_steps": 850, "total_steps": 1122, "loss": 0.1489, "learning_rate": 1.4398042365335746e-05, "epoch": 4.533333333333333, "percentage": 75.76, "elapsed_time": "0:27:43", "remaining_time": "0:08:52"}
+{"current_steps": 860, "total_steps": 1122, "loss": 0.1471, "learning_rate": 1.3429132426746743e-05, "epoch": 4.586666666666667, "percentage": 76.65, "elapsed_time": "0:28:02", "remaining_time": "0:08:32"}
+{"current_steps": 870, "total_steps": 1122, "loss": 0.1439, "learning_rate": 1.2488892041100364e-05, "epoch": 4.64, "percentage": 77.54, "elapsed_time": "0:28:21", "remaining_time": "0:08:12"}
+{"current_steps": 880, "total_steps": 1122, "loss": 0.1413, "learning_rate": 1.1578058305252748e-05, "epoch": 4.693333333333333, "percentage": 78.43, "elapsed_time": "0:28:41", "remaining_time": "0:07:53"}
+{"current_steps": 890, "total_steps": 1122, "loss": 0.1387, "learning_rate": 1.0697345262860636e-05, "epoch": 4.746666666666667, "percentage": 79.32, "elapsed_time": "0:29:01", "remaining_time": "0:07:33"}
+{"current_steps": 900, "total_steps": 1122, "loss": 0.1338, "learning_rate": 9.847443344610297e-06, "epoch": 4.8, "percentage": 80.21, "elapsed_time": "0:29:20", "remaining_time": "0:07:14"}
+{"current_steps": 910, "total_steps": 1122, "loss": 0.1365, "learning_rate": 9.029018826957775e-06, "epoch": 4.8533333333333335, "percentage": 81.11, "elapsed_time": "0:29:39", "remaining_time": "0:06:54"}
+{"current_steps": 920, "total_steps": 1122, "loss": 0.1449, "learning_rate": 8.242713309804728e-06, "epoch": 4.906666666666666, "percentage": 82.0, "elapsed_time": "0:29:59", "remaining_time": "0:06:35"}
+{"current_steps": 930, "total_steps": 1122, "loss": 0.1387, "learning_rate": 7.489143213519301e-06, "epoch": 4.96, "percentage": 82.89, "elapsed_time": "0:30:18", "remaining_time": "0:06:15"}
+{"current_steps": 940, "total_steps": 1122, "loss": 0.1181, "learning_rate": 6.768899295696413e-06, "epoch": 5.013333333333334, "percentage": 83.78, "elapsed_time": "0:30:38", "remaining_time": "0:05:55"}
+{"current_steps": 950, "total_steps": 1122, "loss": 0.0602, "learning_rate": 6.082546188036203e-06, "epoch": 5.066666666666666, "percentage": 84.67, "elapsed_time": "0:30:57", "remaining_time": "0:05:36"}
+{"current_steps": 960, "total_steps": 1122, "loss": 0.0562, "learning_rate": 5.430621953703785e-06, "epoch": 5.12, "percentage": 85.56, "elapsed_time": "0:31:16", "remaining_time": "0:05:16"}
+{"current_steps": 970, "total_steps": 1122, "loss": 0.0576, "learning_rate": 4.813637665517251e-06, "epoch": 5.173333333333334, "percentage": 86.45, "elapsed_time": "0:31:36", "remaining_time": "0:04:57"}
+{"current_steps": 980, "total_steps": 1122, "loss": 0.0552, "learning_rate": 4.232077005294638e-06, "epoch": 5.226666666666667, "percentage": 87.34, "elapsed_time": "0:31:56", "remaining_time": "0:04:37"}
+{"current_steps": 990, "total_steps": 1122, "loss": 0.0528, "learning_rate": 3.686395884673921e-06, "epoch": 5.28, "percentage": 88.24, "elapsed_time": "0:32:15", "remaining_time": "0:04:18"}
+{"current_steps": 1000, "total_steps": 1122, "loss": 0.0556, "learning_rate": 3.177022087703324e-06, "epoch": 5.333333333333333, "percentage": 89.13, "elapsed_time": "0:32:34", "remaining_time": "0:03:58"}
+{"current_steps": 1010, "total_steps": 1122, "loss": 0.0535, "learning_rate": 2.704354935482095e-06, "epoch": 5.386666666666667, "percentage": 90.02, "elapsed_time": "0:32:54", "remaining_time": "0:03:38"}
+{"current_steps": 1020, "total_steps": 1122, "loss": 0.054, "learning_rate": 2.268764973114684e-06, "epoch": 5.44, "percentage": 90.91, "elapsed_time": "0:33:14", "remaining_time": "0:03:19"}
+{"current_steps": 1030, "total_steps": 1122, "loss": 0.0537, "learning_rate": 1.8705936792237255e-06, "epoch": 5.493333333333333, "percentage": 91.8, "elapsed_time": "0:33:33", "remaining_time": "0:02:59"}
+{"current_steps": 1040, "total_steps": 1122, "loss": 0.0538, "learning_rate": 1.5101531982495308e-06, "epoch": 5.546666666666667, "percentage": 92.69, "elapsed_time": "0:33:52", "remaining_time": "0:02:40"}
+{"current_steps": 1050, "total_steps": 1122, "loss": 0.0555, "learning_rate": 1.1877260957459834e-06, "epoch": 5.6, "percentage": 93.58, "elapsed_time": "0:34:12", "remaining_time": "0:02:20"}
+{"current_steps": 1060, "total_steps": 1122, "loss": 0.0581, "learning_rate": 9.035651368646648e-07, "epoch": 5.653333333333333, "percentage": 94.47, "elapsed_time": "0:34:32", "remaining_time": "0:02:01"}
+{"current_steps": 1070, "total_steps": 1122, "loss": 0.0527, "learning_rate": 6.578930882008283e-07, "epoch": 5.706666666666667, "percentage": 95.37, "elapsed_time": "0:34:51", "remaining_time": "0:01:41"}
+{"current_steps": 1080, "total_steps": 1122, "loss": 0.0546, "learning_rate": 4.5090254315662826e-07, "epoch": 5.76, "percentage": 96.26, "elapsed_time": "0:35:10", "remaining_time": "0:01:22"}
+{"current_steps": 1090, "total_steps": 1122, "loss": 0.0546, "learning_rate": 2.8275577095846493e-07, "epoch": 5.8133333333333335, "percentage": 97.15, "elapsed_time": "0:35:30", "remaining_time": "0:01:02"}
+{"current_steps": 1100, "total_steps": 1122, "loss": 0.0539, "learning_rate": 1.5358458944680353e-07, "epoch": 5.866666666666667, "percentage": 98.04, "elapsed_time": "0:35:50", "remaining_time": "0:00:43"}
+{"current_steps": 1110, "total_steps": 1122, "loss": 0.0513, "learning_rate": 6.349026173824713e-08, "epoch": 5.92, "percentage": 98.93, "elapsed_time": "0:36:09", "remaining_time": "0:00:23"}
+{"current_steps": 1120, "total_steps": 1122, "loss": 0.0541, "learning_rate": 1.2543416840771205e-08, "epoch": 5.973333333333334, "percentage": 99.82, "elapsed_time": "0:36:29", "remaining_time": "0:00:03"}
+{"current_steps": 1122, "total_steps": 1122, "epoch": 5.984, "percentage": 100.0, "elapsed_time": "0:36:33", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,826 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.984,
+  "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": 14.895448684692383,
+      "learning_rate": 9.999686404744783e-05,
+      "loss": 2.8019,
+      "step": 10
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 3.8985605239868164,
+      "learning_rate": 9.996158909866488e-05,
+      "loss": 2.0956,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.3862061500549316,
+      "learning_rate": 9.98871470062288e-05,
+      "loss": 2.0049,
+      "step": 30
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 4.111490726470947,
+      "learning_rate": 9.977359612865423e-05,
+      "loss": 1.9912,
+      "step": 40
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 3.1158804893493652,
+      "learning_rate": 9.96210254835968e-05,
+      "loss": 2.0245,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.631307601928711,
+      "learning_rate": 9.94295546780682e-05,
+      "loss": 2.0146,
+      "step": 60
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 2.765378713607788,
+      "learning_rate": 9.919933381467088e-05,
+      "loss": 2.0106,
+      "step": 70
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 2.667142629623413,
+      "learning_rate": 9.89305433739258e-05,
+      "loss": 2.0109,
+      "step": 80
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.601536750793457,
+      "learning_rate": 9.862339407278564e-05,
+      "loss": 2.039,
+      "step": 90
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.5337209701538086,
+      "learning_rate": 9.827812669944423e-05,
+      "loss": 1.9905,
+      "step": 100
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 2.725510835647583,
+      "learning_rate": 9.789501192457188e-05,
+      "loss": 2.0033,
+      "step": 110
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.6179168224334717,
+      "learning_rate": 9.747435008912438e-05,
+      "loss": 1.9661,
+      "step": 120
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 2.63457989692688,
+      "learning_rate": 9.701647096889219e-05,
+      "loss": 2.0196,
+      "step": 130
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 2.5192859172821045,
+      "learning_rate": 9.652173351597435e-05,
+      "loss": 1.9727,
+      "step": 140
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.644923686981201,
+      "learning_rate": 9.599052557737973e-05,
+      "loss": 1.985,
+      "step": 150
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 2.377471446990967,
+      "learning_rate": 9.542326359097619e-05,
+      "loss": 1.9542,
+      "step": 160
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 2.525643825531006,
+      "learning_rate": 9.482039225902624e-05,
+      "loss": 1.9835,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.341500759124756,
+      "learning_rate": 9.418238419956484e-05,
+      "loss": 1.9677,
+      "step": 180
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 2.5298564434051514,
+      "learning_rate": 9.350973957589277e-05,
+      "loss": 1.8294,
+      "step": 190
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 2.342876672744751,
+      "learning_rate": 9.280298570447611e-05,
+      "loss": 1.42,
+      "step": 200
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.60962176322937,
+      "learning_rate": 9.206267664155907e-05,
+      "loss": 1.381,
+      "step": 210
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 2.7232189178466797,
+      "learning_rate": 9.128939274881421e-05,
+      "loss": 1.4036,
+      "step": 220
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 2.5342235565185547,
+      "learning_rate": 9.048374023837085e-05,
+      "loss": 1.3998,
+      "step": 230
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.335803985595703,
+      "learning_rate": 8.964635069757802e-05,
+      "loss": 1.421,
+      "step": 240
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 2.223832607269287,
+      "learning_rate": 8.87778805938746e-05,
+      "loss": 1.441,
+      "step": 250
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 2.348698854446411,
+      "learning_rate": 8.787901076015486e-05,
+      "loss": 1.4158,
+      "step": 260
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.3340389728546143,
+      "learning_rate": 8.695044586103296e-05,
+      "loss": 1.4436,
+      "step": 270
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 2.277675151824951,
+      "learning_rate": 8.599291384042442e-05,
+      "loss": 1.4412,
+      "step": 280
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 2.437199592590332,
+      "learning_rate": 8.500716535087814e-05,
+      "loss": 1.445,
+      "step": 290
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.497368812561035,
+      "learning_rate": 8.399397316510596e-05,
+      "loss": 1.4719,
+      "step": 300
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 2.4297564029693604,
+      "learning_rate": 8.295413157017127e-05,
+      "loss": 1.4665,
+      "step": 310
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 2.555246353149414,
+      "learning_rate": 8.188845574481163e-05,
+      "loss": 1.4728,
+      "step": 320
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.552035331726074,
+      "learning_rate": 8.079778112038318e-05,
+      "loss": 1.4648,
+      "step": 330
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 2.568624496459961,
+      "learning_rate": 7.968296272592861e-05,
+      "loss": 1.4525,
+      "step": 340
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 2.3397440910339355,
+      "learning_rate": 7.854487451788099e-05,
+      "loss": 1.4497,
+      "step": 350
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.2001404762268066,
+      "learning_rate": 7.738440869493018e-05,
+      "loss": 1.4595,
+      "step": 360
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 2.279663324356079,
+      "learning_rate": 7.62024749985878e-05,
+      "loss": 1.4525,
+      "step": 370
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 2.764693021774292,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.1721,
+      "step": 380
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.481473207473755,
+      "learning_rate": 7.377792637356645e-05,
+      "loss": 0.8541,
+      "step": 390
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 2.4774906635284424,
+      "learning_rate": 7.253721215793528e-05,
+      "loss": 0.855,
+      "step": 400
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 2.4302332401275635,
+      "learning_rate": 7.127883000495352e-05,
+      "loss": 0.861,
+      "step": 410
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.2290687561035156,
+      "learning_rate": 7.000376641716133e-05,
+      "loss": 0.8677,
+      "step": 420
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 2.5468499660491943,
+      "learning_rate": 6.87130209744282e-05,
+      "loss": 0.8831,
+      "step": 430
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 2.432751417160034,
+      "learning_rate": 6.740760555033716e-05,
+      "loss": 0.8742,
+      "step": 440
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.4456443786621094,
+      "learning_rate": 6.60885435189314e-05,
+      "loss": 0.8605,
+      "step": 450
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 2.675802707672119,
+      "learning_rate": 6.475686895244533e-05,
+      "loss": 0.8857,
+      "step": 460
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 2.5510013103485107,
+      "learning_rate": 6.341362581064855e-05,
+      "loss": 0.8734,
+      "step": 470
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.669424533843994,
+      "learning_rate": 6.205986712243875e-05,
+      "loss": 0.9104,
+      "step": 480
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 2.881044387817383,
+      "learning_rate": 6.069665416032487e-05,
+      "loss": 0.8724,
+      "step": 490
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 2.5946762561798096,
+      "learning_rate": 5.9325055608447655e-05,
+      "loss": 0.9018,
+      "step": 500
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.388828754425049,
+      "learning_rate": 5.7946146724789996e-05,
+      "loss": 0.9018,
+      "step": 510
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 2.5408201217651367,
+      "learning_rate": 5.656100849823366e-05,
+      "loss": 0.8865,
+      "step": 520
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 2.56980037689209,
+      "learning_rate": 5.5170726801123316e-05,
+      "loss": 0.912,
+      "step": 530
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.4559166431427,
+      "learning_rate": 5.377639153800229e-05,
+      "loss": 0.8963,
+      "step": 540
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 2.4111409187316895,
+      "learning_rate": 5.2379095791187124e-05,
+      "loss": 0.8931,
+      "step": 550
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 2.4074866771698,
+      "learning_rate": 5.097993496385112e-05,
+      "loss": 0.8806,
+      "step": 560
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 3.0234549045562744,
+      "learning_rate": 4.958000592128834e-05,
+      "loss": 0.5508,
+      "step": 570
+    },
+    {
+      "epoch": 3.0933333333333333,
+      "grad_norm": 2.288658618927002,
+      "learning_rate": 4.818040613103139e-05,
+      "loss": 0.4234,
+      "step": 580
+    },
+    {
+      "epoch": 3.1466666666666665,
+      "grad_norm": 2.0306291580200195,
+      "learning_rate": 4.678223280249718e-05,
+      "loss": 0.406,
+      "step": 590
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.1763899326324463,
+      "learning_rate": 4.5386582026834906e-05,
+      "loss": 0.4104,
+      "step": 600
+    },
+    {
+      "epoch": 3.2533333333333334,
+      "grad_norm": 2.181497097015381,
+      "learning_rate": 4.399454791765075e-05,
+      "loss": 0.4013,
+      "step": 610
+    },
+    {
+      "epoch": 3.3066666666666666,
+      "grad_norm": 2.2306203842163086,
+      "learning_rate": 4.26072217532829e-05,
+      "loss": 0.422,
+      "step": 620
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 2.1796200275421143,
+      "learning_rate": 4.122569112129921e-05,
+      "loss": 0.3986,
+      "step": 630
+    },
+    {
+      "epoch": 3.413333333333333,
+      "grad_norm": 2.1730310916900635,
+      "learning_rate": 3.985103906588821e-05,
+      "loss": 0.4245,
+      "step": 640
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 2.2129032611846924,
+      "learning_rate": 3.848434323881197e-05,
+      "loss": 0.4098,
+      "step": 650
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 2.097221612930298,
+      "learning_rate": 3.712667505458622e-05,
+      "loss": 0.4072,
+      "step": 660
+    },
+    {
+      "epoch": 3.5733333333333333,
+      "grad_norm": 2.1691372394561768,
+      "learning_rate": 3.5779098850550186e-05,
+      "loss": 0.4129,
+      "step": 670
+    },
+    {
+      "epoch": 3.626666666666667,
+      "grad_norm": 2.146040916442871,
+      "learning_rate": 3.444267105248454e-05,
+      "loss": 0.4029,
+      "step": 680
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 2.097416877746582,
+      "learning_rate": 3.311843934643157e-05,
+      "loss": 0.4154,
+      "step": 690
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 2.1109459400177,
+      "learning_rate": 3.18074418573668e-05,
+      "loss": 0.4252,
+      "step": 700
+    },
+    {
+      "epoch": 3.7866666666666666,
+      "grad_norm": 2.1149725914001465,
+      "learning_rate": 3.0510706335366035e-05,
+      "loss": 0.4042,
+      "step": 710
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.1683661937713623,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.4096,
+      "step": 720
+    },
+    {
+      "epoch": 3.8933333333333335,
+      "grad_norm": 2.069917917251587,
+      "learning_rate": 2.7964075492928086e-05,
+      "loss": 0.4282,
+      "step": 730
+    },
+    {
+      "epoch": 3.9466666666666668,
+      "grad_norm": 2.2071914672851562,
+      "learning_rate": 2.6716176591296548e-05,
+      "loss": 0.4065,
+      "step": 740
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.092756748199463,
+      "learning_rate": 2.5486530929257572e-05,
+      "loss": 0.4176,
+      "step": 750
+    },
+    {
+      "epoch": 4.053333333333334,
+      "grad_norm": 1.728727102279663,
+      "learning_rate": 2.4276102481519652e-05,
+      "loss": 0.1568,
+      "step": 760
+    },
+    {
+      "epoch": 4.1066666666666665,
+      "grad_norm": 1.3281182050704956,
+      "learning_rate": 2.3085840157550037e-05,
+      "loss": 0.1499,
+      "step": 770
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 1.4647213220596313,
+      "learning_rate": 2.1916677057681785e-05,
+      "loss": 0.1465,
+      "step": 780
+    },
+    {
+      "epoch": 4.213333333333333,
+      "grad_norm": 1.47672438621521,
+      "learning_rate": 2.0769529741614297e-05,
+      "loss": 0.146,
+      "step": 790
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 1.5165902376174927,
+      "learning_rate": 1.9645297509880863e-05,
+      "loss": 0.1455,
+      "step": 800
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 1.497672200202942,
+      "learning_rate": 1.854486169884635e-05,
+      "loss": 0.1546,
+      "step": 810
+    },
+    {
+      "epoch": 4.373333333333333,
+      "grad_norm": 1.5302739143371582,
+      "learning_rate": 1.746908498978791e-05,
+      "loss": 0.1432,
+      "step": 820
+    },
+    {
+      "epoch": 4.426666666666667,
+      "grad_norm": 1.5722713470458984,
+      "learning_rate": 1.6418810732600175e-05,
+      "loss": 0.1508,
+      "step": 830
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 1.3972179889678955,
+      "learning_rate": 1.5394862284655264e-05,
+      "loss": 0.1468,
+      "step": 840
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 1.422791600227356,
+      "learning_rate": 1.4398042365335746e-05,
+      "loss": 0.1489,
+      "step": 850
+    },
+    {
+      "epoch": 4.586666666666667,
+      "grad_norm": 1.4409677982330322,
+      "learning_rate": 1.3429132426746743e-05,
+      "loss": 0.1471,
+      "step": 860
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 1.3254153728485107,
+      "learning_rate": 1.2488892041100364e-05,
+      "loss": 0.1439,
+      "step": 870
+    },
+    {
+      "epoch": 4.693333333333333,
+      "grad_norm": 1.4582805633544922,
+      "learning_rate": 1.1578058305252748e-05,
+      "loss": 0.1413,
+      "step": 880
+    },
+    {
+      "epoch": 4.746666666666667,
+      "grad_norm": 1.3275575637817383,
+      "learning_rate": 1.0697345262860636e-05,
+      "loss": 0.1387,
+      "step": 890
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.4769142866134644,
+      "learning_rate": 9.847443344610297e-06,
+      "loss": 0.1338,
+      "step": 900
+    },
+    {
+      "epoch": 4.8533333333333335,
+      "grad_norm": 1.5396736860275269,
+      "learning_rate": 9.029018826957775e-06,
+      "loss": 0.1365,
+      "step": 910
+    },
+    {
+      "epoch": 4.906666666666666,
+      "grad_norm": 1.4937539100646973,
+      "learning_rate": 8.242713309804728e-06,
+      "loss": 0.1449,
+      "step": 920
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 1.3706806898117065,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 0.1387,
+      "step": 930
+    },
+    {
+      "epoch": 5.013333333333334,
+      "grad_norm": 0.7881463170051575,
+      "learning_rate": 6.768899295696413e-06,
+      "loss": 0.1181,
+      "step": 940
+    },
+    {
+      "epoch": 5.066666666666666,
+      "grad_norm": 0.7070630788803101,
+      "learning_rate": 6.082546188036203e-06,
+      "loss": 0.0602,
+      "step": 950
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.7920947670936584,
+      "learning_rate": 5.430621953703785e-06,
+      "loss": 0.0562,
+      "step": 960
+    },
+    {
+      "epoch": 5.173333333333334,
+      "grad_norm": 0.7710321545600891,
+      "learning_rate": 4.813637665517251e-06,
+      "loss": 0.0576,
+      "step": 970
+    },
+    {
+      "epoch": 5.226666666666667,
+      "grad_norm": 0.7036638259887695,
+      "learning_rate": 4.232077005294638e-06,
+      "loss": 0.0552,
+      "step": 980
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.7647135853767395,
+      "learning_rate": 3.686395884673921e-06,
+      "loss": 0.0528,
+      "step": 990
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.8770582675933838,
+      "learning_rate": 3.177022087703324e-06,
+      "loss": 0.0556,
+      "step": 1000
+    },
+    {
+      "epoch": 5.386666666666667,
+      "grad_norm": 0.8413597345352173,
+      "learning_rate": 2.704354935482095e-06,
+      "loss": 0.0535,
+      "step": 1010
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.8006970882415771,
+      "learning_rate": 2.268764973114684e-06,
+      "loss": 0.054,
+      "step": 1020
+    },
+    {
+      "epoch": 5.493333333333333,
+      "grad_norm": 0.7778401374816895,
+      "learning_rate": 1.8705936792237255e-06,
+      "loss": 0.0537,
+      "step": 1030
+    },
+    {
+      "epoch": 5.546666666666667,
+      "grad_norm": 0.7576852440834045,
+      "learning_rate": 1.5101531982495308e-06,
+      "loss": 0.0538,
+      "step": 1040
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.8617320656776428,
+      "learning_rate": 1.1877260957459834e-06,
+      "loss": 0.0555,
+      "step": 1050
+    },
+    {
+      "epoch": 5.653333333333333,
+      "grad_norm": 0.9345221519470215,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 0.0581,
+      "step": 1060
+    },
+    {
+      "epoch": 5.706666666666667,
+      "grad_norm": 0.8783689737319946,
+      "learning_rate": 6.578930882008283e-07,
+      "loss": 0.0527,
+      "step": 1070
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.7886053323745728,
+      "learning_rate": 4.5090254315662826e-07,
+      "loss": 0.0546,
+      "step": 1080
+    },
+    {
+      "epoch": 5.8133333333333335,
+      "grad_norm": 0.8314456939697266,
+      "learning_rate": 2.8275577095846493e-07,
+      "loss": 0.0546,
+      "step": 1090
+    },
+    {
+      "epoch": 5.866666666666667,
+      "grad_norm": 0.743155837059021,
+      "learning_rate": 1.5358458944680353e-07,
+      "loss": 0.0539,
+      "step": 1100
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 0.8680102825164795,
+      "learning_rate": 6.349026173824713e-08,
+      "loss": 0.0513,
+      "step": 1110
+    },
+    {
+      "epoch": 5.973333333333334,
+      "grad_norm": 0.8589802980422974,
+      "learning_rate": 1.2543416840771205e-08,
+      "loss": 0.0541,
+      "step": 1120
+    },
+    {
+      "epoch": 5.984,
+      "step": 1122,
+      "total_flos": 6.106743890876826e+16,
+      "train_loss": 0.8316886925774356,
+      "train_runtime": 2204.228,
+      "train_samples_per_second": 16.33,
+      "train_steps_per_second": 0.509
+    }
+  ],
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.106743890876826e+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 sha256:91fbc25bce6cbb7a7d71d7730b3d620a1cef1a997307944321ec719a907b4bf3
+size 5368