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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: deepseek-r1-distill-qwen-15b-deepscaler-14b-min-bs1-epoch5.0-ctx32768-ga2-lr5e-05-wr0.0-n8-shuffle-once
+  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. -->
+
+# deepseek-r1-distill-qwen-15b-deepscaler-14b-min-bs1-epoch5.0-ctx32768-ga2-lr5e-05-wr0.0-n8-shuffle-once
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the deepscaler-14b-min 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.8.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.2037958677613773e+18,
+    "train_loss": 0.17663632503225785,
+    "train_runtime": 5647.7775,
+    "train_samples_per_second": 3.416,
+    "train_steps_per_second": 0.214
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.55.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa2840e6e6692126ff1c00c3c0dfa7daedf9ec39f57ebc5db8016bef3ca4518
+size 3554214752

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.2037958677613773e+18,
+    "train_loss": 0.17663632503225785,
+    "train_runtime": 5647.7775,
+    "train_samples_per_second": 3.416,
+    "train_steps_per_second": 0.214
+}

trainer_log.jsonl

@@ -0,0 +1,122 @@
+{"current_steps": 10, "total_steps": 1210, "loss": 0.2832, "lr": 4.999317497454979e-05, "epoch": 0.041407867494824016, "percentage": 0.83, "elapsed_time": "0:00:39", "remaining_time": "1:18:26"}
+{"current_steps": 20, "total_steps": 1210, "loss": 0.2886, "lr": 4.996958707817619e-05, "epoch": 0.08281573498964803, "percentage": 1.65, "elapsed_time": "0:01:24", "remaining_time": "1:23:32"}
+{"current_steps": 30, "total_steps": 1210, "loss": 0.2894, "lr": 4.992916794739796e-05, "epoch": 0.12422360248447205, "percentage": 2.48, "elapsed_time": "0:02:01", "remaining_time": "1:19:45"}
+{"current_steps": 40, "total_steps": 1210, "loss": 0.2803, "lr": 4.987194482751406e-05, "epoch": 0.16563146997929606, "percentage": 3.31, "elapsed_time": "0:02:42", "remaining_time": "1:19:19"}
+{"current_steps": 50, "total_steps": 1210, "loss": 0.2838, "lr": 4.979795629087817e-05, "epoch": 0.2070393374741201, "percentage": 4.13, "elapsed_time": "0:03:18", "remaining_time": "1:16:41"}
+{"current_steps": 60, "total_steps": 1210, "loss": 0.2834, "lr": 4.970725221089826e-05, "epoch": 0.2484472049689441, "percentage": 4.96, "elapsed_time": "0:03:54", "remaining_time": "1:14:49"}
+{"current_steps": 70, "total_steps": 1210, "loss": 0.2873, "lr": 4.959989372841846e-05, "epoch": 0.2898550724637681, "percentage": 5.79, "elapsed_time": "0:04:40", "remaining_time": "1:16:15"}
+{"current_steps": 80, "total_steps": 1210, "loss": 0.2913, "lr": 4.94759532105059e-05, "epoch": 0.33126293995859213, "percentage": 6.61, "elapsed_time": "0:05:27", "remaining_time": "1:16:59"}
+{"current_steps": 90, "total_steps": 1210, "loss": 0.2737, "lr": 4.9335514201670244e-05, "epoch": 0.37267080745341613, "percentage": 7.44, "elapsed_time": "0:06:13", "remaining_time": "1:17:25"}
+{"current_steps": 100, "total_steps": 1210, "loss": 0.276, "lr": 4.917867136754893e-05, "epoch": 0.4140786749482402, "percentage": 8.26, "elapsed_time": "0:06:55", "remaining_time": "1:16:55"}
+{"current_steps": 110, "total_steps": 1210, "loss": 0.2878, "lr": 4.900553043109595e-05, "epoch": 0.4554865424430642, "percentage": 9.09, "elapsed_time": "0:07:40", "remaining_time": "1:16:45"}
+{"current_steps": 120, "total_steps": 1210, "loss": 0.2759, "lr": 4.881620810131723e-05, "epoch": 0.4968944099378882, "percentage": 9.92, "elapsed_time": "0:08:18", "remaining_time": "1:15:25"}
+{"current_steps": 130, "total_steps": 1210, "loss": 0.2939, "lr": 4.86108319946007e-05, "epoch": 0.5383022774327122, "percentage": 10.74, "elapsed_time": "0:09:00", "remaining_time": "1:14:50"}
+{"current_steps": 140, "total_steps": 1210, "loss": 0.288, "lr": 4.838954054869392e-05, "epoch": 0.5797101449275363, "percentage": 11.57, "elapsed_time": "0:09:44", "remaining_time": "1:14:25"}
+{"current_steps": 150, "total_steps": 1210, "loss": 0.2813, "lr": 4.815248292938752e-05, "epoch": 0.6211180124223602, "percentage": 12.4, "elapsed_time": "0:10:28", "remaining_time": "1:14:00"}
+{"current_steps": 160, "total_steps": 1210, "loss": 0.275, "lr": 4.7899818929967035e-05, "epoch": 0.6625258799171843, "percentage": 13.22, "elapsed_time": "0:11:09", "remaining_time": "1:13:15"}
+{"current_steps": 170, "total_steps": 1210, "loss": 0.2893, "lr": 4.7631718863501195e-05, "epoch": 0.7039337474120083, "percentage": 14.05, "elapsed_time": "0:11:56", "remaining_time": "1:13:02"}
+{"current_steps": 180, "total_steps": 1210, "loss": 0.2797, "lr": 4.734836344803905e-05, "epoch": 0.7453416149068323, "percentage": 14.88, "elapsed_time": "0:12:37", "remaining_time": "1:12:12"}
+{"current_steps": 190, "total_steps": 1210, "loss": 0.2812, "lr": 4.70499436847935e-05, "epoch": 0.7867494824016563, "percentage": 15.7, "elapsed_time": "0:13:19", "remaining_time": "1:11:31"}
+{"current_steps": 200, "total_steps": 1210, "loss": 0.2915, "lr": 4.673666072939319e-05, "epoch": 0.8281573498964804, "percentage": 16.53, "elapsed_time": "0:14:07", "remaining_time": "1:11:19"}
+{"current_steps": 210, "total_steps": 1210, "loss": 0.2829, "lr": 4.640872575628973e-05, "epoch": 0.8695652173913043, "percentage": 17.36, "elapsed_time": "0:14:54", "remaining_time": "1:10:58"}
+{"current_steps": 220, "total_steps": 1210, "loss": 0.2836, "lr": 4.606635981641135e-05, "epoch": 0.9109730848861284, "percentage": 18.18, "elapsed_time": "0:15:32", "remaining_time": "1:09:55"}
+{"current_steps": 230, "total_steps": 1210, "loss": 0.2798, "lr": 4.570979368815932e-05, "epoch": 0.9523809523809523, "percentage": 19.01, "elapsed_time": "0:16:15", "remaining_time": "1:09:15"}
+{"current_steps": 240, "total_steps": 1210, "loss": 0.2797, "lr": 4.533926772184728e-05, "epoch": 0.9937888198757764, "percentage": 19.83, "elapsed_time": "0:17:02", "remaining_time": "1:08:51"}
+{"current_steps": 250, "total_steps": 1210, "loss": 0.2179, "lr": 4.495503167768842e-05, "epoch": 1.0331262939958592, "percentage": 20.66, "elapsed_time": "0:17:56", "remaining_time": "1:08:55"}
+{"current_steps": 260, "total_steps": 1210, "loss": 0.189, "lr": 4.455734455743977e-05, "epoch": 1.0745341614906831, "percentage": 21.49, "elapsed_time": "0:18:42", "remaining_time": "1:08:21"}
+{"current_steps": 270, "total_steps": 1210, "loss": 0.196, "lr": 4.4146474429817095e-05, "epoch": 1.1159420289855073, "percentage": 22.31, "elapsed_time": "0:19:34", "remaining_time": "1:08:08"}
+{"current_steps": 280, "total_steps": 1210, "loss": 0.2001, "lr": 4.372269824979789e-05, "epoch": 1.1573498964803313, "percentage": 23.14, "elapsed_time": "0:20:33", "remaining_time": "1:08:17"}
+{"current_steps": 290, "total_steps": 1210, "loss": 0.2058, "lr": 4.328630167193459e-05, "epoch": 1.1987577639751552, "percentage": 23.97, "elapsed_time": "0:21:31", "remaining_time": "1:08:16"}
+{"current_steps": 300, "total_steps": 1210, "loss": 0.2009, "lr": 4.283757885780353e-05, "epoch": 1.2401656314699794, "percentage": 24.79, "elapsed_time": "0:22:23", "remaining_time": "1:07:54"}
+{"current_steps": 310, "total_steps": 1210, "loss": 0.2057, "lr": 4.2376832277719645e-05, "epoch": 1.2815734989648033, "percentage": 25.62, "elapsed_time": "0:23:20", "remaining_time": "1:07:44"}
+{"current_steps": 320, "total_steps": 1210, "loss": 0.2055, "lr": 4.1904372506850484e-05, "epoch": 1.3229813664596273, "percentage": 26.45, "elapsed_time": "0:24:11", "remaining_time": "1:07:18"}
+{"current_steps": 330, "total_steps": 1210, "loss": 0.2029, "lr": 4.142051801586701e-05, "epoch": 1.3643892339544514, "percentage": 27.27, "elapsed_time": "0:25:07", "remaining_time": "1:07:00"}
+{"current_steps": 340, "total_steps": 1210, "loss": 0.2067, "lr": 4.092559495627224e-05, "epoch": 1.4057971014492754, "percentage": 28.1, "elapsed_time": "0:25:58", "remaining_time": "1:06:28"}
+{"current_steps": 350, "total_steps": 1210, "loss": 0.2119, "lr": 4.041993694055253e-05, "epoch": 1.4472049689440993, "percentage": 28.93, "elapsed_time": "0:26:47", "remaining_time": "1:05:49"}
+{"current_steps": 360, "total_steps": 1210, "loss": 0.2105, "lr": 3.990388481729959e-05, "epoch": 1.4886128364389233, "percentage": 29.75, "elapsed_time": "0:27:40", "remaining_time": "1:05:20"}
+{"current_steps": 370, "total_steps": 1210, "loss": 0.2089, "lr": 3.937778644145488e-05, "epoch": 1.5300207039337475, "percentage": 30.58, "elapsed_time": "0:28:28", "remaining_time": "1:04:38"}
+{"current_steps": 380, "total_steps": 1210, "loss": 0.2132, "lr": 3.884199643983125e-05, "epoch": 1.5714285714285714, "percentage": 31.4, "elapsed_time": "0:29:15", "remaining_time": "1:03:54"}
+{"current_steps": 390, "total_steps": 1210, "loss": 0.2158, "lr": 3.829687597206986e-05, "epoch": 1.6128364389233956, "percentage": 32.23, "elapsed_time": "0:30:08", "remaining_time": "1:03:22"}
+{"current_steps": 400, "total_steps": 1210, "loss": 0.2056, "lr": 3.774279248719351e-05, "epoch": 1.6542443064182195, "percentage": 33.06, "elapsed_time": "0:30:54", "remaining_time": "1:02:36"}
+{"current_steps": 410, "total_steps": 1210, "loss": 0.2078, "lr": 3.718011947592051e-05, "epoch": 1.6956521739130435, "percentage": 33.88, "elapsed_time": "0:31:44", "remaining_time": "1:01:56"}
+{"current_steps": 420, "total_steps": 1210, "loss": 0.2134, "lr": 3.660923621890601e-05, "epoch": 1.7370600414078674, "percentage": 34.71, "elapsed_time": "0:32:31", "remaining_time": "1:01:10"}
+{"current_steps": 430, "total_steps": 1210, "loss": 0.2178, "lr": 3.603052753108053e-05, "epoch": 1.7784679089026914, "percentage": 35.54, "elapsed_time": "0:33:34", "remaining_time": "1:00:53"}
+{"current_steps": 440, "total_steps": 1210, "loss": 0.2143, "lr": 3.544438350225799e-05, "epoch": 1.8198757763975155, "percentage": 36.36, "elapsed_time": "0:34:31", "remaining_time": "1:00:25"}
+{"current_steps": 450, "total_steps": 1210, "loss": 0.2008, "lr": 3.485119923418807e-05, "epoch": 1.8612836438923397, "percentage": 37.19, "elapsed_time": "0:35:22", "remaining_time": "0:59:44"}
+{"current_steps": 460, "total_steps": 1210, "loss": 0.2133, "lr": 3.425137457423029e-05, "epoch": 1.9026915113871636, "percentage": 38.02, "elapsed_time": "0:36:17", "remaining_time": "0:59:10"}
+{"current_steps": 470, "total_steps": 1210, "loss": 0.2107, "lr": 3.3645313845829066e-05, "epoch": 1.9440993788819876, "percentage": 38.84, "elapsed_time": "0:37:07", "remaining_time": "0:58:27"}
+{"current_steps": 480, "total_steps": 1210, "loss": 0.212, "lr": 3.303342557597171e-05, "epoch": 1.9855072463768115, "percentage": 39.67, "elapsed_time": "0:37:59", "remaining_time": "0:57:46"}
+{"current_steps": 490, "total_steps": 1210, "loss": 0.1871, "lr": 3.2416122219812846e-05, "epoch": 2.0248447204968945, "percentage": 40.5, "elapsed_time": "0:38:45", "remaining_time": "0:56:57"}
+{"current_steps": 500, "total_steps": 1210, "loss": 0.1728, "lr": 3.179381988265104e-05, "epoch": 2.0662525879917184, "percentage": 41.32, "elapsed_time": "0:39:20", "remaining_time": "0:55:52"}
+{"current_steps": 510, "total_steps": 1210, "loss": 0.1773, "lr": 3.116693803944497e-05, "epoch": 2.1076604554865424, "percentage": 42.15, "elapsed_time": "0:40:03", "remaining_time": "0:54:58"}
+{"current_steps": 520, "total_steps": 1210, "loss": 0.1771, "lr": 3.053589925205812e-05, "epoch": 2.1490683229813663, "percentage": 42.98, "elapsed_time": "0:40:47", "remaining_time": "0:54:07"}
+{"current_steps": 530, "total_steps": 1210, "loss": 0.1796, "lr": 2.9901128884422863e-05, "epoch": 2.1904761904761907, "percentage": 43.8, "elapsed_time": "0:41:26", "remaining_time": "0:53:10"}
+{"current_steps": 540, "total_steps": 1210, "loss": 0.1731, "lr": 2.92630548158156e-05, "epoch": 2.2318840579710146, "percentage": 44.63, "elapsed_time": "0:42:09", "remaining_time": "0:52:18"}
+{"current_steps": 550, "total_steps": 1210, "loss": 0.1727, "lr": 2.862210715243641e-05, "epoch": 2.2732919254658386, "percentage": 45.45, "elapsed_time": "0:42:57", "remaining_time": "0:51:33"}
+{"current_steps": 560, "total_steps": 1210, "loss": 0.1819, "lr": 2.7978717937487697e-05, "epoch": 2.3146997929606625, "percentage": 46.28, "elapsed_time": "0:43:40", "remaining_time": "0:50:41"}
+{"current_steps": 570, "total_steps": 1210, "loss": 0.1774, "lr": 2.733332085994701e-05, "epoch": 2.3561076604554865, "percentage": 47.11, "elapsed_time": "0:44:19", "remaining_time": "0:49:45"}
+{"current_steps": 580, "total_steps": 1210, "loss": 0.1641, "lr": 2.668635096223065e-05, "epoch": 2.3975155279503104, "percentage": 47.93, "elapsed_time": "0:45:04", "remaining_time": "0:48:57"}
+{"current_steps": 590, "total_steps": 1210, "loss": 0.1822, "lr": 2.603824434694483e-05, "epoch": 2.4389233954451344, "percentage": 48.76, "elapsed_time": "0:45:47", "remaining_time": "0:48:07"}
+{"current_steps": 600, "total_steps": 1210, "loss": 0.1799, "lr": 2.53894378829223e-05, "epoch": 2.4803312629399588, "percentage": 49.59, "elapsed_time": "0:46:25", "remaining_time": "0:47:11"}
+{"current_steps": 610, "total_steps": 1210, "loss": 0.1687, "lr": 2.4740368910742436e-05, "epoch": 2.5217391304347827, "percentage": 50.41, "elapsed_time": "0:47:07", "remaining_time": "0:46:21"}
+{"current_steps": 620, "total_steps": 1210, "loss": 0.1878, "lr": 2.4091474947933308e-05, "epoch": 2.5631469979296067, "percentage": 51.24, "elapsed_time": "0:47:50", "remaining_time": "0:45:31"}
+{"current_steps": 630, "total_steps": 1210, "loss": 0.1756, "lr": 2.3443193394054523e-05, "epoch": 2.6045548654244306, "percentage": 52.07, "elapsed_time": "0:48:37", "remaining_time": "0:44:45"}
+{"current_steps": 640, "total_steps": 1210, "loss": 0.1816, "lr": 2.279596123585958e-05, "epoch": 2.6459627329192545, "percentage": 52.89, "elapsed_time": "0:49:23", "remaining_time": "0:43:59"}
+{"current_steps": 650, "total_steps": 1210, "loss": 0.1772, "lr": 2.2150214752736488e-05, "epoch": 2.687370600414079, "percentage": 53.72, "elapsed_time": "0:50:09", "remaining_time": "0:43:12"}
+{"current_steps": 660, "total_steps": 1210, "loss": 0.1785, "lr": 2.1506389222625122e-05, "epoch": 2.728778467908903, "percentage": 54.55, "elapsed_time": "0:50:51", "remaining_time": "0:42:22"}
+{"current_steps": 670, "total_steps": 1210, "loss": 0.1798, "lr": 2.0864918628609757e-05, "epoch": 2.770186335403727, "percentage": 55.37, "elapsed_time": "0:51:35", "remaining_time": "0:41:34"}
+{"current_steps": 680, "total_steps": 1210, "loss": 0.1722, "lr": 2.02262353663843e-05, "epoch": 2.8115942028985508, "percentage": 56.2, "elapsed_time": "0:52:15", "remaining_time": "0:40:43"}
+{"current_steps": 690, "total_steps": 1210, "loss": 0.1794, "lr": 1.9590769952787637e-05, "epoch": 2.8530020703933747, "percentage": 57.02, "elapsed_time": "0:53:00", "remaining_time": "0:39:57"}
+{"current_steps": 700, "total_steps": 1210, "loss": 0.1832, "lr": 1.895895073560536e-05, "epoch": 2.8944099378881987, "percentage": 57.85, "elapsed_time": "0:53:46", "remaining_time": "0:39:10"}
+{"current_steps": 710, "total_steps": 1210, "loss": 0.1821, "lr": 1.8331203604833667e-05, "epoch": 2.9358178053830226, "percentage": 58.68, "elapsed_time": "0:54:29", "remaining_time": "0:38:22"}
+{"current_steps": 720, "total_steps": 1210, "loss": 0.1757, "lr": 1.7707951705599932e-05, "epoch": 2.9772256728778466, "percentage": 59.5, "elapsed_time": "0:55:14", "remaining_time": "0:37:36"}
+{"current_steps": 730, "total_steps": 1210, "loss": 0.1515, "lr": 1.708961515293355e-05, "epoch": 3.0165631469979295, "percentage": 60.33, "elapsed_time": "0:56:01", "remaining_time": "0:36:50"}
+{"current_steps": 740, "total_steps": 1210, "loss": 0.1205, "lr": 1.647661074857924e-05, "epoch": 3.0579710144927534, "percentage": 61.16, "elapsed_time": "0:56:55", "remaining_time": "0:36:09"}
+{"current_steps": 750, "total_steps": 1210, "loss": 0.1158, "lr": 1.5869351700043722e-05, "epoch": 3.099378881987578, "percentage": 61.98, "elapsed_time": "0:57:42", "remaining_time": "0:35:23"}
+{"current_steps": 760, "total_steps": 1210, "loss": 0.1158, "lr": 1.5268247342065215e-05, "epoch": 3.1407867494824018, "percentage": 62.81, "elapsed_time": "0:58:38", "remaining_time": "0:34:43"}
+{"current_steps": 770, "total_steps": 1210, "loss": 0.1212, "lr": 1.467370286069343e-05, "epoch": 3.1821946169772257, "percentage": 63.64, "elapsed_time": "0:59:28", "remaining_time": "0:33:58"}
+{"current_steps": 780, "total_steps": 1210, "loss": 0.1124, "lr": 1.4086119020166022e-05, "epoch": 3.2236024844720497, "percentage": 64.46, "elapsed_time": "1:00:13", "remaining_time": "0:33:12"}
+{"current_steps": 790, "total_steps": 1210, "loss": 0.1169, "lr": 1.3505891892765694e-05, "epoch": 3.2650103519668736, "percentage": 65.29, "elapsed_time": "1:01:02", "remaining_time": "0:32:27"}
+{"current_steps": 800, "total_steps": 1210, "loss": 0.1194, "lr": 1.2933412591839991e-05, "epoch": 3.3064182194616976, "percentage": 66.12, "elapsed_time": "1:02:01", "remaining_time": "0:31:47"}
+{"current_steps": 810, "total_steps": 1210, "loss": 0.1154, "lr": 1.2369067008163798e-05, "epoch": 3.3478260869565215, "percentage": 66.94, "elapsed_time": "1:03:03", "remaining_time": "0:31:08"}
+{"current_steps": 820, "total_steps": 1210, "loss": 0.1182, "lr": 1.1813235549822122e-05, "epoch": 3.389233954451346, "percentage": 67.77, "elapsed_time": "1:03:51", "remaining_time": "0:30:22"}
+{"current_steps": 830, "total_steps": 1210, "loss": 0.1046, "lr": 1.1266292885788681e-05, "epoch": 3.43064182194617, "percentage": 68.6, "elapsed_time": "1:04:36", "remaining_time": "0:29:34"}
+{"current_steps": 840, "total_steps": 1210, "loss": 0.1191, "lr": 1.0728607693373009e-05, "epoch": 3.472049689440994, "percentage": 69.42, "elapsed_time": "1:05:37", "remaining_time": "0:28:54"}
+{"current_steps": 850, "total_steps": 1210, "loss": 0.1155, "lr": 1.020054240970637e-05, "epoch": 3.5134575569358177, "percentage": 70.25, "elapsed_time": "1:06:27", "remaining_time": "0:28:08"}
+{"current_steps": 860, "total_steps": 1210, "loss": 0.1217, "lr": 9.682452987433992e-06, "epoch": 3.5548654244306417, "percentage": 71.07, "elapsed_time": "1:07:25", "remaining_time": "0:27:26"}
+{"current_steps": 870, "total_steps": 1210, "loss": 0.1154, "lr": 9.174688654778243e-06, "epoch": 3.596273291925466, "percentage": 71.9, "elapsed_time": "1:08:11", "remaining_time": "0:26:38"}
+{"current_steps": 880, "total_steps": 1210, "loss": 0.1041, "lr": 8.677591680134604e-06, "epoch": 3.63768115942029, "percentage": 72.73, "elapsed_time": "1:08:57", "remaining_time": "0:25:51"}
+{"current_steps": 890, "total_steps": 1210, "loss": 0.1179, "lr": 8.191497141359034e-06, "epoch": 3.679089026915114, "percentage": 73.55, "elapsed_time": "1:09:52", "remaining_time": "0:25:07"}
+{"current_steps": 900, "total_steps": 1210, "loss": 0.1169, "lr": 7.716732699902207e-06, "epoch": 3.720496894409938, "percentage": 74.38, "elapsed_time": "1:10:48", "remaining_time": "0:24:23"}
+{"current_steps": 910, "total_steps": 1210, "loss": 0.1125, "lr": 7.253618379942978e-06, "epoch": 3.761904761904762, "percentage": 75.21, "elapsed_time": "1:11:42", "remaining_time": "0:23:38"}
+{"current_steps": 920, "total_steps": 1210, "loss": 0.1179, "lr": 6.802466352669884e-06, "epoch": 3.803312629399586, "percentage": 76.03, "elapsed_time": "1:12:30", "remaining_time": "0:22:51"}
+{"current_steps": 930, "total_steps": 1210, "loss": 0.1153, "lr": 6.363580725856099e-06, "epoch": 3.8447204968944098, "percentage": 76.86, "elapsed_time": "1:13:15", "remaining_time": "0:22:03"}
+{"current_steps": 940, "total_steps": 1210, "loss": 0.1075, "lr": 5.937257338869665e-06, "epoch": 3.8861283643892337, "percentage": 77.69, "elapsed_time": "1:14:03", "remaining_time": "0:21:16"}
+{"current_steps": 950, "total_steps": 1210, "loss": 0.1118, "lr": 5.523783563257259e-06, "epoch": 3.927536231884058, "percentage": 78.51, "elapsed_time": "1:14:57", "remaining_time": "0:20:30"}
+{"current_steps": 960, "total_steps": 1210, "loss": 0.1177, "lr": 5.123438109035816e-06, "epoch": 3.968944099378882, "percentage": 79.34, "elapsed_time": "1:15:50", "remaining_time": "0:19:45"}
+{"current_steps": 970, "total_steps": 1210, "loss": 0.1119, "lr": 4.736490836822652e-06, "epoch": 4.008281573498965, "percentage": 80.17, "elapsed_time": "1:16:42", "remaining_time": "0:18:58"}
+{"current_steps": 980, "total_steps": 1210, "loss": 0.1005, "lr": 4.36320257593065e-06, "epoch": 4.049689440993789, "percentage": 80.99, "elapsed_time": "1:17:29", "remaining_time": "0:18:11"}
+{"current_steps": 990, "total_steps": 1210, "loss": 0.1022, "lr": 4.003824948551249e-06, "epoch": 4.091097308488613, "percentage": 81.82, "elapsed_time": "1:18:12", "remaining_time": "0:17:22"}
+{"current_steps": 1000, "total_steps": 1210, "loss": 0.0984, "lr": 3.6586002001435694e-06, "epoch": 4.132505175983437, "percentage": 82.64, "elapsed_time": "1:19:01", "remaining_time": "0:16:35"}
+{"current_steps": 1010, "total_steps": 1210, "loss": 0.0954, "lr": 3.327761036144225e-06, "epoch": 4.173913043478261, "percentage": 83.47, "elapsed_time": "1:19:43", "remaining_time": "0:15:47"}
+{"current_steps": 1020, "total_steps": 1210, "loss": 0.1009, "lr": 3.0115304651076593e-06, "epoch": 4.215320910973085, "percentage": 84.3, "elapsed_time": "1:20:27", "remaining_time": "0:14:59"}
+{"current_steps": 1030, "total_steps": 1210, "loss": 0.0999, "lr": 2.7101216483829265e-06, "epoch": 4.256728778467909, "percentage": 85.12, "elapsed_time": "1:21:17", "remaining_time": "0:14:12"}
+{"current_steps": 1040, "total_steps": 1210, "loss": 0.1014, "lr": 2.4237377564281573e-06, "epoch": 4.298136645962733, "percentage": 85.95, "elapsed_time": "1:21:54", "remaining_time": "0:13:23"}
+{"current_steps": 1050, "total_steps": 1210, "loss": 0.0981, "lr": 2.1525718318595567e-06, "epoch": 4.3395445134575565, "percentage": 86.78, "elapsed_time": "1:22:36", "remaining_time": "0:12:35"}
+{"current_steps": 1060, "total_steps": 1210, "loss": 0.0978, "lr": 1.8968066593273021e-06, "epoch": 4.380952380952381, "percentage": 87.6, "elapsed_time": "1:23:27", "remaining_time": "0:11:48"}
+{"current_steps": 1070, "total_steps": 1210, "loss": 0.0929, "lr": 1.6566146423059815e-06, "epoch": 4.422360248447205, "percentage": 88.43, "elapsed_time": "1:24:13", "remaining_time": "0:11:01"}
+{"current_steps": 1080, "total_steps": 1210, "loss": 0.1, "lr": 1.4321576868827014e-06, "epoch": 4.463768115942029, "percentage": 89.26, "elapsed_time": "1:24:53", "remaining_time": "0:10:13"}
+{"current_steps": 1090, "total_steps": 1210, "loss": 0.0992, "lr": 1.2235870926211619e-06, "epoch": 4.505175983436853, "percentage": 90.08, "elapsed_time": "1:25:33", "remaining_time": "0:09:25"}
+{"current_steps": 1100, "total_steps": 1210, "loss": 0.0967, "lr": 1.0310434505752254e-06, "epoch": 4.546583850931677, "percentage": 90.91, "elapsed_time": "1:26:08", "remaining_time": "0:08:36"}
+{"current_steps": 1110, "total_steps": 1210, "loss": 0.0941, "lr": 8.546565485208019e-07, "epoch": 4.587991718426501, "percentage": 91.74, "elapsed_time": "1:26:53", "remaining_time": "0:07:49"}
+{"current_steps": 1120, "total_steps": 1210, "loss": 0.0998, "lr": 6.94545283469894e-07, "epoch": 4.629399585921325, "percentage": 92.56, "elapsed_time": "1:27:40", "remaining_time": "0:07:02"}
+{"current_steps": 1130, "total_steps": 1210, "loss": 0.0999, "lr": 5.508175815257421e-07, "epoch": 4.670807453416149, "percentage": 93.39, "elapsed_time": "1:28:21", "remaining_time": "0:06:15"}
+{"current_steps": 1140, "total_steps": 1210, "loss": 0.1013, "lr": 4.2357032513315187e-07, "epoch": 4.712215320910973, "percentage": 94.21, "elapsed_time": "1:29:03", "remaining_time": "0:05:28"}
+{"current_steps": 1150, "total_steps": 1210, "loss": 0.1003, "lr": 3.1288928777299385e-07, "epoch": 4.753623188405797, "percentage": 95.04, "elapsed_time": "1:29:51", "remaining_time": "0:04:41"}
+{"current_steps": 1160, "total_steps": 1210, "loss": 0.0966, "lr": 2.1884907614493355e-07, "epoch": 4.795031055900621, "percentage": 95.87, "elapsed_time": "1:30:40", "remaining_time": "0:03:54"}
+{"current_steps": 1170, "total_steps": 1210, "loss": 0.1042, "lr": 1.415130798773423e-07, "epoch": 4.836438923395445, "percentage": 96.69, "elapsed_time": "1:31:18", "remaining_time": "0:03:07"}
+{"current_steps": 1180, "total_steps": 1210, "loss": 0.1034, "lr": 8.093342879827714e-08, "epoch": 4.877846790890269, "percentage": 97.52, "elapsed_time": "1:31:57", "remaining_time": "0:02:20"}
+{"current_steps": 1190, "total_steps": 1210, "loss": 0.1063, "lr": 3.715095779636968e-08, "epoch": 4.919254658385093, "percentage": 98.35, "elapsed_time": "1:32:37", "remaining_time": "0:01:33"}
+{"current_steps": 1200, "total_steps": 1210, "loss": 0.1048, "lr": 1.0195179295269252e-08, "epoch": 4.9606625258799175, "percentage": 99.17, "elapsed_time": "1:33:21", "remaining_time": "0:00:46"}
+{"current_steps": 1210, "total_steps": 1210, "loss": 0.1018, "lr": 8.426336022826498e-11, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:34:01", "remaining_time": "0:00:00"}
+{"current_steps": 1210, "total_steps": 1210, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:34:06", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,890 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041407867494824016,
+      "grad_norm": 0.35360315442085266,
+      "learning_rate": 4.999317497454979e-05,
+      "loss": 0.2832,
+      "step": 10
+    },
+    {
+      "epoch": 0.08281573498964803,
+      "grad_norm": 0.30314165353775024,
+      "learning_rate": 4.996958707817619e-05,
+      "loss": 0.2886,
+      "step": 20
+    },
+    {
+      "epoch": 0.12422360248447205,
+      "grad_norm": 0.27160707116127014,
+      "learning_rate": 4.992916794739796e-05,
+      "loss": 0.2894,
+      "step": 30
+    },
+    {
+      "epoch": 0.16563146997929606,
+      "grad_norm": 0.23829400539398193,
+      "learning_rate": 4.987194482751406e-05,
+      "loss": 0.2803,
+      "step": 40
+    },
+    {
+      "epoch": 0.2070393374741201,
+      "grad_norm": 0.2390674203634262,
+      "learning_rate": 4.979795629087817e-05,
+      "loss": 0.2838,
+      "step": 50
+    },
+    {
+      "epoch": 0.2484472049689441,
+      "grad_norm": 0.2903118431568146,
+      "learning_rate": 4.970725221089826e-05,
+      "loss": 0.2834,
+      "step": 60
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 0.259442538022995,
+      "learning_rate": 4.959989372841846e-05,
+      "loss": 0.2873,
+      "step": 70
+    },
+    {
+      "epoch": 0.33126293995859213,
+      "grad_norm": 0.22768715023994446,
+      "learning_rate": 4.94759532105059e-05,
+      "loss": 0.2913,
+      "step": 80
+    },
+    {
+      "epoch": 0.37267080745341613,
+      "grad_norm": 0.23414920270442963,
+      "learning_rate": 4.9335514201670244e-05,
+      "loss": 0.2737,
+      "step": 90
+    },
+    {
+      "epoch": 0.4140786749482402,
+      "grad_norm": 0.2142115980386734,
+      "learning_rate": 4.917867136754893e-05,
+      "loss": 0.276,
+      "step": 100
+    },
+    {
+      "epoch": 0.4554865424430642,
+      "grad_norm": 0.2646670639514923,
+      "learning_rate": 4.900553043109595e-05,
+      "loss": 0.2878,
+      "step": 110
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 0.21466413140296936,
+      "learning_rate": 4.881620810131723e-05,
+      "loss": 0.2759,
+      "step": 120
+    },
+    {
+      "epoch": 0.5383022774327122,
+      "grad_norm": 0.2301633059978485,
+      "learning_rate": 4.86108319946007e-05,
+      "loss": 0.2939,
+      "step": 130
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.2588035762310028,
+      "learning_rate": 4.838954054869392e-05,
+      "loss": 0.288,
+      "step": 140
+    },
+    {
+      "epoch": 0.6211180124223602,
+      "grad_norm": 0.22933104634284973,
+      "learning_rate": 4.815248292938752e-05,
+      "loss": 0.2813,
+      "step": 150
+    },
+    {
+      "epoch": 0.6625258799171843,
+      "grad_norm": 0.22708487510681152,
+      "learning_rate": 4.7899818929967035e-05,
+      "loss": 0.275,
+      "step": 160
+    },
+    {
+      "epoch": 0.7039337474120083,
+      "grad_norm": 0.25342801213264465,
+      "learning_rate": 4.7631718863501195e-05,
+      "loss": 0.2893,
+      "step": 170
+    },
+    {
+      "epoch": 0.7453416149068323,
+      "grad_norm": 0.2402268946170807,
+      "learning_rate": 4.734836344803905e-05,
+      "loss": 0.2797,
+      "step": 180
+    },
+    {
+      "epoch": 0.7867494824016563,
+      "grad_norm": 0.21311792731285095,
+      "learning_rate": 4.70499436847935e-05,
+      "loss": 0.2812,
+      "step": 190
+    },
+    {
+      "epoch": 0.8281573498964804,
+      "grad_norm": 0.23196695744991302,
+      "learning_rate": 4.673666072939319e-05,
+      "loss": 0.2915,
+      "step": 200
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.21855035424232483,
+      "learning_rate": 4.640872575628973e-05,
+      "loss": 0.2829,
+      "step": 210
+    },
+    {
+      "epoch": 0.9109730848861284,
+      "grad_norm": 0.2444789558649063,
+      "learning_rate": 4.606635981641135e-05,
+      "loss": 0.2836,
+      "step": 220
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.2303490787744522,
+      "learning_rate": 4.570979368815932e-05,
+      "loss": 0.2798,
+      "step": 230
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 0.2174331247806549,
+      "learning_rate": 4.533926772184728e-05,
+      "loss": 0.2797,
+      "step": 240
+    },
+    {
+      "epoch": 1.0331262939958592,
+      "grad_norm": 0.2568439245223999,
+      "learning_rate": 4.495503167768842e-05,
+      "loss": 0.2179,
+      "step": 250
+    },
+    {
+      "epoch": 1.0745341614906831,
+      "grad_norm": 0.147722527384758,
+      "learning_rate": 4.455734455743977e-05,
+      "loss": 0.189,
+      "step": 260
+    },
+    {
+      "epoch": 1.1159420289855073,
+      "grad_norm": 0.1523672342300415,
+      "learning_rate": 4.4146474429817095e-05,
+      "loss": 0.196,
+      "step": 270
+    },
+    {
+      "epoch": 1.1573498964803313,
+      "grad_norm": 0.15824240446090698,
+      "learning_rate": 4.372269824979789e-05,
+      "loss": 0.2001,
+      "step": 280
+    },
+    {
+      "epoch": 1.1987577639751552,
+      "grad_norm": 0.1849469542503357,
+      "learning_rate": 4.328630167193459e-05,
+      "loss": 0.2058,
+      "step": 290
+    },
+    {
+      "epoch": 1.2401656314699794,
+      "grad_norm": 0.1261226087808609,
+      "learning_rate": 4.283757885780353e-05,
+      "loss": 0.2009,
+      "step": 300
+    },
+    {
+      "epoch": 1.2815734989648033,
+      "grad_norm": 0.15541474521160126,
+      "learning_rate": 4.2376832277719645e-05,
+      "loss": 0.2057,
+      "step": 310
+    },
+    {
+      "epoch": 1.3229813664596273,
+      "grad_norm": 0.12406721711158752,
+      "learning_rate": 4.1904372506850484e-05,
+      "loss": 0.2055,
+      "step": 320
+    },
+    {
+      "epoch": 1.3643892339544514,
+      "grad_norm": 0.12859183549880981,
+      "learning_rate": 4.142051801586701e-05,
+      "loss": 0.2029,
+      "step": 330
+    },
+    {
+      "epoch": 1.4057971014492754,
+      "grad_norm": 0.13090819120407104,
+      "learning_rate": 4.092559495627224e-05,
+      "loss": 0.2067,
+      "step": 340
+    },
+    {
+      "epoch": 1.4472049689440993,
+      "grad_norm": 0.163692444562912,
+      "learning_rate": 4.041993694055253e-05,
+      "loss": 0.2119,
+      "step": 350
+    },
+    {
+      "epoch": 1.4886128364389233,
+      "grad_norm": 0.15472349524497986,
+      "learning_rate": 3.990388481729959e-05,
+      "loss": 0.2105,
+      "step": 360
+    },
+    {
+      "epoch": 1.5300207039337475,
+      "grad_norm": 0.16893893480300903,
+      "learning_rate": 3.937778644145488e-05,
+      "loss": 0.2089,
+      "step": 370
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.17143578827381134,
+      "learning_rate": 3.884199643983125e-05,
+      "loss": 0.2132,
+      "step": 380
+    },
+    {
+      "epoch": 1.6128364389233956,
+      "grad_norm": 0.13020960986614227,
+      "learning_rate": 3.829687597206986e-05,
+      "loss": 0.2158,
+      "step": 390
+    },
+    {
+      "epoch": 1.6542443064182195,
+      "grad_norm": 0.1852816492319107,
+      "learning_rate": 3.774279248719351e-05,
+      "loss": 0.2056,
+      "step": 400
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.1697482466697693,
+      "learning_rate": 3.718011947592051e-05,
+      "loss": 0.2078,
+      "step": 410
+    },
+    {
+      "epoch": 1.7370600414078674,
+      "grad_norm": 0.1428823173046112,
+      "learning_rate": 3.660923621890601e-05,
+      "loss": 0.2134,
+      "step": 420
+    },
+    {
+      "epoch": 1.7784679089026914,
+      "grad_norm": 0.16258591413497925,
+      "learning_rate": 3.603052753108053e-05,
+      "loss": 0.2178,
+      "step": 430
+    },
+    {
+      "epoch": 1.8198757763975155,
+      "grad_norm": 0.14834512770175934,
+      "learning_rate": 3.544438350225799e-05,
+      "loss": 0.2143,
+      "step": 440
+    },
+    {
+      "epoch": 1.8612836438923397,
+      "grad_norm": 0.15268157422542572,
+      "learning_rate": 3.485119923418807e-05,
+      "loss": 0.2008,
+      "step": 450
+    },
+    {
+      "epoch": 1.9026915113871636,
+      "grad_norm": 0.14826329052448273,
+      "learning_rate": 3.425137457423029e-05,
+      "loss": 0.2133,
+      "step": 460
+    },
+    {
+      "epoch": 1.9440993788819876,
+      "grad_norm": 0.10517703741788864,
+      "learning_rate": 3.3645313845829066e-05,
+      "loss": 0.2107,
+      "step": 470
+    },
+    {
+      "epoch": 1.9855072463768115,
+      "grad_norm": 0.1559341549873352,
+      "learning_rate": 3.303342557597171e-05,
+      "loss": 0.212,
+      "step": 480
+    },
+    {
+      "epoch": 2.0248447204968945,
+      "grad_norm": 0.21735182404518127,
+      "learning_rate": 3.2416122219812846e-05,
+      "loss": 0.1871,
+      "step": 490
+    },
+    {
+      "epoch": 2.0662525879917184,
+      "grad_norm": 0.2045336365699768,
+      "learning_rate": 3.179381988265104e-05,
+      "loss": 0.1728,
+      "step": 500
+    },
+    {
+      "epoch": 2.1076604554865424,
+      "grad_norm": 0.21433106064796448,
+      "learning_rate": 3.116693803944497e-05,
+      "loss": 0.1773,
+      "step": 510
+    },
+    {
+      "epoch": 2.1490683229813663,
+      "grad_norm": 0.21499335765838623,
+      "learning_rate": 3.053589925205812e-05,
+      "loss": 0.1771,
+      "step": 520
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.24619190394878387,
+      "learning_rate": 2.9901128884422863e-05,
+      "loss": 0.1796,
+      "step": 530
+    },
+    {
+      "epoch": 2.2318840579710146,
+      "grad_norm": 0.2280297726392746,
+      "learning_rate": 2.92630548158156e-05,
+      "loss": 0.1731,
+      "step": 540
+    },
+    {
+      "epoch": 2.2732919254658386,
+      "grad_norm": 0.2194112241268158,
+      "learning_rate": 2.862210715243641e-05,
+      "loss": 0.1727,
+      "step": 550
+    },
+    {
+      "epoch": 2.3146997929606625,
+      "grad_norm": 0.22532561421394348,
+      "learning_rate": 2.7978717937487697e-05,
+      "loss": 0.1819,
+      "step": 560
+    },
+    {
+      "epoch": 2.3561076604554865,
+      "grad_norm": 0.2583187222480774,
+      "learning_rate": 2.733332085994701e-05,
+      "loss": 0.1774,
+      "step": 570
+    },
+    {
+      "epoch": 2.3975155279503104,
+      "grad_norm": 0.2151404619216919,
+      "learning_rate": 2.668635096223065e-05,
+      "loss": 0.1641,
+      "step": 580
+    },
+    {
+      "epoch": 2.4389233954451344,
+      "grad_norm": 0.22841399908065796,
+      "learning_rate": 2.603824434694483e-05,
+      "loss": 0.1822,
+      "step": 590
+    },
+    {
+      "epoch": 2.4803312629399588,
+      "grad_norm": 0.23497164249420166,
+      "learning_rate": 2.53894378829223e-05,
+      "loss": 0.1799,
+      "step": 600
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.231641948223114,
+      "learning_rate": 2.4740368910742436e-05,
+      "loss": 0.1687,
+      "step": 610
+    },
+    {
+      "epoch": 2.5631469979296067,
+      "grad_norm": 0.23137883841991425,
+      "learning_rate": 2.4091474947933308e-05,
+      "loss": 0.1878,
+      "step": 620
+    },
+    {
+      "epoch": 2.6045548654244306,
+      "grad_norm": 0.2286098599433899,
+      "learning_rate": 2.3443193394054523e-05,
+      "loss": 0.1756,
+      "step": 630
+    },
+    {
+      "epoch": 2.6459627329192545,
+      "grad_norm": 0.242770716547966,
+      "learning_rate": 2.279596123585958e-05,
+      "loss": 0.1816,
+      "step": 640
+    },
+    {
+      "epoch": 2.687370600414079,
+      "grad_norm": 0.20602673292160034,
+      "learning_rate": 2.2150214752736488e-05,
+      "loss": 0.1772,
+      "step": 650
+    },
+    {
+      "epoch": 2.728778467908903,
+      "grad_norm": 0.26570940017700195,
+      "learning_rate": 2.1506389222625122e-05,
+      "loss": 0.1785,
+      "step": 660
+    },
+    {
+      "epoch": 2.770186335403727,
+      "grad_norm": 0.2361171692609787,
+      "learning_rate": 2.0864918628609757e-05,
+      "loss": 0.1798,
+      "step": 670
+    },
+    {
+      "epoch": 2.8115942028985508,
+      "grad_norm": 0.2533505856990814,
+      "learning_rate": 2.02262353663843e-05,
+      "loss": 0.1722,
+      "step": 680
+    },
+    {
+      "epoch": 2.8530020703933747,
+      "grad_norm": 0.2173786759376526,
+      "learning_rate": 1.9590769952787637e-05,
+      "loss": 0.1794,
+      "step": 690
+    },
+    {
+      "epoch": 2.8944099378881987,
+      "grad_norm": 0.21721962094306946,
+      "learning_rate": 1.895895073560536e-05,
+      "loss": 0.1832,
+      "step": 700
+    },
+    {
+      "epoch": 2.9358178053830226,
+      "grad_norm": 0.19834774732589722,
+      "learning_rate": 1.8331203604833667e-05,
+      "loss": 0.1821,
+      "step": 710
+    },
+    {
+      "epoch": 2.9772256728778466,
+      "grad_norm": 0.19038452208042145,
+      "learning_rate": 1.7707951705599932e-05,
+      "loss": 0.1757,
+      "step": 720
+    },
+    {
+      "epoch": 3.0165631469979295,
+      "grad_norm": 0.10852309316396713,
+      "learning_rate": 1.708961515293355e-05,
+      "loss": 0.1515,
+      "step": 730
+    },
+    {
+      "epoch": 3.0579710144927534,
+      "grad_norm": 0.15984965860843658,
+      "learning_rate": 1.647661074857924e-05,
+      "loss": 0.1205,
+      "step": 740
+    },
+    {
+      "epoch": 3.099378881987578,
+      "grad_norm": 0.13479475677013397,
+      "learning_rate": 1.5869351700043722e-05,
+      "loss": 0.1158,
+      "step": 750
+    },
+    {
+      "epoch": 3.1407867494824018,
+      "grad_norm": 0.1369597315788269,
+      "learning_rate": 1.5268247342065215e-05,
+      "loss": 0.1158,
+      "step": 760
+    },
+    {
+      "epoch": 3.1821946169772257,
+      "grad_norm": 0.16177116334438324,
+      "learning_rate": 1.467370286069343e-05,
+      "loss": 0.1212,
+      "step": 770
+    },
+    {
+      "epoch": 3.2236024844720497,
+      "grad_norm": 0.17464663088321686,
+      "learning_rate": 1.4086119020166022e-05,
+      "loss": 0.1124,
+      "step": 780
+    },
+    {
+      "epoch": 3.2650103519668736,
+      "grad_norm": 0.1939019113779068,
+      "learning_rate": 1.3505891892765694e-05,
+      "loss": 0.1169,
+      "step": 790
+    },
+    {
+      "epoch": 3.3064182194616976,
+      "grad_norm": 0.15043896436691284,
+      "learning_rate": 1.2933412591839991e-05,
+      "loss": 0.1194,
+      "step": 800
+    },
+    {
+      "epoch": 3.3478260869565215,
+      "grad_norm": 0.14959610998630524,
+      "learning_rate": 1.2369067008163798e-05,
+      "loss": 0.1154,
+      "step": 810
+    },
+    {
+      "epoch": 3.389233954451346,
+      "grad_norm": 0.142011359333992,
+      "learning_rate": 1.1813235549822122e-05,
+      "loss": 0.1182,
+      "step": 820
+    },
+    {
+      "epoch": 3.43064182194617,
+      "grad_norm": 0.11188151687383652,
+      "learning_rate": 1.1266292885788681e-05,
+      "loss": 0.1046,
+      "step": 830
+    },
+    {
+      "epoch": 3.472049689440994,
+      "grad_norm": 0.1680831015110016,
+      "learning_rate": 1.0728607693373009e-05,
+      "loss": 0.1191,
+      "step": 840
+    },
+    {
+      "epoch": 3.5134575569358177,
+      "grad_norm": 0.1537802517414093,
+      "learning_rate": 1.020054240970637e-05,
+      "loss": 0.1155,
+      "step": 850
+    },
+    {
+      "epoch": 3.5548654244306417,
+      "grad_norm": 0.15300725400447845,
+      "learning_rate": 9.682452987433992e-06,
+      "loss": 0.1217,
+      "step": 860
+    },
+    {
+      "epoch": 3.596273291925466,
+      "grad_norm": 0.13289150595664978,
+      "learning_rate": 9.174688654778243e-06,
+      "loss": 0.1154,
+      "step": 870
+    },
+    {
+      "epoch": 3.63768115942029,
+      "grad_norm": 0.148117333650589,
+      "learning_rate": 8.677591680134604e-06,
+      "loss": 0.1041,
+      "step": 880
+    },
+    {
+      "epoch": 3.679089026915114,
+      "grad_norm": 0.14158585667610168,
+      "learning_rate": 8.191497141359034e-06,
+      "loss": 0.1179,
+      "step": 890
+    },
+    {
+      "epoch": 3.720496894409938,
+      "grad_norm": 0.1266346126794815,
+      "learning_rate": 7.716732699902207e-06,
+      "loss": 0.1169,
+      "step": 900
+    },
+    {
+      "epoch": 3.761904761904762,
+      "grad_norm": 0.14878639578819275,
+      "learning_rate": 7.253618379942978e-06,
+      "loss": 0.1125,
+      "step": 910
+    },
+    {
+      "epoch": 3.803312629399586,
+      "grad_norm": 0.13568133115768433,
+      "learning_rate": 6.802466352669884e-06,
+      "loss": 0.1179,
+      "step": 920
+    },
+    {
+      "epoch": 3.8447204968944098,
+      "grad_norm": 0.12874317169189453,
+      "learning_rate": 6.363580725856099e-06,
+      "loss": 0.1153,
+      "step": 930
+    },
+    {
+      "epoch": 3.8861283643892337,
+      "grad_norm": 0.13996338844299316,
+      "learning_rate": 5.937257338869665e-06,
+      "loss": 0.1075,
+      "step": 940
+    },
+    {
+      "epoch": 3.927536231884058,
+      "grad_norm": 0.13954441249370575,
+      "learning_rate": 5.523783563257259e-06,
+      "loss": 0.1118,
+      "step": 950
+    },
+    {
+      "epoch": 3.968944099378882,
+      "grad_norm": 0.15500986576080322,
+      "learning_rate": 5.123438109035816e-06,
+      "loss": 0.1177,
+      "step": 960
+    },
+    {
+      "epoch": 4.008281573498965,
+      "grad_norm": 0.19058023393154144,
+      "learning_rate": 4.736490836822652e-06,
+      "loss": 0.1119,
+      "step": 970
+    },
+    {
+      "epoch": 4.049689440993789,
+      "grad_norm": 0.18524132668972015,
+      "learning_rate": 4.36320257593065e-06,
+      "loss": 0.1005,
+      "step": 980
+    },
+    {
+      "epoch": 4.091097308488613,
+      "grad_norm": 0.17982913553714752,
+      "learning_rate": 4.003824948551249e-06,
+      "loss": 0.1022,
+      "step": 990
+    },
+    {
+      "epoch": 4.132505175983437,
+      "grad_norm": 0.18822088837623596,
+      "learning_rate": 3.6586002001435694e-06,
+      "loss": 0.0984,
+      "step": 1000
+    },
+    {
+      "epoch": 4.173913043478261,
+      "grad_norm": 0.15588361024856567,
+      "learning_rate": 3.327761036144225e-06,
+      "loss": 0.0954,
+      "step": 1010
+    },
+    {
+      "epoch": 4.215320910973085,
+      "grad_norm": 0.21300983428955078,
+      "learning_rate": 3.0115304651076593e-06,
+      "loss": 0.1009,
+      "step": 1020
+    },
+    {
+      "epoch": 4.256728778467909,
+      "grad_norm": 0.18512149155139923,
+      "learning_rate": 2.7101216483829265e-06,
+      "loss": 0.0999,
+      "step": 1030
+    },
+    {
+      "epoch": 4.298136645962733,
+      "grad_norm": 0.19417600333690643,
+      "learning_rate": 2.4237377564281573e-06,
+      "loss": 0.1014,
+      "step": 1040
+    },
+    {
+      "epoch": 4.3395445134575565,
+      "grad_norm": 0.20371508598327637,
+      "learning_rate": 2.1525718318595567e-06,
+      "loss": 0.0981,
+      "step": 1050
+    },
+    {
+      "epoch": 4.380952380952381,
+      "grad_norm": 0.20537497103214264,
+      "learning_rate": 1.8968066593273021e-06,
+      "loss": 0.0978,
+      "step": 1060
+    },
+    {
+      "epoch": 4.422360248447205,
+      "grad_norm": 0.1472494751214981,
+      "learning_rate": 1.6566146423059815e-06,
+      "loss": 0.0929,
+      "step": 1070
+    },
+    {
+      "epoch": 4.463768115942029,
+      "grad_norm": 0.22993667423725128,
+      "learning_rate": 1.4321576868827014e-06,
+      "loss": 0.1,
+      "step": 1080
+    },
+    {
+      "epoch": 4.505175983436853,
+      "grad_norm": 0.1956310123205185,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.0992,
+      "step": 1090
+    },
+    {
+      "epoch": 4.546583850931677,
+      "grad_norm": 0.1923326551914215,
+      "learning_rate": 1.0310434505752254e-06,
+      "loss": 0.0967,
+      "step": 1100
+    },
+    {
+      "epoch": 4.587991718426501,
+      "grad_norm": 0.21617886424064636,
+      "learning_rate": 8.546565485208019e-07,
+      "loss": 0.0941,
+      "step": 1110
+    },
+    {
+      "epoch": 4.629399585921325,
+      "grad_norm": 0.16554707288742065,
+      "learning_rate": 6.94545283469894e-07,
+      "loss": 0.0998,
+      "step": 1120
+    },
+    {
+      "epoch": 4.670807453416149,
+      "grad_norm": 0.20445552468299866,
+      "learning_rate": 5.508175815257421e-07,
+      "loss": 0.0999,
+      "step": 1130
+    },
+    {
+      "epoch": 4.712215320910973,
+      "grad_norm": 0.1816573143005371,
+      "learning_rate": 4.2357032513315187e-07,
+      "loss": 0.1013,
+      "step": 1140
+    },
+    {
+      "epoch": 4.753623188405797,
+      "grad_norm": 0.17379841208457947,
+      "learning_rate": 3.1288928777299385e-07,
+      "loss": 0.1003,
+      "step": 1150
+    },
+    {
+      "epoch": 4.795031055900621,
+      "grad_norm": 0.18466944992542267,
+      "learning_rate": 2.1884907614493355e-07,
+      "loss": 0.0966,
+      "step": 1160
+    },
+    {
+      "epoch": 4.836438923395445,
+      "grad_norm": 0.2321137934923172,
+      "learning_rate": 1.415130798773423e-07,
+      "loss": 0.1042,
+      "step": 1170
+    },
+    {
+      "epoch": 4.877846790890269,
+      "grad_norm": 0.16399921476840973,
+      "learning_rate": 8.093342879827714e-08,
+      "loss": 0.1034,
+      "step": 1180
+    },
+    {
+      "epoch": 4.919254658385093,
+      "grad_norm": 0.1832115352153778,
+      "learning_rate": 3.715095779636968e-08,
+      "loss": 0.1063,
+      "step": 1190
+    },
+    {
+      "epoch": 4.9606625258799175,
+      "grad_norm": 0.18022671341896057,
+      "learning_rate": 1.0195179295269252e-08,
+      "loss": 0.1048,
+      "step": 1200
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.22758908569812775,
+      "learning_rate": 8.426336022826498e-11,
+      "loss": 0.1018,
+      "step": 1210
+    },
+    {
+      "epoch": 5.0,
+      "step": 1210,
+      "total_flos": 1.2037958677613773e+18,
+      "train_loss": 0.17663632503225785,
+      "train_runtime": 5647.7775,
+      "train_samples_per_second": 3.416,
+      "train_steps_per_second": 0.214
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2037958677613773e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a167ac38696fa4d08a3516123c2ce5b7eb78c3b17cd95a21e62cbd9ecd19602c
+size 8145