Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,50 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+"/model.safetensors.index.json" filter=lfs diff=lfs merge=lfs -text
+"/tokenizer.json" filter=lfs diff=lfs merge=lfs -text
+"/trainer_state.json" filter=lfs diff=lfs merge=lfs -texttokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,60 @@
 ---
-license: apache-2.0
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3.5-27B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: CodeV-SVA-Qwen35-27B-0514
+  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. -->
+
+# CodeV-SVA-Qwen35-27B-0514
+
+This model is a fine-tuned version of [/share/collab/codemodel/models/Qwen35/Qwen3.5-27B](https://huggingface.co//share/collab/codemodel/models/Qwen35/Qwen3.5-27B) on the CodeV-SVA-dataset-83K-sva2wavedrom-qwen3p6-plus-diagram-wave2sva-self-verified-pass-training 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 16
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.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_steps: 20
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 8272973614022656.0,
+    "train_loss": 0.11627333357174825,
+    "train_runtime": 52247.9077,
+    "train_samples_per_second": 0.133,
+    "train_steps_per_second": 0.008
+}

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,146 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 5120,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.2.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff4344ad69a870b7ddc7ac78b1fbbc059f11694a413bfdbb6a110aaf8856348
+size 49825162976

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af137df23f6296a54236f9ded63e9f09fd486d7016fc5af09c295d36b3f762c7
+size 4888445168

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 8272973614022656.0,
+    "train_loss": 0.11627333357174825,
+    "train_runtime": 52247.9077,
+    "train_samples_per_second": 0.133,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,3081 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 434,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004608294930875576,
+      "grad_norm": 2.9351394176483154,
+      "learning_rate": 0.0,
+      "loss": 0.3643823266029358,
+      "step": 1
+    },
+    {
+      "epoch": 0.009216589861751152,
+      "grad_norm": 2.956498622894287,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.36728185415267944,
+      "step": 2
+    },
+    {
+      "epoch": 0.013824884792626729,
+      "grad_norm": 2.9857776165008545,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.36666208505630493,
+      "step": 3
+    },
+    {
+      "epoch": 0.018433179723502304,
+      "grad_norm": 2.0103087425231934,
+      "learning_rate": 3e-06,
+      "loss": 0.3373025059700012,
+      "step": 4
+    },
+    {
+      "epoch": 0.02304147465437788,
+      "grad_norm": 1.698964238166809,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3123781085014343,
+      "step": 5
+    },
+    {
+      "epoch": 0.027649769585253458,
+      "grad_norm": 3.207914113998413,
+      "learning_rate": 5e-06,
+      "loss": 0.3116934895515442,
+      "step": 6
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 1.510648250579834,
+      "learning_rate": 6e-06,
+      "loss": 0.2856190800666809,
+      "step": 7
+    },
+    {
+      "epoch": 0.03686635944700461,
+      "grad_norm": 1.6421589851379395,
+      "learning_rate": 7e-06,
+      "loss": 0.2982577681541443,
+      "step": 8
+    },
+    {
+      "epoch": 0.041474654377880185,
+      "grad_norm": 1.1661206483840942,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2779271602630615,
+      "step": 9
+    },
+    {
+      "epoch": 0.04608294930875576,
+      "grad_norm": 0.8330576419830322,
+      "learning_rate": 9e-06,
+      "loss": 0.24233558773994446,
+      "step": 10
+    },
+    {
+      "epoch": 0.05069124423963134,
+      "grad_norm": 0.7435799837112427,
+      "learning_rate": 1e-05,
+      "loss": 0.23245880007743835,
+      "step": 11
+    },
+    {
+      "epoch": 0.055299539170506916,
+      "grad_norm": 0.587920069694519,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.22002160549163818,
+      "step": 12
+    },
+    {
+      "epoch": 0.059907834101382486,
+      "grad_norm": 0.5773729085922241,
+      "learning_rate": 1.2e-05,
+      "loss": 0.2221677601337433,
+      "step": 13
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.586309015750885,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.22140836715698242,
+      "step": 14
+    },
+    {
+      "epoch": 0.06912442396313365,
+      "grad_norm": 1.6926223039627075,
+      "learning_rate": 1.4e-05,
+      "loss": 0.20500807464122772,
+      "step": 15
+    },
+    {
+      "epoch": 0.07373271889400922,
+      "grad_norm": 0.5535533428192139,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.22195743024349213,
+      "step": 16
+    },
+    {
+      "epoch": 0.07834101382488479,
+      "grad_norm": 0.5789612531661987,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.20433521270751953,
+      "step": 17
+    },
+    {
+      "epoch": 0.08294930875576037,
+      "grad_norm": 0.7237910628318787,
+      "learning_rate": 1.7e-05,
+      "loss": 0.2034861445426941,
+      "step": 18
+    },
+    {
+      "epoch": 0.08755760368663594,
+      "grad_norm": 0.6449386477470398,
+      "learning_rate": 1.8e-05,
+      "loss": 0.19543421268463135,
+      "step": 19
+    },
+    {
+      "epoch": 0.09216589861751152,
+      "grad_norm": 0.43145066499710083,
+      "learning_rate": 1.9e-05,
+      "loss": 0.1949930191040039,
+      "step": 20
+    },
+    {
+      "epoch": 0.0967741935483871,
+      "grad_norm": 0.4737650454044342,
+      "learning_rate": 2e-05,
+      "loss": 0.1823633462190628,
+      "step": 21
+    },
+    {
+      "epoch": 0.10138248847926268,
+      "grad_norm": 0.4388849139213562,
+      "learning_rate": 1.9999712083215465e-05,
+      "loss": 0.17654408514499664,
+      "step": 22
+    },
+    {
+      "epoch": 0.10599078341013825,
+      "grad_norm": 0.42295366525650024,
+      "learning_rate": 1.999884834944106e-05,
+      "loss": 0.1786973625421524,
+      "step": 23
+    },
+    {
+      "epoch": 0.11059907834101383,
+      "grad_norm": 0.39451926946640015,
+      "learning_rate": 1.9997408848413494e-05,
+      "loss": 0.1722813844680786,
+      "step": 24
+    },
+    {
+      "epoch": 0.1152073732718894,
+      "grad_norm": 0.39979177713394165,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.16947343945503235,
+      "step": 25
+    },
+    {
+      "epoch": 0.11981566820276497,
+      "grad_norm": 0.45815327763557434,
+      "learning_rate": 1.9992802909313882e-05,
+      "loss": 0.16465973854064941,
+      "step": 26
+    },
+    {
+      "epoch": 0.12442396313364056,
+      "grad_norm": 0.44379693269729614,
+      "learning_rate": 1.9989636736467278e-05,
+      "loss": 0.15591934323310852,
+      "step": 27
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 0.5225381255149841,
+      "learning_rate": 1.9985895326803096e-05,
+      "loss": 0.1638382226228714,
+      "step": 28
+    },
+    {
+      "epoch": 0.1336405529953917,
+      "grad_norm": 0.5012470483779907,
+      "learning_rate": 1.9981578895764272e-05,
+      "loss": 0.16397398710250854,
+      "step": 29
+    },
+    {
+      "epoch": 0.1382488479262673,
+      "grad_norm": 0.4178137183189392,
+      "learning_rate": 1.9976687691905394e-05,
+      "loss": 0.15988710522651672,
+      "step": 30
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.37227189540863037,
+      "learning_rate": 1.9971221996878395e-05,
+      "loss": 0.15102854371070862,
+      "step": 31
+    },
+    {
+      "epoch": 0.14746543778801843,
+      "grad_norm": 0.4815114736557007,
+      "learning_rate": 1.9965182125416344e-05,
+      "loss": 0.16124224662780762,
+      "step": 32
+    },
+    {
+      "epoch": 0.15207373271889402,
+      "grad_norm": 0.4177955985069275,
+      "learning_rate": 1.9958568425315316e-05,
+      "loss": 0.16134393215179443,
+      "step": 33
+    },
+    {
+      "epoch": 0.15668202764976957,
+      "grad_norm": 0.3633759915828705,
+      "learning_rate": 1.995138127741436e-05,
+      "loss": 0.15537649393081665,
+      "step": 34
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 0.3769278824329376,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.15368640422821045,
+      "step": 35
+    },
+    {
+      "epoch": 0.16589861751152074,
+      "grad_norm": 0.36959901452064514,
+      "learning_rate": 1.9935288326650314e-05,
+      "loss": 0.1593797206878662,
+      "step": 36
+    },
+    {
+      "epoch": 0.17050691244239632,
+      "grad_norm": 0.3599304258823395,
+      "learning_rate": 1.9926383450473344e-05,
+      "loss": 0.1527804285287857,
+      "step": 37
+    },
+    {
+      "epoch": 0.17511520737327188,
+      "grad_norm": 0.36388063430786133,
+      "learning_rate": 1.9916906979815345e-05,
+      "loss": 0.14666420221328735,
+      "step": 38
+    },
+    {
+      "epoch": 0.17972350230414746,
+      "grad_norm": 0.42649194598197937,
+      "learning_rate": 1.9906859460363307e-05,
+      "loss": 0.14440573751926422,
+      "step": 39
+    },
+    {
+      "epoch": 0.18433179723502305,
+      "grad_norm": 0.5980634689331055,
+      "learning_rate": 1.9896241470687132e-05,
+      "loss": 0.15595990419387817,
+      "step": 40
+    },
+    {
+      "epoch": 0.1889400921658986,
+      "grad_norm": 0.5153312087059021,
+      "learning_rate": 1.9885053622206305e-05,
+      "loss": 0.14992216229438782,
+      "step": 41
+    },
+    {
+      "epoch": 0.1935483870967742,
+      "grad_norm": 0.5538362264633179,
+      "learning_rate": 1.98732965591547e-05,
+      "loss": 0.15520179271697998,
+      "step": 42
+    },
+    {
+      "epoch": 0.19815668202764977,
+      "grad_norm": 0.5773318409919739,
+      "learning_rate": 1.986097095854347e-05,
+      "loss": 0.15027934312820435,
+      "step": 43
+    },
+    {
+      "epoch": 0.20276497695852536,
+      "grad_norm": 0.5059385895729065,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.1551799327135086,
+      "step": 44
+    },
+    {
+      "epoch": 0.2073732718894009,
+      "grad_norm": 0.3785911202430725,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.13947553932666779,
+      "step": 45
+    },
+    {
+      "epoch": 0.2119815668202765,
+      "grad_norm": 0.3560560643672943,
+      "learning_rate": 1.982059019229106e-05,
+      "loss": 0.1380046308040619,
+      "step": 46
+    },
+    {
+      "epoch": 0.21658986175115208,
+      "grad_norm": 0.45262575149536133,
+      "learning_rate": 1.9805997865694616e-05,
+      "loss": 0.13550859689712524,
+      "step": 47
+    },
+    {
+      "epoch": 0.22119815668202766,
+      "grad_norm": 0.5065012574195862,
+      "learning_rate": 1.979084087682323e-05,
+      "loss": 0.13587568700313568,
+      "step": 48
+    },
+    {
+      "epoch": 0.22580645161290322,
+      "grad_norm": 0.4492853581905365,
+      "learning_rate": 1.9775120098467212e-05,
+      "loss": 0.13608525693416595,
+      "step": 49
+    },
+    {
+      "epoch": 0.2304147465437788,
+      "grad_norm": 0.3212682008743286,
+      "learning_rate": 1.9758836435881745e-05,
+      "loss": 0.13411258161067963,
+      "step": 50
+    },
+    {
+      "epoch": 0.2350230414746544,
+      "grad_norm": 0.34821808338165283,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 0.14918532967567444,
+      "step": 51
+    },
+    {
+      "epoch": 0.23963133640552994,
+      "grad_norm": 0.3524312674999237,
+      "learning_rate": 1.972458424105307e-05,
+      "loss": 0.14321666955947876,
+      "step": 52
+    },
+    {
+      "epoch": 0.24423963133640553,
+      "grad_norm": 0.35644447803497314,
+      "learning_rate": 1.970661768116622e-05,
+      "loss": 0.13105669617652893,
+      "step": 53
+    },
+    {
+      "epoch": 0.2488479262672811,
+      "grad_norm": 0.3896118104457855,
+      "learning_rate": 1.9688092181649065e-05,
+      "loss": 0.13789072632789612,
+      "step": 54
+    },
+    {
+      "epoch": 0.2534562211981567,
+      "grad_norm": 0.42081373929977417,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.1357068419456482,
+      "step": 55
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.4559233486652374,
+      "learning_rate": 1.9649368662889852e-05,
+      "loss": 0.14027000963687897,
+      "step": 56
+    },
+    {
+      "epoch": 0.2626728110599078,
+      "grad_norm": 0.5480946898460388,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.13783793151378632,
+      "step": 57
+    },
+    {
+      "epoch": 0.2672811059907834,
+      "grad_norm": 0.5062631368637085,
+      "learning_rate": 1.9608422603967838e-05,
+      "loss": 0.14237134158611298,
+      "step": 58
+    },
+    {
+      "epoch": 0.271889400921659,
+      "grad_norm": 0.3334342837333679,
+      "learning_rate": 1.9587119049229558e-05,
+      "loss": 0.13876594603061676,
+      "step": 59
+    },
+    {
+      "epoch": 0.2764976958525346,
+      "grad_norm": 0.40752753615379333,
+      "learning_rate": 1.956526343599335e-05,
+      "loss": 0.1354307234287262,
+      "step": 60
+    },
+    {
+      "epoch": 0.28110599078341014,
+      "grad_norm": 0.500220000743866,
+      "learning_rate": 1.954285702277879e-05,
+      "loss": 0.13486963510513306,
+      "step": 61
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.4262498915195465,
+      "learning_rate": 1.951990109982237e-05,
+      "loss": 0.13686300814151764,
+      "step": 62
+    },
+    {
+      "epoch": 0.2903225806451613,
+      "grad_norm": 0.36057838797569275,
+      "learning_rate": 1.9496396989003195e-05,
+      "loss": 0.13742214441299438,
+      "step": 63
+    },
+    {
+      "epoch": 0.29493087557603687,
+      "grad_norm": 0.40592584013938904,
+      "learning_rate": 1.9472346043766866e-05,
+      "loss": 0.13356278836727142,
+      "step": 64
+    },
+    {
+      "epoch": 0.2995391705069124,
+      "grad_norm": 0.34159040451049805,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.13205787539482117,
+      "step": 65
+    },
+    {
+      "epoch": 0.30414746543778803,
+      "grad_norm": 0.34089890122413635,
+      "learning_rate": 1.9422609221188208e-05,
+      "loss": 0.13181942701339722,
+      "step": 66
+    },
+    {
+      "epoch": 0.3087557603686636,
+      "grad_norm": 0.38329455256462097,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.1307462751865387,
+      "step": 67
+    },
+    {
+      "epoch": 0.31336405529953915,
+      "grad_norm": 0.3729923665523529,
+      "learning_rate": 1.9370702087974302e-05,
+      "loss": 0.13535529375076294,
+      "step": 68
+    },
+    {
+      "epoch": 0.31797235023041476,
+      "grad_norm": 0.5034921169281006,
+      "learning_rate": 1.9343938371606714e-05,
+      "loss": 0.14689871668815613,
+      "step": 69
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.41111183166503906,
+      "learning_rate": 1.9316636599900947e-05,
+      "loss": 0.1370428502559662,
+      "step": 70
+    },
+    {
+      "epoch": 0.3271889400921659,
+      "grad_norm": 0.5101066827774048,
+      "learning_rate": 1.9288798344984673e-05,
+      "loss": 0.133246049284935,
+      "step": 71
+    },
+    {
+      "epoch": 0.3317972350230415,
+      "grad_norm": 0.4900591969490051,
+      "learning_rate": 1.9260425209878052e-05,
+      "loss": 0.14536210894584656,
+      "step": 72
+    },
+    {
+      "epoch": 0.33640552995391704,
+      "grad_norm": 0.4653155207633972,
+      "learning_rate": 1.9231518828401458e-05,
+      "loss": 0.13604950904846191,
+      "step": 73
+    },
+    {
+      "epoch": 0.34101382488479265,
+      "grad_norm": 0.3915235698223114,
+      "learning_rate": 1.920208086508137e-05,
+      "loss": 0.1396430879831314,
+      "step": 74
+    },
+    {
+      "epoch": 0.3456221198156682,
+      "grad_norm": 0.4426057040691376,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.15467746555805206,
+      "step": 75
+    },
+    {
+      "epoch": 0.35023041474654376,
+      "grad_norm": 0.43072596192359924,
+      "learning_rate": 1.914161700397035e-05,
+      "loss": 0.14150166511535645,
+      "step": 76
+    },
+    {
+      "epoch": 0.3548387096774194,
+      "grad_norm": 0.36459630727767944,
+      "learning_rate": 1.911059458789152e-05,
+      "loss": 0.14096513390541077,
+      "step": 77
+    },
+    {
+      "epoch": 0.35944700460829493,
+      "grad_norm": 0.4354130029678345,
+      "learning_rate": 1.907904755319289e-05,
+      "loss": 0.15007267892360687,
+      "step": 78
+    },
+    {
+      "epoch": 0.3640552995391705,
+      "grad_norm": 0.46055835485458374,
+      "learning_rate": 1.9046977716458627e-05,
+      "loss": 0.12661416828632355,
+      "step": 79
+    },
+    {
+      "epoch": 0.3686635944700461,
+      "grad_norm": 0.398175984621048,
+      "learning_rate": 1.9014386924377583e-05,
+      "loss": 0.13772934675216675,
+      "step": 80
+    },
+    {
+      "epoch": 0.37327188940092165,
+      "grad_norm": 0.41015535593032837,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 0.13147950172424316,
+      "step": 81
+    },
+    {
+      "epoch": 0.3778801843317972,
+      "grad_norm": 0.36940819025039673,
+      "learning_rate": 1.894765001081428e-05,
+      "loss": 0.13016274571418762,
+      "step": 82
+    },
+    {
+      "epoch": 0.3824884792626728,
+      "grad_norm": 0.4152197539806366,
+      "learning_rate": 1.891350773226754e-05,
+      "loss": 0.11954741179943085,
+      "step": 83
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.40267708897590637,
+      "learning_rate": 1.8878852184023754e-05,
+      "loss": 0.1356607973575592,
+      "step": 84
+    },
+    {
+      "epoch": 0.391705069124424,
+      "grad_norm": 0.43129563331604004,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.14090541005134583,
+      "step": 85
+    },
+    {
+      "epoch": 0.39631336405529954,
+      "grad_norm": 0.38757261633872986,
+      "learning_rate": 1.880800929021714e-05,
+      "loss": 0.1370600312948227,
+      "step": 86
+    },
+    {
+      "epoch": 0.4009216589861751,
+      "grad_norm": 0.3337249457836151,
+      "learning_rate": 1.8771826024025944e-05,
+      "loss": 0.1393272876739502,
+      "step": 87
+    },
+    {
+      "epoch": 0.4055299539170507,
+      "grad_norm": 0.344142884016037,
+      "learning_rate": 1.8735137646646078e-05,
+      "loss": 0.1326616406440735,
+      "step": 88
+    },
+    {
+      "epoch": 0.41013824884792627,
+      "grad_norm": 0.39954492449760437,
+      "learning_rate": 1.8697946270717468e-05,
+      "loss": 0.14050787687301636,
+      "step": 89
+    },
+    {
+      "epoch": 0.4147465437788018,
+      "grad_norm": 0.38469022512435913,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.14494386315345764,
+      "step": 90
+    },
+    {
+      "epoch": 0.41935483870967744,
+      "grad_norm": 0.3960438072681427,
+      "learning_rate": 1.8622063118472135e-05,
+      "loss": 0.12236207723617554,
+      "step": 91
+    },
+    {
+      "epoch": 0.423963133640553,
+      "grad_norm": 0.4286985397338867,
+      "learning_rate": 1.8583375711762054e-05,
+      "loss": 0.12544140219688416,
+      "step": 92
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.4457886219024658,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.13143101334571838,
+      "step": 93
+    },
+    {
+      "epoch": 0.43317972350230416,
+      "grad_norm": 0.4472925066947937,
+      "learning_rate": 1.8504520375792513e-05,
+      "loss": 0.11987829953432083,
+      "step": 94
+    },
+    {
+      "epoch": 0.4377880184331797,
+      "grad_norm": 0.4346664547920227,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.13675761222839355,
+      "step": 95
+    },
+    {
+      "epoch": 0.4423963133640553,
+      "grad_norm": 0.34448540210723877,
+      "learning_rate": 1.8423706192694118e-05,
+      "loss": 0.13568980991840363,
+      "step": 96
+    },
+    {
+      "epoch": 0.4470046082949309,
+      "grad_norm": 0.3212863802909851,
+      "learning_rate": 1.8382570332820045e-05,
+      "loss": 0.1283653825521469,
+      "step": 97
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 0.3854091763496399,
+      "learning_rate": 1.8340951776406695e-05,
+      "loss": 0.12247439473867416,
+      "step": 98
+    },
+    {
+      "epoch": 0.45622119815668205,
+      "grad_norm": 0.3354380428791046,
+      "learning_rate": 1.8298852919990254e-05,
+      "loss": 0.13746307790279388,
+      "step": 99
+    },
+    {
+      "epoch": 0.4608294930875576,
+      "grad_norm": 0.3076857924461365,
+      "learning_rate": 1.8256276187764197e-05,
+      "loss": 0.1372300535440445,
+      "step": 100
+    },
+    {
+      "epoch": 0.46543778801843316,
+      "grad_norm": 0.31850385665893555,
+      "learning_rate": 1.821322403143969e-05,
+      "loss": 0.13008606433868408,
+      "step": 101
+    },
+    {
+      "epoch": 0.4700460829493088,
+      "grad_norm": 0.3917572498321533,
+      "learning_rate": 1.816969893010442e-05,
+      "loss": 0.11819791793823242,
+      "step": 102
+    },
+    {
+      "epoch": 0.47465437788018433,
+      "grad_norm": 0.39096271991729736,
+      "learning_rate": 1.812570339007983e-05,
+      "loss": 0.12205740809440613,
+      "step": 103
+    },
+    {
+      "epoch": 0.4792626728110599,
+      "grad_norm": 0.36574921011924744,
+      "learning_rate": 1.8081239944776804e-05,
+      "loss": 0.1411409229040146,
+      "step": 104
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.37956228852272034,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.1255335807800293,
+      "step": 105
+    },
+    {
+      "epoch": 0.48847926267281105,
+      "grad_norm": 0.3160751461982727,
+      "learning_rate": 1.799091960654933e-05,
+      "loss": 0.12759719789028168,
+      "step": 106
+    },
+    {
+      "epoch": 0.4930875576036866,
+      "grad_norm": 0.3458094298839569,
+      "learning_rate": 1.7945067914573147e-05,
+      "loss": 0.12482710182666779,
+      "step": 107
+    },
+    {
+      "epoch": 0.4976958525345622,
+      "grad_norm": 0.3967854380607605,
+      "learning_rate": 1.789875871891559e-05,
+      "loss": 0.12500208616256714,
+      "step": 108
+    },
+    {
+      "epoch": 0.5023041474654378,
+      "grad_norm": 0.5233955979347229,
+      "learning_rate": 1.7851994686215592e-05,
+      "loss": 0.12323619425296783,
+      "step": 109
+    },
+    {
+      "epoch": 0.5069124423963134,
+      "grad_norm": 0.6709848046302795,
+      "learning_rate": 1.7804778509303136e-05,
+      "loss": 0.13066941499710083,
+      "step": 110
+    },
+    {
+      "epoch": 0.511520737327189,
+      "grad_norm": 0.5507707595825195,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 0.13311028480529785,
+      "step": 111
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.3101849853992462,
+      "learning_rate": 1.7709000624184162e-05,
+      "loss": 0.13673058152198792,
+      "step": 112
+    },
+    {
+      "epoch": 0.5207373271889401,
+      "grad_norm": 0.4039308428764343,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.14140118658542633,
+      "step": 113
+    },
+    {
+      "epoch": 0.5253456221198156,
+      "grad_norm": 0.344824880361557,
+      "learning_rate": 1.761144712408965e-05,
+      "loss": 0.12712520360946655,
+      "step": 114
+    },
+    {
+      "epoch": 0.5299539170506913,
+      "grad_norm": 0.34529098868370056,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.12384551018476486,
+      "step": 115
+    },
+    {
+      "epoch": 0.5345622119815668,
+      "grad_norm": 0.3672998249530792,
+      "learning_rate": 1.7512140478528178e-05,
+      "loss": 0.12366469204425812,
+      "step": 116
+    },
+    {
+      "epoch": 0.5391705069124424,
+      "grad_norm": 0.3039851188659668,
+      "learning_rate": 1.7461836858476858e-05,
+      "loss": 0.1345321238040924,
+      "step": 117
+    },
+    {
+      "epoch": 0.543778801843318,
+      "grad_norm": 0.3157755136489868,
+      "learning_rate": 1.7411103560810528e-05,
+      "loss": 0.1206519603729248,
+      "step": 118
+    },
+    {
+      "epoch": 0.5483870967741935,
+      "grad_norm": 0.33843550086021423,
+      "learning_rate": 1.7359943506922775e-05,
+      "loss": 0.1329212188720703,
+      "step": 119
+    },
+    {
+      "epoch": 0.5529953917050692,
+      "grad_norm": 0.28601428866386414,
+      "learning_rate": 1.730835964278124e-05,
+      "loss": 0.13256123661994934,
+      "step": 120
+    },
+    {
+      "epoch": 0.5576036866359447,
+      "grad_norm": 0.34340178966522217,
+      "learning_rate": 1.725635493875799e-05,
+      "loss": 0.12756165862083435,
+      "step": 121
+    },
+    {
+      "epoch": 0.5622119815668203,
+      "grad_norm": 0.39137405157089233,
+      "learning_rate": 1.7203932389458455e-05,
+      "loss": 0.12404625862836838,
+      "step": 122
+    },
+    {
+      "epoch": 0.5668202764976958,
+      "grad_norm": 0.44808390736579895,
+      "learning_rate": 1.7151095013548996e-05,
+      "loss": 0.12193070352077484,
+      "step": 123
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.46732231974601746,
+      "learning_rate": 1.709784585358309e-05,
+      "loss": 0.12517115473747253,
+      "step": 124
+    },
+    {
+      "epoch": 0.576036866359447,
+      "grad_norm": 0.37003666162490845,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.12209256738424301,
+      "step": 125
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 0.30708032846450806,
+      "learning_rate": 1.699012447007882e-05,
+      "loss": 0.12052929401397705,
+      "step": 126
+    },
+    {
+      "epoch": 0.5852534562211982,
+      "grad_norm": 0.34940996766090393,
+      "learning_rate": 1.693565844949933e-05,
+      "loss": 0.14009058475494385,
+      "step": 127
+    },
+    {
+      "epoch": 0.5898617511520737,
+      "grad_norm": 0.3044739067554474,
+      "learning_rate": 1.6880793050423953e-05,
+      "loss": 0.12717577815055847,
+      "step": 128
+    },
+    {
+      "epoch": 0.5944700460829493,
+      "grad_norm": 0.3132873475551605,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.12005665153265,
+      "step": 129
+    },
+    {
+      "epoch": 0.5990783410138248,
+      "grad_norm": 0.3148765563964844,
+      "learning_rate": 1.676987677693659e-05,
+      "loss": 0.11734700202941895,
+      "step": 130
+    },
+    {
+      "epoch": 0.6036866359447005,
+      "grad_norm": 0.2969941794872284,
+      "learning_rate": 1.671383228945597e-05,
+      "loss": 0.12221560627222061,
+      "step": 131
+    },
+    {
+      "epoch": 0.6082949308755761,
+      "grad_norm": 0.3063923120498657,
+      "learning_rate": 1.6657401196974405e-05,
+      "loss": 0.12006539851427078,
+      "step": 132
+    },
+    {
+      "epoch": 0.6129032258064516,
+      "grad_norm": 0.290458619594574,
+      "learning_rate": 1.6600586748983642e-05,
+      "loss": 0.13108855485916138,
+      "step": 133
+    },
+    {
+      "epoch": 0.6175115207373272,
+      "grad_norm": 0.2822469472885132,
+      "learning_rate": 1.6543392217050312e-05,
+      "loss": 0.12260163575410843,
+      "step": 134
+    },
+    {
+      "epoch": 0.6221198156682027,
+      "grad_norm": 0.31539443135261536,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.12802976369857788,
+      "step": 135
+    },
+    {
+      "epoch": 0.6267281105990783,
+      "grad_norm": 0.3589138984680176,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.11897952854633331,
+      "step": 136
+    },
+    {
+      "epoch": 0.631336405529954,
+      "grad_norm": 0.3790629506111145,
+      "learning_rate": 1.6369561160419783e-05,
+      "loss": 0.12253138422966003,
+      "step": 137
+    },
+    {
+      "epoch": 0.6359447004608295,
+      "grad_norm": 0.40670883655548096,
+      "learning_rate": 1.631087944326053e-05,
+      "loss": 0.11924054473638535,
+      "step": 138
+    },
+    {
+      "epoch": 0.6405529953917051,
+      "grad_norm": 0.3927200138568878,
+      "learning_rate": 1.625183432447789e-05,
+      "loss": 0.1266944706439972,
+      "step": 139
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.32968732714653015,
+      "learning_rate": 1.6192429204088022e-05,
+      "loss": 0.128749817609787,
+      "step": 140
+    },
+    {
+      "epoch": 0.6497695852534562,
+      "grad_norm": 0.3456534445285797,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 0.12518471479415894,
+      "step": 141
+    },
+    {
+      "epoch": 0.6543778801843319,
+      "grad_norm": 0.31864339113235474,
+      "learning_rate": 1.6072552662004696e-05,
+      "loss": 0.1392117142677307,
+      "step": 142
+    },
+    {
+      "epoch": 0.6589861751152074,
+      "grad_norm": 0.3624156415462494,
+      "learning_rate": 1.6012088143204953e-05,
+      "loss": 0.12307983636856079,
+      "step": 143
+    },
+    {
+      "epoch": 0.663594470046083,
+      "grad_norm": 0.45627498626708984,
+      "learning_rate": 1.59512774281879e-05,
+      "loss": 0.12169663608074188,
+      "step": 144
+    },
+    {
+      "epoch": 0.6682027649769585,
+      "grad_norm": 0.39884474873542786,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.11550907790660858,
+      "step": 145
+    },
+    {
+      "epoch": 0.6728110599078341,
+      "grad_norm": 0.34961551427841187,
+      "learning_rate": 1.5828631435975784e-05,
+      "loss": 0.11340060830116272,
+      "step": 146
+    },
+    {
+      "epoch": 0.6774193548387096,
+      "grad_norm": 0.35737621784210205,
+      "learning_rate": 1.5766803221148676e-05,
+      "loss": 0.12644968926906586,
+      "step": 147
+    },
+    {
+      "epoch": 0.6820276497695853,
+      "grad_norm": 0.3347710371017456,
+      "learning_rate": 1.570464293443346e-05,
+      "loss": 0.12000186741352081,
+      "step": 148
+    },
+    {
+      "epoch": 0.6866359447004609,
+      "grad_norm": 0.3257794678211212,
+      "learning_rate": 1.5642154155228124e-05,
+      "loss": 0.12667909264564514,
+      "step": 149
+    },
+    {
+      "epoch": 0.6912442396313364,
+      "grad_norm": 0.3128432631492615,
+      "learning_rate": 1.5579340481846338e-05,
+      "loss": 0.12329016625881195,
+      "step": 150
+    },
+    {
+      "epoch": 0.695852534562212,
+      "grad_norm": 0.36095401644706726,
+      "learning_rate": 1.5516205531310272e-05,
+      "loss": 0.11458329856395721,
+      "step": 151
+    },
+    {
+      "epoch": 0.7004608294930875,
+      "grad_norm": 0.3028973340988159,
+      "learning_rate": 1.545275293914233e-05,
+      "loss": 0.13286074995994568,
+      "step": 152
+    },
+    {
+      "epoch": 0.7050691244239631,
+      "grad_norm": 0.29518672823905945,
+      "learning_rate": 1.538898635915576e-05,
+      "loss": 0.12031916528940201,
+      "step": 153
+    },
+    {
+      "epoch": 0.7096774193548387,
+      "grad_norm": 0.33568844199180603,
+      "learning_rate": 1.53249094632443e-05,
+      "loss": 0.11565984040498734,
+      "step": 154
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.2777860462665558,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.12592938542366028,
+      "step": 155
+    },
+    {
+      "epoch": 0.7188940092165899,
+      "grad_norm": 0.3075020909309387,
+      "learning_rate": 1.5195839500354337e-05,
+      "loss": 0.11593696475028992,
+      "step": 156
+    },
+    {
+      "epoch": 0.7235023041474654,
+      "grad_norm": 0.2833383083343506,
+      "learning_rate": 1.513085386565758e-05,
+      "loss": 0.12151987850666046,
+      "step": 157
+    },
+    {
+      "epoch": 0.728110599078341,
+      "grad_norm": 0.5463114380836487,
+      "learning_rate": 1.506557277917143e-05,
+      "loss": 0.11416973173618317,
+      "step": 158
+    },
+    {
+      "epoch": 0.7327188940092166,
+      "grad_norm": 0.27526748180389404,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.12324878573417664,
+      "step": 159
+    },
+    {
+      "epoch": 0.7373271889400922,
+      "grad_norm": 0.3260738253593445,
+      "learning_rate": 1.4934139304044033e-05,
+      "loss": 0.12444890290498734,
+      "step": 160
+    },
+    {
+      "epoch": 0.7419354838709677,
+      "grad_norm": 0.309612900018692,
+      "learning_rate": 1.4867994483783485e-05,
+      "loss": 0.11911383271217346,
+      "step": 161
+    },
+    {
+      "epoch": 0.7465437788018433,
+      "grad_norm": 0.30645155906677246,
+      "learning_rate": 1.4801569348059158e-05,
+      "loss": 0.11389834433794022,
+      "step": 162
+    },
+    {
+      "epoch": 0.7511520737327189,
+      "grad_norm": 0.38062015175819397,
+      "learning_rate": 1.4734867721853341e-05,
+      "loss": 0.11368335783481598,
+      "step": 163
+    },
+    {
+      "epoch": 0.7557603686635944,
+      "grad_norm": 0.38081395626068115,
+      "learning_rate": 1.4667893446069588e-05,
+      "loss": 0.13980308175086975,
+      "step": 164
+    },
+    {
+      "epoch": 0.7603686635944701,
+      "grad_norm": 0.317385733127594,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.11198699474334717,
+      "step": 165
+    },
+    {
+      "epoch": 0.7649769585253456,
+      "grad_norm": 0.4344049096107483,
+      "learning_rate": 1.4533142387660774e-05,
+      "loss": 0.11324157565832138,
+      "step": 166
+    },
+    {
+      "epoch": 0.7695852534562212,
+      "grad_norm": 0.44433102011680603,
+      "learning_rate": 1.4465373364454001e-05,
+      "loss": 0.11948652565479279,
+      "step": 167
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.42917829751968384,
+      "learning_rate": 1.4397347210059059e-05,
+      "loss": 0.11280357837677002,
+      "step": 168
+    },
+    {
+      "epoch": 0.7788018433179723,
+      "grad_norm": 0.3815264403820038,
+      "learning_rate": 1.4329067841650274e-05,
+      "loss": 0.12808123230934143,
+      "step": 169
+    },
+    {
+      "epoch": 0.783410138248848,
+      "grad_norm": 0.3222845494747162,
+      "learning_rate": 1.4260539190982885e-05,
+      "loss": 0.136204332113266,
+      "step": 170
+    },
+    {
+      "epoch": 0.7880184331797235,
+      "grad_norm": 0.331464946269989,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 0.11928999423980713,
+      "step": 171
+    },
+    {
+      "epoch": 0.7926267281105991,
+      "grad_norm": 0.3539966344833374,
+      "learning_rate": 1.4122749841438576e-05,
+      "loss": 0.12157104909420013,
+      "step": 172
+    },
+    {
+      "epoch": 0.7972350230414746,
+      "grad_norm": 0.33615821599960327,
+      "learning_rate": 1.4053497076934948e-05,
+      "loss": 0.11312949657440186,
+      "step": 173
+    },
+    {
+      "epoch": 0.8018433179723502,
+      "grad_norm": 0.3435479402542114,
+      "learning_rate": 1.3984010898462417e-05,
+      "loss": 0.11193887889385223,
+      "step": 174
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.37916669249534607,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.11309465020895004,
+      "step": 175
+    },
+    {
+      "epoch": 0.8110599078341014,
+      "grad_norm": 0.3692195415496826,
+      "learning_rate": 1.3844354317810651e-05,
+      "loss": 0.12078887224197388,
+      "step": 176
+    },
+    {
+      "epoch": 0.815668202764977,
+      "grad_norm": 0.328268438577652,
+      "learning_rate": 1.3774191957526144e-05,
+      "loss": 0.12565036118030548,
+      "step": 177
+    },
+    {
+      "epoch": 0.8202764976958525,
+      "grad_norm": 0.3040667176246643,
+      "learning_rate": 1.3703812266599113e-05,
+      "loss": 0.10917656123638153,
+      "step": 178
+    },
+    {
+      "epoch": 0.8248847926267281,
+      "grad_norm": 0.40089869499206543,
+      "learning_rate": 1.3633219297728415e-05,
+      "loss": 0.11297084391117096,
+      "step": 179
+    },
+    {
+      "epoch": 0.8294930875576036,
+      "grad_norm": 0.43245014548301697,
+      "learning_rate": 1.356241711589417e-05,
+      "loss": 0.11502915620803833,
+      "step": 180
+    },
+    {
+      "epoch": 0.8341013824884793,
+      "grad_norm": 0.30540385842323303,
+      "learning_rate": 1.3491409798123687e-05,
+      "loss": 0.11241072416305542,
+      "step": 181
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 0.3104119300842285,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.10899341106414795,
+      "step": 182
+    },
+    {
+      "epoch": 0.8433179723502304,
+      "grad_norm": 0.3916040360927582,
+      "learning_rate": 1.3348796121709862e-05,
+      "loss": 0.11369147896766663,
+      "step": 183
+    },
+    {
+      "epoch": 0.847926267281106,
+      "grad_norm": 0.34039434790611267,
+      "learning_rate": 1.327719797524075e-05,
+      "loss": 0.1186954453587532,
+      "step": 184
+    },
+    {
+      "epoch": 0.8525345622119815,
+      "grad_norm": 0.25693196058273315,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.11873431503772736,
+      "step": 185
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.3686501383781433,
+      "learning_rate": 1.3133439679848824e-05,
+      "loss": 0.11316344141960144,
+      "step": 186
+    },
+    {
+      "epoch": 0.8617511520737328,
+      "grad_norm": 0.364483505487442,
+      "learning_rate": 1.3061287809011243e-05,
+      "loss": 0.12383511662483215,
+      "step": 187
+    },
+    {
+      "epoch": 0.8663594470046083,
+      "grad_norm": 0.3034912049770355,
+      "learning_rate": 1.298895965894516e-05,
+      "loss": 0.11857898533344269,
+      "step": 188
+    },
+    {
+      "epoch": 0.8709677419354839,
+      "grad_norm": 0.38670575618743896,
+      "learning_rate": 1.291645939454825e-05,
+      "loss": 0.110545814037323,
+      "step": 189
+    },
+    {
+      "epoch": 0.8755760368663594,
+      "grad_norm": 0.38622674345970154,
+      "learning_rate": 1.284379119062912e-05,
+      "loss": 0.11333891749382019,
+      "step": 190
+    },
+    {
+      "epoch": 0.880184331797235,
+      "grad_norm": 0.31381964683532715,
+      "learning_rate": 1.277095923166689e-05,
+      "loss": 0.11935151368379593,
+      "step": 191
+    },
+    {
+      "epoch": 0.8847926267281107,
+      "grad_norm": 0.32418185472488403,
+      "learning_rate": 1.2697967711570243e-05,
+      "loss": 0.117543064057827,
+      "step": 192
+    },
+    {
+      "epoch": 0.8894009216589862,
+      "grad_norm": 0.34491288661956787,
+      "learning_rate": 1.2624820833435939e-05,
+      "loss": 0.11400233954191208,
+      "step": 193
+    },
+    {
+      "epoch": 0.8940092165898618,
+      "grad_norm": 0.30702248215675354,
+      "learning_rate": 1.2551522809306762e-05,
+      "loss": 0.12614262104034424,
+      "step": 194
+    },
+    {
+      "epoch": 0.8986175115207373,
+      "grad_norm": 0.36233437061309814,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.10664090514183044,
+      "step": 195
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.33313071727752686,
+      "learning_rate": 1.2404490214509385e-05,
+      "loss": 0.12070563435554504,
+      "step": 196
+    },
+    {
+      "epoch": 0.9078341013824884,
+      "grad_norm": 0.2781200706958771,
+      "learning_rate": 1.2330764110471567e-05,
+      "loss": 0.12466859817504883,
+      "step": 197
+    },
+    {
+      "epoch": 0.9124423963133641,
+      "grad_norm": 0.32415518164634705,
+      "learning_rate": 1.2256903793212107e-05,
+      "loss": 0.11295566707849503,
+      "step": 198
+    },
+    {
+      "epoch": 0.9170506912442397,
+      "grad_norm": 0.3215178847312927,
+      "learning_rate": 1.2182913515856016e-05,
+      "loss": 0.12131574004888535,
+      "step": 199
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "grad_norm": 0.2978585362434387,
+      "learning_rate": 1.2108797539011847e-05,
+      "loss": 0.10748541355133057,
+      "step": 200
+    },
+    {
+      "epoch": 0.9262672811059908,
+      "grad_norm": 0.3606584370136261,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.12428630888462067,
+      "step": 201
+    },
+    {
+      "epoch": 0.9308755760368663,
+      "grad_norm": 0.2697555720806122,
+      "learning_rate": 1.1960205565238685e-05,
+      "loss": 0.12559658288955688,
+      "step": 202
+    },
+    {
+      "epoch": 0.9354838709677419,
+      "grad_norm": 0.38737574219703674,
+      "learning_rate": 1.1885738124734359e-05,
+      "loss": 0.12258967757225037,
+      "step": 203
+    },
+    {
+      "epoch": 0.9400921658986175,
+      "grad_norm": 0.2708435654640198,
+      "learning_rate": 1.1811162097098559e-05,
+      "loss": 0.12762704491615295,
+      "step": 204
+    },
+    {
+      "epoch": 0.9447004608294931,
+      "grad_norm": 0.3107895255088806,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.11194954812526703,
+      "step": 205
+    },
+    {
+      "epoch": 0.9493087557603687,
+      "grad_norm": 0.3069012463092804,
+      "learning_rate": 1.1661701463790142e-05,
+      "loss": 0.11807015538215637,
+      "step": 206
+    },
+    {
+      "epoch": 0.9539170506912442,
+      "grad_norm": 0.2611013352870941,
+      "learning_rate": 1.1586825464562515e-05,
+      "loss": 0.12420734018087387,
+      "step": 207
+    },
+    {
+      "epoch": 0.9585253456221198,
+      "grad_norm": 0.3179932236671448,
+      "learning_rate": 1.151185809059781e-05,
+      "loss": 0.11962025612592697,
+      "step": 208
+    },
+    {
+      "epoch": 0.9631336405529954,
+      "grad_norm": 0.26721346378326416,
+      "learning_rate": 1.1436803658769082e-05,
+      "loss": 0.11645902693271637,
+      "step": 209
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.2960895895957947,
+      "learning_rate": 1.1361666490962468e-05,
+      "loss": 0.10729526728391647,
+      "step": 210
+    },
+    {
+      "epoch": 0.9723502304147466,
+      "grad_norm": 0.32413265109062195,
+      "learning_rate": 1.1286450913828313e-05,
+      "loss": 0.1103423684835434,
+      "step": 211
+    },
+    {
+      "epoch": 0.9769585253456221,
+      "grad_norm": 0.29508334398269653,
+      "learning_rate": 1.1211161258532042e-05,
+      "loss": 0.11379773914813995,
+      "step": 212
+    },
+    {
+      "epoch": 0.9815668202764977,
+      "grad_norm": 0.30522626638412476,
+      "learning_rate": 1.113580186050475e-05,
+      "loss": 0.1158430278301239,
+      "step": 213
+    },
+    {
+      "epoch": 0.9861751152073732,
+      "grad_norm": 0.325366735458374,
+      "learning_rate": 1.1060377059193548e-05,
+      "loss": 0.108710378408432,
+      "step": 214
+    },
+    {
+      "epoch": 0.9907834101382489,
+      "grad_norm": 0.3244781196117401,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.11200010031461716,
+      "step": 215
+    },
+    {
+      "epoch": 0.9953917050691244,
+      "grad_norm": 0.32474005222320557,
+      "learning_rate": 1.0909348623088472e-05,
+      "loss": 0.11118399351835251,
+      "step": 216
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.32752424478530884,
+      "learning_rate": 1.0833753685018935e-05,
+      "loss": 0.11793828010559082,
+      "step": 217
+    },
+    {
+      "epoch": 1.0046082949308757,
+      "grad_norm": 0.3572429418563843,
+      "learning_rate": 1.0758110736613385e-05,
+      "loss": 0.09536577761173248,
+      "step": 218
+    },
+    {
+      "epoch": 1.0092165898617511,
+      "grad_norm": 0.37798336148262024,
+      "learning_rate": 1.0682424133646712e-05,
+      "loss": 0.10725440084934235,
+      "step": 219
+    },
+    {
+      "epoch": 1.0138248847926268,
+      "grad_norm": 0.35839393734931946,
+      "learning_rate": 1.0606698234407587e-05,
+      "loss": 0.08877898752689362,
+      "step": 220
+    },
+    {
+      "epoch": 1.0184331797235022,
+      "grad_norm": 0.660598874092102,
+      "learning_rate": 1.0530937399447496e-05,
+      "loss": 0.0908464789390564,
+      "step": 221
+    },
+    {
+      "epoch": 1.023041474654378,
+      "grad_norm": 0.4050118625164032,
+      "learning_rate": 1.0455145991329639e-05,
+      "loss": 0.10394350439310074,
+      "step": 222
+    },
+    {
+      "epoch": 1.0276497695852536,
+      "grad_norm": 0.3411266803741455,
+      "learning_rate": 1.0379328374377715e-05,
+      "loss": 0.09487015753984451,
+      "step": 223
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.4272059202194214,
+      "learning_rate": 1.0303488914424624e-05,
+      "loss": 0.0962924137711525,
+      "step": 224
+    },
+    {
+      "epoch": 1.0368663594470047,
+      "grad_norm": 0.35987433791160583,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.09213538467884064,
+      "step": 225
+    },
+    {
+      "epoch": 1.0414746543778801,
+      "grad_norm": 0.31923431158065796,
+      "learning_rate": 1.0151761934884028e-05,
+      "loss": 0.09832032024860382,
+      "step": 226
+    },
+    {
+      "epoch": 1.0460829493087558,
+      "grad_norm": 0.3016151189804077,
+      "learning_rate": 1.0075883152245334e-05,
+      "loss": 0.09176886081695557,
+      "step": 227
+    },
+    {
+      "epoch": 1.0506912442396312,
+      "grad_norm": 0.29849952459335327,
+      "learning_rate": 1e-05,
+      "loss": 0.09555266797542572,
+      "step": 228
+    },
+    {
+      "epoch": 1.055299539170507,
+      "grad_norm": 0.31398603320121765,
+      "learning_rate": 9.92411684775467e-06,
+      "loss": 0.09747482091188431,
+      "step": 229
+    },
+    {
+      "epoch": 1.0599078341013826,
+      "grad_norm": 0.30930161476135254,
+      "learning_rate": 9.848238065115975e-06,
+      "loss": 0.09331567585468292,
+      "step": 230
+    },
+    {
+      "epoch": 1.064516129032258,
+      "grad_norm": 0.3199133574962616,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 0.09240363538265228,
+      "step": 231
+    },
+    {
+      "epoch": 1.0691244239631337,
+      "grad_norm": 0.355487585067749,
+      "learning_rate": 9.696511085575377e-06,
+      "loss": 0.08570098131895065,
+      "step": 232
+    },
+    {
+      "epoch": 1.0737327188940091,
+      "grad_norm": 0.31286942958831787,
+      "learning_rate": 9.620671625622287e-06,
+      "loss": 0.10226540267467499,
+      "step": 233
+    },
+    {
+      "epoch": 1.0783410138248848,
+      "grad_norm": 0.29606059193611145,
+      "learning_rate": 9.544854008670366e-06,
+      "loss": 0.10021825134754181,
+      "step": 234
+    },
+    {
+      "epoch": 1.0829493087557605,
+      "grad_norm": 0.2840631902217865,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.08670271933078766,
+      "step": 235
+    },
+    {
+      "epoch": 1.087557603686636,
+      "grad_norm": 0.28228437900543213,
+      "learning_rate": 9.393301765592415e-06,
+      "loss": 0.09104766696691513,
+      "step": 236
+    },
+    {
+      "epoch": 1.0921658986175116,
+      "grad_norm": 0.283720999956131,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.10343114286661148,
+      "step": 237
+    },
+    {
+      "epoch": 1.096774193548387,
+      "grad_norm": 0.28975996375083923,
+      "learning_rate": 9.241889263386618e-06,
+      "loss": 0.0953461155295372,
+      "step": 238
+    },
+    {
+      "epoch": 1.1013824884792627,
+      "grad_norm": 0.2927744388580322,
+      "learning_rate": 9.166246314981066e-06,
+      "loss": 0.09123410284519196,
+      "step": 239
+    },
+    {
+      "epoch": 1.1059907834101383,
+      "grad_norm": 0.2917017936706543,
+      "learning_rate": 9.090651376911532e-06,
+      "loss": 0.09305296838283539,
+      "step": 240
+    },
+    {
+      "epoch": 1.1105990783410138,
+      "grad_norm": 0.30169177055358887,
+      "learning_rate": 9.015108802188314e-06,
+      "loss": 0.08989232033491135,
+      "step": 241
+    },
+    {
+      "epoch": 1.1152073732718895,
+      "grad_norm": 0.2873518168926239,
+      "learning_rate": 8.939622940806456e-06,
+      "loss": 0.09378752112388611,
+      "step": 242
+    },
+    {
+      "epoch": 1.119815668202765,
+      "grad_norm": 0.28246840834617615,
+      "learning_rate": 8.86419813949525e-06,
+      "loss": 0.09600290656089783,
+      "step": 243
+    },
+    {
+      "epoch": 1.1244239631336406,
+      "grad_norm": 0.29099470376968384,
+      "learning_rate": 8.788838741467961e-06,
+      "loss": 0.0967070609331131,
+      "step": 244
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.26357755064964294,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.09311351180076599,
+      "step": 245
+    },
+    {
+      "epoch": 1.1336405529953917,
+      "grad_norm": 0.35727375745773315,
+      "learning_rate": 8.638333509037537e-06,
+      "loss": 0.08752685785293579,
+      "step": 246
+    },
+    {
+      "epoch": 1.1382488479262673,
+      "grad_norm": 0.27436915040016174,
+      "learning_rate": 8.56319634123092e-06,
+      "loss": 0.10174702852964401,
+      "step": 247
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.332706481218338,
+      "learning_rate": 8.488141909402192e-06,
+      "loss": 0.09215912222862244,
+      "step": 248
+    },
+    {
+      "epoch": 1.1474654377880185,
+      "grad_norm": 0.31336989998817444,
+      "learning_rate": 8.413174535437486e-06,
+      "loss": 0.09377896785736084,
+      "step": 249
+    },
+    {
+      "epoch": 1.1520737327188941,
+      "grad_norm": 0.30652332305908203,
+      "learning_rate": 8.338298536209861e-06,
+      "loss": 0.09252865612506866,
+      "step": 250
+    },
+    {
+      "epoch": 1.1566820276497696,
+      "grad_norm": 0.29377076029777527,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.09526217728853226,
+      "step": 251
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 0.3223710060119629,
+      "learning_rate": 8.188837902901441e-06,
+      "loss": 0.09533843398094177,
+      "step": 252
+    },
+    {
+      "epoch": 1.1658986175115207,
+      "grad_norm": 0.2809475362300873,
+      "learning_rate": 8.114261875265643e-06,
+      "loss": 0.09845723956823349,
+      "step": 253
+    },
+    {
+      "epoch": 1.1705069124423964,
+      "grad_norm": 0.3227386474609375,
+      "learning_rate": 8.03979443476132e-06,
+      "loss": 0.09502680599689484,
+      "step": 254
+    },
+    {
+      "epoch": 1.1751152073732718,
+      "grad_norm": 0.3008551597595215,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.08639752864837646,
+      "step": 255
+    },
+    {
+      "epoch": 1.1797235023041475,
+      "grad_norm": 0.3245057165622711,
+      "learning_rate": 7.891202460988158e-06,
+      "loss": 0.09135465323925018,
+      "step": 256
+    },
+    {
+      "epoch": 1.1843317972350231,
+      "grad_norm": 0.2826603651046753,
+      "learning_rate": 7.817086484143987e-06,
+      "loss": 0.09027455747127533,
+      "step": 257
+    },
+    {
+      "epoch": 1.1889400921658986,
+      "grad_norm": 0.2956542670726776,
+      "learning_rate": 7.743096206787894e-06,
+      "loss": 0.09775300323963165,
+      "step": 258
+    },
+    {
+      "epoch": 1.1935483870967742,
+      "grad_norm": 0.2778976261615753,
+      "learning_rate": 7.669235889528436e-06,
+      "loss": 0.09744524955749512,
+      "step": 259
+    },
+    {
+      "epoch": 1.1981566820276497,
+      "grad_norm": 0.3103698492050171,
+      "learning_rate": 7.595509785490618e-06,
+      "loss": 0.09268967807292938,
+      "step": 260
+    },
+    {
+      "epoch": 1.2027649769585254,
+      "grad_norm": 0.2766534090042114,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 0.09345951676368713,
+      "step": 261
+    },
+    {
+      "epoch": 1.2073732718894008,
+      "grad_norm": 0.28104367852211,
+      "learning_rate": 7.448477190693238e-06,
+      "loss": 0.09961486607789993,
+      "step": 262
+    },
+    {
+      "epoch": 1.2119815668202765,
+      "grad_norm": 0.26155269145965576,
+      "learning_rate": 7.375179166564062e-06,
+      "loss": 0.0922398790717125,
+      "step": 263
+    },
+    {
+      "epoch": 1.2165898617511521,
+      "grad_norm": 0.28575339913368225,
+      "learning_rate": 7.3020322884297565e-06,
+      "loss": 0.0946994423866272,
+      "step": 264
+    },
+    {
+      "epoch": 1.2211981566820276,
+      "grad_norm": 0.23780789971351624,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.10343548655509949,
+      "step": 265
+    },
+    {
+      "epoch": 1.2258064516129032,
+      "grad_norm": 0.30945390462875366,
+      "learning_rate": 7.156208809370884e-06,
+      "loss": 0.09674638509750366,
+      "step": 266
+    },
+    {
+      "epoch": 1.230414746543779,
+      "grad_norm": 0.27918314933776855,
+      "learning_rate": 7.0835406054517505e-06,
+      "loss": 0.08843756467103958,
+      "step": 267
+    },
+    {
+      "epoch": 1.2350230414746544,
+      "grad_norm": 0.3164294958114624,
+      "learning_rate": 7.0110403410548445e-06,
+      "loss": 0.09062233567237854,
+      "step": 268
+    },
+    {
+      "epoch": 1.23963133640553,
+      "grad_norm": 0.27427372336387634,
+      "learning_rate": 6.93871219098876e-06,
+      "loss": 0.09116892516613007,
+      "step": 269
+    },
+    {
+      "epoch": 1.2442396313364055,
+      "grad_norm": 0.3403918743133545,
+      "learning_rate": 6.866560320151179e-06,
+      "loss": 0.09047368168830872,
+      "step": 270
+    },
+    {
+      "epoch": 1.2488479262672811,
+      "grad_norm": 0.3160417973995209,
+      "learning_rate": 6.79458888328903e-06,
+      "loss": 0.08733657002449036,
+      "step": 271
+    },
+    {
+      "epoch": 1.2534562211981566,
+      "grad_norm": 0.27691933512687683,
+      "learning_rate": 6.7228020247592515e-06,
+      "loss": 0.09268403053283691,
+      "step": 272
+    },
+    {
+      "epoch": 1.2580645161290323,
+      "grad_norm": 0.3128885328769684,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.08689699321985245,
+      "step": 273
+    },
+    {
+      "epoch": 1.262672811059908,
+      "grad_norm": 0.2839488983154297,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.09248564392328262,
+      "step": 274
+    },
+    {
+      "epoch": 1.2672811059907834,
+      "grad_norm": 0.266336590051651,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.09737635403871536,
+      "step": 275
+    },
+    {
+      "epoch": 1.271889400921659,
+      "grad_norm": 0.2838415205478668,
+      "learning_rate": 6.437582884105835e-06,
+      "loss": 0.09304854273796082,
+      "step": 276
+    },
+    {
+      "epoch": 1.2764976958525347,
+      "grad_norm": 0.26388052105903625,
+      "learning_rate": 6.366780702271589e-06,
+      "loss": 0.09412959218025208,
+      "step": 277
+    },
+    {
+      "epoch": 1.2811059907834101,
+      "grad_norm": 0.2514381408691406,
+      "learning_rate": 6.29618773340089e-06,
+      "loss": 0.0996539294719696,
+      "step": 278
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.279520720243454,
+      "learning_rate": 6.225808042473857e-06,
+      "loss": 0.08420069515705109,
+      "step": 279
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.2651165723800659,
+      "learning_rate": 6.15564568218935e-06,
+      "loss": 0.08745840936899185,
+      "step": 280
+    },
+    {
+      "epoch": 1.294930875576037,
+      "grad_norm": 0.2483370155096054,
+      "learning_rate": 6.085704692731609e-06,
+      "loss": 0.08952867984771729,
+      "step": 281
+    },
+    {
+      "epoch": 1.2995391705069124,
+      "grad_norm": 0.2449292242527008,
+      "learning_rate": 6.015989101537586e-06,
+      "loss": 0.09743745625019073,
+      "step": 282
+    },
+    {
+      "epoch": 1.304147465437788,
+      "grad_norm": 0.28545451164245605,
+      "learning_rate": 5.946502923065054e-06,
+      "loss": 0.08434639126062393,
+      "step": 283
+    },
+    {
+      "epoch": 1.3087557603686637,
+      "grad_norm": 0.318413645029068,
+      "learning_rate": 5.877250158561425e-06,
+      "loss": 0.08885297179222107,
+      "step": 284
+    },
+    {
+      "epoch": 1.3133640552995391,
+      "grad_norm": 0.2604139447212219,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.09373261779546738,
+      "step": 285
+    },
+    {
+      "epoch": 1.3179723502304148,
+      "grad_norm": 0.27786052227020264,
+      "learning_rate": 5.73946080901712e-06,
+      "loss": 0.09036208689212799,
+      "step": 286
+    },
+    {
+      "epoch": 1.3225806451612903,
+      "grad_norm": 0.25508561730384827,
+      "learning_rate": 5.670932158349732e-06,
+      "loss": 0.0884193629026413,
+      "step": 287
+    },
+    {
+      "epoch": 1.327188940092166,
+      "grad_norm": 0.25389236211776733,
+      "learning_rate": 5.602652789940941e-06,
+      "loss": 0.1019308865070343,
+      "step": 288
+    },
+    {
+      "epoch": 1.3317972350230414,
+      "grad_norm": 0.24963538348674774,
+      "learning_rate": 5.534626635546e-06,
+      "loss": 0.09635467082262039,
+      "step": 289
+    },
+    {
+      "epoch": 1.336405529953917,
+      "grad_norm": 0.25879931449890137,
+      "learning_rate": 5.466857612339229e-06,
+      "loss": 0.09760430455207825,
+      "step": 290
+    },
+    {
+      "epoch": 1.3410138248847927,
+      "grad_norm": 0.2770460247993469,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 0.08637236058712006,
+      "step": 291
+    },
+    {
+      "epoch": 1.3456221198156681,
+      "grad_norm": 0.2526210844516754,
+      "learning_rate": 5.332106553930414e-06,
+      "loss": 0.08889706432819366,
+      "step": 292
+    },
+    {
+      "epoch": 1.3502304147465438,
+      "grad_norm": 0.2677111029624939,
+      "learning_rate": 5.2651322781466606e-06,
+      "loss": 0.09329430013895035,
+      "step": 293
+    },
+    {
+      "epoch": 1.3548387096774195,
+      "grad_norm": 0.2581748962402344,
+      "learning_rate": 5.198430651940846e-06,
+      "loss": 0.08578409254550934,
+      "step": 294
+    },
+    {
+      "epoch": 1.359447004608295,
+      "grad_norm": 0.28674134612083435,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.08745191991329193,
+      "step": 295
+    },
+    {
+      "epoch": 1.3640552995391704,
+      "grad_norm": 0.24417446553707123,
+      "learning_rate": 5.065860695955971e-06,
+      "loss": 0.09139522910118103,
+      "step": 296
+    },
+    {
+      "epoch": 1.368663594470046,
+      "grad_norm": 0.2578442692756653,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.09083915501832962,
+      "step": 297
+    },
+    {
+      "epoch": 1.3732718894009217,
+      "grad_norm": 0.23622238636016846,
+      "learning_rate": 4.934427220828572e-06,
+      "loss": 0.0965266227722168,
+      "step": 298
+    },
+    {
+      "epoch": 1.3778801843317972,
+      "grad_norm": 0.2619278132915497,
+      "learning_rate": 4.869146134342426e-06,
+      "loss": 0.08366833627223969,
+      "step": 299
+    },
+    {
+      "epoch": 1.3824884792626728,
+      "grad_norm": 0.2349531501531601,
+      "learning_rate": 4.804160499645667e-06,
+      "loss": 0.09620627015829086,
+      "step": 300
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.2449313998222351,
+      "learning_rate": 4.739474058829288e-06,
+      "loss": 0.08856195956468582,
+      "step": 301
+    },
+    {
+      "epoch": 1.391705069124424,
+      "grad_norm": 0.2207731008529663,
+      "learning_rate": 4.675090536755706e-06,
+      "loss": 0.09431906044483185,
+      "step": 302
+    },
+    {
+      "epoch": 1.3963133640552996,
+      "grad_norm": 0.22642095386981964,
+      "learning_rate": 4.611013640844245e-06,
+      "loss": 0.09311524033546448,
+      "step": 303
+    },
+    {
+      "epoch": 1.400921658986175,
+      "grad_norm": 0.24301590025424957,
+      "learning_rate": 4.5472470608576745e-06,
+      "loss": 0.08773519098758698,
+      "step": 304
+    },
+    {
+      "epoch": 1.4055299539170507,
+      "grad_norm": 0.23094524443149567,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.0901784896850586,
+      "step": 305
+    },
+    {
+      "epoch": 1.4101382488479262,
+      "grad_norm": 0.23683691024780273,
+      "learning_rate": 4.420659518153667e-06,
+      "loss": 0.08550785481929779,
+      "step": 306
+    },
+    {
+      "epoch": 1.4147465437788018,
+      "grad_norm": 0.235621377825737,
+      "learning_rate": 4.357845844771881e-06,
+      "loss": 0.08315462619066238,
+      "step": 307
+    },
+    {
+      "epoch": 1.4193548387096775,
+      "grad_norm": 0.23929363489151,
+      "learning_rate": 4.295357065566543e-06,
+      "loss": 0.0901196077466011,
+      "step": 308
+    },
+    {
+      "epoch": 1.423963133640553,
+      "grad_norm": 0.24454443156719208,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.09037616103887558,
+      "step": 309
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.2508774697780609,
+      "learning_rate": 4.171368564024216e-06,
+      "loss": 0.09648489952087402,
+      "step": 310
+    },
+    {
+      "epoch": 1.4331797235023043,
+      "grad_norm": 0.23605868220329285,
+      "learning_rate": 4.109875981361363e-06,
+      "loss": 0.08939523994922638,
+      "step": 311
+    },
+    {
+      "epoch": 1.4377880184331797,
+      "grad_norm": 0.22239117324352264,
+      "learning_rate": 4.048722571812105e-06,
+      "loss": 0.0936923548579216,
+      "step": 312
+    },
+    {
+      "epoch": 1.4423963133640554,
+      "grad_norm": 0.23895694315433502,
+      "learning_rate": 3.987911856795047e-06,
+      "loss": 0.10145039111375809,
+      "step": 313
+    },
+    {
+      "epoch": 1.4470046082949308,
+      "grad_norm": 0.21463164687156677,
+      "learning_rate": 3.9274473379953035e-06,
+      "loss": 0.10095448046922684,
+      "step": 314
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.23943549394607544,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.087343230843544,
+      "step": 315
+    },
+    {
+      "epoch": 1.456221198156682,
+      "grad_norm": 0.22924616932868958,
+      "learning_rate": 3.8075707959119845e-06,
+      "loss": 0.09279239922761917,
+      "step": 316
+    },
+    {
+      "epoch": 1.4608294930875576,
+      "grad_norm": 0.2175876349210739,
+      "learning_rate": 3.748165675522113e-06,
+      "loss": 0.10221215337514877,
+      "step": 317
+    },
+    {
+      "epoch": 1.4654377880184333,
+      "grad_norm": 0.22712922096252441,
+      "learning_rate": 3.689120556739475e-06,
+      "loss": 0.0926864892244339,
+      "step": 318
+    },
+    {
+      "epoch": 1.4700460829493087,
+      "grad_norm": 0.23733589053153992,
+      "learning_rate": 3.630438839580217e-06,
+      "loss": 0.08259569853544235,
+      "step": 319
+    },
+    {
+      "epoch": 1.4746543778801844,
+      "grad_norm": 0.22348667681217194,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.07971324026584625,
+      "step": 320
+    },
+    {
+      "epoch": 1.4792626728110598,
+      "grad_norm": 0.22225157916545868,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 0.092008076608181,
+      "step": 321
+    },
+    {
+      "epoch": 1.4838709677419355,
+      "grad_norm": 0.24107463657855988,
+      "learning_rate": 3.4566077829496892e-06,
+      "loss": 0.09073396027088165,
+      "step": 322
+    },
+    {
+      "epoch": 1.488479262672811,
+      "grad_norm": 0.2076810896396637,
+      "learning_rate": 3.399413251016359e-06,
+      "loss": 0.0967097282409668,
+      "step": 323
+    },
+    {
+      "epoch": 1.4930875576036866,
+      "grad_norm": 0.23102445900440216,
+      "learning_rate": 3.342598803025595e-06,
+      "loss": 0.0861356109380722,
+      "step": 324
+    },
+    {
+      "epoch": 1.4976958525345623,
+      "grad_norm": 0.2405044436454773,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.08794005960226059,
+      "step": 325
+    },
+    {
+      "epoch": 1.5023041474654377,
+      "grad_norm": 0.22912301123142242,
+      "learning_rate": 3.2301232230634104e-06,
+      "loss": 0.08631795644760132,
+      "step": 326
+    },
+    {
+      "epoch": 1.5069124423963134,
+      "grad_norm": 0.23987974226474762,
+      "learning_rate": 3.174468567813461e-06,
+      "loss": 0.0806097760796547,
+      "step": 327
+    },
+    {
+      "epoch": 1.511520737327189,
+      "grad_norm": 0.2155601680278778,
+      "learning_rate": 3.1192069495760525e-06,
+      "loss": 0.08571784198284149,
+      "step": 328
+    },
+    {
+      "epoch": 1.5161290322580645,
+      "grad_norm": 0.22012591361999512,
+      "learning_rate": 3.0643415505006733e-06,
+      "loss": 0.09222391247749329,
+      "step": 329
+    },
+    {
+      "epoch": 1.52073732718894,
+      "grad_norm": 0.22817829251289368,
+      "learning_rate": 3.009875529921181e-06,
+      "loss": 0.08892268687486649,
+      "step": 330
+    },
+    {
+      "epoch": 1.5253456221198156,
+      "grad_norm": 0.2139076441526413,
+      "learning_rate": 2.9558120241738786e-06,
+      "loss": 0.0886528342962265,
+      "step": 331
+    },
+    {
+      "epoch": 1.5299539170506913,
+      "grad_norm": 0.21115992963314056,
+      "learning_rate": 2.90215414641691e-06,
+      "loss": 0.09032206237316132,
+      "step": 332
+    },
+    {
+      "epoch": 1.5345622119815667,
+      "grad_norm": 0.22681404650211334,
+      "learning_rate": 2.8489049864510053e-06,
+      "loss": 0.09330740571022034,
+      "step": 333
+    },
+    {
+      "epoch": 1.5391705069124424,
+      "grad_norm": 0.22494614124298096,
+      "learning_rate": 2.7960676105415474e-06,
+      "loss": 0.08630627393722534,
+      "step": 334
+    },
+    {
+      "epoch": 1.543778801843318,
+      "grad_norm": 0.20977683365345,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.08977203071117401,
+      "step": 335
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.21853460371494293,
+      "learning_rate": 2.691640357218759e-06,
+      "loss": 0.08744624257087708,
+      "step": 336
+    },
+    {
+      "epoch": 1.5529953917050692,
+      "grad_norm": 0.24067096412181854,
+      "learning_rate": 2.640056493077231e-06,
+      "loss": 0.08816929906606674,
+      "step": 337
+    },
+    {
+      "epoch": 1.5576036866359448,
+      "grad_norm": 0.2103225737810135,
+      "learning_rate": 2.588896439189477e-06,
+      "loss": 0.08670391142368317,
+      "step": 338
+    },
+    {
+      "epoch": 1.5622119815668203,
+      "grad_norm": 0.2347419112920761,
+      "learning_rate": 2.5381631415231455e-06,
+      "loss": 0.0886957123875618,
+      "step": 339
+    },
+    {
+      "epoch": 1.5668202764976957,
+      "grad_norm": 0.22054597735404968,
+      "learning_rate": 2.4878595214718236e-06,
+      "loss": 0.07784964144229889,
+      "step": 340
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.23039421439170837,
+      "learning_rate": 2.4379884756868167e-06,
+      "loss": 0.08673332631587982,
+      "step": 341
+    },
+    {
+      "epoch": 1.576036866359447,
+      "grad_norm": 0.22742357850074768,
+      "learning_rate": 2.388552875910354e-06,
+      "loss": 0.0900346040725708,
+      "step": 342
+    },
+    {
+      "epoch": 1.5806451612903225,
+      "grad_norm": 0.21613454818725586,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.08469422161579132,
+      "step": 343
+    },
+    {
+      "epoch": 1.5852534562211982,
+      "grad_norm": 0.21131108701229095,
+      "learning_rate": 2.290999375815841e-06,
+      "loss": 0.0863153338432312,
+      "step": 344
+    },
+    {
+      "epoch": 1.5898617511520738,
+      "grad_norm": 0.2074364274740219,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.0915350615978241,
+      "step": 345
+    },
+    {
+      "epoch": 1.5944700460829493,
+      "grad_norm": 0.20815588533878326,
+      "learning_rate": 2.195221490696863e-06,
+      "loss": 0.09233294427394867,
+      "step": 346
+    },
+    {
+      "epoch": 1.5990783410138247,
+      "grad_norm": 0.19917330145835876,
+      "learning_rate": 2.1480053137844115e-06,
+      "loss": 0.08588294684886932,
+      "step": 347
+    },
+    {
+      "epoch": 1.6036866359447006,
+      "grad_norm": 0.20449714362621307,
+      "learning_rate": 2.101241281084416e-06,
+      "loss": 0.0926763117313385,
+      "step": 348
+    },
+    {
+      "epoch": 1.608294930875576,
+      "grad_norm": 0.1993105113506317,
+      "learning_rate": 2.054932085426856e-06,
+      "loss": 0.09865063428878784,
+      "step": 349
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.21397468447685242,
+      "learning_rate": 2.0090803934506765e-06,
+      "loss": 0.08052094280719757,
+      "step": 350
+    },
+    {
+      "epoch": 1.6175115207373272,
+      "grad_norm": 0.20286151766777039,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 0.08827085793018341,
+      "step": 351
+    },
+    {
+      "epoch": 1.6221198156682028,
+      "grad_norm": 0.2034972757101059,
+      "learning_rate": 1.9187600552231955e-06,
+      "loss": 0.09409059584140778,
+      "step": 352
+    },
+    {
+      "epoch": 1.6267281105990783,
+      "grad_norm": 0.23023094236850739,
+      "learning_rate": 1.8742966099201699e-06,
+      "loss": 0.08801084756851196,
+      "step": 353
+    },
+    {
+      "epoch": 1.631336405529954,
+      "grad_norm": 0.20404526591300964,
+      "learning_rate": 1.8303010698955803e-06,
+      "loss": 0.08932927250862122,
+      "step": 354
+    },
+    {
+      "epoch": 1.6359447004608296,
+      "grad_norm": 0.2178584635257721,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.0822620540857315,
+      "step": 355
+    },
+    {
+      "epoch": 1.640552995391705,
+      "grad_norm": 0.21342331171035767,
+      "learning_rate": 1.7437238122358058e-06,
+      "loss": 0.08029656857252121,
+      "step": 356
+    },
+    {
+      "epoch": 1.6451612903225805,
+      "grad_norm": 0.20857492089271545,
+      "learning_rate": 1.7011470800097496e-06,
+      "loss": 0.0855298638343811,
+      "step": 357
+    },
+    {
+      "epoch": 1.6497695852534562,
+      "grad_norm": 0.2015017420053482,
+      "learning_rate": 1.659048223593308e-06,
+      "loss": 0.08766387403011322,
+      "step": 358
+    },
+    {
+      "epoch": 1.6543778801843319,
+      "grad_norm": 0.2667805254459381,
+      "learning_rate": 1.6174296671799571e-06,
+      "loss": 0.08676134794950485,
+      "step": 359
+    },
+    {
+      "epoch": 1.6589861751152073,
+      "grad_norm": 0.19923104345798492,
+      "learning_rate": 1.5762938073058853e-06,
+      "loss": 0.09383082389831543,
+      "step": 360
+    },
+    {
+      "epoch": 1.663594470046083,
+      "grad_norm": 0.19868069887161255,
+      "learning_rate": 1.5356430127119915e-06,
+      "loss": 0.0831666812300682,
+      "step": 361
+    },
+    {
+      "epoch": 1.6682027649769586,
+      "grad_norm": 0.20258234441280365,
+      "learning_rate": 1.4954796242074897e-06,
+      "loss": 0.08258548378944397,
+      "step": 362
+    },
+    {
+      "epoch": 1.672811059907834,
+      "grad_norm": 0.20538875460624695,
+      "learning_rate": 1.4558059545351144e-06,
+      "loss": 0.08818638324737549,
+      "step": 363
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": 0.21802577376365662,
+      "learning_rate": 1.4166242882379478e-06,
+      "loss": 0.07985609024763107,
+      "step": 364
+    },
+    {
+      "epoch": 1.6820276497695854,
+      "grad_norm": 0.20615556836128235,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.09125086665153503,
+      "step": 365
+    },
+    {
+      "epoch": 1.6866359447004609,
+      "grad_norm": 0.21183592081069946,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.08431504666805267,
+      "step": 366
+    },
+    {
+      "epoch": 1.6912442396313363,
+      "grad_norm": 0.22012415528297424,
+      "learning_rate": 1.302053729282533e-06,
+      "loss": 0.09222625195980072,
+      "step": 367
+    },
+    {
+      "epoch": 1.695852534562212,
+      "grad_norm": 0.2207479327917099,
+      "learning_rate": 1.2648623533539262e-06,
+      "loss": 0.0805463045835495,
+      "step": 368
+    },
+    {
+      "epoch": 1.7004608294930876,
+      "grad_norm": 0.1947096586227417,
+      "learning_rate": 1.2281739759740575e-06,
+      "loss": 0.0870305746793747,
+      "step": 369
+    },
+    {
+      "epoch": 1.705069124423963,
+      "grad_norm": 0.20484814047813416,
+      "learning_rate": 1.1919907097828654e-06,
+      "loss": 0.08505576848983765,
+      "step": 370
+    },
+    {
+      "epoch": 1.7096774193548387,
+      "grad_norm": 0.2027549296617508,
+      "learning_rate": 1.156314638334277e-06,
+      "loss": 0.080368272960186,
+      "step": 371
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.19223064184188843,
+      "learning_rate": 1.121147815976248e-06,
+      "loss": 0.08860905468463898,
+      "step": 372
+    },
+    {
+      "epoch": 1.7188940092165899,
+      "grad_norm": 0.2101166546344757,
+      "learning_rate": 1.086492267732462e-06,
+      "loss": 0.08285060524940491,
+      "step": 373
+    },
+    {
+      "epoch": 1.7235023041474653,
+      "grad_norm": 0.19490844011306763,
+      "learning_rate": 1.0523499891857226e-06,
+      "loss": 0.08373953402042389,
+      "step": 374
+    },
+    {
+      "epoch": 1.728110599078341,
+      "grad_norm": 0.1983107626438141,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.0909026712179184,
+      "step": 375
+    },
+    {
+      "epoch": 1.7327188940092166,
+      "grad_norm": 0.1907951831817627,
+      "learning_rate": 9.856130756224214e-07,
+      "loss": 0.08828463405370712,
+      "step": 376
+    },
+    {
+      "epoch": 1.737327188940092,
+      "grad_norm": 0.19547390937805176,
+      "learning_rate": 9.530222835413739e-07,
+      "loss": 0.09217946231365204,
+      "step": 377
+    },
+    {
+      "epoch": 1.7419354838709677,
+      "grad_norm": 0.19235429167747498,
+      "learning_rate": 9.209524468071096e-07,
+      "loss": 0.09554372727870941,
+      "step": 378
+    },
+    {
+      "epoch": 1.7465437788018434,
+      "grad_norm": 0.20158275961875916,
+      "learning_rate": 8.894054121084839e-07,
+      "loss": 0.07740487158298492,
+      "step": 379
+    },
+    {
+      "epoch": 1.7511520737327189,
+      "grad_norm": 0.20367076992988586,
+      "learning_rate": 8.583829960296519e-07,
+      "loss": 0.08002394437789917,
+      "step": 380
+    },
+    {
+      "epoch": 1.7557603686635943,
+      "grad_norm": 0.19935064017772675,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.08750782907009125,
+      "step": 381
+    },
+    {
+      "epoch": 1.7603686635944702,
+      "grad_norm": 0.1907435655593872,
+      "learning_rate": 7.979191349186322e-07,
+      "loss": 0.08991643786430359,
+      "step": 382
+    },
+    {
+      "epoch": 1.7649769585253456,
+      "grad_norm": 0.19341535866260529,
+      "learning_rate": 7.684811715985429e-07,
+      "loss": 0.08272404968738556,
+      "step": 383
+    },
+    {
+      "epoch": 1.769585253456221,
+      "grad_norm": 0.1893770545721054,
+      "learning_rate": 7.395747901219474e-07,
+      "loss": 0.0907069593667984,
+      "step": 384
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.19289396703243256,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.09233804047107697,
+      "step": 385
+    },
+    {
+      "epoch": 1.7788018433179724,
+      "grad_norm": 0.19262686371803284,
+      "learning_rate": 6.833634000990541e-07,
+      "loss": 0.08571000397205353,
+      "step": 386
+    },
+    {
+      "epoch": 1.7834101382488479,
+      "grad_norm": 0.18920187652111053,
+      "learning_rate": 6.560616283932897e-07,
+      "loss": 0.09849191457033157,
+      "step": 387
+    },
+    {
+      "epoch": 1.7880184331797235,
+      "grad_norm": 0.18442000448703766,
+      "learning_rate": 6.292979120256992e-07,
+      "loss": 0.08185489475727081,
+      "step": 388
+    },
+    {
+      "epoch": 1.7926267281105992,
+      "grad_norm": 0.19440017640590668,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.09217529743909836,
+      "step": 389
+    },
+    {
+      "epoch": 1.7972350230414746,
+      "grad_norm": 0.20208221673965454,
+      "learning_rate": 5.77390778811796e-07,
+      "loss": 0.07973852753639221,
+      "step": 390
+    },
+    {
+      "epoch": 1.80184331797235,
+      "grad_norm": 0.18626391887664795,
+      "learning_rate": 5.522503509524591e-07,
+      "loss": 0.08296719938516617,
+      "step": 391
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 0.19081097841262817,
+      "learning_rate": 5.276539562331384e-07,
+      "loss": 0.08779381960630417,
+      "step": 392
+    },
+    {
+      "epoch": 1.8110599078341014,
+      "grad_norm": 0.18344910442829132,
+      "learning_rate": 5.036030109968082e-07,
+      "loss": 0.08511988073587418,
+      "step": 393
+    },
+    {
+      "epoch": 1.8156682027649769,
+      "grad_norm": 0.185654878616333,
+      "learning_rate": 4.800989001776323e-07,
+      "loss": 0.09555588662624359,
+      "step": 394
+    },
+    {
+      "epoch": 1.8202764976958525,
+      "grad_norm": 0.18537749350070953,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.08605486154556274,
+      "step": 395
+    },
+    {
+      "epoch": 1.8248847926267282,
+      "grad_norm": 0.18790900707244873,
+      "learning_rate": 4.3473656400665256e-07,
+      "loss": 0.08023641258478165,
+      "step": 396
+    },
+    {
+      "epoch": 1.8294930875576036,
+      "grad_norm": 0.20121566951274872,
+      "learning_rate": 4.128809507704445e-07,
+      "loss": 0.07489614188671112,
+      "step": 397
+    },
+    {
+      "epoch": 1.8341013824884793,
+      "grad_norm": 0.19918273389339447,
+      "learning_rate": 3.9157739603216337e-07,
+      "loss": 0.09093454480171204,
+      "step": 398
+    },
+    {
+      "epoch": 1.838709677419355,
+      "grad_norm": 0.1808507889509201,
+      "learning_rate": 3.708271265220087e-07,
+      "loss": 0.08856381475925446,
+      "step": 399
+    },
+    {
+      "epoch": 1.8433179723502304,
+      "grad_norm": 0.1912548691034317,
+      "learning_rate": 3.5063133711014884e-07,
+      "loss": 0.08285252749919891,
+      "step": 400
+    },
+    {
+      "epoch": 1.8479262672811059,
+      "grad_norm": 0.18777187168598175,
+      "learning_rate": 3.309911907379393e-07,
+      "loss": 0.09873615205287933,
+      "step": 401
+    },
+    {
+      "epoch": 1.8525345622119815,
+      "grad_norm": 0.18357273936271667,
+      "learning_rate": 3.119078183509372e-07,
+      "loss": 0.07868198305368423,
+      "step": 402
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.1859491914510727,
+      "learning_rate": 2.9338231883378365e-07,
+      "loss": 0.08919134736061096,
+      "step": 403
+    },
+    {
+      "epoch": 1.8617511520737327,
+      "grad_norm": 0.17287041246891022,
+      "learning_rate": 2.7541575894693194e-07,
+      "loss": 0.09601950645446777,
+      "step": 404
+    },
+    {
+      "epoch": 1.8663594470046083,
+      "grad_norm": 0.1833849549293518,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.08998854458332062,
+      "step": 405
+    },
+    {
+      "epoch": 1.870967741935484,
+      "grad_norm": 0.17766377329826355,
+      "learning_rate": 2.4116356411825526e-07,
+      "loss": 0.08219040930271149,
+      "step": 406
+    },
+    {
+      "epoch": 1.8755760368663594,
+      "grad_norm": 0.18471814692020416,
+      "learning_rate": 2.248799015327907e-07,
+      "loss": 0.0987071543931961,
+      "step": 407
+    },
+    {
+      "epoch": 1.8801843317972349,
+      "grad_norm": 0.19542527198791504,
+      "learning_rate": 2.091591231767709e-07,
+      "loss": 0.09203404933214188,
+      "step": 408
+    },
+    {
+      "epoch": 1.8847926267281108,
+      "grad_norm": 0.1766805797815323,
+      "learning_rate": 1.9400213430538773e-07,
+      "loss": 0.08221668004989624,
+      "step": 409
+    },
+    {
+      "epoch": 1.8894009216589862,
+      "grad_norm": 0.18288938701152802,
+      "learning_rate": 1.7940980770894122e-07,
+      "loss": 0.09058023244142532,
+      "step": 410
+    },
+    {
+      "epoch": 1.8940092165898617,
+      "grad_norm": 0.16981713473796844,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 0.08517719805240631,
+      "step": 411
+    },
+    {
+      "epoch": 1.8986175115207373,
+      "grad_norm": 0.19495777785778046,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.0871797502040863,
+      "step": 412
+    },
+    {
+      "epoch": 1.903225806451613,
+      "grad_norm": 0.17492727935314178,
+      "learning_rate": 1.3902904145653094e-07,
+      "loss": 0.09356344491243362,
+      "step": 413
+    },
+    {
+      "epoch": 1.9078341013824884,
+      "grad_norm": 0.1914207637310028,
+      "learning_rate": 1.2670344084530384e-07,
+      "loss": 0.08517169952392578,
+      "step": 414
+    },
+    {
+      "epoch": 1.912442396313364,
+      "grad_norm": 0.19323883950710297,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.08851385116577148,
+      "step": 415
+    },
+    {
+      "epoch": 1.9170506912442398,
+      "grad_norm": 0.1694461852312088,
+      "learning_rate": 1.0375852931286956e-07,
+      "loss": 0.08682743459939957,
+      "step": 416
+    },
+    {
+      "epoch": 1.9216589861751152,
+      "grad_norm": 0.17110790312290192,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.091385118663311,
+      "step": 417
+    },
+    {
+      "epoch": 1.9262672811059907,
+      "grad_norm": 0.17167358100414276,
+      "learning_rate": 8.309302018465581e-08,
+      "loss": 0.09858612716197968,
+      "step": 418
+    },
+    {
+      "epoch": 1.9308755760368663,
+      "grad_norm": 0.17165997624397278,
+      "learning_rate": 7.361654952665608e-08,
+      "loss": 0.088188037276268,
+      "step": 419
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.1749688982963562,
+      "learning_rate": 6.471167334968887e-08,
+      "loss": 0.09130515903234482,
+      "step": 420
+    },
+    {
+      "epoch": 1.9400921658986174,
+      "grad_norm": 0.17505252361297607,
+      "learning_rate": 5.637890442641403e-08,
+      "loss": 0.08734314143657684,
+      "step": 421
+    },
+    {
+      "epoch": 1.944700460829493,
+      "grad_norm": 0.21069136261940002,
+      "learning_rate": 4.861872258564049e-08,
+      "loss": 0.08940993249416351,
+      "step": 422
+    },
+    {
+      "epoch": 1.9493087557603688,
+      "grad_norm": 0.17113006114959717,
+      "learning_rate": 4.143157468468717e-08,
+      "loss": 0.08437768369913101,
+      "step": 423
+    },
+    {
+      "epoch": 1.9539170506912442,
+      "grad_norm": 0.16990627348423004,
+      "learning_rate": 3.481787458365915e-08,
+      "loss": 0.07766108959913254,
+      "step": 424
+    },
+    {
+      "epoch": 1.9585253456221197,
+      "grad_norm": 0.1732627898454666,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.08289483189582825,
+      "step": 425
+    },
+    {
+      "epoch": 1.9631336405529956,
+      "grad_norm": 0.17184484004974365,
+      "learning_rate": 2.3312308094607382e-08,
+      "loss": 0.08522669970989227,
+      "step": 426
+    },
+    {
+      "epoch": 1.967741935483871,
+      "grad_norm": 0.17134889960289001,
+      "learning_rate": 1.8421104235727406e-08,
+      "loss": 0.08242865651845932,
+      "step": 427
+    },
+    {
+      "epoch": 1.9723502304147464,
+      "grad_norm": 0.17302529513835907,
+      "learning_rate": 1.4104673196903007e-08,
+      "loss": 0.08645319193601608,
+      "step": 428
+    },
+    {
+      "epoch": 1.976958525345622,
+      "grad_norm": 0.18478727340698242,
+      "learning_rate": 1.0363263532724433e-08,
+      "loss": 0.08329476416110992,
+      "step": 429
+    },
+    {
+      "epoch": 1.9815668202764978,
+      "grad_norm": 0.16952385008335114,
+      "learning_rate": 7.197090686119623e-09,
+      "loss": 0.08567382395267487,
+      "step": 430
+    },
+    {
+      "epoch": 1.9861751152073732,
+      "grad_norm": 0.17264612019062042,
+      "learning_rate": 4.606336975948589e-09,
+      "loss": 0.08226893842220306,
+      "step": 431
+    },
+    {
+      "epoch": 1.9907834101382489,
+      "grad_norm": 0.17207252979278564,
+      "learning_rate": 2.591151586508467e-09,
+      "loss": 0.08505456894636154,
+      "step": 432
+    },
+    {
+      "epoch": 1.9953917050691246,
+      "grad_norm": 0.1711321771144867,
+      "learning_rate": 1.1516505589381777e-09,
+      "loss": 0.08563252538442612,
+      "step": 433
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1696888655424118,
+      "learning_rate": 2.8791678453821135e-10,
+      "loss": 0.08493001013994217,
+      "step": 434
+    },
+    {
+      "epoch": 2.0,
+      "step": 434,
+      "total_flos": 8272973614022656.0,
+      "train_loss": 0.11627333357174825,
+      "train_runtime": 52247.9077,
+      "train_samples_per_second": 0.133,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 434,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 8272973614022656.0,
+  "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 sha256:64f05b45000cd4491b7ea94ca216a07bc5c1db7d599f80c0e1b0de732c66218e
+size 7569