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

@@ -1,3 +1,64 @@
----
-license: mit
----
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-14B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+datasets:
+- arrow
+model-index:
+- name: hqa_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. -->
+
+# hqa_sft
+
+This model is a fine-tuned version of [/data/huggingface_models/Qwen2.5-14B-Instruct](https://huggingface.co//data/huggingface_models/Qwen2.5-14B-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

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/huggingface_models/Qwen2.5-14B-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": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233365cf95cc4ccaf2af162d4204566d9319ca09a4ee2aca89826f8b9548981f
+size 6366258992

added_tokens.json

@@ -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

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9984496124031006,
+    "total_flos": 4.2078437233393664e+18,
+    "train_loss": 0.3962208225942629,
+    "train_runtime": 19037.0514,
+    "train_samples_per_second": 1.22,
+    "train_steps_per_second": 0.076
+}

special_tokens_map.json

@@ -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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb2d73624732e138c0dc43481d4775563a7eea7190357fe2a54641bc88246ee
+size 11422642

tokenizer_config.json

@@ -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

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9984496124031006,
+    "total_flos": 4.2078437233393664e+18,
+    "train_loss": 0.3962208225942629,
+    "train_runtime": 19037.0514,
+    "train_samples_per_second": 1.22,
+    "train_steps_per_second": 0.076
+}

trainer_log.jsonl

@@ -0,0 +1,145 @@
+{"current_steps": 10, "total_steps": 1449, "loss": 1.3535, "lr": 6.896551724137932e-06, "epoch": 0.020671834625323, "percentage": 0.69, "elapsed_time": "0:02:04", "remaining_time": "4:58:54"}
+{"current_steps": 20, "total_steps": 1449, "loss": 1.206, "lr": 1.3793103448275863e-05, "epoch": 0.041343669250646, "percentage": 1.38, "elapsed_time": "0:04:14", "remaining_time": "5:03:24"}
+{"current_steps": 30, "total_steps": 1449, "loss": 1.0033, "lr": 2.0689655172413793e-05, "epoch": 0.06201550387596899, "percentage": 2.07, "elapsed_time": "0:06:18", "remaining_time": "4:58:13"}
+{"current_steps": 40, "total_steps": 1449, "loss": 0.8239, "lr": 2.7586206896551727e-05, "epoch": 0.082687338501292, "percentage": 2.76, "elapsed_time": "0:08:19", "remaining_time": "4:53:30"}
+{"current_steps": 50, "total_steps": 1449, "loss": 0.6996, "lr": 3.4482758620689657e-05, "epoch": 0.10335917312661498, "percentage": 3.45, "elapsed_time": "0:10:35", "remaining_time": "4:56:23"}
+{"current_steps": 60, "total_steps": 1449, "loss": 0.6079, "lr": 4.1379310344827587e-05, "epoch": 0.12403100775193798, "percentage": 4.14, "elapsed_time": "0:12:44", "remaining_time": "4:54:55"}
+{"current_steps": 70, "total_steps": 1449, "loss": 0.5793, "lr": 4.827586206896552e-05, "epoch": 0.14470284237726097, "percentage": 4.83, "elapsed_time": "0:14:58", "remaining_time": "4:55:01"}
+{"current_steps": 80, "total_steps": 1449, "loss": 0.5363, "lr": 5.517241379310345e-05, "epoch": 0.165374677002584, "percentage": 5.52, "elapsed_time": "0:17:08", "remaining_time": "4:53:22"}
+{"current_steps": 90, "total_steps": 1449, "loss": 0.5114, "lr": 6.206896551724138e-05, "epoch": 0.18604651162790697, "percentage": 6.21, "elapsed_time": "0:19:14", "remaining_time": "4:50:28"}
+{"current_steps": 100, "total_steps": 1449, "loss": 0.5212, "lr": 6.896551724137931e-05, "epoch": 0.20671834625322996, "percentage": 6.9, "elapsed_time": "0:21:27", "remaining_time": "4:49:28"}
+{"current_steps": 110, "total_steps": 1449, "loss": 0.4891, "lr": 7.586206896551724e-05, "epoch": 0.22739018087855298, "percentage": 7.59, "elapsed_time": "0:23:39", "remaining_time": "4:47:54"}
+{"current_steps": 120, "total_steps": 1449, "loss": 0.4861, "lr": 8.275862068965517e-05, "epoch": 0.24806201550387597, "percentage": 8.28, "elapsed_time": "0:25:46", "remaining_time": "4:45:30"}
+{"current_steps": 130, "total_steps": 1449, "loss": 0.4796, "lr": 8.96551724137931e-05, "epoch": 0.268733850129199, "percentage": 8.97, "elapsed_time": "0:27:57", "remaining_time": "4:43:36"}
+{"current_steps": 140, "total_steps": 1449, "loss": 0.4783, "lr": 9.655172413793105e-05, "epoch": 0.28940568475452194, "percentage": 9.66, "elapsed_time": "0:30:03", "remaining_time": "4:41:04"}
+{"current_steps": 150, "total_steps": 1449, "loss": 0.5361, "lr": 9.999637240054163e-05, "epoch": 0.31007751937984496, "percentage": 10.35, "elapsed_time": "0:32:18", "remaining_time": "4:39:49"}
+{"current_steps": 160, "total_steps": 1449, "loss": 0.4998, "lr": 9.996735476307291e-05, "epoch": 0.330749354005168, "percentage": 11.04, "elapsed_time": "0:34:29", "remaining_time": "4:37:54"}
+{"current_steps": 170, "total_steps": 1449, "loss": 0.4657, "lr": 9.990933632982306e-05, "epoch": 0.35142118863049093, "percentage": 11.73, "elapsed_time": "0:36:44", "remaining_time": "4:36:27"}
+{"current_steps": 180, "total_steps": 1449, "loss": 0.4723, "lr": 9.982235077439241e-05, "epoch": 0.37209302325581395, "percentage": 12.42, "elapsed_time": "0:38:52", "remaining_time": "4:34:07"}
+{"current_steps": 190, "total_steps": 1449, "loss": 0.4929, "lr": 9.970644858275008e-05, "epoch": 0.39276485788113696, "percentage": 13.11, "elapsed_time": "0:41:02", "remaining_time": "4:31:59"}
+{"current_steps": 200, "total_steps": 1449, "loss": 0.4682, "lr": 9.956169702393215e-05, "epoch": 0.4134366925064599, "percentage": 13.8, "elapsed_time": "0:43:08", "remaining_time": "4:29:26"}
+{"current_steps": 210, "total_steps": 1449, "loss": 0.4573, "lr": 9.938818011099905e-05, "epoch": 0.43410852713178294, "percentage": 14.49, "elapsed_time": "0:45:16", "remaining_time": "4:27:09"}
+{"current_steps": 220, "total_steps": 1449, "loss": 0.4665, "lr": 9.918599855227486e-05, "epoch": 0.45478036175710596, "percentage": 15.18, "elapsed_time": "0:47:26", "remaining_time": "4:25:02"}
+{"current_steps": 230, "total_steps": 1449, "loss": 0.4567, "lr": 9.895526969289671e-05, "epoch": 0.4754521963824289, "percentage": 15.87, "elapsed_time": "0:49:31", "remaining_time": "4:22:31"}
+{"current_steps": 240, "total_steps": 1449, "loss": 0.4326, "lr": 9.869612744670818e-05, "epoch": 0.49612403100775193, "percentage": 16.56, "elapsed_time": "0:51:37", "remaining_time": "4:20:02"}
+{"current_steps": 250, "total_steps": 1449, "loss": 0.4412, "lr": 9.84087222185365e-05, "epoch": 0.5167958656330749, "percentage": 17.25, "elapsed_time": "0:53:48", "remaining_time": "4:18:04"}
+{"current_steps": 260, "total_steps": 1449, "loss": 0.4649, "lr": 9.809322081689833e-05, "epoch": 0.537467700258398, "percentage": 17.94, "elapsed_time": "0:56:01", "remaining_time": "4:16:13"}
+{"current_steps": 270, "total_steps": 1449, "loss": 0.4896, "lr": 9.774980635718494e-05, "epoch": 0.5581395348837209, "percentage": 18.63, "elapsed_time": "0:58:10", "remaining_time": "4:14:02"}
+{"current_steps": 280, "total_steps": 1449, "loss": 0.4871, "lr": 9.737867815538293e-05, "epoch": 0.5788113695090439, "percentage": 19.32, "elapsed_time": "1:00:21", "remaining_time": "4:12:00"}
+{"current_steps": 290, "total_steps": 1449, "loss": 0.4668, "lr": 9.698005161239236e-05, "epoch": 0.599483204134367, "percentage": 20.01, "elapsed_time": "1:02:28", "remaining_time": "4:09:39"}
+{"current_steps": 300, "total_steps": 1449, "loss": 0.4591, "lr": 9.655415808900914e-05, "epoch": 0.6201550387596899, "percentage": 20.7, "elapsed_time": "1:04:39", "remaining_time": "4:07:39"}
+{"current_steps": 310, "total_steps": 1449, "loss": 0.4667, "lr": 9.610124477164435e-05, "epoch": 0.6408268733850129, "percentage": 21.39, "elapsed_time": "1:06:49", "remaining_time": "4:05:31"}
+{"current_steps": 320, "total_steps": 1449, "loss": 0.4766, "lr": 9.56215745288586e-05, "epoch": 0.661498708010336, "percentage": 22.08, "elapsed_time": "1:09:07", "remaining_time": "4:03:54"}
+{"current_steps": 330, "total_steps": 1449, "loss": 0.4678, "lr": 9.51154257587944e-05, "epoch": 0.6821705426356589, "percentage": 22.77, "elapsed_time": "1:11:17", "remaining_time": "4:01:45"}
+{"current_steps": 340, "total_steps": 1449, "loss": 0.4507, "lr": 9.45830922275954e-05, "epoch": 0.7028423772609819, "percentage": 23.46, "elapsed_time": "1:13:28", "remaining_time": "3:59:39"}
+{"current_steps": 350, "total_steps": 1449, "loss": 0.4665, "lr": 9.402488289890591e-05, "epoch": 0.7235142118863049, "percentage": 24.15, "elapsed_time": "1:15:47", "remaining_time": "3:58:00"}
+{"current_steps": 360, "total_steps": 1449, "loss": 0.4449, "lr": 9.344112175455013e-05, "epoch": 0.7441860465116279, "percentage": 24.84, "elapsed_time": "1:17:59", "remaining_time": "3:55:55"}
+{"current_steps": 370, "total_steps": 1449, "loss": 0.4419, "lr": 9.283214760649461e-05, "epoch": 0.7648578811369509, "percentage": 25.53, "elapsed_time": "1:20:12", "remaining_time": "3:53:55"}
+{"current_steps": 380, "total_steps": 1449, "loss": 0.4738, "lr": 9.219831390020366e-05, "epoch": 0.7855297157622739, "percentage": 26.22, "elapsed_time": "1:22:28", "remaining_time": "3:52:02"}
+{"current_steps": 390, "total_steps": 1449, "loss": 0.4634, "lr": 9.153998850950132e-05, "epoch": 0.8062015503875969, "percentage": 26.92, "elapsed_time": "1:24:39", "remaining_time": "3:49:52"}
+{"current_steps": 400, "total_steps": 1449, "loss": 0.4155, "lr": 9.08575535230594e-05, "epoch": 0.8268733850129198, "percentage": 27.61, "elapsed_time": "1:26:45", "remaining_time": "3:47:32"}
+{"current_steps": 410, "total_steps": 1449, "loss": 0.4184, "lr": 9.015140502263506e-05, "epoch": 0.8475452196382429, "percentage": 28.3, "elapsed_time": "1:28:50", "remaining_time": "3:45:08"}
+{"current_steps": 420, "total_steps": 1449, "loss": 0.4578, "lr": 8.942195285318704e-05, "epoch": 0.8682170542635659, "percentage": 28.99, "elapsed_time": "1:30:58", "remaining_time": "3:42:53"}
+{"current_steps": 430, "total_steps": 1449, "loss": 0.431, "lr": 8.866962038500379e-05, "epoch": 0.8888888888888888, "percentage": 29.68, "elapsed_time": "1:33:10", "remaining_time": "3:40:49"}
+{"current_steps": 440, "total_steps": 1449, "loss": 0.4498, "lr": 8.789484426798146e-05, "epoch": 0.9095607235142119, "percentage": 30.37, "elapsed_time": "1:35:31", "remaining_time": "3:39:02"}
+{"current_steps": 450, "total_steps": 1449, "loss": 0.4523, "lr": 8.709807417819465e-05, "epoch": 0.9302325581395349, "percentage": 31.06, "elapsed_time": "1:37:42", "remaining_time": "3:36:54"}
+{"current_steps": 460, "total_steps": 1449, "loss": 0.4384, "lr": 8.627977255690657e-05, "epoch": 0.9509043927648578, "percentage": 31.75, "elapsed_time": "1:39:52", "remaining_time": "3:34:42"}
+{"current_steps": 470, "total_steps": 1449, "loss": 0.4487, "lr": 8.544041434217068e-05, "epoch": 0.9715762273901809, "percentage": 32.44, "elapsed_time": "1:42:04", "remaining_time": "3:32:36"}
+{"current_steps": 480, "total_steps": 1449, "loss": 0.4375, "lr": 8.458048669317896e-05, "epoch": 0.9922480620155039, "percentage": 33.13, "elapsed_time": "1:44:18", "remaining_time": "3:30:34"}
+{"current_steps": 490, "total_steps": 1449, "loss": 0.4313, "lr": 8.370048870751733e-05, "epoch": 1.014470284237726, "percentage": 33.82, "elapsed_time": "1:46:31", "remaining_time": "3:28:28"}
+{"current_steps": 500, "total_steps": 1449, "loss": 0.3756, "lr": 8.280093113149182e-05, "epoch": 1.0351421188630492, "percentage": 34.51, "elapsed_time": "1:48:40", "remaining_time": "3:26:16"}
+{"current_steps": 510, "total_steps": 1449, "loss": 0.3842, "lr": 8.188233606369422e-05, "epoch": 1.0558139534883721, "percentage": 35.2, "elapsed_time": "1:51:32", "remaining_time": "3:25:21"}
+{"current_steps": 520, "total_steps": 1449, "loss": 0.3852, "lr": 8.094523665197862e-05, "epoch": 1.076485788113695, "percentage": 35.89, "elapsed_time": "1:53:50", "remaining_time": "3:23:22"}
+{"current_steps": 530, "total_steps": 1449, "loss": 0.3889, "lr": 7.999017678402519e-05, "epoch": 1.097157622739018, "percentage": 36.58, "elapsed_time": "1:56:01", "remaining_time": "3:21:10"}
+{"current_steps": 540, "total_steps": 1449, "loss": 0.3705, "lr": 7.901771077167052e-05, "epoch": 1.117829457364341, "percentage": 37.27, "elapsed_time": "1:58:09", "remaining_time": "3:18:53"}
+{"current_steps": 550, "total_steps": 1449, "loss": 0.3378, "lr": 7.802840302918795e-05, "epoch": 1.138501291989664, "percentage": 37.96, "elapsed_time": "2:00:12", "remaining_time": "3:16:28"}
+{"current_steps": 560, "total_steps": 1449, "loss": 0.3839, "lr": 7.702282774570435e-05, "epoch": 1.1591731266149872, "percentage": 38.65, "elapsed_time": "2:02:28", "remaining_time": "3:14:26"}
+{"current_steps": 570, "total_steps": 1449, "loss": 0.3385, "lr": 7.600156855194376e-05, "epoch": 1.1798449612403101, "percentage": 39.34, "elapsed_time": "2:04:34", "remaining_time": "3:12:05"}
+{"current_steps": 580, "total_steps": 1449, "loss": 0.3455, "lr": 7.496521818149114e-05, "epoch": 1.200516795865633, "percentage": 40.03, "elapsed_time": "2:06:41", "remaining_time": "3:09:49"}
+{"current_steps": 590, "total_steps": 1449, "loss": 0.3821, "lr": 7.391437812677273e-05, "epoch": 1.221188630490956, "percentage": 40.72, "elapsed_time": "2:08:54", "remaining_time": "3:07:40"}
+{"current_steps": 600, "total_steps": 1449, "loss": 0.3808, "lr": 7.284965828995309e-05, "epoch": 1.241860465116279, "percentage": 41.41, "elapsed_time": "2:11:07", "remaining_time": "3:05:32"}
+{"current_steps": 610, "total_steps": 1449, "loss": 0.3515, "lr": 7.177167662895087e-05, "epoch": 1.262532299741602, "percentage": 42.1, "elapsed_time": "2:13:19", "remaining_time": "3:03:21"}
+{"current_steps": 620, "total_steps": 1449, "loss": 0.3868, "lr": 7.068105879877933e-05, "epoch": 1.2832041343669252, "percentage": 42.79, "elapsed_time": "2:15:32", "remaining_time": "3:01:13"}
+{"current_steps": 630, "total_steps": 1449, "loss": 0.3771, "lr": 6.957843778841937e-05, "epoch": 1.3038759689922481, "percentage": 43.48, "elapsed_time": "2:17:41", "remaining_time": "2:58:59"}
+{"current_steps": 640, "total_steps": 1449, "loss": 0.3894, "lr": 6.84644535534359e-05, "epoch": 1.324547803617571, "percentage": 44.17, "elapsed_time": "2:19:57", "remaining_time": "2:56:55"}
+{"current_steps": 650, "total_steps": 1449, "loss": 0.3542, "lr": 6.733975264455097e-05, "epoch": 1.345219638242894, "percentage": 44.86, "elapsed_time": "2:22:04", "remaining_time": "2:54:38"}
+{"current_steps": 660, "total_steps": 1449, "loss": 0.3731, "lr": 6.620498783238911e-05, "epoch": 1.365891472868217, "percentage": 45.55, "elapsed_time": "2:24:15", "remaining_time": "2:52:27"}
+{"current_steps": 670, "total_steps": 1449, "loss": 0.3669, "lr": 6.506081772861254e-05, "epoch": 1.3865633074935402, "percentage": 46.24, "elapsed_time": "2:26:25", "remaining_time": "2:50:14"}
+{"current_steps": 680, "total_steps": 1449, "loss": 0.3852, "lr": 6.390790640366635e-05, "epoch": 1.407235142118863, "percentage": 46.93, "elapsed_time": "2:28:35", "remaining_time": "2:48:02"}
+{"current_steps": 690, "total_steps": 1449, "loss": 0.3458, "lr": 6.27469230013555e-05, "epoch": 1.427906976744186, "percentage": 47.62, "elapsed_time": "2:30:39", "remaining_time": "2:45:43"}
+{"current_steps": 700, "total_steps": 1449, "loss": 0.3716, "lr": 6.157854135047707e-05, "epoch": 1.448578811369509, "percentage": 48.31, "elapsed_time": "2:32:51", "remaining_time": "2:43:33"}
+{"current_steps": 710, "total_steps": 1449, "loss": 0.3656, "lr": 6.0403439573733666e-05, "epoch": 1.469250645994832, "percentage": 49.0, "elapsed_time": "2:34:57", "remaining_time": "2:41:17"}
+{"current_steps": 720, "total_steps": 1449, "loss": 0.3842, "lr": 5.9222299694154316e-05, "epoch": 1.489922480620155, "percentage": 49.69, "elapsed_time": "2:37:07", "remaining_time": "2:39:05"}
+{"current_steps": 730, "total_steps": 1449, "loss": 0.3699, "lr": 5.803580723925193e-05, "epoch": 1.510594315245478, "percentage": 50.38, "elapsed_time": "2:39:21", "remaining_time": "2:36:57"}
+{"current_steps": 740, "total_steps": 1449, "loss": 0.3505, "lr": 5.6844650843146595e-05, "epoch": 1.5312661498708011, "percentage": 51.07, "elapsed_time": "2:41:28", "remaining_time": "2:34:42"}
+{"current_steps": 750, "total_steps": 1449, "loss": 0.3611, "lr": 5.5649521846885876e-05, "epoch": 1.551937984496124, "percentage": 51.76, "elapsed_time": "2:43:38", "remaining_time": "2:32:31"}
+{"current_steps": 760, "total_steps": 1449, "loss": 0.4034, "lr": 5.445111389719408e-05, "epoch": 1.572609819121447, "percentage": 52.45, "elapsed_time": "2:45:53", "remaining_time": "2:30:23"}
+{"current_steps": 770, "total_steps": 1449, "loss": 0.3688, "lr": 5.3250122543883197e-05, "epoch": 1.59328165374677, "percentage": 53.14, "elapsed_time": "2:48:06", "remaining_time": "2:28:14"}
+{"current_steps": 780, "total_steps": 1449, "loss": 0.3741, "lr": 5.20472448361594e-05, "epoch": 1.613953488372093, "percentage": 53.83, "elapsed_time": "2:50:20", "remaining_time": "2:26:05"}
+{"current_steps": 790, "total_steps": 1449, "loss": 0.3529, "lr": 5.084317891805928e-05, "epoch": 1.6346253229974161, "percentage": 54.52, "elapsed_time": "2:52:28", "remaining_time": "2:23:52"}
+{"current_steps": 800, "total_steps": 1449, "loss": 0.3898, "lr": 4.963862362325058e-05, "epoch": 1.6552971576227389, "percentage": 55.21, "elapsed_time": "2:54:43", "remaining_time": "2:21:44"}
+{"current_steps": 810, "total_steps": 1449, "loss": 0.3616, "lr": 4.8434278069432834e-05, "epoch": 1.675968992248062, "percentage": 55.9, "elapsed_time": "2:56:54", "remaining_time": "2:19:34"}
+{"current_steps": 820, "total_steps": 1449, "loss": 0.3578, "lr": 4.7230841252572906e-05, "epoch": 1.696640826873385, "percentage": 56.59, "elapsed_time": "2:59:05", "remaining_time": "2:17:22"}
+{"current_steps": 830, "total_steps": 1449, "loss": 0.3561, "lr": 4.602901164121145e-05, "epoch": 1.717312661498708, "percentage": 57.28, "elapsed_time": "3:01:14", "remaining_time": "2:15:09"}
+{"current_steps": 840, "total_steps": 1449, "loss": 0.3364, "lr": 4.482948677107533e-05, "epoch": 1.7379844961240312, "percentage": 57.97, "elapsed_time": "3:03:18", "remaining_time": "2:12:53"}
+{"current_steps": 850, "total_steps": 1449, "loss": 0.363, "lr": 4.363296284023139e-05, "epoch": 1.758656330749354, "percentage": 58.66, "elapsed_time": "3:05:36", "remaining_time": "2:10:48"}
+{"current_steps": 860, "total_steps": 1449, "loss": 0.3431, "lr": 4.24401343050168e-05, "epoch": 1.779328165374677, "percentage": 59.35, "elapsed_time": "3:07:47", "remaining_time": "2:08:36"}
+{"current_steps": 870, "total_steps": 1449, "loss": 0.3659, "lr": 4.125169347698009e-05, "epoch": 1.8, "percentage": 60.04, "elapsed_time": "3:09:58", "remaining_time": "2:06:25"}
+{"current_steps": 880, "total_steps": 1449, "loss": 0.3403, "lr": 4.006833012106707e-05, "epoch": 1.820671834625323, "percentage": 60.73, "elapsed_time": "3:12:03", "remaining_time": "2:04:10"}
+{"current_steps": 890, "total_steps": 1449, "loss": 0.3525, "lr": 3.8890731055284893e-05, "epoch": 1.841343669250646, "percentage": 61.42, "elapsed_time": "3:14:14", "remaining_time": "2:01:59"}
+{"current_steps": 900, "total_steps": 1449, "loss": 0.3734, "lr": 3.77195797520763e-05, "epoch": 1.862015503875969, "percentage": 62.11, "elapsed_time": "3:16:27", "remaining_time": "1:59:50"}
+{"current_steps": 910, "total_steps": 1449, "loss": 0.3617, "lr": 3.6555555941635865e-05, "epoch": 1.882687338501292, "percentage": 62.8, "elapsed_time": "3:18:34", "remaining_time": "1:57:36"}
+{"current_steps": 920, "total_steps": 1449, "loss": 0.3687, "lr": 3.539933521739793e-05, "epoch": 1.9033591731266148, "percentage": 63.49, "elapsed_time": "3:20:47", "remaining_time": "1:55:27"}
+{"current_steps": 930, "total_steps": 1449, "loss": 0.355, "lr": 3.425158864392576e-05, "epoch": 1.924031007751938, "percentage": 64.18, "elapsed_time": "3:22:56", "remaining_time": "1:53:15"}
+{"current_steps": 940, "total_steps": 1449, "loss": 0.3651, "lr": 3.31129823674291e-05, "epoch": 1.944702842377261, "percentage": 64.87, "elapsed_time": "3:25:03", "remaining_time": "1:51:02"}
+{"current_steps": 950, "total_steps": 1449, "loss": 0.3521, "lr": 3.1984177229136285e-05, "epoch": 1.965374677002584, "percentage": 65.56, "elapsed_time": "3:27:07", "remaining_time": "1:48:47"}
+{"current_steps": 960, "total_steps": 1449, "loss": 0.3429, "lr": 3.086582838174551e-05, "epoch": 1.9860465116279071, "percentage": 66.25, "elapsed_time": "3:29:14", "remaining_time": "1:46:35"}
+{"current_steps": 970, "total_steps": 1449, "loss": 0.3837, "lr": 2.9758584909177433e-05, "epoch": 2.0082687338501293, "percentage": 66.94, "elapsed_time": "3:31:35", "remaining_time": "1:44:29"}
+{"current_steps": 980, "total_steps": 1449, "loss": 0.3148, "lr": 2.8663089449850243e-05, "epoch": 2.028940568475452, "percentage": 67.63, "elapsed_time": "3:33:51", "remaining_time": "1:42:20"}
+{"current_steps": 990, "total_steps": 1449, "loss": 0.28, "lr": 2.7579977823695723e-05, "epoch": 2.049612403100775, "percentage": 68.32, "elapsed_time": "3:35:55", "remaining_time": "1:40:06"}
+{"current_steps": 1000, "total_steps": 1449, "loss": 0.2941, "lr": 2.6509878663132514e-05, "epoch": 2.0702842377260984, "percentage": 69.01, "elapsed_time": "3:38:05", "remaining_time": "1:37:55"}
+{"current_steps": 1010, "total_steps": 1449, "loss": 0.3039, "lr": 2.5453413048211172e-05, "epoch": 2.090956072351421, "percentage": 69.7, "elapsed_time": "3:40:49", "remaining_time": "1:35:58"}
+{"current_steps": 1020, "total_steps": 1449, "loss": 0.2757, "lr": 2.4411194146142407e-05, "epoch": 2.1116279069767443, "percentage": 70.39, "elapsed_time": "3:42:56", "remaining_time": "1:33:45"}
+{"current_steps": 1030, "total_steps": 1449, "loss": 0.2781, "lr": 2.338382685541806e-05, "epoch": 2.132299741602067, "percentage": 71.08, "elapsed_time": "3:45:02", "remaining_time": "1:31:32"}
+{"current_steps": 1040, "total_steps": 1449, "loss": 0.3046, "lr": 2.2371907454731167e-05, "epoch": 2.15297157622739, "percentage": 71.77, "elapsed_time": "3:47:17", "remaining_time": "1:29:23"}
+{"current_steps": 1050, "total_steps": 1449, "loss": 0.3032, "lr": 2.137602325689873e-05, "epoch": 2.173643410852713, "percentage": 72.46, "elapsed_time": "3:49:32", "remaining_time": "1:27:13"}
+{"current_steps": 1060, "total_steps": 1449, "loss": 0.2932, "lr": 2.039675226798854e-05, "epoch": 2.194315245478036, "percentage": 73.15, "elapsed_time": "3:51:40", "remaining_time": "1:25:01"}
+{"current_steps": 1070, "total_steps": 1449, "loss": 0.2966, "lr": 1.9434662851847325e-05, "epoch": 2.2149870801033593, "percentage": 73.84, "elapsed_time": "3:53:56", "remaining_time": "1:22:51"}
+{"current_steps": 1080, "total_steps": 1449, "loss": 0.294, "lr": 1.8490313400225294e-05, "epoch": 2.235658914728682, "percentage": 74.53, "elapsed_time": "3:56:06", "remaining_time": "1:20:40"}
+{"current_steps": 1090, "total_steps": 1449, "loss": 0.2861, "lr": 1.7564252008688514e-05, "epoch": 2.2563307493540052, "percentage": 75.22, "elapsed_time": "3:58:12", "remaining_time": "1:18:27"}
+{"current_steps": 1100, "total_steps": 1449, "loss": 0.2867, "lr": 1.6657016158506966e-05, "epoch": 2.277002583979328, "percentage": 75.91, "elapsed_time": "4:00:29", "remaining_time": "1:16:18"}
+{"current_steps": 1110, "total_steps": 1449, "loss": 0.2916, "lr": 1.5769132404703274e-05, "epoch": 2.297674418604651, "percentage": 76.6, "elapsed_time": "4:02:43", "remaining_time": "1:14:07"}
+{"current_steps": 1120, "total_steps": 1449, "loss": 0.2974, "lr": 1.4901116070442772e-05, "epoch": 2.3183462532299743, "percentage": 77.29, "elapsed_time": "4:04:52", "remaining_time": "1:11:55"}
+{"current_steps": 1130, "total_steps": 1449, "loss": 0.2906, "lr": 1.4053470947942693e-05, "epoch": 2.339018087855297, "percentage": 77.98, "elapsed_time": "4:07:02", "remaining_time": "1:09:44"}
+{"current_steps": 1140, "total_steps": 1449, "loss": 0.2864, "lr": 1.3226689006073712e-05, "epoch": 2.3596899224806203, "percentage": 78.67, "elapsed_time": "4:09:15", "remaining_time": "1:07:33"}
+{"current_steps": 1150, "total_steps": 1449, "loss": 0.2965, "lr": 1.2421250104823684e-05, "epoch": 2.380361757105943, "percentage": 79.37, "elapsed_time": "4:11:29", "remaining_time": "1:05:23"}
+{"current_steps": 1160, "total_steps": 1449, "loss": 0.288, "lr": 1.163762171678951e-05, "epoch": 2.401033591731266, "percentage": 80.06, "elapsed_time": "4:13:37", "remaining_time": "1:03:11"}
+{"current_steps": 1170, "total_steps": 1449, "loss": 0.3008, "lr": 1.0876258655858307e-05, "epoch": 2.4217054263565894, "percentage": 80.75, "elapsed_time": "4:15:55", "remaining_time": "1:01:01"}
+{"current_steps": 1180, "total_steps": 1449, "loss": 0.293, "lr": 1.0137602813235824e-05, "epoch": 2.442377260981912, "percentage": 81.44, "elapsed_time": "4:18:12", "remaining_time": "0:58:51"}
+{"current_steps": 1190, "total_steps": 1449, "loss": 0.2882, "lr": 9.422082900975104e-06, "epoch": 2.4630490956072353, "percentage": 82.13, "elapsed_time": "4:20:21", "remaining_time": "0:56:39"}
+{"current_steps": 1200, "total_steps": 1449, "loss": 0.2994, "lr": 8.730114203154144e-06, "epoch": 2.483720930232558, "percentage": 82.82, "elapsed_time": "4:22:31", "remaining_time": "0:54:28"}
+{"current_steps": 1210, "total_steps": 1449, "loss": 0.2942, "lr": 8.062098334847184e-06, "epoch": 2.504392764857881, "percentage": 83.51, "elapsed_time": "4:24:40", "remaining_time": "0:52:16"}
+{"current_steps": 1220, "total_steps": 1449, "loss": 0.2748, "lr": 7.418423009029362e-06, "epoch": 2.525064599483204, "percentage": 84.2, "elapsed_time": "4:26:44", "remaining_time": "0:50:04"}
+{"current_steps": 1230, "total_steps": 1449, "loss": 0.3129, "lr": 6.799461811550101e-06, "epoch": 2.545736434108527, "percentage": 84.89, "elapsed_time": "4:29:02", "remaining_time": "0:47:54"}
+{"current_steps": 1240, "total_steps": 1449, "loss": 0.3043, "lr": 6.205573984305857e-06, "epoch": 2.5664082687338503, "percentage": 85.58, "elapsed_time": "4:31:18", "remaining_time": "0:45:43"}
+{"current_steps": 1250, "total_steps": 1449, "loss": 0.2922, "lr": 5.6371042167378706e-06, "epoch": 2.587080103359173, "percentage": 86.27, "elapsed_time": "4:33:32", "remaining_time": "0:43:32"}
+{"current_steps": 1260, "total_steps": 1449, "loss": 0.3101, "lr": 5.09438244577628e-06, "epoch": 2.6077519379844962, "percentage": 86.96, "elapsed_time": "4:35:46", "remaining_time": "0:41:22"}
+{"current_steps": 1270, "total_steps": 1449, "loss": 0.2807, "lr": 4.5777236643463786e-06, "epoch": 2.628423772609819, "percentage": 87.65, "elapsed_time": "4:37:55", "remaining_time": "0:39:10"}
+{"current_steps": 1280, "total_steps": 1449, "loss": 0.2832, "lr": 4.087427738548321e-06, "epoch": 2.649095607235142, "percentage": 88.34, "elapsed_time": "4:40:03", "remaining_time": "0:36:58"}
+{"current_steps": 1290, "total_steps": 1449, "loss": 0.2925, "lr": 3.623779233616442e-06, "epoch": 2.669767441860465, "percentage": 89.03, "elapsed_time": "4:42:12", "remaining_time": "0:34:47"}
+{"current_steps": 1300, "total_steps": 1449, "loss": 0.278, "lr": 3.1870472487589843e-06, "epoch": 2.690439276485788, "percentage": 89.72, "elapsed_time": "4:44:21", "remaining_time": "0:32:35"}
+{"current_steps": 1310, "total_steps": 1449, "loss": 0.2882, "lr": 2.7774852609743886e-06, "epoch": 2.7111111111111112, "percentage": 90.41, "elapsed_time": "4:46:30", "remaining_time": "0:30:24"}
+{"current_steps": 1320, "total_steps": 1449, "loss": 0.266, "lr": 2.39533097793444e-06, "epoch": 2.731782945736434, "percentage": 91.1, "elapsed_time": "4:48:39", "remaining_time": "0:28:12"}
+{"current_steps": 1330, "total_steps": 1449, "loss": 0.3037, "lr": 2.0408062000200625e-06, "epoch": 2.752454780361757, "percentage": 91.79, "elapsed_time": "4:50:54", "remaining_time": "0:26:01"}
+{"current_steps": 1340, "total_steps": 1449, "loss": 0.2835, "lr": 1.714116691589457e-06, "epoch": 2.7731266149870804, "percentage": 92.48, "elapsed_time": "4:53:03", "remaining_time": "0:23:50"}
+{"current_steps": 1350, "total_steps": 1449, "loss": 0.3005, "lr": 1.4154520615535183e-06, "epoch": 2.793798449612403, "percentage": 93.17, "elapsed_time": "4:55:11", "remaining_time": "0:21:38"}
+{"current_steps": 1360, "total_steps": 1449, "loss": 0.2907, "lr": 1.1449856533278625e-06, "epoch": 2.814470284237726, "percentage": 93.86, "elapsed_time": "4:57:14", "remaining_time": "0:19:27"}
+{"current_steps": 1370, "total_steps": 1449, "loss": 0.3095, "lr": 9.028744442251102e-07, "epoch": 2.835142118863049, "percentage": 94.55, "elapsed_time": "4:59:33", "remaining_time": "0:17:16"}
+{"current_steps": 1380, "total_steps": 1449, "loss": 0.2964, "lr": 6.892589543461392e-07, "epoch": 2.855813953488372, "percentage": 95.24, "elapsed_time": "5:01:44", "remaining_time": "0:15:05"}
+{"current_steps": 1390, "total_steps": 1449, "loss": 0.2909, "lr": 5.042631650229058e-07, "epoch": 2.876485788113695, "percentage": 95.93, "elapsed_time": "5:03:58", "remaining_time": "0:12:54"}
+{"current_steps": 1400, "total_steps": 1449, "loss": 0.2787, "lr": 3.4799444686031693e-07, "epoch": 2.897157622739018, "percentage": 96.62, "elapsed_time": "5:06:07", "remaining_time": "0:10:42"}
+{"current_steps": 1410, "total_steps": 1449, "loss": 0.2773, "lr": 2.2054349741888468e-07, "epoch": 2.9178294573643413, "percentage": 97.31, "elapsed_time": "5:08:15", "remaining_time": "0:08:31"}
+{"current_steps": 1420, "total_steps": 1449, "loss": 0.2716, "lr": 1.219842885743394e-07, "epoch": 2.938501291989664, "percentage": 98.0, "elapsed_time": "5:10:20", "remaining_time": "0:06:20"}
+{"current_steps": 1430, "total_steps": 1449, "loss": 0.2951, "lr": 5.237402358471144e-08, "epoch": 2.959173126614987, "percentage": 98.69, "elapsed_time": "5:12:32", "remaining_time": "0:04:09"}
+{"current_steps": 1440, "total_steps": 1449, "loss": 0.2693, "lr": 1.1753103889883266e-08, "epoch": 2.97984496124031, "percentage": 99.38, "elapsed_time": "5:14:40", "remaining_time": "0:01:58"}
+{"current_steps": 1449, "total_steps": 1449, "epoch": 2.9984496124031006, "percentage": 100.0, "elapsed_time": "5:17:16", "remaining_time": "0:00:00"}

trainer_state.json

@@ -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": 25.431514739990234,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.3535,
+      "step": 10
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 12.720418930053711,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 1.206,
+      "step": 20
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 3.606902599334717,
+      "learning_rate": 2.0689655172413793e-05,
+      "loss": 1.0033,
+      "step": 30
+    },
+    {
+      "epoch": 0.082687338501292,
+      "grad_norm": 3.4004132747650146,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 0.8239,
+      "step": 40
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 1.858629822731018,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.6996,
+      "step": 50
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 7.138153076171875,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 0.6079,
+      "step": 60
+    },
+    {
+      "epoch": 0.14470284237726097,
+      "grad_norm": 1.7673451900482178,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 0.5793,
+      "step": 70
+    },
+    {
+      "epoch": 0.165374677002584,
+      "grad_norm": 1.6019272804260254,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 0.5363,
+      "step": 80
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 1.4543627500534058,
+      "learning_rate": 6.206896551724138e-05,
+      "loss": 0.5114,
+      "step": 90
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 1.7967498302459717,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 0.5212,
+      "step": 100
+    },
+    {
+      "epoch": 0.22739018087855298,
+      "grad_norm": 1.3074356317520142,
+      "learning_rate": 7.586206896551724e-05,
+      "loss": 0.4891,
+      "step": 110
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 1.3332639932632446,
+      "learning_rate": 8.275862068965517e-05,
+      "loss": 0.4861,
+      "step": 120
+    },
+    {
+      "epoch": 0.268733850129199,
+      "grad_norm": 1.1522668600082397,
+      "learning_rate": 8.96551724137931e-05,
+      "loss": 0.4796,
+      "step": 130
+    },
+    {
+      "epoch": 0.28940568475452194,
+      "grad_norm": 1.0479172468185425,
+      "learning_rate": 9.655172413793105e-05,
+      "loss": 0.4783,
+      "step": 140
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 4.110249042510986,
+      "learning_rate": 9.999637240054163e-05,
+      "loss": 0.5361,
+      "step": 150
+    },
+    {
+      "epoch": 0.330749354005168,
+      "grad_norm": 0.8967037200927734,
+      "learning_rate": 9.996735476307291e-05,
+      "loss": 0.4998,
+      "step": 160
+    },
+    {
+      "epoch": 0.35142118863049093,
+      "grad_norm": 0.847356379032135,
+      "learning_rate": 9.990933632982306e-05,
+      "loss": 0.4657,
+      "step": 170
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.7598176598548889,
+      "learning_rate": 9.982235077439241e-05,
+      "loss": 0.4723,
+      "step": 180
+    },
+    {
+      "epoch": 0.39276485788113696,
+      "grad_norm": 0.7648685574531555,
+      "learning_rate": 9.970644858275008e-05,
+      "loss": 0.4929,
+      "step": 190
+    },
+    {
+      "epoch": 0.4134366925064599,
+      "grad_norm": 0.652588963508606,
+      "learning_rate": 9.956169702393215e-05,
+      "loss": 0.4682,
+      "step": 200
+    },
+    {
+      "epoch": 0.43410852713178294,
+      "grad_norm": 0.749594509601593,
+      "learning_rate": 9.938818011099905e-05,
+      "loss": 0.4573,
+      "step": 210
+    },
+    {
+      "epoch": 0.45478036175710596,
+      "grad_norm": 17.151500701904297,
+      "learning_rate": 9.918599855227486e-05,
+      "loss": 0.4665,
+      "step": 220
+    },
+    {
+      "epoch": 0.4754521963824289,
+      "grad_norm": 0.7545647621154785,
+      "learning_rate": 9.895526969289671e-05,
+      "loss": 0.4567,
+      "step": 230
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 0.6985858678817749,
+      "learning_rate": 9.869612744670818e-05,
+      "loss": 0.4326,
+      "step": 240
+    },
+    {
+      "epoch": 0.5167958656330749,
+      "grad_norm": 0.6718879342079163,
+      "learning_rate": 9.84087222185365e-05,
+      "loss": 0.4412,
+      "step": 250
+    },
+    {
+      "epoch": 0.537467700258398,
+      "grad_norm": 0.6358970403671265,
+      "learning_rate": 9.809322081689833e-05,
+      "loss": 0.4649,
+      "step": 260
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.611393392086029,
+      "learning_rate": 9.774980635718494e-05,
+      "loss": 0.4896,
+      "step": 270
+    },
+    {
+      "epoch": 0.5788113695090439,
+      "grad_norm": 0.6750462055206299,
+      "learning_rate": 9.737867815538293e-05,
+      "loss": 0.4871,
+      "step": 280
+    },
+    {
+      "epoch": 0.599483204134367,
+      "grad_norm": 0.6707327365875244,
+      "learning_rate": 9.698005161239236e-05,
+      "loss": 0.4668,
+      "step": 290
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 0.6388987898826599,
+      "learning_rate": 9.655415808900914e-05,
+      "loss": 0.4591,
+      "step": 300
+    },
+    {
+      "epoch": 0.6408268733850129,
+      "grad_norm": 0.655411958694458,
+      "learning_rate": 9.610124477164435e-05,
+      "loss": 0.4667,
+      "step": 310
+    },
+    {
+      "epoch": 0.661498708010336,
+      "grad_norm": 0.6179244518280029,
+      "learning_rate": 9.56215745288586e-05,
+      "loss": 0.4766,
+      "step": 320
+    },
+    {
+      "epoch": 0.6821705426356589,
+      "grad_norm": 0.5961921215057373,
+      "learning_rate": 9.51154257587944e-05,
+      "loss": 0.4678,
+      "step": 330
+    },
+    {
+      "epoch": 0.7028423772609819,
+      "grad_norm": 0.688832700252533,
+      "learning_rate": 9.45830922275954e-05,
+      "loss": 0.4507,
+      "step": 340
+    },
+    {
+      "epoch": 0.7235142118863049,
+      "grad_norm": 0.6594329476356506,
+      "learning_rate": 9.402488289890591e-05,
+      "loss": 0.4665,
+      "step": 350
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.6485221982002258,
+      "learning_rate": 9.344112175455013e-05,
+      "loss": 0.4449,
+      "step": 360
+    },
+    {
+      "epoch": 0.7648578811369509,
+      "grad_norm": 0.5708068013191223,
+      "learning_rate": 9.283214760649461e-05,
+      "loss": 0.4419,
+      "step": 370
+    },
+    {
+      "epoch": 0.7855297157622739,
+      "grad_norm": 0.584071159362793,
+      "learning_rate": 9.219831390020366e-05,
+      "loss": 0.4738,
+      "step": 380
+    },
+    {
+      "epoch": 0.8062015503875969,
+      "grad_norm": 0.5921798348426819,
+      "learning_rate": 9.153998850950132e-05,
+      "loss": 0.4634,
+      "step": 390
+    },
+    {
+      "epoch": 0.8268733850129198,
+      "grad_norm": 0.5958707928657532,
+      "learning_rate": 9.08575535230594e-05,
+      "loss": 0.4155,
+      "step": 400
+    },
+    {
+      "epoch": 0.8475452196382429,
+      "grad_norm": 0.6374726295471191,
+      "learning_rate": 9.015140502263506e-05,
+      "loss": 0.4184,
+      "step": 410
+    },
+    {
+      "epoch": 0.8682170542635659,
+      "grad_norm": 0.5996224284172058,
+      "learning_rate": 8.942195285318704e-05,
+      "loss": 0.4578,
+      "step": 420
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.5867141485214233,
+      "learning_rate": 8.866962038500379e-05,
+      "loss": 0.431,
+      "step": 430
+    },
+    {
+      "epoch": 0.9095607235142119,
+      "grad_norm": 0.6046242117881775,
+      "learning_rate": 8.789484426798146e-05,
+      "loss": 0.4498,
+      "step": 440
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.6051985621452332,
+      "learning_rate": 8.709807417819465e-05,
+      "loss": 0.4523,
+      "step": 450
+    },
+    {
+      "epoch": 0.9509043927648578,
+      "grad_norm": 0.6067334413528442,
+      "learning_rate": 8.627977255690657e-05,
+      "loss": 0.4384,
+      "step": 460
+    },
+    {
+      "epoch": 0.9715762273901809,
+      "grad_norm": 0.6319149136543274,
+      "learning_rate": 8.544041434217068e-05,
+      "loss": 0.4487,
+      "step": 470
+    },
+    {
+      "epoch": 0.9922480620155039,
+      "grad_norm": 0.5510629415512085,
+      "learning_rate": 8.458048669317896e-05,
+      "loss": 0.4375,
+      "step": 480
+    },
+    {
+      "epoch": 1.014470284237726,
+      "grad_norm": 0.5569271445274353,
+      "learning_rate": 8.370048870751733e-05,
+      "loss": 0.4313,
+      "step": 490
+    },
+    {
+      "epoch": 1.0351421188630492,
+      "grad_norm": 0.6630957126617432,
+      "learning_rate": 8.280093113149182e-05,
+      "loss": 0.3756,
+      "step": 500
+    },
+    {
+      "epoch": 1.0558139534883721,
+      "grad_norm": 0.6708993911743164,
+      "learning_rate": 8.188233606369422e-05,
+      "loss": 0.3842,
+      "step": 510
+    },
+    {
+      "epoch": 1.076485788113695,
+      "grad_norm": 0.6796870827674866,
+      "learning_rate": 8.094523665197862e-05,
+      "loss": 0.3852,
+      "step": 520
+    },
+    {
+      "epoch": 1.097157622739018,
+      "grad_norm": 0.6640834808349609,
+      "learning_rate": 7.999017678402519e-05,
+      "loss": 0.3889,
+      "step": 530
+    },
+    {
+      "epoch": 1.117829457364341,
+      "grad_norm": 0.6472955346107483,
+      "learning_rate": 7.901771077167052e-05,
+      "loss": 0.3705,
+      "step": 540
+    },
+    {
+      "epoch": 1.138501291989664,
+      "grad_norm": 0.6622855067253113,
+      "learning_rate": 7.802840302918795e-05,
+      "loss": 0.3378,
+      "step": 550
+    },
+    {
+      "epoch": 1.1591731266149872,
+      "grad_norm": 0.6263028383255005,
+      "learning_rate": 7.702282774570435e-05,
+      "loss": 0.3839,
+      "step": 560
+    },
+    {
+      "epoch": 1.1798449612403101,
+      "grad_norm": 0.6828025579452515,
+      "learning_rate": 7.600156855194376e-05,
+      "loss": 0.3385,
+      "step": 570
+    },
+    {
+      "epoch": 1.200516795865633,
+      "grad_norm": 0.6470462679862976,
+      "learning_rate": 7.496521818149114e-05,
+      "loss": 0.3455,
+      "step": 580
+    },
+    {
+      "epoch": 1.221188630490956,
+      "grad_norm": 0.6800803542137146,
+      "learning_rate": 7.391437812677273e-05,
+      "loss": 0.3821,
+      "step": 590
+    },
+    {
+      "epoch": 1.241860465116279,
+      "grad_norm": 0.5358985066413879,
+      "learning_rate": 7.284965828995309e-05,
+      "loss": 0.3808,
+      "step": 600
+    },
+    {
+      "epoch": 1.262532299741602,
+      "grad_norm": 0.6730731725692749,
+      "learning_rate": 7.177167662895087e-05,
+      "loss": 0.3515,
+      "step": 610
+    },
+    {
+      "epoch": 1.2832041343669252,
+      "grad_norm": 0.646278977394104,
+      "learning_rate": 7.068105879877933e-05,
+      "loss": 0.3868,
+      "step": 620
+    },
+    {
+      "epoch": 1.3038759689922481,
+      "grad_norm": 0.6382839679718018,
+      "learning_rate": 6.957843778841937e-05,
+      "loss": 0.3771,
+      "step": 630
+    },
+    {
+      "epoch": 1.324547803617571,
+      "grad_norm": 0.6202185153961182,
+      "learning_rate": 6.84644535534359e-05,
+      "loss": 0.3894,
+      "step": 640
+    },
+    {
+      "epoch": 1.345219638242894,
+      "grad_norm": 0.6306319236755371,
+      "learning_rate": 6.733975264455097e-05,
+      "loss": 0.3542,
+      "step": 650
+    },
+    {
+      "epoch": 1.365891472868217,
+      "grad_norm": 0.6184442043304443,
+      "learning_rate": 6.620498783238911e-05,
+      "loss": 0.3731,
+      "step": 660
+    },
+    {
+      "epoch": 1.3865633074935402,
+      "grad_norm": 0.6922541856765747,
+      "learning_rate": 6.506081772861254e-05,
+      "loss": 0.3669,
+      "step": 670
+    },
+    {
+      "epoch": 1.407235142118863,
+      "grad_norm": 0.6143668293952942,
+      "learning_rate": 6.390790640366635e-05,
+      "loss": 0.3852,
+      "step": 680
+    },
+    {
+      "epoch": 1.427906976744186,
+      "grad_norm": 0.5965337753295898,
+      "learning_rate": 6.27469230013555e-05,
+      "loss": 0.3458,
+      "step": 690
+    },
+    {
+      "epoch": 1.448578811369509,
+      "grad_norm": 0.6029977798461914,
+      "learning_rate": 6.157854135047707e-05,
+      "loss": 0.3716,
+      "step": 700
+    },
+    {
+      "epoch": 1.469250645994832,
+      "grad_norm": 0.6470662355422974,
+      "learning_rate": 6.0403439573733666e-05,
+      "loss": 0.3656,
+      "step": 710
+    },
+    {
+      "epoch": 1.489922480620155,
+      "grad_norm": 0.6394416093826294,
+      "learning_rate": 5.9222299694154316e-05,
+      "loss": 0.3842,
+      "step": 720
+    },
+    {
+      "epoch": 1.510594315245478,
+      "grad_norm": 0.6629073619842529,
+      "learning_rate": 5.803580723925193e-05,
+      "loss": 0.3699,
+      "step": 730
+    },
+    {
+      "epoch": 1.5312661498708011,
+      "grad_norm": 0.6032027006149292,
+      "learning_rate": 5.6844650843146595e-05,
+      "loss": 0.3505,
+      "step": 740
+    },
+    {
+      "epoch": 1.551937984496124,
+      "grad_norm": 0.5825933218002319,
+      "learning_rate": 5.5649521846885876e-05,
+      "loss": 0.3611,
+      "step": 750
+    },
+    {
+      "epoch": 1.572609819121447,
+      "grad_norm": 0.6460690498352051,
+      "learning_rate": 5.445111389719408e-05,
+      "loss": 0.4034,
+      "step": 760
+    },
+    {
+      "epoch": 1.59328165374677,
+      "grad_norm": 0.6348506212234497,
+      "learning_rate": 5.3250122543883197e-05,
+      "loss": 0.3688,
+      "step": 770
+    },
+    {
+      "epoch": 1.613953488372093,
+      "grad_norm": 0.606900691986084,
+      "learning_rate": 5.20472448361594e-05,
+      "loss": 0.3741,
+      "step": 780
+    },
+    {
+      "epoch": 1.6346253229974161,
+      "grad_norm": 0.6467698812484741,
+      "learning_rate": 5.084317891805928e-05,
+      "loss": 0.3529,
+      "step": 790
+    },
+    {
+      "epoch": 1.6552971576227389,
+      "grad_norm": 0.6873207092285156,
+      "learning_rate": 4.963862362325058e-05,
+      "loss": 0.3898,
+      "step": 800
+    },
+    {
+      "epoch": 1.675968992248062,
+      "grad_norm": 0.5890557765960693,
+      "learning_rate": 4.8434278069432834e-05,
+      "loss": 0.3616,
+      "step": 810
+    },
+    {
+      "epoch": 1.696640826873385,
+      "grad_norm": 0.8989288210868835,
+      "learning_rate": 4.7230841252572906e-05,
+      "loss": 0.3578,
+      "step": 820
+    },
+    {
+      "epoch": 1.717312661498708,
+      "grad_norm": 0.6329242587089539,
+      "learning_rate": 4.602901164121145e-05,
+      "loss": 0.3561,
+      "step": 830
+    },
+    {
+      "epoch": 1.7379844961240312,
+      "grad_norm": 0.7022557258605957,
+      "learning_rate": 4.482948677107533e-05,
+      "loss": 0.3364,
+      "step": 840
+    },
+    {
+      "epoch": 1.758656330749354,
+      "grad_norm": 0.6582462787628174,
+      "learning_rate": 4.363296284023139e-05,
+      "loss": 0.363,
+      "step": 850
+    },
+    {
+      "epoch": 1.779328165374677,
+      "grad_norm": 0.6494821906089783,
+      "learning_rate": 4.24401343050168e-05,
+      "loss": 0.3431,
+      "step": 860
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.8662239909172058,
+      "learning_rate": 4.125169347698009e-05,
+      "loss": 0.3659,
+      "step": 870
+    },
+    {
+      "epoch": 1.820671834625323,
+      "grad_norm": 0.6380391120910645,
+      "learning_rate": 4.006833012106707e-05,
+      "loss": 0.3403,
+      "step": 880
+    },
+    {
+      "epoch": 1.841343669250646,
+      "grad_norm": 0.5601009726524353,
+      "learning_rate": 3.8890731055284893e-05,
+      "loss": 0.3525,
+      "step": 890
+    },
+    {
+      "epoch": 1.862015503875969,
+      "grad_norm": 0.625625729560852,
+      "learning_rate": 3.77195797520763e-05,
+      "loss": 0.3734,
+      "step": 900
+    },
+    {
+      "epoch": 1.882687338501292,
+      "grad_norm": 0.642276406288147,
+      "learning_rate": 3.6555555941635865e-05,
+      "loss": 0.3617,
+      "step": 910
+    },
+    {
+      "epoch": 1.9033591731266148,
+      "grad_norm": 0.616190493106842,
+      "learning_rate": 3.539933521739793e-05,
+      "loss": 0.3687,
+      "step": 920
+    },
+    {
+      "epoch": 1.924031007751938,
+      "grad_norm": 0.6477541923522949,
+      "learning_rate": 3.425158864392576e-05,
+      "loss": 0.355,
+      "step": 930
+    },
+    {
+      "epoch": 1.944702842377261,
+      "grad_norm": 0.5676634907722473,
+      "learning_rate": 3.31129823674291e-05,
+      "loss": 0.3651,
+      "step": 940
+    },
+    {
+      "epoch": 1.965374677002584,
+      "grad_norm": 0.6344164609909058,
+      "learning_rate": 3.1984177229136285e-05,
+      "loss": 0.3521,
+      "step": 950
+    },
+    {
+      "epoch": 1.9860465116279071,
+      "grad_norm": 0.625709593296051,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3429,
+      "step": 960
+    },
+    {
+      "epoch": 2.0082687338501293,
+      "grad_norm": 0.5501049160957336,
+      "learning_rate": 2.9758584909177433e-05,
+      "loss": 0.3837,
+      "step": 970
+    },
+    {
+      "epoch": 2.028940568475452,
+      "grad_norm": 0.6693717837333679,
+      "learning_rate": 2.8663089449850243e-05,
+      "loss": 0.3148,
+      "step": 980
+    },
+    {
+      "epoch": 2.049612403100775,
+      "grad_norm": 0.6951258778572083,
+      "learning_rate": 2.7579977823695723e-05,
+      "loss": 0.28,
+      "step": 990
+    },
+    {
+      "epoch": 2.0702842377260984,
+      "grad_norm": 0.6282662153244019,
+      "learning_rate": 2.6509878663132514e-05,
+      "loss": 0.2941,
+      "step": 1000
+    },
+    {
+      "epoch": 2.090956072351421,
+      "grad_norm": 0.6619746685028076,
+      "learning_rate": 2.5453413048211172e-05,
+      "loss": 0.3039,
+      "step": 1010
+    },
+    {
+      "epoch": 2.1116279069767443,
+      "grad_norm": 0.7403082847595215,
+      "learning_rate": 2.4411194146142407e-05,
+      "loss": 0.2757,
+      "step": 1020
+    },
+    {
+      "epoch": 2.132299741602067,
+      "grad_norm": 0.6996748447418213,
+      "learning_rate": 2.338382685541806e-05,
+      "loss": 0.2781,
+      "step": 1030
+    },
+    {
+      "epoch": 2.15297157622739,
+      "grad_norm": 0.6600786447525024,
+      "learning_rate": 2.2371907454731167e-05,
+      "loss": 0.3046,
+      "step": 1040
+    },
+    {
+      "epoch": 2.173643410852713,
+      "grad_norm": 0.6990802884101868,
+      "learning_rate": 2.137602325689873e-05,
+      "loss": 0.3032,
+      "step": 1050
+    },
+    {
+      "epoch": 2.194315245478036,
+      "grad_norm": 0.7348816394805908,
+      "learning_rate": 2.039675226798854e-05,
+      "loss": 0.2932,
+      "step": 1060
+    },
+    {
+      "epoch": 2.2149870801033593,
+      "grad_norm": 0.7239446043968201,
+      "learning_rate": 1.9434662851847325e-05,
+      "loss": 0.2966,
+      "step": 1070
+    },
+    {
+      "epoch": 2.235658914728682,
+      "grad_norm": 0.6211996078491211,
+      "learning_rate": 1.8490313400225294e-05,
+      "loss": 0.294,
+      "step": 1080
+    },
+    {
+      "epoch": 2.2563307493540052,
+      "grad_norm": 0.6428045630455017,
+      "learning_rate": 1.7564252008688514e-05,
+      "loss": 0.2861,
+      "step": 1090
+    },
+    {
+      "epoch": 2.277002583979328,
+      "grad_norm": 0.7073536515235901,
+      "learning_rate": 1.6657016158506966e-05,
+      "loss": 0.2867,
+      "step": 1100
+    },
+    {
+      "epoch": 2.297674418604651,
+      "grad_norm": 0.6491702795028687,
+      "learning_rate": 1.5769132404703274e-05,
+      "loss": 0.2916,
+      "step": 1110
+    },
+    {
+      "epoch": 2.3183462532299743,
+      "grad_norm": 0.6686069965362549,
+      "learning_rate": 1.4901116070442772e-05,
+      "loss": 0.2974,
+      "step": 1120
+    },
+    {
+      "epoch": 2.339018087855297,
+      "grad_norm": 0.7418672442436218,
+      "learning_rate": 1.4053470947942693e-05,
+      "loss": 0.2906,
+      "step": 1130
+    },
+    {
+      "epoch": 2.3596899224806203,
+      "grad_norm": 0.6745268702507019,
+      "learning_rate": 1.3226689006073712e-05,
+      "loss": 0.2864,
+      "step": 1140
+    },
+    {
+      "epoch": 2.380361757105943,
+      "grad_norm": 0.6955289244651794,
+      "learning_rate": 1.2421250104823684e-05,
+      "loss": 0.2965,
+      "step": 1150
+    },
+    {
+      "epoch": 2.401033591731266,
+      "grad_norm": 0.7368502020835876,
+      "learning_rate": 1.163762171678951e-05,
+      "loss": 0.288,
+      "step": 1160
+    },
+    {
+      "epoch": 2.4217054263565894,
+      "grad_norm": 0.6743959784507751,
+      "learning_rate": 1.0876258655858307e-05,
+      "loss": 0.3008,
+      "step": 1170
+    },
+    {
+      "epoch": 2.442377260981912,
+      "grad_norm": 0.7214462757110596,
+      "learning_rate": 1.0137602813235824e-05,
+      "loss": 0.293,
+      "step": 1180
+    },
+    {
+      "epoch": 2.4630490956072353,
+      "grad_norm": 0.6965330839157104,
+      "learning_rate": 9.422082900975104e-06,
+      "loss": 0.2882,
+      "step": 1190
+    },
+    {
+      "epoch": 2.483720930232558,
+      "grad_norm": 0.754625678062439,
+      "learning_rate": 8.730114203154144e-06,
+      "loss": 0.2994,
+      "step": 1200
+    },
+    {
+      "epoch": 2.504392764857881,
+      "grad_norm": 0.7887938618659973,
+      "learning_rate": 8.062098334847184e-06,
+      "loss": 0.2942,
+      "step": 1210
+    },
+    {
+      "epoch": 2.525064599483204,
+      "grad_norm": 0.7565446496009827,
+      "learning_rate": 7.418423009029362e-06,
+      "loss": 0.2748,
+      "step": 1220
+    },
+    {
+      "epoch": 2.545736434108527,
+      "grad_norm": 0.7032991051673889,
+      "learning_rate": 6.799461811550101e-06,
+      "loss": 0.3129,
+      "step": 1230
+    },
+    {
+      "epoch": 2.5664082687338503,
+      "grad_norm": 0.7270398736000061,
+      "learning_rate": 6.205573984305857e-06,
+      "loss": 0.3043,
+      "step": 1240
+    },
+    {
+      "epoch": 2.587080103359173,
+      "grad_norm": 0.7108693718910217,
+      "learning_rate": 5.6371042167378706e-06,
+      "loss": 0.2922,
+      "step": 1250
+    },
+    {
+      "epoch": 2.6077519379844962,
+      "grad_norm": 0.8679313063621521,
+      "learning_rate": 5.09438244577628e-06,
+      "loss": 0.3101,
+      "step": 1260
+    },
+    {
+      "epoch": 2.628423772609819,
+      "grad_norm": 0.670774519443512,
+      "learning_rate": 4.5777236643463786e-06,
+      "loss": 0.2807,
+      "step": 1270
+    },
+    {
+      "epoch": 2.649095607235142,
+      "grad_norm": 0.7098003029823303,
+      "learning_rate": 4.087427738548321e-06,
+      "loss": 0.2832,
+      "step": 1280
+    },
+    {
+      "epoch": 2.669767441860465,
+      "grad_norm": 0.7402998208999634,
+      "learning_rate": 3.623779233616442e-06,
+      "loss": 0.2925,
+      "step": 1290
+    },
+    {
+      "epoch": 2.690439276485788,
+      "grad_norm": 0.7356811165809631,
+      "learning_rate": 3.1870472487589843e-06,
+      "loss": 0.278,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.7134336233139038,
+      "learning_rate": 2.7774852609743886e-06,
+      "loss": 0.2882,
+      "step": 1310
+    },
+    {
+      "epoch": 2.731782945736434,
+      "grad_norm": 0.7377035021781921,
+      "learning_rate": 2.39533097793444e-06,
+      "loss": 0.266,
+      "step": 1320
+    },
+    {
+      "epoch": 2.752454780361757,
+      "grad_norm": 0.7013545036315918,
+      "learning_rate": 2.0408062000200625e-06,
+      "loss": 0.3037,
+      "step": 1330
+    },
+    {
+      "epoch": 2.7731266149870804,
+      "grad_norm": 0.8144780397415161,
+      "learning_rate": 1.714116691589457e-06,
+      "loss": 0.2835,
+      "step": 1340
+    },
+    {
+      "epoch": 2.793798449612403,
+      "grad_norm": 0.7584831714630127,
+      "learning_rate": 1.4154520615535183e-06,
+      "loss": 0.3005,
+      "step": 1350
+    },
+    {
+      "epoch": 2.814470284237726,
+      "grad_norm": 0.7693983316421509,
+      "learning_rate": 1.1449856533278625e-06,
+      "loss": 0.2907,
+      "step": 1360
+    },
+    {
+      "epoch": 2.835142118863049,
+      "grad_norm": 0.7604910135269165,
+      "learning_rate": 9.028744442251102e-07,
+      "loss": 0.3095,
+      "step": 1370
+    },
+    {
+      "epoch": 2.855813953488372,
+      "grad_norm": 0.7710656523704529,
+      "learning_rate": 6.892589543461392e-07,
+      "loss": 0.2964,
+      "step": 1380
+    },
+    {
+      "epoch": 2.876485788113695,
+      "grad_norm": 0.6526795625686646,
+      "learning_rate": 5.042631650229058e-07,
+      "loss": 0.2909,
+      "step": 1390
+    },
+    {
+      "epoch": 2.897157622739018,
+      "grad_norm": 0.7427286505699158,
+      "learning_rate": 3.4799444686031693e-07,
+      "loss": 0.2787,
+      "step": 1400
+    },
+    {
+      "epoch": 2.9178294573643413,
+      "grad_norm": 0.7637118101119995,
+      "learning_rate": 2.2054349741888468e-07,
+      "loss": 0.2773,
+      "step": 1410
+    },
+    {
+      "epoch": 2.938501291989664,
+      "grad_norm": 0.6580797433853149,
+      "learning_rate": 1.219842885743394e-07,
+      "loss": 0.2716,
+      "step": 1420
+    },
+    {
+      "epoch": 2.959173126614987,
+      "grad_norm": 0.7096510529518127,
+      "learning_rate": 5.237402358471144e-08,
+      "loss": 0.2951,
+      "step": 1430
+    },
+    {
+      "epoch": 2.97984496124031,
+      "grad_norm": 0.7303985953330994,
+      "learning_rate": 1.1753103889883266e-08,
+      "loss": 0.2693,
+      "step": 1440
+    },
+    {
+      "epoch": 2.9984496124031006,
+      "step": 1449,
+      "total_flos": 4.2078437233393664e+18,
+      "train_loss": 0.3962208225942629,
+      "train_runtime": 19037.0514,
+      "train_samples_per_second": 1.22,
+      "train_steps_per_second": 0.076
+    }
+  ],
+  "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": 4.2078437233393664e+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:ae07e616aa35297ef153e46a30ac2325e61d10d0c3509ef33bb88d6677c1025f
+size 5688