Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Math-1.5B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: forget_data_2000_7-8epochs
+  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. -->
+
+# forget_data_2000_7-8epochs
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) on the forget_data_2000_7-8epochs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2264
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.2069        | 1.3158 | 100  | 0.2267          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.2264215648174286,
+    "eval_runtime": 1.2961,
+    "eval_samples_per_second": 19.289,
+    "eval_steps_per_second": 5.401,
+    "total_flos": 17263553937408.0,
+    "train_loss": 0.22410145088245995,
+    "train_runtime": 539.2177,
+    "train_samples_per_second": 8.969,
+    "train_steps_per_second": 0.282
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Math-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 4096,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.2264215648174286,
+    "eval_runtime": 1.2961,
+    "eval_samples_per_second": 19.289,
+    "eval_steps_per_second": 5.401
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139d0e0ef789973d2b29ad50445a58c633c53810bdd362b71146a6b8f98e143d
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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",
+  "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": 2.0,
+    "total_flos": 17263553937408.0,
+    "train_loss": 0.22410145088245995,
+    "train_runtime": 539.2177,
+    "train_samples_per_second": 8.969,
+    "train_steps_per_second": 0.282
+}

trainer_log.jsonl

@@ -0,0 +1,154 @@
+{"current_steps": 1, "total_steps": 152, "loss": 0.2643, "lr": 9.998932083939657e-06, "epoch": 0.013157894736842105, "percentage": 0.66, "elapsed_time": "0:00:06", "remaining_time": "0:16:34"}
+{"current_steps": 2, "total_steps": 152, "loss": 0.2402, "lr": 9.995728791936505e-06, "epoch": 0.02631578947368421, "percentage": 1.32, "elapsed_time": "0:00:10", "remaining_time": "0:12:30"}
+{"current_steps": 3, "total_steps": 152, "loss": 0.2408, "lr": 9.990391492329341e-06, "epoch": 0.039473684210526314, "percentage": 1.97, "elapsed_time": "0:00:13", "remaining_time": "0:11:07"}
+{"current_steps": 4, "total_steps": 152, "loss": 0.2341, "lr": 9.98292246503335e-06, "epoch": 0.05263157894736842, "percentage": 2.63, "elapsed_time": "0:00:16", "remaining_time": "0:10:24"}
+{"current_steps": 5, "total_steps": 152, "loss": 0.2458, "lr": 9.973324900566214e-06, "epoch": 0.06578947368421052, "percentage": 3.29, "elapsed_time": "0:00:20", "remaining_time": "0:09:57"}
+{"current_steps": 6, "total_steps": 152, "loss": 0.2454, "lr": 9.961602898685225e-06, "epoch": 0.07894736842105263, "percentage": 3.95, "elapsed_time": "0:00:23", "remaining_time": "0:09:37"}
+{"current_steps": 7, "total_steps": 152, "loss": 0.2137, "lr": 9.947761466636014e-06, "epoch": 0.09210526315789473, "percentage": 4.61, "elapsed_time": "0:00:27", "remaining_time": "0:09:22"}
+{"current_steps": 8, "total_steps": 152, "loss": 0.2298, "lr": 9.931806517013612e-06, "epoch": 0.10526315789473684, "percentage": 5.26, "elapsed_time": "0:00:30", "remaining_time": "0:09:11"}
+{"current_steps": 9, "total_steps": 152, "loss": 0.2218, "lr": 9.913744865236798e-06, "epoch": 0.11842105263157894, "percentage": 5.92, "elapsed_time": "0:00:34", "remaining_time": "0:09:01"}
+{"current_steps": 10, "total_steps": 152, "loss": 0.3474, "lr": 9.893584226636773e-06, "epoch": 0.13157894736842105, "percentage": 6.58, "elapsed_time": "0:00:37", "remaining_time": "0:08:52"}
+{"current_steps": 11, "total_steps": 152, "loss": 0.2211, "lr": 9.871333213161438e-06, "epoch": 0.14473684210526316, "percentage": 7.24, "elapsed_time": "0:00:40", "remaining_time": "0:08:45"}
+{"current_steps": 12, "total_steps": 152, "loss": 0.2389, "lr": 9.847001329696653e-06, "epoch": 0.15789473684210525, "percentage": 7.89, "elapsed_time": "0:00:44", "remaining_time": "0:08:38"}
+{"current_steps": 13, "total_steps": 152, "loss": 0.2252, "lr": 9.820598970006068e-06, "epoch": 0.17105263157894737, "percentage": 8.55, "elapsed_time": "0:00:47", "remaining_time": "0:08:31"}
+{"current_steps": 14, "total_steps": 152, "loss": 0.2289, "lr": 9.792137412291265e-06, "epoch": 0.18421052631578946, "percentage": 9.21, "elapsed_time": "0:00:51", "remaining_time": "0:08:25"}
+{"current_steps": 15, "total_steps": 152, "loss": 0.2407, "lr": 9.761628814374074e-06, "epoch": 0.19736842105263158, "percentage": 9.87, "elapsed_time": "0:00:54", "remaining_time": "0:08:20"}
+{"current_steps": 16, "total_steps": 152, "loss": 0.2317, "lr": 9.729086208503174e-06, "epoch": 0.21052631578947367, "percentage": 10.53, "elapsed_time": "0:00:58", "remaining_time": "0:08:15"}
+{"current_steps": 17, "total_steps": 152, "loss": 0.2575, "lr": 9.694523495787149e-06, "epoch": 0.2236842105263158, "percentage": 11.18, "elapsed_time": "0:01:01", "remaining_time": "0:08:10"}
+{"current_steps": 18, "total_steps": 152, "loss": 0.24, "lr": 9.657955440256396e-06, "epoch": 0.23684210526315788, "percentage": 11.84, "elapsed_time": "0:01:05", "remaining_time": "0:08:05"}
+{"current_steps": 19, "total_steps": 152, "loss": 0.2444, "lr": 9.619397662556434e-06, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:01:08", "remaining_time": "0:08:00"}
+{"current_steps": 20, "total_steps": 152, "loss": 0.2364, "lr": 9.578866633275289e-06, "epoch": 0.2631578947368421, "percentage": 13.16, "elapsed_time": "0:01:12", "remaining_time": "0:07:55"}
+{"current_steps": 21, "total_steps": 152, "loss": 0.2312, "lr": 9.536379665907801e-06, "epoch": 0.27631578947368424, "percentage": 13.82, "elapsed_time": "0:01:15", "remaining_time": "0:07:51"}
+{"current_steps": 22, "total_steps": 152, "loss": 0.2087, "lr": 9.491954909459895e-06, "epoch": 0.2894736842105263, "percentage": 14.47, "elapsed_time": "0:01:18", "remaining_time": "0:07:46"}
+{"current_steps": 23, "total_steps": 152, "loss": 0.224, "lr": 9.445611340695926e-06, "epoch": 0.3026315789473684, "percentage": 15.13, "elapsed_time": "0:01:22", "remaining_time": "0:07:42"}
+{"current_steps": 24, "total_steps": 152, "loss": 0.2258, "lr": 9.397368756032445e-06, "epoch": 0.3157894736842105, "percentage": 15.79, "elapsed_time": "0:01:25", "remaining_time": "0:07:38"}
+{"current_steps": 25, "total_steps": 152, "loss": 0.2237, "lr": 9.347247763081834e-06, "epoch": 0.32894736842105265, "percentage": 16.45, "elapsed_time": "0:01:29", "remaining_time": "0:07:34"}
+{"current_steps": 26, "total_steps": 152, "loss": 0.2385, "lr": 9.295269771849426e-06, "epoch": 0.34210526315789475, "percentage": 17.11, "elapsed_time": "0:01:32", "remaining_time": "0:07:30"}
+{"current_steps": 27, "total_steps": 152, "loss": 0.2478, "lr": 9.241456985587868e-06, "epoch": 0.35526315789473684, "percentage": 17.76, "elapsed_time": "0:01:36", "remaining_time": "0:07:26"}
+{"current_steps": 28, "total_steps": 152, "loss": 0.2301, "lr": 9.185832391312644e-06, "epoch": 0.3684210526315789, "percentage": 18.42, "elapsed_time": "0:01:39", "remaining_time": "0:07:22"}
+{"current_steps": 29, "total_steps": 152, "loss": 0.2419, "lr": 9.12841974998278e-06, "epoch": 0.3815789473684211, "percentage": 19.08, "elapsed_time": "0:01:43", "remaining_time": "0:07:18"}
+{"current_steps": 30, "total_steps": 152, "loss": 0.2565, "lr": 9.069243586350976e-06, "epoch": 0.39473684210526316, "percentage": 19.74, "elapsed_time": "0:01:46", "remaining_time": "0:07:14"}
+{"current_steps": 31, "total_steps": 152, "loss": 0.2334, "lr": 9.008329178487442e-06, "epoch": 0.40789473684210525, "percentage": 20.39, "elapsed_time": "0:01:50", "remaining_time": "0:07:10"}
+{"current_steps": 32, "total_steps": 152, "loss": 0.2221, "lr": 8.94570254698197e-06, "epoch": 0.42105263157894735, "percentage": 21.05, "elapsed_time": "0:01:53", "remaining_time": "0:07:06"}
+{"current_steps": 33, "total_steps": 152, "loss": 0.2273, "lr": 8.881390443828788e-06, "epoch": 0.4342105263157895, "percentage": 21.71, "elapsed_time": "0:01:57", "remaining_time": "0:07:02"}
+{"current_steps": 34, "total_steps": 152, "loss": 0.2144, "lr": 8.815420340999034e-06, "epoch": 0.4473684210526316, "percentage": 22.37, "elapsed_time": "0:02:00", "remaining_time": "0:06:58"}
+{"current_steps": 35, "total_steps": 152, "loss": 0.2191, "lr": 8.747820418705632e-06, "epoch": 0.4605263157894737, "percentage": 23.03, "elapsed_time": "0:02:04", "remaining_time": "0:06:55"}
+{"current_steps": 36, "total_steps": 152, "loss": 0.2365, "lr": 8.67861955336566e-06, "epoch": 0.47368421052631576, "percentage": 23.68, "elapsed_time": "0:02:07", "remaining_time": "0:06:51"}
+{"current_steps": 37, "total_steps": 152, "loss": 0.2349, "lr": 8.607847305265312e-06, "epoch": 0.4868421052631579, "percentage": 24.34, "elapsed_time": "0:02:11", "remaining_time": "0:06:47"}
+{"current_steps": 38, "total_steps": 152, "loss": 0.2272, "lr": 8.535533905932739e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:02:14", "remaining_time": "0:06:44"}
+{"current_steps": 39, "total_steps": 152, "loss": 0.2122, "lr": 8.461710245224149e-06, "epoch": 0.5131578947368421, "percentage": 25.66, "elapsed_time": "0:02:18", "remaining_time": "0:06:40"}
+{"current_steps": 40, "total_steps": 152, "loss": 0.2438, "lr": 8.386407858128707e-06, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "0:02:21", "remaining_time": "0:06:36"}
+{"current_steps": 41, "total_steps": 152, "loss": 0.2265, "lr": 8.309658911297833e-06, "epoch": 0.5394736842105263, "percentage": 26.97, "elapsed_time": "0:02:25", "remaining_time": "0:06:32"}
+{"current_steps": 42, "total_steps": 152, "loss": 0.2249, "lr": 8.231496189304704e-06, "epoch": 0.5526315789473685, "percentage": 27.63, "elapsed_time": "0:02:28", "remaining_time": "0:06:29"}
+{"current_steps": 43, "total_steps": 152, "loss": 0.226, "lr": 8.151953080639777e-06, "epoch": 0.5657894736842105, "percentage": 28.29, "elapsed_time": "0:02:32", "remaining_time": "0:06:25"}
+{"current_steps": 44, "total_steps": 152, "loss": 0.2422, "lr": 8.071063563448341e-06, "epoch": 0.5789473684210527, "percentage": 28.95, "elapsed_time": "0:02:35", "remaining_time": "0:06:22"}
+{"current_steps": 45, "total_steps": 152, "loss": 0.2219, "lr": 7.988862191016204e-06, "epoch": 0.5921052631578947, "percentage": 29.61, "elapsed_time": "0:02:39", "remaining_time": "0:06:18"}
+{"current_steps": 46, "total_steps": 152, "loss": 0.2106, "lr": 7.905384077009693e-06, "epoch": 0.6052631578947368, "percentage": 30.26, "elapsed_time": "0:02:42", "remaining_time": "0:06:14"}
+{"current_steps": 47, "total_steps": 152, "loss": 0.2096, "lr": 7.820664880476257e-06, "epoch": 0.618421052631579, "percentage": 30.92, "elapsed_time": "0:02:46", "remaining_time": "0:06:11"}
+{"current_steps": 48, "total_steps": 152, "loss": 0.2616, "lr": 7.734740790612137e-06, "epoch": 0.631578947368421, "percentage": 31.58, "elapsed_time": "0:02:49", "remaining_time": "0:06:07"}
+{"current_steps": 49, "total_steps": 152, "loss": 0.233, "lr": 7.647648511303545e-06, "epoch": 0.6447368421052632, "percentage": 32.24, "elapsed_time": "0:02:53", "remaining_time": "0:06:03"}
+{"current_steps": 50, "total_steps": 152, "loss": 0.2236, "lr": 7.559425245448006e-06, "epoch": 0.6578947368421053, "percentage": 32.89, "elapsed_time": "0:02:56", "remaining_time": "0:06:00"}
+{"current_steps": 51, "total_steps": 152, "loss": 0.2156, "lr": 7.470108679062521e-06, "epoch": 0.6710526315789473, "percentage": 33.55, "elapsed_time": "0:03:00", "remaining_time": "0:05:56"}
+{"current_steps": 52, "total_steps": 152, "loss": 0.2309, "lr": 7.379736965185369e-06, "epoch": 0.6842105263157895, "percentage": 34.21, "elapsed_time": "0:03:03", "remaining_time": "0:05:53"}
+{"current_steps": 53, "total_steps": 152, "loss": 0.2546, "lr": 7.288348707578409e-06, "epoch": 0.6973684210526315, "percentage": 34.87, "elapsed_time": "0:03:07", "remaining_time": "0:05:49"}
+{"current_steps": 54, "total_steps": 152, "loss": 0.235, "lr": 7.195982944236853e-06, "epoch": 0.7105263157894737, "percentage": 35.53, "elapsed_time": "0:03:10", "remaining_time": "0:05:45"}
+{"current_steps": 55, "total_steps": 152, "loss": 0.2372, "lr": 7.102679130713538e-06, "epoch": 0.7236842105263158, "percentage": 36.18, "elapsed_time": "0:03:14", "remaining_time": "0:05:42"}
+{"current_steps": 56, "total_steps": 152, "loss": 0.2032, "lr": 7.008477123264849e-06, "epoch": 0.7368421052631579, "percentage": 36.84, "elapsed_time": "0:03:17", "remaining_time": "0:05:38"}
+{"current_steps": 57, "total_steps": 152, "loss": 0.2303, "lr": 6.913417161825449e-06, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:03:21", "remaining_time": "0:05:35"}
+{"current_steps": 58, "total_steps": 152, "loss": 0.252, "lr": 6.817539852819149e-06, "epoch": 0.7631578947368421, "percentage": 38.16, "elapsed_time": "0:03:24", "remaining_time": "0:05:31"}
+{"current_steps": 59, "total_steps": 152, "loss": 0.2084, "lr": 6.720886151813194e-06, "epoch": 0.7763157894736842, "percentage": 38.82, "elapsed_time": "0:03:28", "remaining_time": "0:05:28"}
+{"current_steps": 60, "total_steps": 152, "loss": 0.222, "lr": 6.6234973460234184e-06, "epoch": 0.7894736842105263, "percentage": 39.47, "elapsed_time": "0:03:31", "remaining_time": "0:05:24"}
+{"current_steps": 61, "total_steps": 152, "loss": 0.2428, "lr": 6.525415036677745e-06, "epoch": 0.8026315789473685, "percentage": 40.13, "elapsed_time": "0:03:35", "remaining_time": "0:05:20"}
+{"current_steps": 62, "total_steps": 152, "loss": 0.2396, "lr": 6.426681121245527e-06, "epoch": 0.8157894736842105, "percentage": 40.79, "elapsed_time": "0:03:38", "remaining_time": "0:05:17"}
+{"current_steps": 63, "total_steps": 152, "loss": 0.2284, "lr": 6.327337775540362e-06, "epoch": 0.8289473684210527, "percentage": 41.45, "elapsed_time": "0:03:42", "remaining_time": "0:05:13"}
+{"current_steps": 64, "total_steps": 152, "loss": 0.2319, "lr": 6.227427435703997e-06, "epoch": 0.8421052631578947, "percentage": 42.11, "elapsed_time": "0:03:45", "remaining_time": "0:05:10"}
+{"current_steps": 65, "total_steps": 152, "loss": 0.2178, "lr": 6.126992780079032e-06, "epoch": 0.8552631578947368, "percentage": 42.76, "elapsed_time": "0:03:49", "remaining_time": "0:05:06"}
+{"current_steps": 66, "total_steps": 152, "loss": 0.2052, "lr": 6.026076710978172e-06, "epoch": 0.868421052631579, "percentage": 43.42, "elapsed_time": "0:03:52", "remaining_time": "0:05:03"}
+{"current_steps": 67, "total_steps": 152, "loss": 0.2169, "lr": 5.924722336357793e-06, "epoch": 0.881578947368421, "percentage": 44.08, "elapsed_time": "0:03:56", "remaining_time": "0:04:59"}
+{"current_steps": 68, "total_steps": 152, "loss": 0.2424, "lr": 5.82297295140367e-06, "epoch": 0.8947368421052632, "percentage": 44.74, "elapsed_time": "0:03:59", "remaining_time": "0:04:56"}
+{"current_steps": 69, "total_steps": 152, "loss": 0.2378, "lr": 5.720872020036734e-06, "epoch": 0.9078947368421053, "percentage": 45.39, "elapsed_time": "0:04:03", "remaining_time": "0:04:52"}
+{"current_steps": 70, "total_steps": 152, "loss": 0.234, "lr": 5.61846315634674e-06, "epoch": 0.9210526315789473, "percentage": 46.05, "elapsed_time": "0:04:06", "remaining_time": "0:04:49"}
+{"current_steps": 71, "total_steps": 152, "loss": 0.2492, "lr": 5.515790105961785e-06, "epoch": 0.9342105263157895, "percentage": 46.71, "elapsed_time": "0:04:10", "remaining_time": "0:04:45"}
+{"current_steps": 72, "total_steps": 152, "loss": 0.2212, "lr": 5.412896727361663e-06, "epoch": 0.9473684210526315, "percentage": 47.37, "elapsed_time": "0:04:13", "remaining_time": "0:04:41"}
+{"current_steps": 73, "total_steps": 152, "loss": 0.23, "lr": 5.309826973142974e-06, "epoch": 0.9605263157894737, "percentage": 48.03, "elapsed_time": "0:04:17", "remaining_time": "0:04:38"}
+{"current_steps": 74, "total_steps": 152, "loss": 0.2299, "lr": 5.206624871244066e-06, "epoch": 0.9736842105263158, "percentage": 48.68, "elapsed_time": "0:04:20", "remaining_time": "0:04:34"}
+{"current_steps": 75, "total_steps": 152, "loss": 0.2431, "lr": 5.103334506137773e-06, "epoch": 0.9868421052631579, "percentage": 49.34, "elapsed_time": "0:04:24", "remaining_time": "0:04:31"}
+{"current_steps": 76, "total_steps": 152, "loss": 0.2265, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:04:27", "remaining_time": "0:04:27"}
+{"current_steps": 77, "total_steps": 152, "loss": 0.2044, "lr": 4.89666549386223e-06, "epoch": 1.013157894736842, "percentage": 50.66, "elapsed_time": "0:04:31", "remaining_time": "0:04:24"}
+{"current_steps": 78, "total_steps": 152, "loss": 0.2153, "lr": 4.793375128755934e-06, "epoch": 1.0263157894736843, "percentage": 51.32, "elapsed_time": "0:04:34", "remaining_time": "0:04:20"}
+{"current_steps": 79, "total_steps": 152, "loss": 0.2445, "lr": 4.690173026857028e-06, "epoch": 1.0394736842105263, "percentage": 51.97, "elapsed_time": "0:04:38", "remaining_time": "0:04:17"}
+{"current_steps": 80, "total_steps": 152, "loss": 0.208, "lr": 4.587103272638339e-06, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "0:04:41", "remaining_time": "0:04:13"}
+{"current_steps": 81, "total_steps": 152, "loss": 0.2308, "lr": 4.4842098940382155e-06, "epoch": 1.0657894736842106, "percentage": 53.29, "elapsed_time": "0:04:45", "remaining_time": "0:04:10"}
+{"current_steps": 82, "total_steps": 152, "loss": 0.2316, "lr": 4.381536843653262e-06, "epoch": 1.0789473684210527, "percentage": 53.95, "elapsed_time": "0:04:48", "remaining_time": "0:04:06"}
+{"current_steps": 83, "total_steps": 152, "loss": 0.2219, "lr": 4.279127979963266e-06, "epoch": 1.0921052631578947, "percentage": 54.61, "elapsed_time": "0:04:52", "remaining_time": "0:04:03"}
+{"current_steps": 84, "total_steps": 152, "loss": 0.2181, "lr": 4.17702704859633e-06, "epoch": 1.1052631578947367, "percentage": 55.26, "elapsed_time": "0:04:55", "remaining_time": "0:03:59"}
+{"current_steps": 85, "total_steps": 152, "loss": 0.1866, "lr": 4.075277663642208e-06, "epoch": 1.118421052631579, "percentage": 55.92, "elapsed_time": "0:04:59", "remaining_time": "0:03:55"}
+{"current_steps": 86, "total_steps": 152, "loss": 0.2293, "lr": 3.973923289021829e-06, "epoch": 1.131578947368421, "percentage": 56.58, "elapsed_time": "0:05:02", "remaining_time": "0:03:52"}
+{"current_steps": 87, "total_steps": 152, "loss": 0.1958, "lr": 3.8730072199209705e-06, "epoch": 1.1447368421052633, "percentage": 57.24, "elapsed_time": "0:05:06", "remaining_time": "0:03:48"}
+{"current_steps": 88, "total_steps": 152, "loss": 0.2051, "lr": 3.7725725642960047e-06, "epoch": 1.1578947368421053, "percentage": 57.89, "elapsed_time": "0:05:09", "remaining_time": "0:03:45"}
+{"current_steps": 89, "total_steps": 152, "loss": 0.1952, "lr": 3.67266222445964e-06, "epoch": 1.1710526315789473, "percentage": 58.55, "elapsed_time": "0:05:13", "remaining_time": "0:03:41"}
+{"current_steps": 90, "total_steps": 152, "loss": 0.2198, "lr": 3.573318878754475e-06, "epoch": 1.1842105263157894, "percentage": 59.21, "elapsed_time": "0:05:16", "remaining_time": "0:03:38"}
+{"current_steps": 91, "total_steps": 152, "loss": 0.2304, "lr": 3.4745849633222566e-06, "epoch": 1.1973684210526316, "percentage": 59.87, "elapsed_time": "0:05:20", "remaining_time": "0:03:34"}
+{"current_steps": 92, "total_steps": 152, "loss": 0.2117, "lr": 3.3765026539765832e-06, "epoch": 1.2105263157894737, "percentage": 60.53, "elapsed_time": "0:05:23", "remaining_time": "0:03:31"}
+{"current_steps": 93, "total_steps": 152, "loss": 0.2007, "lr": 3.2791138481868084e-06, "epoch": 1.2236842105263157, "percentage": 61.18, "elapsed_time": "0:05:27", "remaining_time": "0:03:27"}
+{"current_steps": 94, "total_steps": 152, "loss": 0.2262, "lr": 3.1824601471808504e-06, "epoch": 1.236842105263158, "percentage": 61.84, "elapsed_time": "0:05:30", "remaining_time": "0:03:24"}
+{"current_steps": 95, "total_steps": 152, "loss": 0.2145, "lr": 3.0865828381745515e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "0:05:34", "remaining_time": "0:03:20"}
+{"current_steps": 96, "total_steps": 152, "loss": 0.2194, "lr": 2.991522876735154e-06, "epoch": 1.263157894736842, "percentage": 63.16, "elapsed_time": "0:05:37", "remaining_time": "0:03:17"}
+{"current_steps": 97, "total_steps": 152, "loss": 0.2267, "lr": 2.8973208692864623e-06, "epoch": 1.2763157894736843, "percentage": 63.82, "elapsed_time": "0:05:41", "remaining_time": "0:03:13"}
+{"current_steps": 98, "total_steps": 152, "loss": 0.2035, "lr": 2.804017055763149e-06, "epoch": 1.2894736842105263, "percentage": 64.47, "elapsed_time": "0:05:44", "remaining_time": "0:03:10"}
+{"current_steps": 99, "total_steps": 152, "loss": 0.1873, "lr": 2.711651292421593e-06, "epoch": 1.3026315789473684, "percentage": 65.13, "elapsed_time": "0:05:48", "remaining_time": "0:03:06"}
+{"current_steps": 100, "total_steps": 152, "loss": 0.2069, "lr": 2.6202630348146323e-06, "epoch": 1.3157894736842106, "percentage": 65.79, "elapsed_time": "0:05:51", "remaining_time": "0:03:03"}
+{"current_steps": 100, "total_steps": 152, "eval_loss": 0.2266910970211029, "epoch": 1.3157894736842106, "percentage": 65.79, "elapsed_time": "0:05:53", "remaining_time": "0:03:03"}
+{"current_steps": 101, "total_steps": 152, "loss": 0.2283, "lr": 2.529891320937481e-06, "epoch": 1.3289473684210527, "percentage": 66.45, "elapsed_time": "0:05:57", "remaining_time": "0:03:00"}
+{"current_steps": 102, "total_steps": 152, "loss": 0.2123, "lr": 2.4405747545519966e-06, "epoch": 1.3421052631578947, "percentage": 67.11, "elapsed_time": "0:06:00", "remaining_time": "0:02:56"}
+{"current_steps": 103, "total_steps": 152, "loss": 0.2032, "lr": 2.352351488696457e-06, "epoch": 1.3552631578947367, "percentage": 67.76, "elapsed_time": "0:06:04", "remaining_time": "0:02:53"}
+{"current_steps": 104, "total_steps": 152, "loss": 0.1993, "lr": 2.265259209387867e-06, "epoch": 1.368421052631579, "percentage": 68.42, "elapsed_time": "0:06:07", "remaining_time": "0:02:49"}
+{"current_steps": 105, "total_steps": 152, "loss": 0.2211, "lr": 2.179335119523745e-06, "epoch": 1.381578947368421, "percentage": 69.08, "elapsed_time": "0:06:11", "remaining_time": "0:02:46"}
+{"current_steps": 106, "total_steps": 152, "loss": 0.2021, "lr": 2.094615922990309e-06, "epoch": 1.3947368421052633, "percentage": 69.74, "elapsed_time": "0:06:14", "remaining_time": "0:02:42"}
+{"current_steps": 107, "total_steps": 152, "loss": 0.2065, "lr": 2.0111378089837958e-06, "epoch": 1.4078947368421053, "percentage": 70.39, "elapsed_time": "0:06:18", "remaining_time": "0:02:38"}
+{"current_steps": 108, "total_steps": 152, "loss": 0.2353, "lr": 1.928936436551661e-06, "epoch": 1.4210526315789473, "percentage": 71.05, "elapsed_time": "0:06:21", "remaining_time": "0:02:35"}
+{"current_steps": 109, "total_steps": 152, "loss": 0.2104, "lr": 1.848046919360225e-06, "epoch": 1.4342105263157894, "percentage": 71.71, "elapsed_time": "0:06:24", "remaining_time": "0:02:31"}
+{"current_steps": 110, "total_steps": 152, "loss": 0.2167, "lr": 1.7685038106952952e-06, "epoch": 1.4473684210526316, "percentage": 72.37, "elapsed_time": "0:06:28", "remaining_time": "0:02:28"}
+{"current_steps": 111, "total_steps": 152, "loss": 0.214, "lr": 1.6903410887021676e-06, "epoch": 1.4605263157894737, "percentage": 73.03, "elapsed_time": "0:06:31", "remaining_time": "0:02:24"}
+{"current_steps": 112, "total_steps": 152, "loss": 0.2269, "lr": 1.6135921418712959e-06, "epoch": 1.4736842105263157, "percentage": 73.68, "elapsed_time": "0:06:35", "remaining_time": "0:02:21"}
+{"current_steps": 113, "total_steps": 152, "loss": 0.2096, "lr": 1.5382897547758513e-06, "epoch": 1.486842105263158, "percentage": 74.34, "elapsed_time": "0:06:38", "remaining_time": "0:02:17"}
+{"current_steps": 114, "total_steps": 152, "loss": 0.2051, "lr": 1.4644660940672628e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:06:42", "remaining_time": "0:02:14"}
+{"current_steps": 115, "total_steps": 152, "loss": 0.303, "lr": 1.3921526947346902e-06, "epoch": 1.513157894736842, "percentage": 75.66, "elapsed_time": "0:06:45", "remaining_time": "0:02:10"}
+{"current_steps": 116, "total_steps": 152, "loss": 0.2089, "lr": 1.321380446634342e-06, "epoch": 1.526315789473684, "percentage": 76.32, "elapsed_time": "0:06:49", "remaining_time": "0:02:06"}
+{"current_steps": 117, "total_steps": 152, "loss": 0.1929, "lr": 1.2521795812943704e-06, "epoch": 1.5394736842105263, "percentage": 76.97, "elapsed_time": "0:06:52", "remaining_time": "0:02:03"}
+{"current_steps": 118, "total_steps": 152, "loss": 0.2217, "lr": 1.1845796590009684e-06, "epoch": 1.5526315789473686, "percentage": 77.63, "elapsed_time": "0:06:56", "remaining_time": "0:01:59"}
+{"current_steps": 119, "total_steps": 152, "loss": 0.2012, "lr": 1.118609556171213e-06, "epoch": 1.5657894736842106, "percentage": 78.29, "elapsed_time": "0:06:59", "remaining_time": "0:01:56"}
+{"current_steps": 120, "total_steps": 152, "loss": 0.2394, "lr": 1.0542974530180327e-06, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "0:07:03", "remaining_time": "0:01:52"}
+{"current_steps": 121, "total_steps": 152, "loss": 0.2116, "lr": 9.916708215125586e-07, "epoch": 1.5921052631578947, "percentage": 79.61, "elapsed_time": "0:07:06", "remaining_time": "0:01:49"}
+{"current_steps": 122, "total_steps": 152, "loss": 0.2175, "lr": 9.307564136490255e-07, "epoch": 1.6052631578947367, "percentage": 80.26, "elapsed_time": "0:07:09", "remaining_time": "0:01:45"}
+{"current_steps": 123, "total_steps": 152, "loss": 0.2224, "lr": 8.715802500172215e-07, "epoch": 1.618421052631579, "percentage": 80.92, "elapsed_time": "0:07:13", "remaining_time": "0:01:42"}
+{"current_steps": 124, "total_steps": 152, "loss": 0.2299, "lr": 8.141676086873574e-07, "epoch": 1.631578947368421, "percentage": 81.58, "elapsed_time": "0:07:16", "remaining_time": "0:01:38"}
+{"current_steps": 125, "total_steps": 152, "loss": 0.2037, "lr": 7.585430144121319e-07, "epoch": 1.6447368421052633, "percentage": 82.24, "elapsed_time": "0:07:20", "remaining_time": "0:01:35"}
+{"current_steps": 126, "total_steps": 152, "loss": 0.2116, "lr": 7.047302281505735e-07, "epoch": 1.6578947368421053, "percentage": 82.89, "elapsed_time": "0:07:23", "remaining_time": "0:01:31"}
+{"current_steps": 127, "total_steps": 152, "loss": 0.2149, "lr": 6.527522369181655e-07, "epoch": 1.6710526315789473, "percentage": 83.55, "elapsed_time": "0:07:27", "remaining_time": "0:01:28"}
+{"current_steps": 128, "total_steps": 152, "loss": 0.2107, "lr": 6.026312439675553e-07, "epoch": 1.6842105263157894, "percentage": 84.21, "elapsed_time": "0:07:30", "remaining_time": "0:01:24"}
+{"current_steps": 129, "total_steps": 152, "loss": 0.2159, "lr": 5.543886593040737e-07, "epoch": 1.6973684210526314, "percentage": 84.87, "elapsed_time": "0:07:34", "remaining_time": "0:01:20"}
+{"current_steps": 130, "total_steps": 152, "loss": 0.2144, "lr": 5.080450905401057e-07, "epoch": 1.7105263157894737, "percentage": 85.53, "elapsed_time": "0:07:37", "remaining_time": "0:01:17"}
+{"current_steps": 131, "total_steps": 152, "loss": 0.2155, "lr": 4.6362033409220077e-07, "epoch": 1.723684210526316, "percentage": 86.18, "elapsed_time": "0:07:41", "remaining_time": "0:01:13"}
+{"current_steps": 132, "total_steps": 152, "loss": 0.2179, "lr": 4.211333667247125e-07, "epoch": 1.736842105263158, "percentage": 86.84, "elapsed_time": "0:07:44", "remaining_time": "0:01:10"}
+{"current_steps": 133, "total_steps": 152, "loss": 0.2092, "lr": 3.8060233744356634e-07, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "0:07:48", "remaining_time": "0:01:06"}
+{"current_steps": 134, "total_steps": 152, "loss": 0.2038, "lr": 3.420445597436056e-07, "epoch": 1.763157894736842, "percentage": 88.16, "elapsed_time": "0:07:51", "remaining_time": "0:01:03"}
+{"current_steps": 135, "total_steps": 152, "loss": 0.2173, "lr": 3.0547650421285216e-07, "epoch": 1.776315789473684, "percentage": 88.82, "elapsed_time": "0:07:55", "remaining_time": "0:00:59"}
+{"current_steps": 136, "total_steps": 152, "loss": 0.2155, "lr": 2.7091379149682683e-07, "epoch": 1.7894736842105263, "percentage": 89.47, "elapsed_time": "0:07:58", "remaining_time": "0:00:56"}
+{"current_steps": 137, "total_steps": 152, "loss": 0.2244, "lr": 2.3837118562592799e-07, "epoch": 1.8026315789473686, "percentage": 90.13, "elapsed_time": "0:08:02", "remaining_time": "0:00:52"}
+{"current_steps": 138, "total_steps": 152, "loss": 0.2052, "lr": 2.0786258770873647e-07, "epoch": 1.8157894736842106, "percentage": 90.79, "elapsed_time": "0:08:05", "remaining_time": "0:00:49"}
+{"current_steps": 139, "total_steps": 152, "loss": 0.2252, "lr": 1.7940102999393194e-07, "epoch": 1.8289473684210527, "percentage": 91.45, "elapsed_time": "0:08:09", "remaining_time": "0:00:45"}
+{"current_steps": 140, "total_steps": 152, "loss": 0.2105, "lr": 1.5299867030334815e-07, "epoch": 1.8421052631578947, "percentage": 92.11, "elapsed_time": "0:08:12", "remaining_time": "0:00:42"}
+{"current_steps": 141, "total_steps": 152, "loss": 0.2156, "lr": 1.286667868385627e-07, "epoch": 1.8552631578947367, "percentage": 92.76, "elapsed_time": "0:08:16", "remaining_time": "0:00:38"}
+{"current_steps": 142, "total_steps": 152, "loss": 0.2131, "lr": 1.0641577336322761e-07, "epoch": 1.868421052631579, "percentage": 93.42, "elapsed_time": "0:08:19", "remaining_time": "0:00:35"}
+{"current_steps": 143, "total_steps": 152, "loss": 0.1935, "lr": 8.625513476320291e-08, "epoch": 1.881578947368421, "percentage": 94.08, "elapsed_time": "0:08:22", "remaining_time": "0:00:31"}
+{"current_steps": 144, "total_steps": 152, "loss": 0.2132, "lr": 6.819348298638839e-08, "epoch": 1.8947368421052633, "percentage": 94.74, "elapsed_time": "0:08:26", "remaining_time": "0:00:28"}
+{"current_steps": 145, "total_steps": 152, "loss": 0.2395, "lr": 5.223853336398632e-08, "epoch": 1.9078947368421053, "percentage": 95.39, "elapsed_time": "0:08:29", "remaining_time": "0:00:24"}
+{"current_steps": 146, "total_steps": 152, "loss": 0.225, "lr": 3.839710131477492e-08, "epoch": 1.9210526315789473, "percentage": 96.05, "elapsed_time": "0:08:33", "remaining_time": "0:00:21"}
+{"current_steps": 147, "total_steps": 152, "loss": 0.2159, "lr": 2.6675099433787212e-08, "epoch": 1.9342105263157894, "percentage": 96.71, "elapsed_time": "0:08:36", "remaining_time": "0:00:17"}
+{"current_steps": 148, "total_steps": 152, "loss": 0.2128, "lr": 1.7077534966650767e-08, "epoch": 1.9473684210526314, "percentage": 97.37, "elapsed_time": "0:08:40", "remaining_time": "0:00:14"}
+{"current_steps": 149, "total_steps": 152, "loss": 0.2111, "lr": 9.608507670659239e-09, "epoch": 1.9605263157894737, "percentage": 98.03, "elapsed_time": "0:08:43", "remaining_time": "0:00:10"}
+{"current_steps": 150, "total_steps": 152, "loss": 0.1887, "lr": 4.2712080634949024e-09, "epoch": 1.973684210526316, "percentage": 98.68, "elapsed_time": "0:08:47", "remaining_time": "0:00:07"}
+{"current_steps": 151, "total_steps": 152, "loss": 0.2216, "lr": 1.0679160603449533e-09, "epoch": 1.986842105263158, "percentage": 99.34, "elapsed_time": "0:08:50", "remaining_time": "0:00:03"}
+{"current_steps": 152, "total_steps": 152, "loss": 0.2118, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:54", "remaining_time": "0:00:00"}
+{"current_steps": 152, "total_steps": 152, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:59", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 100,
+  "global_step": 152,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 0.8720962215415559,
+      "learning_rate": 9.998932083939657e-06,
+      "loss": 0.2643,
+      "step": 1
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 0.747417196895451,
+      "learning_rate": 9.995728791936505e-06,
+      "loss": 0.2402,
+      "step": 2
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 0.44935149689684434,
+      "learning_rate": 9.990391492329341e-06,
+      "loss": 0.2408,
+      "step": 3
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.3745832126689934,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 0.2341,
+      "step": 4
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 0.787443658812722,
+      "learning_rate": 9.973324900566214e-06,
+      "loss": 0.2458,
+      "step": 5
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 0.45662591287732757,
+      "learning_rate": 9.961602898685225e-06,
+      "loss": 0.2454,
+      "step": 6
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 0.21149288778417216,
+      "learning_rate": 9.947761466636014e-06,
+      "loss": 0.2137,
+      "step": 7
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.19971613064783947,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 0.2298,
+      "step": 8
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 0.19225174500381764,
+      "learning_rate": 9.913744865236798e-06,
+      "loss": 0.2218,
+      "step": 9
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.1995939834971319,
+      "learning_rate": 9.893584226636773e-06,
+      "loss": 0.3474,
+      "step": 10
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 0.20206117790575712,
+      "learning_rate": 9.871333213161438e-06,
+      "loss": 0.2211,
+      "step": 11
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.20078847341460862,
+      "learning_rate": 9.847001329696653e-06,
+      "loss": 0.2389,
+      "step": 12
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 0.1868638975780885,
+      "learning_rate": 9.820598970006068e-06,
+      "loss": 0.2252,
+      "step": 13
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 0.19418968285074564,
+      "learning_rate": 9.792137412291265e-06,
+      "loss": 0.2289,
+      "step": 14
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 0.2060157337835201,
+      "learning_rate": 9.761628814374074e-06,
+      "loss": 0.2407,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.1790111483921519,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.2317,
+      "step": 16
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 0.20165111462114726,
+      "learning_rate": 9.694523495787149e-06,
+      "loss": 0.2575,
+      "step": 17
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.19251140214773363,
+      "learning_rate": 9.657955440256396e-06,
+      "loss": 0.24,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2030644237326319,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.2444,
+      "step": 19
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.18844775173365788,
+      "learning_rate": 9.578866633275289e-06,
+      "loss": 0.2364,
+      "step": 20
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 0.19639119770968017,
+      "learning_rate": 9.536379665907801e-06,
+      "loss": 0.2312,
+      "step": 21
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.17725272522073218,
+      "learning_rate": 9.491954909459895e-06,
+      "loss": 0.2087,
+      "step": 22
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 0.1855774663879287,
+      "learning_rate": 9.445611340695926e-06,
+      "loss": 0.224,
+      "step": 23
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.19740821896989008,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.2258,
+      "step": 24
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 0.19285755352298933,
+      "learning_rate": 9.347247763081834e-06,
+      "loss": 0.2237,
+      "step": 25
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.189006195678192,
+      "learning_rate": 9.295269771849426e-06,
+      "loss": 0.2385,
+      "step": 26
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 0.19789730919795956,
+      "learning_rate": 9.241456985587868e-06,
+      "loss": 0.2478,
+      "step": 27
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.189523914668433,
+      "learning_rate": 9.185832391312644e-06,
+      "loss": 0.2301,
+      "step": 28
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 0.18241663298591654,
+      "learning_rate": 9.12841974998278e-06,
+      "loss": 0.2419,
+      "step": 29
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.2046300247578689,
+      "learning_rate": 9.069243586350976e-06,
+      "loss": 0.2565,
+      "step": 30
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 0.19962441541775156,
+      "learning_rate": 9.008329178487442e-06,
+      "loss": 0.2334,
+      "step": 31
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.18450295711265163,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.2221,
+      "step": 32
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 0.19119705874914159,
+      "learning_rate": 8.881390443828788e-06,
+      "loss": 0.2273,
+      "step": 33
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 0.1759965473059521,
+      "learning_rate": 8.815420340999034e-06,
+      "loss": 0.2144,
+      "step": 34
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 0.17958189855732734,
+      "learning_rate": 8.747820418705632e-06,
+      "loss": 0.2191,
+      "step": 35
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.19176379775498073,
+      "learning_rate": 8.67861955336566e-06,
+      "loss": 0.2365,
+      "step": 36
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.19037229638803108,
+      "learning_rate": 8.607847305265312e-06,
+      "loss": 0.2349,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1807010374223924,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.2272,
+      "step": 38
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.18923911960854278,
+      "learning_rate": 8.461710245224149e-06,
+      "loss": 0.2122,
+      "step": 39
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.18817118147299453,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.2438,
+      "step": 40
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.19072379614495816,
+      "learning_rate": 8.309658911297833e-06,
+      "loss": 0.2265,
+      "step": 41
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.17940514896497553,
+      "learning_rate": 8.231496189304704e-06,
+      "loss": 0.2249,
+      "step": 42
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.19570670262847478,
+      "learning_rate": 8.151953080639777e-06,
+      "loss": 0.226,
+      "step": 43
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.18787973982646042,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 0.2422,
+      "step": 44
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.18265168276531513,
+      "learning_rate": 7.988862191016204e-06,
+      "loss": 0.2219,
+      "step": 45
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.17321408855740025,
+      "learning_rate": 7.905384077009693e-06,
+      "loss": 0.2106,
+      "step": 46
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.1841414888369389,
+      "learning_rate": 7.820664880476257e-06,
+      "loss": 0.2096,
+      "step": 47
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.21724705554824444,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.2616,
+      "step": 48
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.1889926351887918,
+      "learning_rate": 7.647648511303545e-06,
+      "loss": 0.233,
+      "step": 49
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.1805527745124061,
+      "learning_rate": 7.559425245448006e-06,
+      "loss": 0.2236,
+      "step": 50
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.16697552604760169,
+      "learning_rate": 7.470108679062521e-06,
+      "loss": 0.2156,
+      "step": 51
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.1968382804037924,
+      "learning_rate": 7.379736965185369e-06,
+      "loss": 0.2309,
+      "step": 52
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.2010023531577106,
+      "learning_rate": 7.288348707578409e-06,
+      "loss": 0.2546,
+      "step": 53
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.2082061721394445,
+      "learning_rate": 7.195982944236853e-06,
+      "loss": 0.235,
+      "step": 54
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.1883455055928294,
+      "learning_rate": 7.102679130713538e-06,
+      "loss": 0.2372,
+      "step": 55
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.16705564777190354,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.2032,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.19440699657388982,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.2303,
+      "step": 57
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.20536126748343225,
+      "learning_rate": 6.817539852819149e-06,
+      "loss": 0.252,
+      "step": 58
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.18086703519295244,
+      "learning_rate": 6.720886151813194e-06,
+      "loss": 0.2084,
+      "step": 59
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.1894003099357131,
+      "learning_rate": 6.6234973460234184e-06,
+      "loss": 0.222,
+      "step": 60
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.1930381703943333,
+      "learning_rate": 6.525415036677745e-06,
+      "loss": 0.2428,
+      "step": 61
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.19247680963641886,
+      "learning_rate": 6.426681121245527e-06,
+      "loss": 0.2396,
+      "step": 62
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.2016055465560358,
+      "learning_rate": 6.327337775540362e-06,
+      "loss": 0.2284,
+      "step": 63
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.1891641296024966,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.2319,
+      "step": 64
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.1767726650948819,
+      "learning_rate": 6.126992780079032e-06,
+      "loss": 0.2178,
+      "step": 65
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.16731584594653343,
+      "learning_rate": 6.026076710978172e-06,
+      "loss": 0.2052,
+      "step": 66
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.17989020025454264,
+      "learning_rate": 5.924722336357793e-06,
+      "loss": 0.2169,
+      "step": 67
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.19303171381852505,
+      "learning_rate": 5.82297295140367e-06,
+      "loss": 0.2424,
+      "step": 68
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.19120387479893808,
+      "learning_rate": 5.720872020036734e-06,
+      "loss": 0.2378,
+      "step": 69
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.17614241487129237,
+      "learning_rate": 5.61846315634674e-06,
+      "loss": 0.234,
+      "step": 70
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.2083745124644529,
+      "learning_rate": 5.515790105961785e-06,
+      "loss": 0.2492,
+      "step": 71
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.18503711883072851,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 0.2212,
+      "step": 72
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.18221695993450496,
+      "learning_rate": 5.309826973142974e-06,
+      "loss": 0.23,
+      "step": 73
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.18616795574651362,
+      "learning_rate": 5.206624871244066e-06,
+      "loss": 0.2299,
+      "step": 74
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.19887474979537578,
+      "learning_rate": 5.103334506137773e-06,
+      "loss": 0.2431,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2028888733188661,
+      "learning_rate": 5e-06,
+      "loss": 0.2265,
+      "step": 76
+    },
+    {
+      "epoch": 1.013157894736842,
+      "grad_norm": 0.1772036957738317,
+      "learning_rate": 4.89666549386223e-06,
+      "loss": 0.2044,
+      "step": 77
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.20445789705976125,
+      "learning_rate": 4.793375128755934e-06,
+      "loss": 0.2153,
+      "step": 78
+    },
+    {
+      "epoch": 1.0394736842105263,
+      "grad_norm": 0.2065035670655954,
+      "learning_rate": 4.690173026857028e-06,
+      "loss": 0.2445,
+      "step": 79
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.17679194619251173,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 0.208,
+      "step": 80
+    },
+    {
+      "epoch": 1.0657894736842106,
+      "grad_norm": 0.21367509172855706,
+      "learning_rate": 4.4842098940382155e-06,
+      "loss": 0.2308,
+      "step": 81
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.1865805684084479,
+      "learning_rate": 4.381536843653262e-06,
+      "loss": 0.2316,
+      "step": 82
+    },
+    {
+      "epoch": 1.0921052631578947,
+      "grad_norm": 0.19084540950162612,
+      "learning_rate": 4.279127979963266e-06,
+      "loss": 0.2219,
+      "step": 83
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.18971592616718258,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 0.2181,
+      "step": 84
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.1722195300694031,
+      "learning_rate": 4.075277663642208e-06,
+      "loss": 0.1866,
+      "step": 85
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.19802241899691667,
+      "learning_rate": 3.973923289021829e-06,
+      "loss": 0.2293,
+      "step": 86
+    },
+    {
+      "epoch": 1.1447368421052633,
+      "grad_norm": 0.16971936119293682,
+      "learning_rate": 3.8730072199209705e-06,
+      "loss": 0.1958,
+      "step": 87
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.19422357983967678,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 0.2051,
+      "step": 88
+    },
+    {
+      "epoch": 1.1710526315789473,
+      "grad_norm": 0.1731731902696854,
+      "learning_rate": 3.67266222445964e-06,
+      "loss": 0.1952,
+      "step": 89
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.17491334297750008,
+      "learning_rate": 3.573318878754475e-06,
+      "loss": 0.2198,
+      "step": 90
+    },
+    {
+      "epoch": 1.1973684210526316,
+      "grad_norm": 0.19256087818042938,
+      "learning_rate": 3.4745849633222566e-06,
+      "loss": 0.2304,
+      "step": 91
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.1924515126133127,
+      "learning_rate": 3.3765026539765832e-06,
+      "loss": 0.2117,
+      "step": 92
+    },
+    {
+      "epoch": 1.2236842105263157,
+      "grad_norm": 0.1671372148489463,
+      "learning_rate": 3.2791138481868084e-06,
+      "loss": 0.2007,
+      "step": 93
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.2072760998746941,
+      "learning_rate": 3.1824601471808504e-06,
+      "loss": 0.2262,
+      "step": 94
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.1869772831162441,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.2145,
+      "step": 95
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.20152947251639636,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 0.2194,
+      "step": 96
+    },
+    {
+      "epoch": 1.2763157894736843,
+      "grad_norm": 0.21175841868224737,
+      "learning_rate": 2.8973208692864623e-06,
+      "loss": 0.2267,
+      "step": 97
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.18463388860657626,
+      "learning_rate": 2.804017055763149e-06,
+      "loss": 0.2035,
+      "step": 98
+    },
+    {
+      "epoch": 1.3026315789473684,
+      "grad_norm": 0.1766237400962105,
+      "learning_rate": 2.711651292421593e-06,
+      "loss": 0.1873,
+      "step": 99
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.2009834271125523,
+      "learning_rate": 2.6202630348146323e-06,
+      "loss": 0.2069,
+      "step": 100
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "eval_loss": 0.2266910970211029,
+      "eval_runtime": 1.6783,
+      "eval_samples_per_second": 14.896,
+      "eval_steps_per_second": 4.171,
+      "step": 100
+    },
+    {
+      "epoch": 1.3289473684210527,
+      "grad_norm": 0.19611551501685243,
+      "learning_rate": 2.529891320937481e-06,
+      "loss": 0.2283,
+      "step": 101
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.17539999298533723,
+      "learning_rate": 2.4405747545519966e-06,
+      "loss": 0.2123,
+      "step": 102
+    },
+    {
+      "epoch": 1.3552631578947367,
+      "grad_norm": 0.18578600699219228,
+      "learning_rate": 2.352351488696457e-06,
+      "loss": 0.2032,
+      "step": 103
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.18408216118265866,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 0.1993,
+      "step": 104
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.19278949641258977,
+      "learning_rate": 2.179335119523745e-06,
+      "loss": 0.2211,
+      "step": 105
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.18202842579887263,
+      "learning_rate": 2.094615922990309e-06,
+      "loss": 0.2021,
+      "step": 106
+    },
+    {
+      "epoch": 1.4078947368421053,
+      "grad_norm": 0.18828321168645237,
+      "learning_rate": 2.0111378089837958e-06,
+      "loss": 0.2065,
+      "step": 107
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.2033238708782755,
+      "learning_rate": 1.928936436551661e-06,
+      "loss": 0.2353,
+      "step": 108
+    },
+    {
+      "epoch": 1.4342105263157894,
+      "grad_norm": 0.19896448516655665,
+      "learning_rate": 1.848046919360225e-06,
+      "loss": 0.2104,
+      "step": 109
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.19024050330433492,
+      "learning_rate": 1.7685038106952952e-06,
+      "loss": 0.2167,
+      "step": 110
+    },
+    {
+      "epoch": 1.4605263157894737,
+      "grad_norm": 0.19767315142859695,
+      "learning_rate": 1.6903410887021676e-06,
+      "loss": 0.214,
+      "step": 111
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.18650867489311443,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 0.2269,
+      "step": 112
+    },
+    {
+      "epoch": 1.486842105263158,
+      "grad_norm": 0.1847901673638147,
+      "learning_rate": 1.5382897547758513e-06,
+      "loss": 0.2096,
+      "step": 113
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.1929865678422701,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.2051,
+      "step": 114
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 0.1893061145432117,
+      "learning_rate": 1.3921526947346902e-06,
+      "loss": 0.303,
+      "step": 115
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.19565544422379177,
+      "learning_rate": 1.321380446634342e-06,
+      "loss": 0.2089,
+      "step": 116
+    },
+    {
+      "epoch": 1.5394736842105263,
+      "grad_norm": 0.19309997871582435,
+      "learning_rate": 1.2521795812943704e-06,
+      "loss": 0.1929,
+      "step": 117
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.20712400250824642,
+      "learning_rate": 1.1845796590009684e-06,
+      "loss": 0.2217,
+      "step": 118
+    },
+    {
+      "epoch": 1.5657894736842106,
+      "grad_norm": 0.19309403172903913,
+      "learning_rate": 1.118609556171213e-06,
+      "loss": 0.2012,
+      "step": 119
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.18646267065745462,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 0.2394,
+      "step": 120
+    },
+    {
+      "epoch": 1.5921052631578947,
+      "grad_norm": 0.21328556653964198,
+      "learning_rate": 9.916708215125586e-07,
+      "loss": 0.2116,
+      "step": 121
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.21199157857336046,
+      "learning_rate": 9.307564136490255e-07,
+      "loss": 0.2175,
+      "step": 122
+    },
+    {
+      "epoch": 1.618421052631579,
+      "grad_norm": 0.18552781734639998,
+      "learning_rate": 8.715802500172215e-07,
+      "loss": 0.2224,
+      "step": 123
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.19673332097520063,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 0.2299,
+      "step": 124
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 0.1900324583086327,
+      "learning_rate": 7.585430144121319e-07,
+      "loss": 0.2037,
+      "step": 125
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.20475694825478188,
+      "learning_rate": 7.047302281505735e-07,
+      "loss": 0.2116,
+      "step": 126
+    },
+    {
+      "epoch": 1.6710526315789473,
+      "grad_norm": 0.1899195542415956,
+      "learning_rate": 6.527522369181655e-07,
+      "loss": 0.2149,
+      "step": 127
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.194430084575516,
+      "learning_rate": 6.026312439675553e-07,
+      "loss": 0.2107,
+      "step": 128
+    },
+    {
+      "epoch": 1.6973684210526314,
+      "grad_norm": 0.186271142690739,
+      "learning_rate": 5.543886593040737e-07,
+      "loss": 0.2159,
+      "step": 129
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.1855050805813639,
+      "learning_rate": 5.080450905401057e-07,
+      "loss": 0.2144,
+      "step": 130
+    },
+    {
+      "epoch": 1.723684210526316,
+      "grad_norm": 0.1987005667760386,
+      "learning_rate": 4.6362033409220077e-07,
+      "loss": 0.2155,
+      "step": 131
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.18124165191423836,
+      "learning_rate": 4.211333667247125e-07,
+      "loss": 0.2179,
+      "step": 132
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.18433138453657422,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.2092,
+      "step": 133
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.19664062065481905,
+      "learning_rate": 3.420445597436056e-07,
+      "loss": 0.2038,
+      "step": 134
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.195390235140428,
+      "learning_rate": 3.0547650421285216e-07,
+      "loss": 0.2173,
+      "step": 135
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.18830557902660156,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 0.2155,
+      "step": 136
+    },
+    {
+      "epoch": 1.8026315789473686,
+      "grad_norm": 0.1875393396866791,
+      "learning_rate": 2.3837118562592799e-07,
+      "loss": 0.2244,
+      "step": 137
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.19370733323617545,
+      "learning_rate": 2.0786258770873647e-07,
+      "loss": 0.2052,
+      "step": 138
+    },
+    {
+      "epoch": 1.8289473684210527,
+      "grad_norm": 0.19560289949097517,
+      "learning_rate": 1.7940102999393194e-07,
+      "loss": 0.2252,
+      "step": 139
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.18617005749507912,
+      "learning_rate": 1.5299867030334815e-07,
+      "loss": 0.2105,
+      "step": 140
+    },
+    {
+      "epoch": 1.8552631578947367,
+      "grad_norm": 0.19785196036612812,
+      "learning_rate": 1.286667868385627e-07,
+      "loss": 0.2156,
+      "step": 141
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.18693910478538694,
+      "learning_rate": 1.0641577336322761e-07,
+      "loss": 0.2131,
+      "step": 142
+    },
+    {
+      "epoch": 1.881578947368421,
+      "grad_norm": 0.17734017497146556,
+      "learning_rate": 8.625513476320291e-08,
+      "loss": 0.1935,
+      "step": 143
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.19687670178446698,
+      "learning_rate": 6.819348298638839e-08,
+      "loss": 0.2132,
+      "step": 144
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 0.19846013568780121,
+      "learning_rate": 5.223853336398632e-08,
+      "loss": 0.2395,
+      "step": 145
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.19081464024952235,
+      "learning_rate": 3.839710131477492e-08,
+      "loss": 0.225,
+      "step": 146
+    },
+    {
+      "epoch": 1.9342105263157894,
+      "grad_norm": 0.19381609894140142,
+      "learning_rate": 2.6675099433787212e-08,
+      "loss": 0.2159,
+      "step": 147
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.19241369346284165,
+      "learning_rate": 1.7077534966650767e-08,
+      "loss": 0.2128,
+      "step": 148
+    },
+    {
+      "epoch": 1.9605263157894737,
+      "grad_norm": 0.19542477441938874,
+      "learning_rate": 9.608507670659239e-09,
+      "loss": 0.2111,
+      "step": 149
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.17248983028035092,
+      "learning_rate": 4.2712080634949024e-09,
+      "loss": 0.1887,
+      "step": 150
+    },
+    {
+      "epoch": 1.986842105263158,
+      "grad_norm": 0.1915147138290703,
+      "learning_rate": 1.0679160603449533e-09,
+      "loss": 0.2216,
+      "step": 151
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1951250112430735,
+      "learning_rate": 0.0,
+      "loss": 0.2118,
+      "step": 152
+    },
+    {
+      "epoch": 2.0,
+      "step": 152,
+      "total_flos": 17263553937408.0,
+      "train_loss": 0.22410145088245995,
+      "train_runtime": 539.2177,
+      "train_samples_per_second": 8.969,
+      "train_steps_per_second": 0.282
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 152,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 3700000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 17263553937408.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c4c66bd39357545e6278fbef63197b40e6e921a0586a2235446e8b15d72908
+size 7160