Upload folder using huggingface_hub

Browse files

Files changed (16) hide show

.gitattributes +1 -0
README.md +64 -3
adapter_config.json +37 -0
adapter_model.safetensors +3 -0
added_tokens.json +28 -0
all_results.json +8 -0
merges.txt +0 -0
special_tokens_map.json +59 -0
tokenizer.json +3 -0
tokenizer_config.json +245 -0
train_results.json +8 -0
trainer_log.jsonl +145 -0
trainer_state.json +1050 -0
training_args.bin +3 -0
training_loss_hqa_sft.png +0 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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 CHANGED Viewed

@@ -1,3 +1,64 @@
----
-license: mit
----

+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-72B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+datasets:
+- arrow
+model-index:
+- name: 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. -->
+# sft
+This model is a fine-tuned version of [/data/huggingface_models/Qwen2.5-7B-Instruct](https://huggingface.co//data/huggingface_models/Qwen2.5-7B-Instruct) on the hqa_sft dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+### Training results
+### Framework versions
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/huggingface_models/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:104706d2602302db6a6feb4289f9d5df1f4fa2f67deb088c1a2f5ce8df68c258
+size 4440772992

added_tokens.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "</retrieval>": 151668,
+  "</think>": 151666,
+  "</tool_call>": 151658,
+  "<retrieval>": 151667,
+  "<think>": 151665,
+  "<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 ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 2.9984496124031006,
+    "total_flos": 2.170312406348071e+18,
+    "train_loss": 0.43735031344464437,
+    "train_runtime": 9561.9202,
+    "train_samples_per_second": 2.428,
+    "train_steps_per_second": 0.152
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,59 @@

+{
+  "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|>",
+    {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<retrieval>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</retrieval>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb2d73624732e138c0dc43481d4775563a7eea7190357fe2a54641bc88246ee
+size 11422642

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,245 @@

+{
+  "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
+    },
+    "151665": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<retrieval>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "</retrieval>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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|>",
+    "<think>",
+    "</think>",
+    "<retrieval>",
+    "</retrieval>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 2.9984496124031006,
+    "total_flos": 2.170312406348071e+18,
+    "train_loss": 0.43735031344464437,
+    "train_runtime": 9561.9202,
+    "train_samples_per_second": 2.428,
+    "train_steps_per_second": 0.152
+}

trainer_log.jsonl ADDED Viewed

	@@ -0,0 +1,145 @@

+{"current_steps": 10, "total_steps": 1449, "loss": 1.4671, "lr": 6.896551724137932e-06, "epoch": 0.020671834625323, "percentage": 0.69, "elapsed_time": "0:01:02", "remaining_time": "2:30:09"}
+{"current_steps": 20, "total_steps": 1449, "loss": 1.2814, "lr": 1.3793103448275863e-05, "epoch": 0.041343669250646, "percentage": 1.38, "elapsed_time": "0:02:07", "remaining_time": "2:31:55"}
+{"current_steps": 30, "total_steps": 1449, "loss": 1.0494, "lr": 2.0689655172413793e-05, "epoch": 0.06201550387596899, "percentage": 2.07, "elapsed_time": "0:03:09", "remaining_time": "2:29:21"}
+{"current_steps": 40, "total_steps": 1449, "loss": 0.8603, "lr": 2.7586206896551727e-05, "epoch": 0.082687338501292, "percentage": 2.76, "elapsed_time": "0:04:10", "remaining_time": "2:27:04"}
+{"current_steps": 50, "total_steps": 1449, "loss": 0.7456, "lr": 3.4482758620689657e-05, "epoch": 0.10335917312661498, "percentage": 3.45, "elapsed_time": "0:05:18", "remaining_time": "2:28:24"}
+{"current_steps": 60, "total_steps": 1449, "loss": 0.6606, "lr": 4.1379310344827587e-05, "epoch": 0.12403100775193798, "percentage": 4.14, "elapsed_time": "0:06:22", "remaining_time": "2:27:44"}
+{"current_steps": 70, "total_steps": 1449, "loss": 0.6343, "lr": 4.827586206896552e-05, "epoch": 0.14470284237726097, "percentage": 4.83, "elapsed_time": "0:07:29", "remaining_time": "2:27:43"}
+{"current_steps": 80, "total_steps": 1449, "loss": 0.5962, "lr": 5.517241379310345e-05, "epoch": 0.165374677002584, "percentage": 5.52, "elapsed_time": "0:08:35", "remaining_time": "2:26:56"}
+{"current_steps": 90, "total_steps": 1449, "loss": 0.5689, "lr": 6.206896551724138e-05, "epoch": 0.18604651162790697, "percentage": 6.21, "elapsed_time": "0:09:38", "remaining_time": "2:25:29"}
+{"current_steps": 100, "total_steps": 1449, "loss": 0.5812, "lr": 6.896551724137931e-05, "epoch": 0.20671834625322996, "percentage": 6.9, "elapsed_time": "0:10:45", "remaining_time": "2:25:02"}
+{"current_steps": 110, "total_steps": 1449, "loss": 0.5438, "lr": 7.586206896551724e-05, "epoch": 0.22739018087855298, "percentage": 7.59, "elapsed_time": "0:11:51", "remaining_time": "2:24:15"}
+{"current_steps": 120, "total_steps": 1449, "loss": 0.5379, "lr": 8.275862068965517e-05, "epoch": 0.24806201550387597, "percentage": 8.28, "elapsed_time": "0:12:54", "remaining_time": "2:23:02"}
+{"current_steps": 130, "total_steps": 1449, "loss": 0.5383, "lr": 8.96551724137931e-05, "epoch": 0.268733850129199, "percentage": 8.97, "elapsed_time": "0:14:00", "remaining_time": "2:22:09"}
+{"current_steps": 140, "total_steps": 1449, "loss": 0.5359, "lr": 9.655172413793105e-05, "epoch": 0.28940568475452194, "percentage": 9.66, "elapsed_time": "0:15:04", "remaining_time": "2:20:57"}
+{"current_steps": 150, "total_steps": 1449, "loss": 0.5957, "lr": 9.999637240054163e-05, "epoch": 0.31007751937984496, "percentage": 10.35, "elapsed_time": "0:16:12", "remaining_time": "2:20:22"}
+{"current_steps": 160, "total_steps": 1449, "loss": 0.5528, "lr": 9.996735476307291e-05, "epoch": 0.330749354005168, "percentage": 11.04, "elapsed_time": "0:17:18", "remaining_time": "2:19:24"}
+{"current_steps": 170, "total_steps": 1449, "loss": 0.5274, "lr": 9.990933632982306e-05, "epoch": 0.35142118863049093, "percentage": 11.73, "elapsed_time": "0:18:25", "remaining_time": "2:18:38"}
+{"current_steps": 180, "total_steps": 1449, "loss": 0.5363, "lr": 9.982235077439241e-05, "epoch": 0.37209302325581395, "percentage": 12.42, "elapsed_time": "0:19:29", "remaining_time": "2:17:26"}
+{"current_steps": 190, "total_steps": 1449, "loss": 0.5626, "lr": 9.970644858275008e-05, "epoch": 0.39276485788113696, "percentage": 13.11, "elapsed_time": "0:20:35", "remaining_time": "2:16:24"}
+{"current_steps": 200, "total_steps": 1449, "loss": 0.5331, "lr": 9.956169702393215e-05, "epoch": 0.4134366925064599, "percentage": 13.8, "elapsed_time": "0:21:38", "remaining_time": "2:15:07"}
+{"current_steps": 210, "total_steps": 1449, "loss": 0.5232, "lr": 9.938818011099905e-05, "epoch": 0.43410852713178294, "percentage": 14.49, "elapsed_time": "0:22:42", "remaining_time": "2:13:58"}
+{"current_steps": 220, "total_steps": 1449, "loss": 0.536, "lr": 9.918599855227486e-05, "epoch": 0.45478036175710596, "percentage": 15.18, "elapsed_time": "0:23:47", "remaining_time": "2:12:54"}
+{"current_steps": 230, "total_steps": 1449, "loss": 0.5162, "lr": 9.895526969289671e-05, "epoch": 0.4754521963824289, "percentage": 15.87, "elapsed_time": "0:24:50", "remaining_time": "2:11:39"}
+{"current_steps": 240, "total_steps": 1449, "loss": 0.4939, "lr": 9.869612744670818e-05, "epoch": 0.49612403100775193, "percentage": 16.56, "elapsed_time": "0:25:53", "remaining_time": "2:10:25"}
+{"current_steps": 250, "total_steps": 1449, "loss": 0.5053, "lr": 9.84087222185365e-05, "epoch": 0.5167958656330749, "percentage": 17.25, "elapsed_time": "0:26:59", "remaining_time": "2:09:26"}
+{"current_steps": 260, "total_steps": 1449, "loss": 0.5277, "lr": 9.809322081689833e-05, "epoch": 0.537467700258398, "percentage": 17.94, "elapsed_time": "0:28:06", "remaining_time": "2:08:30"}
+{"current_steps": 270, "total_steps": 1449, "loss": 0.5568, "lr": 9.774980635718494e-05, "epoch": 0.5581395348837209, "percentage": 18.63, "elapsed_time": "0:29:10", "remaining_time": "2:07:24"}
+{"current_steps": 280, "total_steps": 1449, "loss": 0.5567, "lr": 9.737867815538293e-05, "epoch": 0.5788113695090439, "percentage": 19.32, "elapsed_time": "0:30:16", "remaining_time": "2:06:24"}
+{"current_steps": 290, "total_steps": 1449, "loss": 0.5373, "lr": 9.698005161239236e-05, "epoch": 0.599483204134367, "percentage": 20.01, "elapsed_time": "0:31:20", "remaining_time": "2:05:13"}
+{"current_steps": 300, "total_steps": 1449, "loss": 0.528, "lr": 9.655415808900914e-05, "epoch": 0.6201550387596899, "percentage": 20.7, "elapsed_time": "0:32:26", "remaining_time": "2:04:13"}
+{"current_steps": 310, "total_steps": 1449, "loss": 0.5364, "lr": 9.610124477164435e-05, "epoch": 0.6408268733850129, "percentage": 21.39, "elapsed_time": "0:33:31", "remaining_time": "2:03:10"}
+{"current_steps": 320, "total_steps": 1449, "loss": 0.546, "lr": 9.56215745288586e-05, "epoch": 0.661498708010336, "percentage": 22.08, "elapsed_time": "0:34:41", "remaining_time": "2:02:22"}
+{"current_steps": 330, "total_steps": 1449, "loss": 0.5283, "lr": 9.51154257587944e-05, "epoch": 0.6821705426356589, "percentage": 22.77, "elapsed_time": "0:35:46", "remaining_time": "2:01:18"}
+{"current_steps": 340, "total_steps": 1449, "loss": 0.5165, "lr": 9.45830922275954e-05, "epoch": 0.7028423772609819, "percentage": 23.46, "elapsed_time": "0:36:52", "remaining_time": "2:00:15"}
+{"current_steps": 350, "total_steps": 1449, "loss": 0.5344, "lr": 9.402488289890591e-05, "epoch": 0.7235142118863049, "percentage": 24.15, "elapsed_time": "0:38:01", "remaining_time": "1:59:24"}
+{"current_steps": 360, "total_steps": 1449, "loss": 0.5108, "lr": 9.344112175455013e-05, "epoch": 0.7441860465116279, "percentage": 24.84, "elapsed_time": "0:39:07", "remaining_time": "1:58:21"}
+{"current_steps": 370, "total_steps": 1449, "loss": 0.5082, "lr": 9.283214760649461e-05, "epoch": 0.7648578811369509, "percentage": 25.53, "elapsed_time": "0:40:14", "remaining_time": "1:57:22"}
+{"current_steps": 380, "total_steps": 1449, "loss": 0.5438, "lr": 9.219831390020366e-05, "epoch": 0.7855297157622739, "percentage": 26.22, "elapsed_time": "0:41:22", "remaining_time": "1:56:24"}
+{"current_steps": 390, "total_steps": 1449, "loss": 0.5383, "lr": 9.153998850950132e-05, "epoch": 0.8062015503875969, "percentage": 26.92, "elapsed_time": "0:42:28", "remaining_time": "1:55:20"}
+{"current_steps": 400, "total_steps": 1449, "loss": 0.4745, "lr": 9.08575535230594e-05, "epoch": 0.8268733850129198, "percentage": 27.61, "elapsed_time": "0:43:32", "remaining_time": "1:54:10"}
+{"current_steps": 410, "total_steps": 1449, "loss": 0.4849, "lr": 9.015140502263506e-05, "epoch": 0.8475452196382429, "percentage": 28.3, "elapsed_time": "0:44:34", "remaining_time": "1:52:58"}
+{"current_steps": 420, "total_steps": 1449, "loss": 0.5239, "lr": 8.942195285318704e-05, "epoch": 0.8682170542635659, "percentage": 28.99, "elapsed_time": "0:45:39", "remaining_time": "1:51:51"}
+{"current_steps": 430, "total_steps": 1449, "loss": 0.4919, "lr": 8.866962038500379e-05, "epoch": 0.8888888888888888, "percentage": 29.68, "elapsed_time": "0:46:45", "remaining_time": "1:50:49"}
+{"current_steps": 440, "total_steps": 1449, "loss": 0.5155, "lr": 8.789484426798146e-05, "epoch": 0.9095607235142119, "percentage": 30.37, "elapsed_time": "0:47:56", "remaining_time": "1:49:55"}
+{"current_steps": 450, "total_steps": 1449, "loss": 0.5188, "lr": 8.709807417819465e-05, "epoch": 0.9302325581395349, "percentage": 31.06, "elapsed_time": "0:49:01", "remaining_time": "1:48:50"}
+{"current_steps": 460, "total_steps": 1449, "loss": 0.5031, "lr": 8.627977255690657e-05, "epoch": 0.9509043927648578, "percentage": 31.75, "elapsed_time": "0:50:06", "remaining_time": "1:47:44"}
+{"current_steps": 470, "total_steps": 1449, "loss": 0.513, "lr": 8.544041434217068e-05, "epoch": 0.9715762273901809, "percentage": 32.44, "elapsed_time": "0:51:13", "remaining_time": "1:46:41"}
+{"current_steps": 480, "total_steps": 1449, "loss": 0.5067, "lr": 8.458048669317896e-05, "epoch": 0.9922480620155039, "percentage": 33.13, "elapsed_time": "0:52:20", "remaining_time": "1:45:40"}
+{"current_steps": 490, "total_steps": 1449, "loss": 0.4898, "lr": 8.370048870751733e-05, "epoch": 1.014470284237726, "percentage": 33.82, "elapsed_time": "0:53:27", "remaining_time": "1:44:37"}
+{"current_steps": 500, "total_steps": 1449, "loss": 0.4215, "lr": 8.280093113149182e-05, "epoch": 1.0351421188630492, "percentage": 34.51, "elapsed_time": "0:54:32", "remaining_time": "1:43:31"}
+{"current_steps": 510, "total_steps": 1449, "loss": 0.428, "lr": 8.188233606369422e-05, "epoch": 1.0558139534883721, "percentage": 35.2, "elapsed_time": "0:56:02", "remaining_time": "1:43:11"}
+{"current_steps": 520, "total_steps": 1449, "loss": 0.4318, "lr": 8.094523665197862e-05, "epoch": 1.076485788113695, "percentage": 35.89, "elapsed_time": "0:57:11", "remaining_time": "1:42:10"}
+{"current_steps": 530, "total_steps": 1449, "loss": 0.4303, "lr": 7.999017678402519e-05, "epoch": 1.097157622739018, "percentage": 36.58, "elapsed_time": "0:58:17", "remaining_time": "1:41:04"}
+{"current_steps": 540, "total_steps": 1449, "loss": 0.4068, "lr": 7.901771077167052e-05, "epoch": 1.117829457364341, "percentage": 37.27, "elapsed_time": "0:59:21", "remaining_time": "1:39:54"}
+{"current_steps": 550, "total_steps": 1449, "loss": 0.3728, "lr": 7.802840302918795e-05, "epoch": 1.138501291989664, "percentage": 37.96, "elapsed_time": "1:00:23", "remaining_time": "1:38:42"}
+{"current_steps": 560, "total_steps": 1449, "loss": 0.4264, "lr": 7.702282774570435e-05, "epoch": 1.1591731266149872, "percentage": 38.65, "elapsed_time": "1:01:31", "remaining_time": "1:37:40"}
+{"current_steps": 570, "total_steps": 1449, "loss": 0.3708, "lr": 7.600156855194376e-05, "epoch": 1.1798449612403101, "percentage": 39.34, "elapsed_time": "1:02:34", "remaining_time": "1:36:30"}
+{"current_steps": 580, "total_steps": 1449, "loss": 0.3771, "lr": 7.496521818149114e-05, "epoch": 1.200516795865633, "percentage": 40.03, "elapsed_time": "1:03:38", "remaining_time": "1:35:21"}
+{"current_steps": 590, "total_steps": 1449, "loss": 0.424, "lr": 7.391437812677273e-05, "epoch": 1.221188630490956, "percentage": 40.72, "elapsed_time": "1:04:45", "remaining_time": "1:34:17"}
+{"current_steps": 600, "total_steps": 1449, "loss": 0.4202, "lr": 7.284965828995309e-05, "epoch": 1.241860465116279, "percentage": 41.41, "elapsed_time": "1:05:52", "remaining_time": "1:33:13"}
+{"current_steps": 610, "total_steps": 1449, "loss": 0.3821, "lr": 7.177167662895087e-05, "epoch": 1.262532299741602, "percentage": 42.1, "elapsed_time": "1:06:58", "remaining_time": "1:32:06"}
+{"current_steps": 620, "total_steps": 1449, "loss": 0.4288, "lr": 7.068105879877933e-05, "epoch": 1.2832041343669252, "percentage": 42.79, "elapsed_time": "1:08:05", "remaining_time": "1:31:02"}
+{"current_steps": 630, "total_steps": 1449, "loss": 0.4177, "lr": 6.957843778841937e-05, "epoch": 1.3038759689922481, "percentage": 43.48, "elapsed_time": "1:09:09", "remaining_time": "1:29:54"}
+{"current_steps": 640, "total_steps": 1449, "loss": 0.4326, "lr": 6.84644535534359e-05, "epoch": 1.324547803617571, "percentage": 44.17, "elapsed_time": "1:10:18", "remaining_time": "1:28:51"}
+{"current_steps": 650, "total_steps": 1449, "loss": 0.391, "lr": 6.733975264455097e-05, "epoch": 1.345219638242894, "percentage": 44.86, "elapsed_time": "1:11:21", "remaining_time": "1:27:43"}
+{"current_steps": 660, "total_steps": 1449, "loss": 0.4072, "lr": 6.620498783238911e-05, "epoch": 1.365891472868217, "percentage": 45.55, "elapsed_time": "1:12:28", "remaining_time": "1:26:38"}
+{"current_steps": 670, "total_steps": 1449, "loss": 0.4062, "lr": 6.506081772861254e-05, "epoch": 1.3865633074935402, "percentage": 46.24, "elapsed_time": "1:13:33", "remaining_time": "1:25:31"}
+{"current_steps": 680, "total_steps": 1449, "loss": 0.4287, "lr": 6.390790640366635e-05, "epoch": 1.407235142118863, "percentage": 46.93, "elapsed_time": "1:14:38", "remaining_time": "1:24:24"}
+{"current_steps": 690, "total_steps": 1449, "loss": 0.3781, "lr": 6.27469230013555e-05, "epoch": 1.427906976744186, "percentage": 47.62, "elapsed_time": "1:15:41", "remaining_time": "1:23:15"}
+{"current_steps": 700, "total_steps": 1449, "loss": 0.4089, "lr": 6.157854135047707e-05, "epoch": 1.448578811369509, "percentage": 48.31, "elapsed_time": "1:16:47", "remaining_time": "1:22:09"}
+{"current_steps": 710, "total_steps": 1449, "loss": 0.4034, "lr": 6.0403439573733666e-05, "epoch": 1.469250645994832, "percentage": 49.0, "elapsed_time": "1:17:50", "remaining_time": "1:21:01"}
+{"current_steps": 720, "total_steps": 1449, "loss": 0.4237, "lr": 5.9222299694154316e-05, "epoch": 1.489922480620155, "percentage": 49.69, "elapsed_time": "1:18:56", "remaining_time": "1:19:55"}
+{"current_steps": 730, "total_steps": 1449, "loss": 0.4131, "lr": 5.803580723925193e-05, "epoch": 1.510594315245478, "percentage": 50.38, "elapsed_time": "1:20:02", "remaining_time": "1:18:50"}
+{"current_steps": 740, "total_steps": 1449, "loss": 0.3821, "lr": 5.6844650843146595e-05, "epoch": 1.5312661498708011, "percentage": 51.07, "elapsed_time": "1:21:06", "remaining_time": "1:17:42"}
+{"current_steps": 750, "total_steps": 1449, "loss": 0.3998, "lr": 5.5649521846885876e-05, "epoch": 1.551937984496124, "percentage": 51.76, "elapsed_time": "1:22:12", "remaining_time": "1:16:36"}
+{"current_steps": 760, "total_steps": 1449, "loss": 0.4448, "lr": 5.445111389719408e-05, "epoch": 1.572609819121447, "percentage": 52.45, "elapsed_time": "1:23:19", "remaining_time": "1:15:32"}
+{"current_steps": 770, "total_steps": 1449, "loss": 0.4061, "lr": 5.3250122543883197e-05, "epoch": 1.59328165374677, "percentage": 53.14, "elapsed_time": "1:24:26", "remaining_time": "1:14:27"}
+{"current_steps": 780, "total_steps": 1449, "loss": 0.4181, "lr": 5.20472448361594e-05, "epoch": 1.613953488372093, "percentage": 53.83, "elapsed_time": "1:25:33", "remaining_time": "1:13:22"}
+{"current_steps": 790, "total_steps": 1449, "loss": 0.3888, "lr": 5.084317891805928e-05, "epoch": 1.6346253229974161, "percentage": 54.52, "elapsed_time": "1:26:37", "remaining_time": "1:12:15"}
+{"current_steps": 800, "total_steps": 1449, "loss": 0.4265, "lr": 4.963862362325058e-05, "epoch": 1.6552971576227389, "percentage": 55.21, "elapsed_time": "1:27:45", "remaining_time": "1:11:11"}
+{"current_steps": 810, "total_steps": 1449, "loss": 0.3958, "lr": 4.8434278069432834e-05, "epoch": 1.675968992248062, "percentage": 55.9, "elapsed_time": "1:28:51", "remaining_time": "1:10:05"}
+{"current_steps": 820, "total_steps": 1449, "loss": 0.3952, "lr": 4.7230841252572906e-05, "epoch": 1.696640826873385, "percentage": 56.59, "elapsed_time": "1:29:56", "remaining_time": "1:08:59"}
+{"current_steps": 830, "total_steps": 1449, "loss": 0.3905, "lr": 4.602901164121145e-05, "epoch": 1.717312661498708, "percentage": 57.28, "elapsed_time": "1:31:01", "remaining_time": "1:07:52"}
+{"current_steps": 840, "total_steps": 1449, "loss": 0.3677, "lr": 4.482948677107533e-05, "epoch": 1.7379844961240312, "percentage": 57.97, "elapsed_time": "1:32:04", "remaining_time": "1:06:44"}
+{"current_steps": 850, "total_steps": 1449, "loss": 0.4024, "lr": 4.363296284023139e-05, "epoch": 1.758656330749354, "percentage": 58.66, "elapsed_time": "1:33:13", "remaining_time": "1:05:41"}
+{"current_steps": 860, "total_steps": 1449, "loss": 0.3809, "lr": 4.24401343050168e-05, "epoch": 1.779328165374677, "percentage": 59.35, "elapsed_time": "1:34:18", "remaining_time": "1:04:35"}
+{"current_steps": 870, "total_steps": 1449, "loss": 0.4011, "lr": 4.125169347698009e-05, "epoch": 1.8, "percentage": 60.04, "elapsed_time": "1:35:24", "remaining_time": "1:03:29"}
+{"current_steps": 880, "total_steps": 1449, "loss": 0.3726, "lr": 4.006833012106707e-05, "epoch": 1.820671834625323, "percentage": 60.73, "elapsed_time": "1:36:27", "remaining_time": "1:02:22"}
+{"current_steps": 890, "total_steps": 1449, "loss": 0.3845, "lr": 3.8890731055284893e-05, "epoch": 1.841343669250646, "percentage": 61.42, "elapsed_time": "1:37:33", "remaining_time": "1:01:16"}
+{"current_steps": 900, "total_steps": 1449, "loss": 0.4097, "lr": 3.77195797520763e-05, "epoch": 1.862015503875969, "percentage": 62.11, "elapsed_time": "1:38:40", "remaining_time": "1:00:11"}
+{"current_steps": 910, "total_steps": 1449, "loss": 0.3979, "lr": 3.6555555941635865e-05, "epoch": 1.882687338501292, "percentage": 62.8, "elapsed_time": "1:39:44", "remaining_time": "0:59:04"}
+{"current_steps": 920, "total_steps": 1449, "loss": 0.4075, "lr": 3.539933521739793e-05, "epoch": 1.9033591731266148, "percentage": 63.49, "elapsed_time": "1:40:50", "remaining_time": "0:57:59"}
+{"current_steps": 930, "total_steps": 1449, "loss": 0.3885, "lr": 3.425158864392576e-05, "epoch": 1.924031007751938, "percentage": 64.18, "elapsed_time": "1:41:55", "remaining_time": "0:56:52"}
+{"current_steps": 940, "total_steps": 1449, "loss": 0.402, "lr": 3.31129823674291e-05, "epoch": 1.944702842377261, "percentage": 64.87, "elapsed_time": "1:42:59", "remaining_time": "0:55:45"}
+{"current_steps": 950, "total_steps": 1449, "loss": 0.3899, "lr": 3.1984177229136285e-05, "epoch": 1.965374677002584, "percentage": 65.56, "elapsed_time": "1:44:01", "remaining_time": "0:54:38"}
+{"current_steps": 960, "total_steps": 1449, "loss": 0.3789, "lr": 3.086582838174551e-05, "epoch": 1.9860465116279071, "percentage": 66.25, "elapsed_time": "1:45:05", "remaining_time": "0:53:31"}
+{"current_steps": 970, "total_steps": 1449, "loss": 0.4181, "lr": 2.9758584909177433e-05, "epoch": 2.0082687338501293, "percentage": 66.94, "elapsed_time": "1:46:16", "remaining_time": "0:52:28"}
+{"current_steps": 980, "total_steps": 1449, "loss": 0.3397, "lr": 2.8663089449850243e-05, "epoch": 2.028940568475452, "percentage": 67.63, "elapsed_time": "1:47:24", "remaining_time": "0:51:24"}
+{"current_steps": 990, "total_steps": 1449, "loss": 0.298, "lr": 2.7579977823695723e-05, "epoch": 2.049612403100775, "percentage": 68.32, "elapsed_time": "1:48:26", "remaining_time": "0:50:16"}
+{"current_steps": 1000, "total_steps": 1449, "loss": 0.3163, "lr": 2.6509878663132514e-05, "epoch": 2.0702842377260984, "percentage": 69.01, "elapsed_time": "1:49:32", "remaining_time": "0:49:10"}
+{"current_steps": 1010, "total_steps": 1449, "loss": 0.3213, "lr": 2.5453413048211172e-05, "epoch": 2.090956072351421, "percentage": 69.7, "elapsed_time": "1:50:55", "remaining_time": "0:48:12"}
+{"current_steps": 1020, "total_steps": 1449, "loss": 0.2921, "lr": 2.4411194146142407e-05, "epoch": 2.1116279069767443, "percentage": 70.39, "elapsed_time": "1:51:59", "remaining_time": "0:47:06"}
+{"current_steps": 1030, "total_steps": 1449, "loss": 0.2943, "lr": 2.338382685541806e-05, "epoch": 2.132299741602067, "percentage": 71.08, "elapsed_time": "1:53:02", "remaining_time": "0:45:59"}
+{"current_steps": 1040, "total_steps": 1449, "loss": 0.3286, "lr": 2.2371907454731167e-05, "epoch": 2.15297157622739, "percentage": 71.77, "elapsed_time": "1:54:10", "remaining_time": "0:44:54"}
+{"current_steps": 1050, "total_steps": 1449, "loss": 0.3214, "lr": 2.137602325689873e-05, "epoch": 2.173643410852713, "percentage": 72.46, "elapsed_time": "1:55:18", "remaining_time": "0:43:48"}
+{"current_steps": 1060, "total_steps": 1449, "loss": 0.3143, "lr": 2.039675226798854e-05, "epoch": 2.194315245478036, "percentage": 73.15, "elapsed_time": "1:56:22", "remaining_time": "0:42:42"}
+{"current_steps": 1070, "total_steps": 1449, "loss": 0.3213, "lr": 1.9434662851847325e-05, "epoch": 2.2149870801033593, "percentage": 73.84, "elapsed_time": "1:57:30", "remaining_time": "0:41:37"}
+{"current_steps": 1080, "total_steps": 1449, "loss": 0.3204, "lr": 1.8490313400225294e-05, "epoch": 2.235658914728682, "percentage": 74.53, "elapsed_time": "1:58:35", "remaining_time": "0:40:31"}
+{"current_steps": 1090, "total_steps": 1449, "loss": 0.3066, "lr": 1.7564252008688514e-05, "epoch": 2.2563307493540052, "percentage": 75.22, "elapsed_time": "1:59:38", "remaining_time": "0:39:24"}
+{"current_steps": 1100, "total_steps": 1449, "loss": 0.3079, "lr": 1.6657016158506966e-05, "epoch": 2.277002583979328, "percentage": 75.91, "elapsed_time": "2:00:47", "remaining_time": "0:38:19"}
+{"current_steps": 1110, "total_steps": 1449, "loss": 0.3127, "lr": 1.5769132404703274e-05, "epoch": 2.297674418604651, "percentage": 76.6, "elapsed_time": "2:01:54", "remaining_time": "0:37:13"}
+{"current_steps": 1120, "total_steps": 1449, "loss": 0.3221, "lr": 1.4901116070442772e-05, "epoch": 2.3183462532299743, "percentage": 77.29, "elapsed_time": "2:02:59", "remaining_time": "0:36:07"}
+{"current_steps": 1130, "total_steps": 1449, "loss": 0.3112, "lr": 1.4053470947942693e-05, "epoch": 2.339018087855297, "percentage": 77.98, "elapsed_time": "2:04:04", "remaining_time": "0:35:01"}
+{"current_steps": 1140, "total_steps": 1449, "loss": 0.3053, "lr": 1.3226689006073712e-05, "epoch": 2.3596899224806203, "percentage": 78.67, "elapsed_time": "2:05:11", "remaining_time": "0:33:55"}
+{"current_steps": 1150, "total_steps": 1449, "loss": 0.3172, "lr": 1.2421250104823684e-05, "epoch": 2.380361757105943, "percentage": 79.37, "elapsed_time": "2:06:18", "remaining_time": "0:32:50"}
+{"current_steps": 1160, "total_steps": 1449, "loss": 0.3085, "lr": 1.163762171678951e-05, "epoch": 2.401033591731266, "percentage": 80.06, "elapsed_time": "2:07:22", "remaining_time": "0:31:44"}
+{"current_steps": 1170, "total_steps": 1449, "loss": 0.3281, "lr": 1.0876258655858307e-05, "epoch": 2.4217054263565894, "percentage": 80.75, "elapsed_time": "2:08:31", "remaining_time": "0:30:38"}
+{"current_steps": 1180, "total_steps": 1449, "loss": 0.3118, "lr": 1.0137602813235824e-05, "epoch": 2.442377260981912, "percentage": 81.44, "elapsed_time": "2:09:40", "remaining_time": "0:29:33"}
+{"current_steps": 1190, "total_steps": 1449, "loss": 0.309, "lr": 9.422082900975104e-06, "epoch": 2.4630490956072353, "percentage": 82.13, "elapsed_time": "2:10:44", "remaining_time": "0:28:27"}
+{"current_steps": 1200, "total_steps": 1449, "loss": 0.3219, "lr": 8.730114203154144e-06, "epoch": 2.483720930232558, "percentage": 82.82, "elapsed_time": "2:11:49", "remaining_time": "0:27:21"}
+{"current_steps": 1210, "total_steps": 1449, "loss": 0.3165, "lr": 8.062098334847184e-06, "epoch": 2.504392764857881, "percentage": 83.51, "elapsed_time": "2:12:55", "remaining_time": "0:26:15"}
+{"current_steps": 1220, "total_steps": 1449, "loss": 0.2978, "lr": 7.418423009029362e-06, "epoch": 2.525064599483204, "percentage": 84.2, "elapsed_time": "2:13:57", "remaining_time": "0:25:08"}
+{"current_steps": 1230, "total_steps": 1449, "loss": 0.3369, "lr": 6.799461811550101e-06, "epoch": 2.545736434108527, "percentage": 84.89, "elapsed_time": "2:15:06", "remaining_time": "0:24:03"}
+{"current_steps": 1240, "total_steps": 1449, "loss": 0.3295, "lr": 6.205573984305857e-06, "epoch": 2.5664082687338503, "percentage": 85.58, "elapsed_time": "2:16:14", "remaining_time": "0:22:57"}
+{"current_steps": 1250, "total_steps": 1449, "loss": 0.3166, "lr": 5.6371042167378706e-06, "epoch": 2.587080103359173, "percentage": 86.27, "elapsed_time": "2:17:22", "remaining_time": "0:21:52"}
+{"current_steps": 1260, "total_steps": 1449, "loss": 0.339, "lr": 5.09438244577628e-06, "epoch": 2.6077519379844962, "percentage": 86.96, "elapsed_time": "2:18:29", "remaining_time": "0:20:46"}
+{"current_steps": 1270, "total_steps": 1449, "loss": 0.3011, "lr": 4.5777236643463786e-06, "epoch": 2.628423772609819, "percentage": 87.65, "elapsed_time": "2:19:33", "remaining_time": "0:19:40"}
+{"current_steps": 1280, "total_steps": 1449, "loss": 0.3072, "lr": 4.087427738548321e-06, "epoch": 2.649095607235142, "percentage": 88.34, "elapsed_time": "2:20:38", "remaining_time": "0:18:34"}
+{"current_steps": 1290, "total_steps": 1449, "loss": 0.3159, "lr": 3.623779233616442e-06, "epoch": 2.669767441860465, "percentage": 89.03, "elapsed_time": "2:21:43", "remaining_time": "0:17:28"}
+{"current_steps": 1300, "total_steps": 1449, "loss": 0.2953, "lr": 3.1870472487589843e-06, "epoch": 2.690439276485788, "percentage": 89.72, "elapsed_time": "2:22:48", "remaining_time": "0:16:22"}
+{"current_steps": 1310, "total_steps": 1449, "loss": 0.3072, "lr": 2.7774852609743886e-06, "epoch": 2.7111111111111112, "percentage": 90.41, "elapsed_time": "2:23:53", "remaining_time": "0:15:16"}
+{"current_steps": 1320, "total_steps": 1449, "loss": 0.2828, "lr": 2.39533097793444e-06, "epoch": 2.731782945736434, "percentage": 91.1, "elapsed_time": "2:24:58", "remaining_time": "0:14:10"}
+{"current_steps": 1330, "total_steps": 1449, "loss": 0.3278, "lr": 2.0408062000200625e-06, "epoch": 2.752454780361757, "percentage": 91.79, "elapsed_time": "2:26:06", "remaining_time": "0:13:04"}
+{"current_steps": 1340, "total_steps": 1449, "loss": 0.3071, "lr": 1.714116691589457e-06, "epoch": 2.7731266149870804, "percentage": 92.48, "elapsed_time": "2:27:10", "remaining_time": "0:11:58"}
+{"current_steps": 1350, "total_steps": 1449, "loss": 0.3256, "lr": 1.4154520615535183e-06, "epoch": 2.793798449612403, "percentage": 93.17, "elapsed_time": "2:28:15", "remaining_time": "0:10:52"}
+{"current_steps": 1360, "total_steps": 1449, "loss": 0.3147, "lr": 1.1449856533278625e-06, "epoch": 2.814470284237726, "percentage": 93.86, "elapsed_time": "2:29:17", "remaining_time": "0:09:46"}
+{"current_steps": 1370, "total_steps": 1449, "loss": 0.3353, "lr": 9.028744442251102e-07, "epoch": 2.835142118863049, "percentage": 94.55, "elapsed_time": "2:30:26", "remaining_time": "0:08:40"}
+{"current_steps": 1380, "total_steps": 1449, "loss": 0.3174, "lr": 6.892589543461392e-07, "epoch": 2.855813953488372, "percentage": 95.24, "elapsed_time": "2:31:32", "remaining_time": "0:07:34"}
+{"current_steps": 1390, "total_steps": 1449, "loss": 0.3113, "lr": 5.042631650229058e-07, "epoch": 2.876485788113695, "percentage": 95.93, "elapsed_time": "2:32:39", "remaining_time": "0:06:28"}
+{"current_steps": 1400, "total_steps": 1449, "loss": 0.2972, "lr": 3.4799444686031693e-07, "epoch": 2.897157622739018, "percentage": 96.62, "elapsed_time": "2:33:44", "remaining_time": "0:05:22"}
+{"current_steps": 1410, "total_steps": 1449, "loss": 0.296, "lr": 2.2054349741888468e-07, "epoch": 2.9178294573643413, "percentage": 97.31, "elapsed_time": "2:34:49", "remaining_time": "0:04:16"}
+{"current_steps": 1420, "total_steps": 1449, "loss": 0.2913, "lr": 1.219842885743394e-07, "epoch": 2.938501291989664, "percentage": 98.0, "elapsed_time": "2:35:51", "remaining_time": "0:03:10"}
+{"current_steps": 1430, "total_steps": 1449, "loss": 0.3192, "lr": 5.237402358471144e-08, "epoch": 2.959173126614987, "percentage": 98.69, "elapsed_time": "2:36:58", "remaining_time": "0:02:05"}
+{"current_steps": 1440, "total_steps": 1449, "loss": 0.288, "lr": 1.1753103889883266e-08, "epoch": 2.97984496124031, "percentage": 99.38, "elapsed_time": "2:38:02", "remaining_time": "0:00:59"}
+{"current_steps": 1449, "total_steps": 1449, "epoch": 2.9984496124031006, "percentage": 100.0, "elapsed_time": "2:39:21", "remaining_time": "0:00:00"}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,1050 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9984496124031006,
+  "eval_steps": 500,
+  "global_step": 1449,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020671834625323,
+      "grad_norm": 19.961172103881836,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.4671,
+      "step": 10
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 10.104804039001465,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 1.2814,
+      "step": 20
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 10.660629272460938,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 1.0494,
+      "step": 30
+    },
+    {
+      "epoch": 0.082687338501292,
+      "grad_norm": 4.328464031219482,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 0.8603,
+      "step": 40
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 2.360297918319702,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.7456,
+      "step": 50
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 2.756227731704712,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 0.6606,
+      "step": 60
+    },
+    {
+      "epoch": 0.14470284237726097,
+      "grad_norm": 2.7377092838287354,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 0.6343,
+      "step": 70
+    },
+    {
+      "epoch": 0.165374677002584,
+      "grad_norm": 2.682518243789673,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 0.5962,
+      "step": 80
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 2.2480661869049072,
+      "learning_rate": 6.206896551724138e-05,
+      "loss": 0.5689,
+      "step": 90
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 2.5809719562530518,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 0.5812,
+      "step": 100
+    },
+    {
+      "epoch": 0.22739018087855298,
+      "grad_norm": 1.933281660079956,
+      "learning_rate": 7.586206896551724e-05,
+      "loss": 0.5438,
+      "step": 110
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 2.1786251068115234,
+      "learning_rate": 8.275862068965517e-05,
+      "loss": 0.5379,
+      "step": 120
+    },
+    {
+      "epoch": 0.268733850129199,
+      "grad_norm": 1.6331806182861328,
+      "learning_rate": 8.96551724137931e-05,
+      "loss": 0.5383,
+      "step": 130
+    },
+    {
+      "epoch": 0.28940568475452194,
+      "grad_norm": 1.713693380355835,
+      "learning_rate": 9.655172413793105e-05,
+      "loss": 0.5359,
+      "step": 140
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.6057534217834473,
+      "learning_rate": 9.999637240054163e-05,
+      "loss": 0.5957,
+      "step": 150
+    },
+    {
+      "epoch": 0.330749354005168,
+      "grad_norm": 1.2600524425506592,
+      "learning_rate": 9.996735476307291e-05,
+      "loss": 0.5528,
+      "step": 160
+    },
+    {
+      "epoch": 0.35142118863049093,
+      "grad_norm": 1.258549451828003,
+      "learning_rate": 9.990933632982306e-05,
+      "loss": 0.5274,
+      "step": 170
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 1.1361678838729858,
+      "learning_rate": 9.982235077439241e-05,
+      "loss": 0.5363,
+      "step": 180
+    },
+    {
+      "epoch": 0.39276485788113696,
+      "grad_norm": 1.1429818868637085,
+      "learning_rate": 9.970644858275008e-05,
+      "loss": 0.5626,
+      "step": 190
+    },
+    {
+      "epoch": 0.4134366925064599,
+      "grad_norm": 1.168615460395813,
+      "learning_rate": 9.956169702393215e-05,
+      "loss": 0.5331,
+      "step": 200
+    },
+    {
+      "epoch": 0.43410852713178294,
+      "grad_norm": 1.353784441947937,
+      "learning_rate": 9.938818011099905e-05,
+      "loss": 0.5232,
+      "step": 210
+    },
+    {
+      "epoch": 0.45478036175710596,
+      "grad_norm": 1.1773430109024048,
+      "learning_rate": 9.918599855227486e-05,
+      "loss": 0.536,
+      "step": 220
+    },
+    {
+      "epoch": 0.4754521963824289,
+      "grad_norm": 1.1550217866897583,
+      "learning_rate": 9.895526969289671e-05,
+      "loss": 0.5162,
+      "step": 230
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 1.0943946838378906,
+      "learning_rate": 9.869612744670818e-05,
+      "loss": 0.4939,
+      "step": 240
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "grad_norm": 1.0564571619033813,
+      "learning_rate": 9.84087222185365e-05,
+      "loss": 0.5053,
+      "step": 250
+    },
+    {
+      "epoch": 0.537467700258398,
+      "grad_norm": 0.9963967800140381,
+      "learning_rate": 9.809322081689833e-05,
+      "loss": 0.5277,
+      "step": 260
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 1.1690253019332886,
+      "learning_rate": 9.774980635718494e-05,
+      "loss": 0.5568,
+      "step": 270
+    },
+    {
+      "epoch": 0.5788113695090439,
+      "grad_norm": 1.0432251691818237,
+      "learning_rate": 9.737867815538293e-05,
+      "loss": 0.5567,
+      "step": 280
+    },
+    {
+      "epoch": 0.599483204134367,
+      "grad_norm": 1.033795714378357,
+      "learning_rate": 9.698005161239236e-05,
+      "loss": 0.5373,
+      "step": 290
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.0568259954452515,
+      "learning_rate": 9.655415808900914e-05,
+      "loss": 0.528,
+      "step": 300
+    },
+    {
+      "epoch": 0.6408268733850129,
+      "grad_norm": 1.0200306177139282,
+      "learning_rate": 9.610124477164435e-05,
+      "loss": 0.5364,
+      "step": 310
+    },
+    {
+      "epoch": 0.661498708010336,
+      "grad_norm": 1.0433367490768433,
+      "learning_rate": 9.56215745288586e-05,
+      "loss": 0.546,
+      "step": 320
+    },
+    {
+      "epoch": 0.6821705426356589,
+      "grad_norm": 0.936161458492279,
+      "learning_rate": 9.51154257587944e-05,
+      "loss": 0.5283,
+      "step": 330
+    },
+    {
+      "epoch": 0.7028423772609819,
+      "grad_norm": 0.8251316547393799,
+      "learning_rate": 9.45830922275954e-05,
+      "loss": 0.5165,
+      "step": 340
+    },
+    {
+      "epoch": 0.7235142118863049,
+      "grad_norm": 0.9545398354530334,
+      "learning_rate": 9.402488289890591e-05,
+      "loss": 0.5344,
+      "step": 350
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 1.0172969102859497,
+      "learning_rate": 9.344112175455013e-05,
+      "loss": 0.5108,
+      "step": 360
+    },
+    {
+      "epoch": 0.7648578811369509,
+      "grad_norm": 0.9597331881523132,
+      "learning_rate": 9.283214760649461e-05,
+      "loss": 0.5082,
+      "step": 370
+    },
+    {
+      "epoch": 0.7855297157622739,
+      "grad_norm": 0.9407294988632202,
+      "learning_rate": 9.219831390020366e-05,
+      "loss": 0.5438,
+      "step": 380
+    },
+    {
+      "epoch": 0.8062015503875969,
+      "grad_norm": 0.8958045840263367,
+      "learning_rate": 9.153998850950132e-05,
+      "loss": 0.5383,
+      "step": 390
+    },
+    {
+      "epoch": 0.8268733850129198,
+      "grad_norm": 1.0094271898269653,
+      "learning_rate": 9.08575535230594e-05,
+      "loss": 0.4745,
+      "step": 400
+    },
+    {
+      "epoch": 0.8475452196382429,
+      "grad_norm": 0.9919396638870239,
+      "learning_rate": 9.015140502263506e-05,
+      "loss": 0.4849,
+      "step": 410
+    },
+    {
+      "epoch": 0.8682170542635659,
+      "grad_norm": 1.1863609552383423,
+      "learning_rate": 8.942195285318704e-05,
+      "loss": 0.5239,
+      "step": 420
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.9280211925506592,
+      "learning_rate": 8.866962038500379e-05,
+      "loss": 0.4919,
+      "step": 430
+    },
+    {
+      "epoch": 0.9095607235142119,
+      "grad_norm": 1.0376496315002441,
+      "learning_rate": 8.789484426798146e-05,
+      "loss": 0.5155,
+      "step": 440
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.9633381962776184,
+      "learning_rate": 8.709807417819465e-05,
+      "loss": 0.5188,
+      "step": 450
+    },
+    {
+      "epoch": 0.9509043927648578,
+      "grad_norm": 1.0249930620193481,
+      "learning_rate": 8.627977255690657e-05,
+      "loss": 0.5031,
+      "step": 460
+    },
+    {
+      "epoch": 0.9715762273901809,
+      "grad_norm": 1.0092591047286987,
+      "learning_rate": 8.544041434217068e-05,
+      "loss": 0.513,
+      "step": 470
+    },
+    {
+      "epoch": 0.9922480620155039,
+      "grad_norm": 0.8698219060897827,
+      "learning_rate": 8.458048669317896e-05,
+      "loss": 0.5067,
+      "step": 480
+    },
+    {
+      "epoch": 1.014470284237726,
+      "grad_norm": 0.8564507365226746,
+      "learning_rate": 8.370048870751733e-05,
+      "loss": 0.4898,
+      "step": 490
+    },
+    {
+      "epoch": 1.0351421188630492,
+      "grad_norm": 1.9524496793746948,
+      "learning_rate": 8.280093113149182e-05,
+      "loss": 0.4215,
+      "step": 500
+    },
+    {
+      "epoch": 1.0558139534883721,
+      "grad_norm": 1.0247145891189575,
+      "learning_rate": 8.188233606369422e-05,
+      "loss": 0.428,
+      "step": 510
+    },
+    {
+      "epoch": 1.076485788113695,
+      "grad_norm": 1.123751163482666,
+      "learning_rate": 8.094523665197862e-05,
+      "loss": 0.4318,
+      "step": 520
+    },
+    {
+      "epoch": 1.097157622739018,
+      "grad_norm": 1.0905773639678955,
+      "learning_rate": 7.999017678402519e-05,
+      "loss": 0.4303,
+      "step": 530
+    },
+    {
+      "epoch": 1.117829457364341,
+      "grad_norm": 0.9824921488761902,
+      "learning_rate": 7.901771077167052e-05,
+      "loss": 0.4068,
+      "step": 540
+    },
+    {
+      "epoch": 1.138501291989664,
+      "grad_norm": 0.9725044965744019,
+      "learning_rate": 7.802840302918795e-05,
+      "loss": 0.3728,
+      "step": 550
+    },
+    {
+      "epoch": 1.1591731266149872,
+      "grad_norm": 0.9440091848373413,
+      "learning_rate": 7.702282774570435e-05,
+      "loss": 0.4264,
+      "step": 560
+    },
+    {
+      "epoch": 1.1798449612403101,
+      "grad_norm": 1.0231075286865234,
+      "learning_rate": 7.600156855194376e-05,
+      "loss": 0.3708,
+      "step": 570
+    },
+    {
+      "epoch": 1.200516795865633,
+      "grad_norm": 0.9228759407997131,
+      "learning_rate": 7.496521818149114e-05,
+      "loss": 0.3771,
+      "step": 580
+    },
+    {
+      "epoch": 1.221188630490956,
+      "grad_norm": 0.9908185601234436,
+      "learning_rate": 7.391437812677273e-05,
+      "loss": 0.424,
+      "step": 590
+    },
+    {
+      "epoch": 1.241860465116279,
+      "grad_norm": 0.8130841255187988,
+      "learning_rate": 7.284965828995309e-05,
+      "loss": 0.4202,
+      "step": 600
+    },
+    {
+      "epoch": 1.262532299741602,
+      "grad_norm": 1.2041234970092773,
+      "learning_rate": 7.177167662895087e-05,
+      "loss": 0.3821,
+      "step": 610
+    },
+    {
+      "epoch": 1.2832041343669252,
+      "grad_norm": 0.9226158261299133,
+      "learning_rate": 7.068105879877933e-05,
+      "loss": 0.4288,
+      "step": 620
+    },
+    {
+      "epoch": 1.3038759689922481,
+      "grad_norm": 0.9127386808395386,
+      "learning_rate": 6.957843778841937e-05,
+      "loss": 0.4177,
+      "step": 630
+    },
+    {
+      "epoch": 1.324547803617571,
+      "grad_norm": 0.9465218186378479,
+      "learning_rate": 6.84644535534359e-05,
+      "loss": 0.4326,
+      "step": 640
+    },
+    {
+      "epoch": 1.345219638242894,
+      "grad_norm": 0.9808584451675415,
+      "learning_rate": 6.733975264455097e-05,
+      "loss": 0.391,
+      "step": 650
+    },
+    {
+      "epoch": 1.365891472868217,
+      "grad_norm": 0.8926200866699219,
+      "learning_rate": 6.620498783238911e-05,
+      "loss": 0.4072,
+      "step": 660
+    },
+    {
+      "epoch": 1.3865633074935402,
+      "grad_norm": 1.060142993927002,
+      "learning_rate": 6.506081772861254e-05,
+      "loss": 0.4062,
+      "step": 670
+    },
+    {
+      "epoch": 1.407235142118863,
+      "grad_norm": 0.931640625,
+      "learning_rate": 6.390790640366635e-05,
+      "loss": 0.4287,
+      "step": 680
+    },
+    {
+      "epoch": 1.427906976744186,
+      "grad_norm": 0.8396949172019958,
+      "learning_rate": 6.27469230013555e-05,
+      "loss": 0.3781,
+      "step": 690
+    },
+    {
+      "epoch": 1.448578811369509,
+      "grad_norm": 0.8786910176277161,
+      "learning_rate": 6.157854135047707e-05,
+      "loss": 0.4089,
+      "step": 700
+    },
+    {
+      "epoch": 1.469250645994832,
+      "grad_norm": 0.877200722694397,
+      "learning_rate": 6.0403439573733666e-05,
+      "loss": 0.4034,
+      "step": 710
+    },
+    {
+      "epoch": 1.489922480620155,
+      "grad_norm": 0.8826427459716797,
+      "learning_rate": 5.9222299694154316e-05,
+      "loss": 0.4237,
+      "step": 720
+    },
+    {
+      "epoch": 1.510594315245478,
+      "grad_norm": 1.0366460084915161,
+      "learning_rate": 5.803580723925193e-05,
+      "loss": 0.4131,
+      "step": 730
+    },
+    {
+      "epoch": 1.5312661498708011,
+      "grad_norm": 0.8167237639427185,
+      "learning_rate": 5.6844650843146595e-05,
+      "loss": 0.3821,
+      "step": 740
+    },
+    {
+      "epoch": 1.551937984496124,
+      "grad_norm": 0.8496309518814087,
+      "learning_rate": 5.5649521846885876e-05,
+      "loss": 0.3998,
+      "step": 750
+    },
+    {
+      "epoch": 1.572609819121447,
+      "grad_norm": 1.0631760358810425,
+      "learning_rate": 5.445111389719408e-05,
+      "loss": 0.4448,
+      "step": 760
+    },
+    {
+      "epoch": 1.59328165374677,
+      "grad_norm": 0.9399399757385254,
+      "learning_rate": 5.3250122543883197e-05,
+      "loss": 0.4061,
+      "step": 770
+    },
+    {
+      "epoch": 1.613953488372093,
+      "grad_norm": 0.9156986474990845,
+      "learning_rate": 5.20472448361594e-05,
+      "loss": 0.4181,
+      "step": 780
+    },
+    {
+      "epoch": 1.6346253229974161,
+      "grad_norm": 0.9186833500862122,
+      "learning_rate": 5.084317891805928e-05,
+      "loss": 0.3888,
+      "step": 790
+    },
+    {
+      "epoch": 1.6552971576227389,
+      "grad_norm": 1.0180436372756958,
+      "learning_rate": 4.963862362325058e-05,
+      "loss": 0.4265,
+      "step": 800
+    },
+    {
+      "epoch": 1.675968992248062,
+      "grad_norm": 0.9096766710281372,
+      "learning_rate": 4.8434278069432834e-05,
+      "loss": 0.3958,
+      "step": 810
+    },
+    {
+      "epoch": 1.696640826873385,
+      "grad_norm": 0.88401198387146,
+      "learning_rate": 4.7230841252572906e-05,
+      "loss": 0.3952,
+      "step": 820
+    },
+    {
+      "epoch": 1.717312661498708,
+      "grad_norm": 0.834771454334259,
+      "learning_rate": 4.602901164121145e-05,
+      "loss": 0.3905,
+      "step": 830
+    },
+    {
+      "epoch": 1.7379844961240312,
+      "grad_norm": 1.0104914903640747,
+      "learning_rate": 4.482948677107533e-05,
+      "loss": 0.3677,
+      "step": 840
+    },
+    {
+      "epoch": 1.758656330749354,
+      "grad_norm": 0.9692713618278503,
+      "learning_rate": 4.363296284023139e-05,
+      "loss": 0.4024,
+      "step": 850
+    },
+    {
+      "epoch": 1.779328165374677,
+      "grad_norm": 0.9530401229858398,
+      "learning_rate": 4.24401343050168e-05,
+      "loss": 0.3809,
+      "step": 860
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.4324836730957031,
+      "learning_rate": 4.125169347698009e-05,
+      "loss": 0.4011,
+      "step": 870
+    },
+    {
+      "epoch": 1.820671834625323,
+      "grad_norm": 0.9663997888565063,
+      "learning_rate": 4.006833012106707e-05,
+      "loss": 0.3726,
+      "step": 880
+    },
+    {
+      "epoch": 1.841343669250646,
+      "grad_norm": 0.8397408127784729,
+      "learning_rate": 3.8890731055284893e-05,
+      "loss": 0.3845,
+      "step": 890
+    },
+    {
+      "epoch": 1.862015503875969,
+      "grad_norm": 0.9423091411590576,
+      "learning_rate": 3.77195797520763e-05,
+      "loss": 0.4097,
+      "step": 900
+    },
+    {
+      "epoch": 1.882687338501292,
+      "grad_norm": 0.9247391223907471,
+      "learning_rate": 3.6555555941635865e-05,
+      "loss": 0.3979,
+      "step": 910
+    },
+    {
+      "epoch": 1.9033591731266148,
+      "grad_norm": 0.9327929019927979,
+      "learning_rate": 3.539933521739793e-05,
+      "loss": 0.4075,
+      "step": 920
+    },
+    {
+      "epoch": 1.924031007751938,
+      "grad_norm": 0.93698650598526,
+      "learning_rate": 3.425158864392576e-05,
+      "loss": 0.3885,
+      "step": 930
+    },
+    {
+      "epoch": 1.944702842377261,
+      "grad_norm": 0.8598852753639221,
+      "learning_rate": 3.31129823674291e-05,
+      "loss": 0.402,
+      "step": 940
+    },
+    {
+      "epoch": 1.965374677002584,
+      "grad_norm": 0.8426728844642639,
+      "learning_rate": 3.1984177229136285e-05,
+      "loss": 0.3899,
+      "step": 950
+    },
+    {
+      "epoch": 1.9860465116279071,
+      "grad_norm": 0.8942709565162659,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3789,
+      "step": 960
+    },
+    {
+      "epoch": 2.0082687338501293,
+      "grad_norm": 0.7830824255943298,
+      "learning_rate": 2.9758584909177433e-05,
+      "loss": 0.4181,
+      "step": 970
+    },
+    {
+      "epoch": 2.028940568475452,
+      "grad_norm": 0.9163928627967834,
+      "learning_rate": 2.8663089449850243e-05,
+      "loss": 0.3397,
+      "step": 980
+    },
+    {
+      "epoch": 2.049612403100775,
+      "grad_norm": 0.9074885845184326,
+      "learning_rate": 2.7579977823695723e-05,
+      "loss": 0.298,
+      "step": 990
+    },
+    {
+      "epoch": 2.0702842377260984,
+      "grad_norm": 0.9496545791625977,
+      "learning_rate": 2.6509878663132514e-05,
+      "loss": 0.3163,
+      "step": 1000
+    },
+    {
+      "epoch": 2.090956072351421,
+      "grad_norm": 0.9921571016311646,
+      "learning_rate": 2.5453413048211172e-05,
+      "loss": 0.3213,
+      "step": 1010
+    },
+    {
+      "epoch": 2.1116279069767443,
+      "grad_norm": 1.1148159503936768,
+      "learning_rate": 2.4411194146142407e-05,
+      "loss": 0.2921,
+      "step": 1020
+    },
+    {
+      "epoch": 2.132299741602067,
+      "grad_norm": 1.0226593017578125,
+      "learning_rate": 2.338382685541806e-05,
+      "loss": 0.2943,
+      "step": 1030
+    },
+    {
+      "epoch": 2.15297157622739,
+      "grad_norm": 0.955251932144165,
+      "learning_rate": 2.2371907454731167e-05,
+      "loss": 0.3286,
+      "step": 1040
+    },
+    {
+      "epoch": 2.173643410852713,
+      "grad_norm": 1.0427072048187256,
+      "learning_rate": 2.137602325689873e-05,
+      "loss": 0.3214,
+      "step": 1050
+    },
+    {
+      "epoch": 2.194315245478036,
+      "grad_norm": 1.0497926473617554,
+      "learning_rate": 2.039675226798854e-05,
+      "loss": 0.3143,
+      "step": 1060
+    },
+    {
+      "epoch": 2.2149870801033593,
+      "grad_norm": 1.0081120729446411,
+      "learning_rate": 1.9434662851847325e-05,
+      "loss": 0.3213,
+      "step": 1070
+    },
+    {
+      "epoch": 2.235658914728682,
+      "grad_norm": 0.9074374437332153,
+      "learning_rate": 1.8490313400225294e-05,
+      "loss": 0.3204,
+      "step": 1080
+    },
+    {
+      "epoch": 2.2563307493540052,
+      "grad_norm": 0.9639903903007507,
+      "learning_rate": 1.7564252008688514e-05,
+      "loss": 0.3066,
+      "step": 1090
+    },
+    {
+      "epoch": 2.277002583979328,
+      "grad_norm": 0.9500643610954285,
+      "learning_rate": 1.6657016158506966e-05,
+      "loss": 0.3079,
+      "step": 1100
+    },
+    {
+      "epoch": 2.297674418604651,
+      "grad_norm": 0.9133275151252747,
+      "learning_rate": 1.5769132404703274e-05,
+      "loss": 0.3127,
+      "step": 1110
+    },
+    {
+      "epoch": 2.3183462532299743,
+      "grad_norm": 0.9715905785560608,
+      "learning_rate": 1.4901116070442772e-05,
+      "loss": 0.3221,
+      "step": 1120
+    },
+    {
+      "epoch": 2.339018087855297,
+      "grad_norm": 1.0215041637420654,
+      "learning_rate": 1.4053470947942693e-05,
+      "loss": 0.3112,
+      "step": 1130
+    },
+    {
+      "epoch": 2.3596899224806203,
+      "grad_norm": 0.9813144207000732,
+      "learning_rate": 1.3226689006073712e-05,
+      "loss": 0.3053,
+      "step": 1140
+    },
+    {
+      "epoch": 2.380361757105943,
+      "grad_norm": 0.9730923175811768,
+      "learning_rate": 1.2421250104823684e-05,
+      "loss": 0.3172,
+      "step": 1150
+    },
+    {
+      "epoch": 2.401033591731266,
+      "grad_norm": 1.038800597190857,
+      "learning_rate": 1.163762171678951e-05,
+      "loss": 0.3085,
+      "step": 1160
+    },
+    {
+      "epoch": 2.4217054263565894,
+      "grad_norm": 0.9317840933799744,
+      "learning_rate": 1.0876258655858307e-05,
+      "loss": 0.3281,
+      "step": 1170
+    },
+    {
+      "epoch": 2.442377260981912,
+      "grad_norm": 1.0310304164886475,
+      "learning_rate": 1.0137602813235824e-05,
+      "loss": 0.3118,
+      "step": 1180
+    },
+    {
+      "epoch": 2.4630490956072353,
+      "grad_norm": 0.9994140267372131,
+      "learning_rate": 9.422082900975104e-06,
+      "loss": 0.309,
+      "step": 1190
+    },
+    {
+      "epoch": 2.483720930232558,
+      "grad_norm": 1.1645585298538208,
+      "learning_rate": 8.730114203154144e-06,
+      "loss": 0.3219,
+      "step": 1200
+    },
+    {
+      "epoch": 2.504392764857881,
+      "grad_norm": 1.0404480695724487,
+      "learning_rate": 8.062098334847184e-06,
+      "loss": 0.3165,
+      "step": 1210
+    },
+    {
+      "epoch": 2.525064599483204,
+      "grad_norm": 1.055424451828003,
+      "learning_rate": 7.418423009029362e-06,
+      "loss": 0.2978,
+      "step": 1220
+    },
+    {
+      "epoch": 2.545736434108527,
+      "grad_norm": 0.9607129693031311,
+      "learning_rate": 6.799461811550101e-06,
+      "loss": 0.3369,
+      "step": 1230
+    },
+    {
+      "epoch": 2.5664082687338503,
+      "grad_norm": 1.0298357009887695,
+      "learning_rate": 6.205573984305857e-06,
+      "loss": 0.3295,
+      "step": 1240
+    },
+    {
+      "epoch": 2.587080103359173,
+      "grad_norm": 0.9973547458648682,
+      "learning_rate": 5.6371042167378706e-06,
+      "loss": 0.3166,
+      "step": 1250
+    },
+    {
+      "epoch": 2.6077519379844962,
+      "grad_norm": 1.4321331977844238,
+      "learning_rate": 5.09438244577628e-06,
+      "loss": 0.339,
+      "step": 1260
+    },
+    {
+      "epoch": 2.628423772609819,
+      "grad_norm": 0.9741699695587158,
+      "learning_rate": 4.5777236643463786e-06,
+      "loss": 0.3011,
+      "step": 1270
+    },
+    {
+      "epoch": 2.649095607235142,
+      "grad_norm": 0.980993390083313,
+      "learning_rate": 4.087427738548321e-06,
+      "loss": 0.3072,
+      "step": 1280
+    },
+    {
+      "epoch": 2.669767441860465,
+      "grad_norm": 1.0376126766204834,
+      "learning_rate": 3.623779233616442e-06,
+      "loss": 0.3159,
+      "step": 1290
+    },
+    {
+      "epoch": 2.690439276485788,
+      "grad_norm": 1.0413364171981812,
+      "learning_rate": 3.1870472487589843e-06,
+      "loss": 0.2953,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.9663779139518738,
+      "learning_rate": 2.7774852609743886e-06,
+      "loss": 0.3072,
+      "step": 1310
+    },
+    {
+      "epoch": 2.731782945736434,
+      "grad_norm": 0.9956408739089966,
+      "learning_rate": 2.39533097793444e-06,
+      "loss": 0.2828,
+      "step": 1320
+    },
+    {
+      "epoch": 2.752454780361757,
+      "grad_norm": 0.9878751039505005,
+      "learning_rate": 2.0408062000200625e-06,
+      "loss": 0.3278,
+      "step": 1330
+    },
+    {
+      "epoch": 2.7731266149870804,
+      "grad_norm": 1.0932310819625854,
+      "learning_rate": 1.714116691589457e-06,
+      "loss": 0.3071,
+      "step": 1340
+    },
+    {
+      "epoch": 2.793798449612403,
+      "grad_norm": 1.0455061197280884,
+      "learning_rate": 1.4154520615535183e-06,
+      "loss": 0.3256,
+      "step": 1350
+    },
+    {
+      "epoch": 2.814470284237726,
+      "grad_norm": 1.0817687511444092,
+      "learning_rate": 1.1449856533278625e-06,
+      "loss": 0.3147,
+      "step": 1360
+    },
+    {
+      "epoch": 2.835142118863049,
+      "grad_norm": 1.0755105018615723,
+      "learning_rate": 9.028744442251102e-07,
+      "loss": 0.3353,
+      "step": 1370
+    },
+    {
+      "epoch": 2.855813953488372,
+      "grad_norm": 1.0853437185287476,
+      "learning_rate": 6.892589543461392e-07,
+      "loss": 0.3174,
+      "step": 1380
+    },
+    {
+      "epoch": 2.876485788113695,
+      "grad_norm": 0.9791375398635864,
+      "learning_rate": 5.042631650229058e-07,
+      "loss": 0.3113,
+      "step": 1390
+    },
+    {
+      "epoch": 2.897157622739018,
+      "grad_norm": 0.9765632748603821,
+      "learning_rate": 3.4799444686031693e-07,
+      "loss": 0.2972,
+      "step": 1400
+    },
+    {
+      "epoch": 2.9178294573643413,
+      "grad_norm": 1.0426656007766724,
+      "learning_rate": 2.2054349741888468e-07,
+      "loss": 0.296,
+      "step": 1410
+    },
+    {
+      "epoch": 2.938501291989664,
+      "grad_norm": 0.9949988722801208,
+      "learning_rate": 1.219842885743394e-07,
+      "loss": 0.2913,
+      "step": 1420
+    },
+    {
+      "epoch": 2.959173126614987,
+      "grad_norm": 0.9954948425292969,
+      "learning_rate": 5.237402358471144e-08,
+      "loss": 0.3192,
+      "step": 1430
+    },
+    {
+      "epoch": 2.97984496124031,
+      "grad_norm": 1.0401126146316528,
+      "learning_rate": 1.1753103889883266e-08,
+      "loss": 0.288,
+      "step": 1440
+    },
+    {
+      "epoch": 2.9984496124031006,
+      "step": 1449,
+      "total_flos": 2.170312406348071e+18,
+      "train_loss": 0.43735031344464437,
+      "train_runtime": 9561.9202,
+      "train_samples_per_second": 2.428,
+      "train_steps_per_second": 0.152
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1449,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.170312406348071e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40709ae10f6a1253f7061d9786e7bba9a51fbf44fcd9310f6415aae6c9419f9a
+size 5624

training_loss_hqa_sft.png ADDED Viewed

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff