Upload folder using huggingface_hub

.gitattributes

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

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen3.5-9B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen35_caption_galore
+  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. -->
+
+# qwen35_caption_galore
+
+This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption 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:
+- family_to_adamw_lr = {
+        "language": _fallback(getattr(training_args, "language_adamw_lr", 3e-6), language_lr),
+        "vision": _fallback(getattr(training_args, "vision_adamw_lr", 2e-6), vision_lr),
+        "merger": _fallback(getattr(training_args, "merger_adamw_lr", 5e-6), merger_lr),
+    }
+- train_batch_size: 3
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 20
+- total_train_batch_size: 60
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine_with_min_lr
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.5.3
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen3.5-9B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen35_caption_galore
+  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. -->
+
+# qwen35_caption_galore
+
+This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption 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:
+- family_to_adamw_lr = {
+        "language": _fallback(getattr(training_args, "language_adamw_lr", 3e-6), language_lr),
+        "vision": _fallback(getattr(training_args, "vision_adamw_lr", 2e-6), vision_lr),
+        "merger": _fallback(getattr(training_args, "merger_adamw_lr", 5e-6), merger_lr),
+    }
+- train_batch_size: 3
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 20
+- total_train_batch_size: 60
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine_with_min_lr
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.5.3
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,9 @@
+{
+    "effective_tokens_per_sec": 7619.424096418565,
+    "epoch": 4.0,
+    "total_flos": 4.038502240003031e+18,
+    "train_loss": 0.9239894755600221,
+    "train_runtime": 10281.2731,
+    "train_samples_per_second": 5.859,
+    "train_steps_per_second": 0.098
+}

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 +1,113 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 4096,
+  "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": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "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_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "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": 16,
+    "num_hidden_layers": 32,
+    "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": "5.5.3",
+  "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": 4096,
+    "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 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "transformers_version": "5.5.3",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07036bd50133ea69a0fd3e62d9ecdfce11085d8ace5dfc6f249f3cd7987c1cfe
+size 20859273368

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "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": {
+    "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": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "effective_tokens_per_sec": 7619.424096418565,
+    "epoch": 4.0,
+    "total_flos": 4.038502240003031e+18,
+    "train_loss": 0.9239894755600221,
+    "train_runtime": 10281.2731,
+    "train_samples_per_second": 5.859,
+    "train_steps_per_second": 0.098
+}

trainer_state.json

@@ -0,0 +1,3557 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1004,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00796812749003984,
+      "grad_norm": 0.8635491728782654,
+      "learning_rate": 5.882352941176471e-08,
+      "loss": 2.092526435852051,
+      "step": 2
+    },
+    {
+      "epoch": 0.01593625498007968,
+      "grad_norm": 0.65386563539505,
+      "learning_rate": 1.764705882352941e-07,
+      "loss": 2.009572982788086,
+      "step": 4
+    },
+    {
+      "epoch": 0.02390438247011952,
+      "grad_norm": 2.1573679447174072,
+      "learning_rate": 2.9411764705882356e-07,
+      "loss": 2.2031428813934326,
+      "step": 6
+    },
+    {
+      "epoch": 0.03187250996015936,
+      "grad_norm": 0.7024685740470886,
+      "learning_rate": 4.11764705882353e-07,
+      "loss": 1.9222521781921387,
+      "step": 8
+    },
+    {
+      "epoch": 0.0398406374501992,
+      "grad_norm": 2.466196298599243,
+      "learning_rate": 5.294117647058824e-07,
+      "loss": 1.5961482524871826,
+      "step": 10
+    },
+    {
+      "epoch": 0.04780876494023904,
+      "grad_norm": 0.8721945285797119,
+      "learning_rate": 6.470588235294118e-07,
+      "loss": 1.8626258373260498,
+      "step": 12
+    },
+    {
+      "epoch": 0.055776892430278883,
+      "grad_norm": 0.9898734092712402,
+      "learning_rate": 7.647058823529412e-07,
+      "loss": 2.907916784286499,
+      "step": 14
+    },
+    {
+      "epoch": 0.06374501992031872,
+      "grad_norm": 3.7050821781158447,
+      "learning_rate": 8.823529411764706e-07,
+      "loss": 5.169388771057129,
+      "step": 16
+    },
+    {
+      "epoch": 0.07171314741035857,
+      "grad_norm": 1.2959784269332886,
+      "learning_rate": 1e-06,
+      "loss": 1.9087082147598267,
+      "step": 18
+    },
+    {
+      "epoch": 0.0796812749003984,
+      "grad_norm": 0.5755355358123779,
+      "learning_rate": 1.1176470588235294e-06,
+      "loss": 1.741716980934143,
+      "step": 20
+    },
+    {
+      "epoch": 0.08764940239043825,
+      "grad_norm": 0.5503631234169006,
+      "learning_rate": 1.2352941176470588e-06,
+      "loss": 2.108546733856201,
+      "step": 22
+    },
+    {
+      "epoch": 0.09561752988047809,
+      "grad_norm": 1.9359296560287476,
+      "learning_rate": 1.3529411764705883e-06,
+      "loss": 1.5568987131118774,
+      "step": 24
+    },
+    {
+      "epoch": 0.10358565737051793,
+      "grad_norm": 0.3511880934238434,
+      "learning_rate": 1.4705882352941175e-06,
+      "loss": 1.6464097499847412,
+      "step": 26
+    },
+    {
+      "epoch": 0.11155378486055777,
+      "grad_norm": 1.7009022235870361,
+      "learning_rate": 1.5882352941176472e-06,
+      "loss": 1.681158185005188,
+      "step": 28
+    },
+    {
+      "epoch": 0.11952191235059761,
+      "grad_norm": 0.9740716814994812,
+      "learning_rate": 1.7058823529411764e-06,
+      "loss": 1.4671032428741455,
+      "step": 30
+    },
+    {
+      "epoch": 0.12749003984063745,
+      "grad_norm": 1.555565595626831,
+      "learning_rate": 1.8235294117647058e-06,
+      "loss": 1.2685446739196777,
+      "step": 32
+    },
+    {
+      "epoch": 0.13545816733067728,
+      "grad_norm": 0.8954079151153564,
+      "learning_rate": 1.9411764705882353e-06,
+      "loss": 1.3833661079406738,
+      "step": 34
+    },
+    {
+      "epoch": 0.14342629482071714,
+      "grad_norm": 0.5755887627601624,
+      "learning_rate": 2.058823529411765e-06,
+      "loss": 1.5257431268692017,
+      "step": 36
+    },
+    {
+      "epoch": 0.15139442231075698,
+      "grad_norm": 2.27645206451416,
+      "learning_rate": 2.176470588235294e-06,
+      "loss": 1.2891892194747925,
+      "step": 38
+    },
+    {
+      "epoch": 0.1593625498007968,
+      "grad_norm": 0.37568527460098267,
+      "learning_rate": 2.2941176470588234e-06,
+      "loss": 1.424462080001831,
+      "step": 40
+    },
+    {
+      "epoch": 0.16733067729083664,
+      "grad_norm": 2.9606502056121826,
+      "learning_rate": 2.411764705882353e-06,
+      "loss": 0.9945810437202454,
+      "step": 42
+    },
+    {
+      "epoch": 0.1752988047808765,
+      "grad_norm": 0.474932461977005,
+      "learning_rate": 2.5294117647058823e-06,
+      "loss": 1.1145226955413818,
+      "step": 44
+    },
+    {
+      "epoch": 0.18326693227091634,
+      "grad_norm": 0.6873041391372681,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 0.9955132603645325,
+      "step": 46
+    },
+    {
+      "epoch": 0.19123505976095617,
+      "grad_norm": 1.075629711151123,
+      "learning_rate": 2.764705882352941e-06,
+      "loss": 1.2583197355270386,
+      "step": 48
+    },
+    {
+      "epoch": 0.199203187250996,
+      "grad_norm": 0.3792019784450531,
+      "learning_rate": 2.882352941176471e-06,
+      "loss": 1.4063794612884521,
+      "step": 50
+    },
+    {
+      "epoch": 0.20717131474103587,
+      "grad_norm": 0.45150187611579895,
+      "learning_rate": 3e-06,
+      "loss": 1.3480579853057861,
+      "step": 52
+    },
+    {
+      "epoch": 0.2151394422310757,
+      "grad_norm": 37.446346282958984,
+      "learning_rate": 2.999970658917326e-06,
+      "loss": 1.171717882156372,
+      "step": 54
+    },
+    {
+      "epoch": 0.22310756972111553,
+      "grad_norm": 0.5553145408630371,
+      "learning_rate": 2.9998826369447094e-06,
+      "loss": 1.567508339881897,
+      "step": 56
+    },
+    {
+      "epoch": 0.23107569721115537,
+      "grad_norm": 0.5614340901374817,
+      "learning_rate": 2.9997359379083137e-06,
+      "loss": 1.3946313858032227,
+      "step": 58
+    },
+    {
+      "epoch": 0.23904382470119523,
+      "grad_norm": 0.4262371063232422,
+      "learning_rate": 2.9995305681848922e-06,
+      "loss": 0.8638534545898438,
+      "step": 60
+    },
+    {
+      "epoch": 0.24701195219123506,
+      "grad_norm": 0.37590524554252625,
+      "learning_rate": 2.9992665367015114e-06,
+      "loss": 1.3967615365982056,
+      "step": 62
+    },
+    {
+      "epoch": 0.2549800796812749,
+      "grad_norm": 0.8519444465637207,
+      "learning_rate": 2.998943854935163e-06,
+      "loss": 1.1325318813323975,
+      "step": 64
+    },
+    {
+      "epoch": 0.26294820717131473,
+      "grad_norm": 0.3111265301704407,
+      "learning_rate": 2.9985625369122664e-06,
+      "loss": 1.312957525253296,
+      "step": 66
+    },
+    {
+      "epoch": 0.27091633466135456,
+      "grad_norm": 1.5971601009368896,
+      "learning_rate": 2.998122599208055e-06,
+      "loss": 0.9911661148071289,
+      "step": 68
+    },
+    {
+      "epoch": 0.2788844621513944,
+      "grad_norm": 0.5279662013053894,
+      "learning_rate": 2.9976240609458617e-06,
+      "loss": 1.567615032196045,
+      "step": 70
+    },
+    {
+      "epoch": 0.2868525896414343,
+      "grad_norm": 2.7161941528320312,
+      "learning_rate": 2.9970669437962822e-06,
+      "loss": 0.8429480791091919,
+      "step": 72
+    },
+    {
+      "epoch": 0.2948207171314741,
+      "grad_norm": 1.455247163772583,
+      "learning_rate": 2.9964512719762347e-06,
+      "loss": 1.1409013271331787,
+      "step": 74
+    },
+    {
+      "epoch": 0.30278884462151395,
+      "grad_norm": 0.41458117961883545,
+      "learning_rate": 2.9957770722479088e-06,
+      "loss": 1.4755173921585083,
+      "step": 76
+    },
+    {
+      "epoch": 0.3107569721115538,
+      "grad_norm": 2.052013635635376,
+      "learning_rate": 2.9950443739176006e-06,
+      "loss": 0.9957228899002075,
+      "step": 78
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 0.35525253415107727,
+      "learning_rate": 2.99425320883444e-06,
+      "loss": 0.8386018872261047,
+      "step": 80
+    },
+    {
+      "epoch": 0.32669322709163345,
+      "grad_norm": 0.39254093170166016,
+      "learning_rate": 2.993403611389005e-06,
+      "loss": 1.3378560543060303,
+      "step": 82
+    },
+    {
+      "epoch": 0.3346613545816733,
+      "grad_norm": 0.6873935461044312,
+      "learning_rate": 2.992495618511827e-06,
+      "loss": 0.8897277116775513,
+      "step": 84
+    },
+    {
+      "epoch": 0.3426294820717131,
+      "grad_norm": 0.6063620448112488,
+      "learning_rate": 2.991529269671786e-06,
+      "loss": 1.3212584257125854,
+      "step": 86
+    },
+    {
+      "epoch": 0.350597609561753,
+      "grad_norm": 0.685740053653717,
+      "learning_rate": 2.9905046068743946e-06,
+      "loss": 0.8896841406822205,
+      "step": 88
+    },
+    {
+      "epoch": 0.35856573705179284,
+      "grad_norm": 0.3957422375679016,
+      "learning_rate": 2.9894216746599727e-06,
+      "loss": 1.3377217054367065,
+      "step": 90
+    },
+    {
+      "epoch": 0.3665338645418327,
+      "grad_norm": 2.463545799255371,
+      "learning_rate": 2.9882805201017116e-06,
+      "loss": 1.133660912513733,
+      "step": 92
+    },
+    {
+      "epoch": 0.3745019920318725,
+      "grad_norm": 0.4274525046348572,
+      "learning_rate": 2.9870811928036256e-06,
+      "loss": 1.2548623085021973,
+      "step": 94
+    },
+    {
+      "epoch": 0.38247011952191234,
+      "grad_norm": 0.9313490986824036,
+      "learning_rate": 2.985823744898399e-06,
+      "loss": 1.1074374914169312,
+      "step": 96
+    },
+    {
+      "epoch": 0.3904382470119522,
+      "grad_norm": 0.2799544632434845,
+      "learning_rate": 2.984508231045117e-06,
+      "loss": 1.2744643688201904,
+      "step": 98
+    },
+    {
+      "epoch": 0.398406374501992,
+      "grad_norm": 0.5394402146339417,
+      "learning_rate": 2.9831347084268923e-06,
+      "loss": 0.9088782072067261,
+      "step": 100
+    },
+    {
+      "epoch": 0.4063745019920319,
+      "grad_norm": 0.5486662983894348,
+      "learning_rate": 2.981703236748378e-06,
+      "loss": 1.2874795198440552,
+      "step": 102
+    },
+    {
+      "epoch": 0.41434262948207173,
+      "grad_norm": 0.40334078669548035,
+      "learning_rate": 2.9802138782331712e-06,
+      "loss": 0.776800274848938,
+      "step": 104
+    },
+    {
+      "epoch": 0.42231075697211157,
+      "grad_norm": 1.1005347967147827,
+      "learning_rate": 2.978666697621112e-06,
+      "loss": 0.733248770236969,
+      "step": 106
+    },
+    {
+      "epoch": 0.4302788844621514,
+      "grad_norm": 0.7740170955657959,
+      "learning_rate": 2.9770617621654656e-06,
+      "loss": 0.9902894496917725,
+      "step": 108
+    },
+    {
+      "epoch": 0.43824701195219123,
+      "grad_norm": 0.4173789918422699,
+      "learning_rate": 2.9753991416300007e-06,
+      "loss": 1.2939473390579224,
+      "step": 110
+    },
+    {
+      "epoch": 0.44621513944223107,
+      "grad_norm": 1.0325746536254883,
+      "learning_rate": 2.9736789082859568e-06,
+      "loss": 0.8199123740196228,
+      "step": 112
+    },
+    {
+      "epoch": 0.4541832669322709,
+      "grad_norm": 0.8412153720855713,
+      "learning_rate": 2.9719011369089025e-06,
+      "loss": 1.1337602138519287,
+      "step": 114
+    },
+    {
+      "epoch": 0.46215139442231074,
+      "grad_norm": 0.42725688219070435,
+      "learning_rate": 2.970065904775485e-06,
+      "loss": 1.2960267066955566,
+      "step": 116
+    },
+    {
+      "epoch": 0.4701195219123506,
+      "grad_norm": 0.4095574617385864,
+      "learning_rate": 2.968173291660071e-06,
+      "loss": 1.36135995388031,
+      "step": 118
+    },
+    {
+      "epoch": 0.47808764940239046,
+      "grad_norm": 0.5657700300216675,
+      "learning_rate": 2.9662233798312805e-06,
+      "loss": 1.2439430952072144,
+      "step": 120
+    },
+    {
+      "epoch": 0.4860557768924303,
+      "grad_norm": 0.4052128791809082,
+      "learning_rate": 2.9642162540484077e-06,
+      "loss": 0.9588472247123718,
+      "step": 122
+    },
+    {
+      "epoch": 0.4940239043824701,
+      "grad_norm": 1.1219152212142944,
+      "learning_rate": 2.96215200155774e-06,
+      "loss": 1.0325348377227783,
+      "step": 124
+    },
+    {
+      "epoch": 0.50199203187251,
+      "grad_norm": 1.6725101470947266,
+      "learning_rate": 2.9600307120887623e-06,
+      "loss": 0.9328906536102295,
+      "step": 126
+    },
+    {
+      "epoch": 0.5099601593625498,
+      "grad_norm": 0.5302041172981262,
+      "learning_rate": 2.9578524778502605e-06,
+      "loss": 1.2722545862197876,
+      "step": 128
+    },
+    {
+      "epoch": 0.5179282868525896,
+      "grad_norm": 0.4805465042591095,
+      "learning_rate": 2.9556173935263094e-06,
+      "loss": 0.9367498159408569,
+      "step": 130
+    },
+    {
+      "epoch": 0.5258964143426295,
+      "grad_norm": 0.34964123368263245,
+      "learning_rate": 2.9533255562721594e-06,
+      "loss": 0.8116304278373718,
+      "step": 132
+    },
+    {
+      "epoch": 0.5338645418326693,
+      "grad_norm": 0.3873235881328583,
+      "learning_rate": 2.950977065710012e-06,
+      "loss": 0.8979853391647339,
+      "step": 134
+    },
+    {
+      "epoch": 0.5418326693227091,
+      "grad_norm": 0.49073103070259094,
+      "learning_rate": 2.9485720239246913e-06,
+      "loss": 1.2764328718185425,
+      "step": 136
+    },
+    {
+      "epoch": 0.549800796812749,
+      "grad_norm": 0.9829900860786438,
+      "learning_rate": 2.946110535459204e-06,
+      "loss": 0.9340943694114685,
+      "step": 138
+    },
+    {
+      "epoch": 0.5577689243027888,
+      "grad_norm": 0.6929047703742981,
+      "learning_rate": 2.9435927073101974e-06,
+      "loss": 1.0783215761184692,
+      "step": 140
+    },
+    {
+      "epoch": 0.5657370517928287,
+      "grad_norm": 0.33450594544410706,
+      "learning_rate": 2.9410186489233063e-06,
+      "loss": 1.015251636505127,
+      "step": 142
+    },
+    {
+      "epoch": 0.5737051792828686,
+      "grad_norm": 0.4002437889575958,
+      "learning_rate": 2.9383884721883973e-06,
+      "loss": 1.2262054681777954,
+      "step": 144
+    },
+    {
+      "epoch": 0.5816733067729084,
+      "grad_norm": 0.5956969261169434,
+      "learning_rate": 2.9357022914347046e-06,
+      "loss": 1.382331132888794,
+      "step": 146
+    },
+    {
+      "epoch": 0.5896414342629482,
+      "grad_norm": 0.49758458137512207,
+      "learning_rate": 2.9329602234258606e-06,
+      "loss": 0.9430940747261047,
+      "step": 148
+    },
+    {
+      "epoch": 0.5976095617529881,
+      "grad_norm": 0.6348124146461487,
+      "learning_rate": 2.9301623873548187e-06,
+      "loss": 0.9293842315673828,
+      "step": 150
+    },
+    {
+      "epoch": 0.6055776892430279,
+      "grad_norm": 0.8025413155555725,
+      "learning_rate": 2.9273089048386757e-06,
+      "loss": 0.9237926602363586,
+      "step": 152
+    },
+    {
+      "epoch": 0.6135458167330677,
+      "grad_norm": 9.821154594421387,
+      "learning_rate": 2.9243998999133803e-06,
+      "loss": 1.1090776920318604,
+      "step": 154
+    },
+    {
+      "epoch": 0.6215139442231076,
+      "grad_norm": 1.79253351688385,
+      "learning_rate": 2.921435499028347e-06,
+      "loss": 0.8607668280601501,
+      "step": 156
+    },
+    {
+      "epoch": 0.6294820717131474,
+      "grad_norm": 0.6355870366096497,
+      "learning_rate": 2.918415831040955e-06,
+      "loss": 1.1218218803405762,
+      "step": 158
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": 0.4850366711616516,
+      "learning_rate": 2.91534102721095e-06,
+      "loss": 1.0082756280899048,
+      "step": 160
+    },
+    {
+      "epoch": 0.6454183266932271,
+      "grad_norm": 0.22921444475650787,
+      "learning_rate": 2.9122112211947373e-06,
+      "loss": 0.7417871952056885,
+      "step": 162
+    },
+    {
+      "epoch": 0.6533864541832669,
+      "grad_norm": 0.2860549986362457,
+      "learning_rate": 2.9090265490395713e-06,
+      "loss": 1.1341336965560913,
+      "step": 164
+    },
+    {
+      "epoch": 0.6613545816733067,
+      "grad_norm": 0.9676735401153564,
+      "learning_rate": 2.9057871491776436e-06,
+      "loss": 0.7781538963317871,
+      "step": 166
+    },
+    {
+      "epoch": 0.6693227091633466,
+      "grad_norm": 0.3801421523094177,
+      "learning_rate": 2.9024931624200637e-06,
+      "loss": 1.2313846349716187,
+      "step": 168
+    },
+    {
+      "epoch": 0.6772908366533864,
+      "grad_norm": 1.8267383575439453,
+      "learning_rate": 2.899144731950739e-06,
+      "loss": 0.8328909873962402,
+      "step": 170
+    },
+    {
+      "epoch": 0.6852589641434262,
+      "grad_norm": 0.43613070249557495,
+      "learning_rate": 2.895742003320152e-06,
+      "loss": 0.8186226487159729,
+      "step": 172
+    },
+    {
+      "epoch": 0.6932270916334662,
+      "grad_norm": 0.6106582283973694,
+      "learning_rate": 2.8922851244390312e-06,
+      "loss": 1.2231653928756714,
+      "step": 174
+    },
+    {
+      "epoch": 0.701195219123506,
+      "grad_norm": 0.9366831183433533,
+      "learning_rate": 2.888774245571924e-06,
+      "loss": 0.7547324299812317,
+      "step": 176
+    },
+    {
+      "epoch": 0.7091633466135459,
+      "grad_norm": 1.2000120878219604,
+      "learning_rate": 2.8852095193306633e-06,
+      "loss": 0.8711674809455872,
+      "step": 178
+    },
+    {
+      "epoch": 0.7171314741035857,
+      "grad_norm": 0.8977218270301819,
+      "learning_rate": 2.8815911006677326e-06,
+      "loss": 1.0363984107971191,
+      "step": 180
+    },
+    {
+      "epoch": 0.7250996015936255,
+      "grad_norm": 0.23066113889217377,
+      "learning_rate": 2.877919146869535e-06,
+      "loss": 0.4867554008960724,
+      "step": 182
+    },
+    {
+      "epoch": 0.7330677290836654,
+      "grad_norm": 0.45316410064697266,
+      "learning_rate": 2.874193817549551e-06,
+      "loss": 1.250420331954956,
+      "step": 184
+    },
+    {
+      "epoch": 0.7410358565737052,
+      "grad_norm": 0.40230974555015564,
+      "learning_rate": 2.870415274641405e-06,
+      "loss": 1.2383266687393188,
+      "step": 186
+    },
+    {
+      "epoch": 0.749003984063745,
+      "grad_norm": 0.46227118372917175,
+      "learning_rate": 2.866583682391821e-06,
+      "loss": 1.0794142484664917,
+      "step": 188
+    },
+    {
+      "epoch": 0.7569721115537849,
+      "grad_norm": 1.3957983255386353,
+      "learning_rate": 2.8626992073534888e-06,
+      "loss": 0.8541224598884583,
+      "step": 190
+    },
+    {
+      "epoch": 0.7649402390438247,
+      "grad_norm": 0.618249237537384,
+      "learning_rate": 2.858762018377821e-06,
+      "loss": 1.187286615371704,
+      "step": 192
+    },
+    {
+      "epoch": 0.7729083665338645,
+      "grad_norm": 0.6879091858863831,
+      "learning_rate": 2.8547722866076125e-06,
+      "loss": 0.8607790470123291,
+      "step": 194
+    },
+    {
+      "epoch": 0.7808764940239044,
+      "grad_norm": 0.6802543997764587,
+      "learning_rate": 2.850730185469604e-06,
+      "loss": 0.5753005743026733,
+      "step": 196
+    },
+    {
+      "epoch": 0.7888446215139442,
+      "grad_norm": 2.574225664138794,
+      "learning_rate": 2.8466358906669423e-06,
+      "loss": 0.7759158611297607,
+      "step": 198
+    },
+    {
+      "epoch": 0.796812749003984,
+      "grad_norm": 1.023215651512146,
+      "learning_rate": 2.842489580171541e-06,
+      "loss": 1.0175625085830688,
+      "step": 200
+    },
+    {
+      "epoch": 0.8047808764940239,
+      "grad_norm": 0.2602544128894806,
+      "learning_rate": 2.838291434216347e-06,
+      "loss": 0.95418781042099,
+      "step": 202
+    },
+    {
+      "epoch": 0.8127490039840638,
+      "grad_norm": 0.4951968193054199,
+      "learning_rate": 2.8340416352875057e-06,
+      "loss": 1.4974547624588013,
+      "step": 204
+    },
+    {
+      "epoch": 0.8207171314741036,
+      "grad_norm": 0.4747754633426666,
+      "learning_rate": 2.8297403681164256e-06,
+      "loss": 1.2074265480041504,
+      "step": 206
+    },
+    {
+      "epoch": 0.8286852589641435,
+      "grad_norm": 0.5524476766586304,
+      "learning_rate": 2.825387819671754e-06,
+      "loss": 0.5993782877922058,
+      "step": 208
+    },
+    {
+      "epoch": 0.8366533864541833,
+      "grad_norm": 0.6101752519607544,
+      "learning_rate": 2.820984179151243e-06,
+      "loss": 1.2540825605392456,
+      "step": 210
+    },
+    {
+      "epoch": 0.8446215139442231,
+      "grad_norm": 0.4768051505088806,
+      "learning_rate": 2.816529637973531e-06,
+      "loss": 1.2111059427261353,
+      "step": 212
+    },
+    {
+      "epoch": 0.852589641434263,
+      "grad_norm": 0.4470526874065399,
+      "learning_rate": 2.8120243897698197e-06,
+      "loss": 0.936885416507721,
+      "step": 214
+    },
+    {
+      "epoch": 0.8605577689243028,
+      "grad_norm": 0.8324171900749207,
+      "learning_rate": 2.807468630375457e-06,
+      "loss": 1.4127908945083618,
+      "step": 216
+    },
+    {
+      "epoch": 0.8685258964143426,
+      "grad_norm": 0.8571661710739136,
+      "learning_rate": 2.802862557821425e-06,
+      "loss": 0.9163059592247009,
+      "step": 218
+    },
+    {
+      "epoch": 0.8764940239043825,
+      "grad_norm": 0.656310498714447,
+      "learning_rate": 2.7982063723257324e-06,
+      "loss": 1.2317224740982056,
+      "step": 220
+    },
+    {
+      "epoch": 0.8844621513944223,
+      "grad_norm": 0.94222491979599,
+      "learning_rate": 2.7935002762847104e-06,
+      "loss": 1.4826358556747437,
+      "step": 222
+    },
+    {
+      "epoch": 0.8924302788844621,
+      "grad_norm": 0.6392826437950134,
+      "learning_rate": 2.7887444742642153e-06,
+      "loss": 0.7295237183570862,
+      "step": 224
+    },
+    {
+      "epoch": 0.900398406374502,
+      "grad_norm": 0.40648454427719116,
+      "learning_rate": 2.783939172990736e-06,
+      "loss": 0.9684391021728516,
+      "step": 226
+    },
+    {
+      "epoch": 0.9083665338645418,
+      "grad_norm": 1.8654367923736572,
+      "learning_rate": 2.7790845813424085e-06,
+      "loss": 1.076025128364563,
+      "step": 228
+    },
+    {
+      "epoch": 0.9163346613545816,
+      "grad_norm": 0.5885425806045532,
+      "learning_rate": 2.7741809103399372e-06,
+      "loss": 1.1793254613876343,
+      "step": 230
+    },
+    {
+      "epoch": 0.9243027888446215,
+      "grad_norm": 0.4949474334716797,
+      "learning_rate": 2.76922837313742e-06,
+      "loss": 1.3203648328781128,
+      "step": 232
+    },
+    {
+      "epoch": 0.9322709163346613,
+      "grad_norm": 0.6972324252128601,
+      "learning_rate": 2.7642271850130845e-06,
+      "loss": 0.8468176126480103,
+      "step": 234
+    },
+    {
+      "epoch": 0.9402390438247012,
+      "grad_norm": 0.3574720323085785,
+      "learning_rate": 2.7591775633599295e-06,
+      "loss": 0.8511747121810913,
+      "step": 236
+    },
+    {
+      "epoch": 0.9482071713147411,
+      "grad_norm": 1.726371169090271,
+      "learning_rate": 2.7540797276762748e-06,
+      "loss": 0.43165379762649536,
+      "step": 238
+    },
+    {
+      "epoch": 0.9561752988047809,
+      "grad_norm": 1.3261985778808594,
+      "learning_rate": 2.7489338995562223e-06,
+      "loss": 0.8357299566268921,
+      "step": 240
+    },
+    {
+      "epoch": 0.9641434262948207,
+      "grad_norm": 0.796555757522583,
+      "learning_rate": 2.743740302680021e-06,
+      "loss": 1.1258844137191772,
+      "step": 242
+    },
+    {
+      "epoch": 0.9721115537848606,
+      "grad_norm": 0.3952471911907196,
+      "learning_rate": 2.738499162804346e-06,
+      "loss": 1.2129818201065063,
+      "step": 244
+    },
+    {
+      "epoch": 0.9800796812749004,
+      "grad_norm": 3.2808635234832764,
+      "learning_rate": 2.733210707752483e-06,
+      "loss": 0.9465621113777161,
+      "step": 246
+    },
+    {
+      "epoch": 0.9880478087649402,
+      "grad_norm": 0.36960551142692566,
+      "learning_rate": 2.7278751674044277e-06,
+      "loss": 0.9761192202568054,
+      "step": 248
+    },
+    {
+      "epoch": 0.9960159362549801,
+      "grad_norm": 0.40931713581085205,
+      "learning_rate": 2.7224927736868926e-06,
+      "loss": 0.9702551364898682,
+      "step": 250
+    },
+    {
+      "epoch": 1.00398406374502,
+      "grad_norm": 0.870992124080658,
+      "learning_rate": 2.7170637605632236e-06,
+      "loss": 0.9026790857315063,
+      "step": 252
+    },
+    {
+      "epoch": 1.0119521912350598,
+      "grad_norm": 0.5800741910934448,
+      "learning_rate": 2.7115883640232326e-06,
+      "loss": 0.696426272392273,
+      "step": 254
+    },
+    {
+      "epoch": 1.0199203187250996,
+      "grad_norm": 0.5435763001441956,
+      "learning_rate": 2.706066822072938e-06,
+      "loss": 1.1814464330673218,
+      "step": 256
+    },
+    {
+      "epoch": 1.0278884462151394,
+      "grad_norm": 0.7086870074272156,
+      "learning_rate": 2.70049937472422e-06,
+      "loss": 1.1569794416427612,
+      "step": 258
+    },
+    {
+      "epoch": 1.0358565737051793,
+      "grad_norm": 0.6994827389717102,
+      "learning_rate": 2.694886263984387e-06,
+      "loss": 1.092099905014038,
+      "step": 260
+    },
+    {
+      "epoch": 1.043824701195219,
+      "grad_norm": 0.5085208415985107,
+      "learning_rate": 2.6892277338456545e-06,
+      "loss": 1.0143777132034302,
+      "step": 262
+    },
+    {
+      "epoch": 1.051792828685259,
+      "grad_norm": 0.7572088837623596,
+      "learning_rate": 2.6835240302745432e-06,
+      "loss": 1.1160310506820679,
+      "step": 264
+    },
+    {
+      "epoch": 1.0597609561752988,
+      "grad_norm": 0.969849705696106,
+      "learning_rate": 2.6777754012011822e-06,
+      "loss": 0.6508786678314209,
+      "step": 266
+    },
+    {
+      "epoch": 1.0677290836653386,
+      "grad_norm": 0.40249520540237427,
+      "learning_rate": 2.6719820965085373e-06,
+      "loss": 0.9302061796188354,
+      "step": 268
+    },
+    {
+      "epoch": 1.0756972111553784,
+      "grad_norm": 0.39779043197631836,
+      "learning_rate": 2.6661443680215436e-06,
+      "loss": 0.5909485220909119,
+      "step": 270
+    },
+    {
+      "epoch": 1.0836653386454183,
+      "grad_norm": 0.4452027976512909,
+      "learning_rate": 2.6602624694961634e-06,
+      "loss": 1.2358585596084595,
+      "step": 272
+    },
+    {
+      "epoch": 1.091633466135458,
+      "grad_norm": 1.504374623298645,
+      "learning_rate": 2.6543366566083536e-06,
+      "loss": 0.602242648601532,
+      "step": 274
+    },
+    {
+      "epoch": 1.099601593625498,
+      "grad_norm": 0.4246741831302643,
+      "learning_rate": 2.6483671869429515e-06,
+      "loss": 0.925746500492096,
+      "step": 276
+    },
+    {
+      "epoch": 1.1075697211155378,
+      "grad_norm": 0.4856192171573639,
+      "learning_rate": 2.6423543199824814e-06,
+      "loss": 0.8335383534431458,
+      "step": 278
+    },
+    {
+      "epoch": 1.1155378486055776,
+      "grad_norm": 0.46481937170028687,
+      "learning_rate": 2.6362983170958708e-06,
+      "loss": 1.0746686458587646,
+      "step": 280
+    },
+    {
+      "epoch": 1.1235059760956174,
+      "grad_norm": 0.40899351239204407,
+      "learning_rate": 2.6301994415270927e-06,
+      "loss": 1.1849327087402344,
+      "step": 282
+    },
+    {
+      "epoch": 1.1314741035856573,
+      "grad_norm": 1.2962706089019775,
+      "learning_rate": 2.62405795838372e-06,
+      "loss": 1.1970727443695068,
+      "step": 284
+    },
+    {
+      "epoch": 1.139442231075697,
+      "grad_norm": 1.8368911743164062,
+      "learning_rate": 2.617874134625405e-06,
+      "loss": 0.3501308858394623,
+      "step": 286
+    },
+    {
+      "epoch": 1.1474103585657371,
+      "grad_norm": 0.2166207730770111,
+      "learning_rate": 2.6116482390522715e-06,
+      "loss": 0.7515382170677185,
+      "step": 288
+    },
+    {
+      "epoch": 1.155378486055777,
+      "grad_norm": 0.823740541934967,
+      "learning_rate": 2.605380542293234e-06,
+      "loss": 0.9569700360298157,
+      "step": 290
+    },
+    {
+      "epoch": 1.1633466135458168,
+      "grad_norm": 0.6585810780525208,
+      "learning_rate": 2.5990713167942306e-06,
+      "loss": 0.5356516242027283,
+      "step": 292
+    },
+    {
+      "epoch": 1.1713147410358566,
+      "grad_norm": 0.4426569640636444,
+      "learning_rate": 2.5927208368063825e-06,
+      "loss": 1.1944938898086548,
+      "step": 294
+    },
+    {
+      "epoch": 1.1792828685258965,
+      "grad_norm": 0.3524056673049927,
+      "learning_rate": 2.586329378374074e-06,
+      "loss": 1.2448694705963135,
+      "step": 296
+    },
+    {
+      "epoch": 1.1872509960159363,
+      "grad_norm": 0.3419857621192932,
+      "learning_rate": 2.5798972193229485e-06,
+      "loss": 1.384804129600525,
+      "step": 298
+    },
+    {
+      "epoch": 1.1952191235059761,
+      "grad_norm": 1.195278286933899,
+      "learning_rate": 2.573424639247837e-06,
+      "loss": 0.6737868189811707,
+      "step": 300
+    },
+    {
+      "epoch": 1.203187250996016,
+      "grad_norm": 0.5209558606147766,
+      "learning_rate": 2.5669119195006016e-06,
+      "loss": 0.9476598501205444,
+      "step": 302
+    },
+    {
+      "epoch": 1.2111553784860558,
+      "grad_norm": 0.6349844336509705,
+      "learning_rate": 2.560359343177907e-06,
+      "loss": 0.6187256574630737,
+      "step": 304
+    },
+    {
+      "epoch": 1.2191235059760956,
+      "grad_norm": 0.6629199385643005,
+      "learning_rate": 2.553767195108914e-06,
+      "loss": 1.175504207611084,
+      "step": 306
+    },
+    {
+      "epoch": 1.2270916334661355,
+      "grad_norm": 2.9705917835235596,
+      "learning_rate": 2.547135761842899e-06,
+      "loss": 1.0829224586486816,
+      "step": 308
+    },
+    {
+      "epoch": 1.2350597609561753,
+      "grad_norm": 0.5714198350906372,
+      "learning_rate": 2.5404653316367983e-06,
+      "loss": 1.107988953590393,
+      "step": 310
+    },
+    {
+      "epoch": 1.2430278884462151,
+      "grad_norm": 0.5963674783706665,
+      "learning_rate": 2.533756194442676e-06,
+      "loss": 1.066701054573059,
+      "step": 312
+    },
+    {
+      "epoch": 1.250996015936255,
+      "grad_norm": 0.4868275225162506,
+      "learning_rate": 2.527008641895124e-06,
+      "loss": 0.8929526209831238,
+      "step": 314
+    },
+    {
+      "epoch": 1.2589641434262948,
+      "grad_norm": 0.5656901001930237,
+      "learning_rate": 2.5202229672985834e-06,
+      "loss": 0.7201364040374756,
+      "step": 316
+    },
+    {
+      "epoch": 1.2669322709163346,
+      "grad_norm": 1.8498417139053345,
+      "learning_rate": 2.513399465614593e-06,
+      "loss": 0.7000647187232971,
+      "step": 318
+    },
+    {
+      "epoch": 1.2749003984063745,
+      "grad_norm": 1.8695796728134155,
+      "learning_rate": 2.5065384334489707e-06,
+      "loss": 0.6135216355323792,
+      "step": 320
+    },
+    {
+      "epoch": 1.2828685258964143,
+      "grad_norm": 1.0598129034042358,
+      "learning_rate": 2.499640169038919e-06,
+      "loss": 0.9898048639297485,
+      "step": 322
+    },
+    {
+      "epoch": 1.2908366533864541,
+      "grad_norm": 0.43019378185272217,
+      "learning_rate": 2.4927049722400632e-06,
+      "loss": 0.9241266250610352,
+      "step": 324
+    },
+    {
+      "epoch": 1.298804780876494,
+      "grad_norm": 8.146377563476562,
+      "learning_rate": 2.4857331445134148e-06,
+      "loss": 1.3060351610183716,
+      "step": 326
+    },
+    {
+      "epoch": 1.3067729083665338,
+      "grad_norm": 0.3936547338962555,
+      "learning_rate": 2.4787249889122664e-06,
+      "loss": 0.7562607526779175,
+      "step": 328
+    },
+    {
+      "epoch": 1.3147410358565736,
+      "grad_norm": 0.45019447803497314,
+      "learning_rate": 2.4716808100690243e-06,
+      "loss": 0.9096888303756714,
+      "step": 330
+    },
+    {
+      "epoch": 1.3227091633466135,
+      "grad_norm": 0.6943168044090271,
+      "learning_rate": 2.4646009141819594e-06,
+      "loss": 1.000761866569519,
+      "step": 332
+    },
+    {
+      "epoch": 1.3306772908366533,
+      "grad_norm": 1.2407184839248657,
+      "learning_rate": 2.4574856090019033e-06,
+      "loss": 0.7026602029800415,
+      "step": 334
+    },
+    {
+      "epoch": 1.3386454183266931,
+      "grad_norm": 1.955567479133606,
+      "learning_rate": 2.4503352038188665e-06,
+      "loss": 0.8961894512176514,
+      "step": 336
+    },
+    {
+      "epoch": 1.3466135458167332,
+      "grad_norm": 0.6083151698112488,
+      "learning_rate": 2.4431500094485963e-06,
+      "loss": 1.196513056755066,
+      "step": 338
+    },
+    {
+      "epoch": 1.354581673306773,
+      "grad_norm": 0.3481491804122925,
+      "learning_rate": 2.435930338219066e-06,
+      "loss": 1.1471824645996094,
+      "step": 340
+    },
+    {
+      "epoch": 1.3625498007968129,
+      "grad_norm": 0.3202623128890991,
+      "learning_rate": 2.4286765039568996e-06,
+      "loss": 1.1803168058395386,
+      "step": 342
+    },
+    {
+      "epoch": 1.3705179282868527,
+      "grad_norm": 0.5573057532310486,
+      "learning_rate": 2.4213888219737273e-06,
+      "loss": 1.145288109779358,
+      "step": 344
+    },
+    {
+      "epoch": 1.3784860557768925,
+      "grad_norm": 0.7530761361122131,
+      "learning_rate": 2.4140676090524813e-06,
+      "loss": 0.7112540006637573,
+      "step": 346
+    },
+    {
+      "epoch": 1.3864541832669324,
+      "grad_norm": 0.31881389021873474,
+      "learning_rate": 2.4067131834336265e-06,
+      "loss": 1.1765650510787964,
+      "step": 348
+    },
+    {
+      "epoch": 1.3944223107569722,
+      "grad_norm": 0.5150675773620605,
+      "learning_rate": 2.3993258648013265e-06,
+      "loss": 0.7162399291992188,
+      "step": 350
+    },
+    {
+      "epoch": 1.402390438247012,
+      "grad_norm": 0.4000639021396637,
+      "learning_rate": 2.391905974269546e-06,
+      "loss": 1.1982700824737549,
+      "step": 352
+    },
+    {
+      "epoch": 1.4103585657370519,
+      "grad_norm": 0.5254287719726562,
+      "learning_rate": 2.3844538343680954e-06,
+      "loss": 1.1246976852416992,
+      "step": 354
+    },
+    {
+      "epoch": 1.4183266932270917,
+      "grad_norm": 0.7500051259994507,
+      "learning_rate": 2.376969769028608e-06,
+      "loss": 0.9707033634185791,
+      "step": 356
+    },
+    {
+      "epoch": 1.4262948207171315,
+      "grad_norm": 0.4242282211780548,
+      "learning_rate": 2.3694541035704623e-06,
+      "loss": 1.1708297729492188,
+      "step": 358
+    },
+    {
+      "epoch": 1.4342629482071714,
+      "grad_norm": 0.5363942384719849,
+      "learning_rate": 2.361907164686638e-06,
+      "loss": 0.6365261077880859,
+      "step": 360
+    },
+    {
+      "epoch": 1.4422310756972112,
+      "grad_norm": 0.34740063548088074,
+      "learning_rate": 2.3543292804295164e-06,
+      "loss": 0.7796180844306946,
+      "step": 362
+    },
+    {
+      "epoch": 1.450199203187251,
+      "grad_norm": 0.8936453461647034,
+      "learning_rate": 2.3467207801966217e-06,
+      "loss": 1.069722056388855,
+      "step": 364
+    },
+    {
+      "epoch": 1.4581673306772909,
+      "grad_norm": 0.5224515199661255,
+      "learning_rate": 2.339081994716301e-06,
+      "loss": 1.1437441110610962,
+      "step": 366
+    },
+    {
+      "epoch": 1.4661354581673307,
+      "grad_norm": 0.3716191351413727,
+      "learning_rate": 2.3314132560333486e-06,
+      "loss": 0.6178401708602905,
+      "step": 368
+    },
+    {
+      "epoch": 1.4741035856573705,
+      "grad_norm": 0.38474348187446594,
+      "learning_rate": 2.3237148974945732e-06,
+      "loss": 0.6917285323143005,
+      "step": 370
+    },
+    {
+      "epoch": 1.4820717131474104,
+      "grad_norm": 0.6348185539245605,
+      "learning_rate": 2.315987253734307e-06,
+      "loss": 1.248483657836914,
+      "step": 372
+    },
+    {
+      "epoch": 1.4900398406374502,
+      "grad_norm": 0.5666549205780029,
+      "learning_rate": 2.308230660659861e-06,
+      "loss": 1.1805977821350098,
+      "step": 374
+    },
+    {
+      "epoch": 1.49800796812749,
+      "grad_norm": 0.3927704393863678,
+      "learning_rate": 2.300445455436921e-06,
+      "loss": 1.144189715385437,
+      "step": 376
+    },
+    {
+      "epoch": 1.5059760956175299,
+      "grad_norm": 1.197426676750183,
+      "learning_rate": 2.292631976474895e-06,
+      "loss": 0.9748780131340027,
+      "step": 378
+    },
+    {
+      "epoch": 1.5139442231075697,
+      "grad_norm": 0.5384941101074219,
+      "learning_rate": 2.284790563412201e-06,
+      "loss": 1.1320137977600098,
+      "step": 380
+    },
+    {
+      "epoch": 1.5219123505976095,
+      "grad_norm": 0.40527671575546265,
+      "learning_rate": 2.2769215571015054e-06,
+      "loss": 0.756669282913208,
+      "step": 382
+    },
+    {
+      "epoch": 1.5298804780876494,
+      "grad_norm": 0.5759975910186768,
+      "learning_rate": 2.2690252995949015e-06,
+      "loss": 0.7979004979133606,
+      "step": 384
+    },
+    {
+      "epoch": 1.5378486055776892,
+      "grad_norm": 0.7272588014602661,
+      "learning_rate": 2.2611021341290494e-06,
+      "loss": 1.049770474433899,
+      "step": 386
+    },
+    {
+      "epoch": 1.545816733067729,
+      "grad_norm": 0.495037317276001,
+      "learning_rate": 2.2531524051102493e-06,
+      "loss": 1.1562248468399048,
+      "step": 388
+    },
+    {
+      "epoch": 1.5537848605577689,
+      "grad_norm": 0.6938880681991577,
+      "learning_rate": 2.245176458099474e-06,
+      "loss": 0.5849276781082153,
+      "step": 390
+    },
+    {
+      "epoch": 1.5617529880478087,
+      "grad_norm": 0.6492685675621033,
+      "learning_rate": 2.237174639797346e-06,
+      "loss": 0.6089207530021667,
+      "step": 392
+    },
+    {
+      "epoch": 1.5697211155378485,
+      "grad_norm": 0.7078109383583069,
+      "learning_rate": 2.2291472980290696e-06,
+      "loss": 1.174211025238037,
+      "step": 394
+    },
+    {
+      "epoch": 1.5776892430278884,
+      "grad_norm": 0.5934572219848633,
+      "learning_rate": 2.221094781729308e-06,
+      "loss": 1.045981526374817,
+      "step": 396
+    },
+    {
+      "epoch": 1.5856573705179282,
+      "grad_norm": 0.40928709506988525,
+      "learning_rate": 2.2130174409270204e-06,
+      "loss": 1.1423792839050293,
+      "step": 398
+    },
+    {
+      "epoch": 1.593625498007968,
+      "grad_norm": 0.9985561370849609,
+      "learning_rate": 2.204915626730242e-06,
+      "loss": 0.6377730369567871,
+      "step": 400
+    },
+    {
+      "epoch": 1.6015936254980079,
+      "grad_norm": 0.6911800503730774,
+      "learning_rate": 2.1967896913108245e-06,
+      "loss": 1.1229146718978882,
+      "step": 402
+    },
+    {
+      "epoch": 1.6095617529880477,
+      "grad_norm": 0.45020508766174316,
+      "learning_rate": 2.1886399878891288e-06,
+      "loss": 1.2710224390029907,
+      "step": 404
+    },
+    {
+      "epoch": 1.6175298804780875,
+      "grad_norm": 1.1965842247009277,
+      "learning_rate": 2.1804668707186685e-06,
+      "loss": 0.7574101686477661,
+      "step": 406
+    },
+    {
+      "epoch": 1.6254980079681274,
+      "grad_norm": 0.3679886758327484,
+      "learning_rate": 2.1722706950707116e-06,
+      "loss": 0.5999529957771301,
+      "step": 408
+    },
+    {
+      "epoch": 1.6334661354581672,
+      "grad_norm": 0.3366493284702301,
+      "learning_rate": 2.1640518172188405e-06,
+      "loss": 0.8446294665336609,
+      "step": 410
+    },
+    {
+      "epoch": 1.641434262948207,
+      "grad_norm": 0.5908185243606567,
+      "learning_rate": 2.1558105944234613e-06,
+      "loss": 0.5261144638061523,
+      "step": 412
+    },
+    {
+      "epoch": 1.6494023904382469,
+      "grad_norm": 0.41685259342193604,
+      "learning_rate": 2.147547384916277e-06,
+      "loss": 0.8532723188400269,
+      "step": 414
+    },
+    {
+      "epoch": 1.6573705179282867,
+      "grad_norm": 0.45444801449775696,
+      "learning_rate": 2.1392625478847147e-06,
+      "loss": 0.7636860609054565,
+      "step": 416
+    },
+    {
+      "epoch": 1.6653386454183265,
+      "grad_norm": 0.7797396779060364,
+      "learning_rate": 2.130956443456313e-06,
+      "loss": 1.0055797100067139,
+      "step": 418
+    },
+    {
+      "epoch": 1.6733067729083664,
+      "grad_norm": 0.48384949564933777,
+      "learning_rate": 2.1226294326830663e-06,
+      "loss": 1.1412853002548218,
+      "step": 420
+    },
+    {
+      "epoch": 1.6812749003984062,
+      "grad_norm": 0.5391873121261597,
+      "learning_rate": 2.1142818775257326e-06,
+      "loss": 1.0306801795959473,
+      "step": 422
+    },
+    {
+      "epoch": 1.6892430278884463,
+      "grad_norm": 0.4576083719730377,
+      "learning_rate": 2.105914140838099e-06,
+      "loss": 0.6449341773986816,
+      "step": 424
+    },
+    {
+      "epoch": 1.697211155378486,
+      "grad_norm": 0.40177881717681885,
+      "learning_rate": 2.0975265863512077e-06,
+      "loss": 1.2080342769622803,
+      "step": 426
+    },
+    {
+      "epoch": 1.705179282868526,
+      "grad_norm": 0.41376203298568726,
+      "learning_rate": 2.0891195786575484e-06,
+      "loss": 1.1480873823165894,
+      "step": 428
+    },
+    {
+      "epoch": 1.7131474103585658,
+      "grad_norm": 0.5125391483306885,
+      "learning_rate": 2.080693483195205e-06,
+      "loss": 0.7938195466995239,
+      "step": 430
+    },
+    {
+      "epoch": 1.7211155378486056,
+      "grad_norm": 4.272192478179932,
+      "learning_rate": 2.072248666231976e-06,
+      "loss": 0.9956310987472534,
+      "step": 432
+    },
+    {
+      "epoch": 1.7290836653386454,
+      "grad_norm": 0.7369029521942139,
+      "learning_rate": 2.0637854948494514e-06,
+      "loss": 0.6916837096214294,
+      "step": 434
+    },
+    {
+      "epoch": 1.7370517928286853,
+      "grad_norm": 0.5697792768478394,
+      "learning_rate": 2.0553043369270544e-06,
+      "loss": 0.37542012333869934,
+      "step": 436
+    },
+    {
+      "epoch": 1.745019920318725,
+      "grad_norm": 0.8396166563034058,
+      "learning_rate": 2.0468055611260523e-06,
+      "loss": 0.7680933475494385,
+      "step": 438
+    },
+    {
+      "epoch": 1.752988047808765,
+      "grad_norm": 0.7971356511116028,
+      "learning_rate": 2.038289536873533e-06,
+      "loss": 0.6482405066490173,
+      "step": 440
+    },
+    {
+      "epoch": 1.7609561752988048,
+      "grad_norm": 0.6245846152305603,
+      "learning_rate": 2.029756634346343e-06,
+      "loss": 1.559065818786621,
+      "step": 442
+    },
+    {
+      "epoch": 1.7689243027888446,
+      "grad_norm": 0.3909813165664673,
+      "learning_rate": 2.021207224454998e-06,
+      "loss": 0.8277990818023682,
+      "step": 444
+    },
+    {
+      "epoch": 1.7768924302788844,
+      "grad_norm": 0.4216088652610779,
+      "learning_rate": 2.0126416788275607e-06,
+      "loss": 1.0609842538833618,
+      "step": 446
+    },
+    {
+      "epoch": 1.7848605577689243,
+      "grad_norm": 0.5274325013160706,
+      "learning_rate": 2.0040603697934875e-06,
+      "loss": 1.1131477355957031,
+      "step": 448
+    },
+    {
+      "epoch": 1.792828685258964,
+      "grad_norm": 0.40741127729415894,
+      "learning_rate": 1.995463670367441e-06,
+      "loss": 0.8610782623291016,
+      "step": 450
+    },
+    {
+      "epoch": 1.800796812749004,
+      "grad_norm": 0.3124333620071411,
+      "learning_rate": 1.986851954233079e-06,
+      "loss": 0.5843238830566406,
+      "step": 452
+    },
+    {
+      "epoch": 1.8087649402390438,
+      "grad_norm": 0.5109219551086426,
+      "learning_rate": 1.9782255957268082e-06,
+      "loss": 0.9527801275253296,
+      "step": 454
+    },
+    {
+      "epoch": 1.8167330677290838,
+      "grad_norm": 0.6287890672683716,
+      "learning_rate": 1.969584969821516e-06,
+      "loss": 0.684226930141449,
+      "step": 456
+    },
+    {
+      "epoch": 1.8247011952191237,
+      "grad_norm": 0.6896864175796509,
+      "learning_rate": 1.9609304521102664e-06,
+      "loss": 1.0557795763015747,
+      "step": 458
+    },
+    {
+      "epoch": 1.8326693227091635,
+      "grad_norm": 0.5463947057723999,
+      "learning_rate": 1.9522624187899774e-06,
+      "loss": 0.730643630027771,
+      "step": 460
+    },
+    {
+      "epoch": 1.8406374501992033,
+      "grad_norm": 0.5176675319671631,
+      "learning_rate": 1.943581246645068e-06,
+      "loss": 0.792547345161438,
+      "step": 462
+    },
+    {
+      "epoch": 1.8486055776892432,
+      "grad_norm": 0.33698317408561707,
+      "learning_rate": 1.9348873130310776e-06,
+      "loss": 0.11931800842285156,
+      "step": 464
+    },
+    {
+      "epoch": 1.856573705179283,
+      "grad_norm": 0.4697937071323395,
+      "learning_rate": 1.926180995858266e-06,
+      "loss": 1.1590396165847778,
+      "step": 466
+    },
+    {
+      "epoch": 1.8645418326693228,
+      "grad_norm": 0.6702647805213928,
+      "learning_rate": 1.9174626735751844e-06,
+      "loss": 0.5630046129226685,
+      "step": 468
+    },
+    {
+      "epoch": 1.8725099601593627,
+      "grad_norm": 0.5800269246101379,
+      "learning_rate": 1.9087327251522246e-06,
+      "loss": 1.14718759059906,
+      "step": 470
+    },
+    {
+      "epoch": 1.8804780876494025,
+      "grad_norm": 1.194881796836853,
+      "learning_rate": 1.8999915300651478e-06,
+      "loss": 1.059720516204834,
+      "step": 472
+    },
+    {
+      "epoch": 1.8884462151394423,
+      "grad_norm": 0.7230931520462036,
+      "learning_rate": 1.8912394682785866e-06,
+      "loss": 1.2374215126037598,
+      "step": 474
+    },
+    {
+      "epoch": 1.8964143426294822,
+      "grad_norm": 0.41785743832588196,
+      "learning_rate": 1.8824769202295325e-06,
+      "loss": 0.9771887063980103,
+      "step": 476
+    },
+    {
+      "epoch": 1.904382470119522,
+      "grad_norm": 0.36748501658439636,
+      "learning_rate": 1.8737042668107945e-06,
+      "loss": 0.8857436180114746,
+      "step": 478
+    },
+    {
+      "epoch": 1.9123505976095618,
+      "grad_norm": 2.2149970531463623,
+      "learning_rate": 1.8649218893544465e-06,
+      "loss": 0.6210463047027588,
+      "step": 480
+    },
+    {
+      "epoch": 1.9203187250996017,
+      "grad_norm": 0.5847256779670715,
+      "learning_rate": 1.8561301696152485e-06,
+      "loss": 0.758573591709137,
+      "step": 482
+    },
+    {
+      "epoch": 1.9282868525896415,
+      "grad_norm": 1.2704209089279175,
+      "learning_rate": 1.847329489754052e-06,
+      "loss": 1.1186835765838623,
+      "step": 484
+    },
+    {
+      "epoch": 1.9362549800796813,
+      "grad_norm": 0.3778979778289795,
+      "learning_rate": 1.8385202323211921e-06,
+      "loss": 1.2423903942108154,
+      "step": 486
+    },
+    {
+      "epoch": 1.9442231075697212,
+      "grad_norm": 0.33054208755493164,
+      "learning_rate": 1.8297027802398551e-06,
+      "loss": 1.1193066835403442,
+      "step": 488
+    },
+    {
+      "epoch": 1.952191235059761,
+      "grad_norm": 0.29046395421028137,
+      "learning_rate": 1.8208775167894336e-06,
+      "loss": 1.1333787441253662,
+      "step": 490
+    },
+    {
+      "epoch": 1.9601593625498008,
+      "grad_norm": 0.4164031147956848,
+      "learning_rate": 1.8120448255888684e-06,
+      "loss": 0.8040657639503479,
+      "step": 492
+    },
+    {
+      "epoch": 1.9681274900398407,
+      "grad_norm": 2.26190185546875,
+      "learning_rate": 1.8032050905799704e-06,
+      "loss": 0.6147015690803528,
+      "step": 494
+    },
+    {
+      "epoch": 1.9760956175298805,
+      "grad_norm": 0.3113175332546234,
+      "learning_rate": 1.7943586960107338e-06,
+      "loss": 1.0835860967636108,
+      "step": 496
+    },
+    {
+      "epoch": 1.9840637450199203,
+      "grad_norm": 0.9167985916137695,
+      "learning_rate": 1.785506026418631e-06,
+      "loss": 0.8612701296806335,
+      "step": 498
+    },
+    {
+      "epoch": 1.9920318725099602,
+      "grad_norm": 0.40828704833984375,
+      "learning_rate": 1.7766474666139e-06,
+      "loss": 1.1791200637817383,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0138927698135376,
+      "learning_rate": 1.7677834016628158e-06,
+      "loss": 0.616978108882904,
+      "step": 502
+    },
+    {
+      "epoch": 2.00796812749004,
+      "grad_norm": 0.34795933961868286,
+      "learning_rate": 1.7589142168709526e-06,
+      "loss": 0.7058793306350708,
+      "step": 504
+    },
+    {
+      "epoch": 2.0159362549800797,
+      "grad_norm": 0.6295813322067261,
+      "learning_rate": 1.7500402977664356e-06,
+      "loss": 0.6776050925254822,
+      "step": 506
+    },
+    {
+      "epoch": 2.0239043824701195,
+      "grad_norm": 0.09192030876874924,
+      "learning_rate": 1.741162030083181e-06,
+      "loss": 0.5675944685935974,
+      "step": 508
+    },
+    {
+      "epoch": 2.0318725099601593,
+      "grad_norm": 0.3637365400791168,
+      "learning_rate": 1.7322797997441324e-06,
+      "loss": 0.9497091770172119,
+      "step": 510
+    },
+    {
+      "epoch": 2.039840637450199,
+      "grad_norm": 0.9041894674301147,
+      "learning_rate": 1.7233939928444803e-06,
+      "loss": 0.8332242369651794,
+      "step": 512
+    },
+    {
+      "epoch": 2.047808764940239,
+      "grad_norm": 0.5637346506118774,
+      "learning_rate": 1.7145049956348851e-06,
+      "loss": 0.2743958532810211,
+      "step": 514
+    },
+    {
+      "epoch": 2.055776892430279,
+      "grad_norm": 1.7006338834762573,
+      "learning_rate": 1.7056131945046828e-06,
+      "loss": 0.932583212852478,
+      "step": 516
+    },
+    {
+      "epoch": 2.0637450199203187,
+      "grad_norm": 0.5010867118835449,
+      "learning_rate": 1.6967189759650917e-06,
+      "loss": 0.607980489730835,
+      "step": 518
+    },
+    {
+      "epoch": 2.0717131474103585,
+      "grad_norm": 1.4660816192626953,
+      "learning_rate": 1.6878227266324096e-06,
+      "loss": 0.9215792417526245,
+      "step": 520
+    },
+    {
+      "epoch": 2.0796812749003983,
+      "grad_norm": 0.5361967086791992,
+      "learning_rate": 1.6789248332112101e-06,
+      "loss": 1.0473201274871826,
+      "step": 522
+    },
+    {
+      "epoch": 2.087649402390438,
+      "grad_norm": 0.8016868233680725,
+      "learning_rate": 1.6700256824775327e-06,
+      "loss": 1.0217143297195435,
+      "step": 524
+    },
+    {
+      "epoch": 2.095617529880478,
+      "grad_norm": 1.3889236450195312,
+      "learning_rate": 1.6611256612620702e-06,
+      "loss": 0.4960322380065918,
+      "step": 526
+    },
+    {
+      "epoch": 2.103585657370518,
+      "grad_norm": 0.5141186714172363,
+      "learning_rate": 1.6522251564333527e-06,
+      "loss": 0.8312227725982666,
+      "step": 528
+    },
+    {
+      "epoch": 2.1115537848605577,
+      "grad_norm": 0.3196059763431549,
+      "learning_rate": 1.6433245548809335e-06,
+      "loss": 0.7172638773918152,
+      "step": 530
+    },
+    {
+      "epoch": 2.1195219123505975,
+      "grad_norm": 0.35435977578163147,
+      "learning_rate": 1.6344242434985692e-06,
+      "loss": 0.44665032625198364,
+      "step": 532
+    },
+    {
+      "epoch": 2.1274900398406373,
+      "grad_norm": 0.41664063930511475,
+      "learning_rate": 1.6255246091674037e-06,
+      "loss": 0.8600306510925293,
+      "step": 534
+    },
+    {
+      "epoch": 2.135458167330677,
+      "grad_norm": 14.959745407104492,
+      "learning_rate": 1.61662603873915e-06,
+      "loss": 0.6659224629402161,
+      "step": 536
+    },
+    {
+      "epoch": 2.143426294820717,
+      "grad_norm": 0.8924800753593445,
+      "learning_rate": 1.607728919019277e-06,
+      "loss": 0.6953543424606323,
+      "step": 538
+    },
+    {
+      "epoch": 2.151394422310757,
+      "grad_norm": 0.5326530337333679,
+      "learning_rate": 1.5988336367501924e-06,
+      "loss": 1.0279146432876587,
+      "step": 540
+    },
+    {
+      "epoch": 2.1593625498007967,
+      "grad_norm": 1.0475772619247437,
+      "learning_rate": 1.5899405785944315e-06,
+      "loss": 0.9707013368606567,
+      "step": 542
+    },
+    {
+      "epoch": 2.1673306772908365,
+      "grad_norm": 0.4958283305168152,
+      "learning_rate": 1.5810501311178543e-06,
+      "loss": 0.9405574798583984,
+      "step": 544
+    },
+    {
+      "epoch": 2.1752988047808763,
+      "grad_norm": 0.49418023228645325,
+      "learning_rate": 1.5721626807728383e-06,
+      "loss": 0.7293884754180908,
+      "step": 546
+    },
+    {
+      "epoch": 2.183266932270916,
+      "grad_norm": 0.5774815678596497,
+      "learning_rate": 1.5632786138814786e-06,
+      "loss": 1.044211983680725,
+      "step": 548
+    },
+    {
+      "epoch": 2.191235059760956,
+      "grad_norm": 0.4045267105102539,
+      "learning_rate": 1.5543983166187998e-06,
+      "loss": 1.1075928211212158,
+      "step": 550
+    },
+    {
+      "epoch": 2.199203187250996,
+      "grad_norm": 1.0713002681732178,
+      "learning_rate": 1.5455221749959674e-06,
+      "loss": 0.7906201481819153,
+      "step": 552
+    },
+    {
+      "epoch": 2.2071713147410357,
+      "grad_norm": 1.4011352062225342,
+      "learning_rate": 1.5366505748435069e-06,
+      "loss": 0.529036819934845,
+      "step": 554
+    },
+    {
+      "epoch": 2.2151394422310755,
+      "grad_norm": 0.5856610536575317,
+      "learning_rate": 1.5277839017945342e-06,
+      "loss": 0.6787835359573364,
+      "step": 556
+    },
+    {
+      "epoch": 2.2231075697211153,
+      "grad_norm": 5.952252388000488,
+      "learning_rate": 1.5189225412679937e-06,
+      "loss": 0.8648924231529236,
+      "step": 558
+    },
+    {
+      "epoch": 2.231075697211155,
+      "grad_norm": 0.513113260269165,
+      "learning_rate": 1.5100668784519027e-06,
+      "loss": 0.9975270628929138,
+      "step": 560
+    },
+    {
+      "epoch": 2.239043824701195,
+      "grad_norm": 0.4902089536190033,
+      "learning_rate": 1.5012172982866095e-06,
+      "loss": 1.0877983570098877,
+      "step": 562
+    },
+    {
+      "epoch": 2.247011952191235,
+      "grad_norm": 1.1996077299118042,
+      "learning_rate": 1.4923741854480581e-06,
+      "loss": 0.8970789909362793,
+      "step": 564
+    },
+    {
+      "epoch": 2.2549800796812747,
+      "grad_norm": 0.8139443397521973,
+      "learning_rate": 1.4835379243310724e-06,
+      "loss": 0.7339902520179749,
+      "step": 566
+    },
+    {
+      "epoch": 2.2629482071713145,
+      "grad_norm": 0.3560384511947632,
+      "learning_rate": 1.4747088990326413e-06,
+      "loss": 0.8087087869644165,
+      "step": 568
+    },
+    {
+      "epoch": 2.2709163346613543,
+      "grad_norm": 0.4162435531616211,
+      "learning_rate": 1.4658874933352252e-06,
+      "loss": 1.0762511491775513,
+      "step": 570
+    },
+    {
+      "epoch": 2.278884462151394,
+      "grad_norm": 0.9825732707977295,
+      "learning_rate": 1.4570740906900752e-06,
+      "loss": 0.6623214483261108,
+      "step": 572
+    },
+    {
+      "epoch": 2.2868525896414345,
+      "grad_norm": 0.3757762908935547,
+      "learning_rate": 1.448269074200563e-06,
+      "loss": 0.7657751441001892,
+      "step": 574
+    },
+    {
+      "epoch": 2.2948207171314743,
+      "grad_norm": 0.5589696168899536,
+      "learning_rate": 1.4394728266055265e-06,
+      "loss": 0.3244088888168335,
+      "step": 576
+    },
+    {
+      "epoch": 2.302788844621514,
+      "grad_norm": 0.7052986025810242,
+      "learning_rate": 1.4306857302626383e-06,
+      "loss": 0.6619569659233093,
+      "step": 578
+    },
+    {
+      "epoch": 2.310756972111554,
+      "grad_norm": 0.425970196723938,
+      "learning_rate": 1.4219081671317795e-06,
+      "loss": 0.6385777592658997,
+      "step": 580
+    },
+    {
+      "epoch": 2.318725099601594,
+      "grad_norm": 0.6843652129173279,
+      "learning_rate": 1.4131405187584408e-06,
+      "loss": 0.7549704909324646,
+      "step": 582
+    },
+    {
+      "epoch": 2.3266932270916336,
+      "grad_norm": 0.3465102016925812,
+      "learning_rate": 1.4043831662571323e-06,
+      "loss": 0.8688426613807678,
+      "step": 584
+    },
+    {
+      "epoch": 2.3346613545816735,
+      "grad_norm": 0.3654971122741699,
+      "learning_rate": 1.3956364902948247e-06,
+      "loss": 0.6648116707801819,
+      "step": 586
+    },
+    {
+      "epoch": 2.3426294820717133,
+      "grad_norm": 0.744594395160675,
+      "learning_rate": 1.3869008710743948e-06,
+      "loss": 0.9290102124214172,
+      "step": 588
+    },
+    {
+      "epoch": 2.350597609561753,
+      "grad_norm": 0.4022054672241211,
+      "learning_rate": 1.378176688318103e-06,
+      "loss": 1.0422040224075317,
+      "step": 590
+    },
+    {
+      "epoch": 2.358565737051793,
+      "grad_norm": 0.5497289896011353,
+      "learning_rate": 1.3694643212510864e-06,
+      "loss": 1.1029999256134033,
+      "step": 592
+    },
+    {
+      "epoch": 2.366533864541833,
+      "grad_norm": 0.5594106912612915,
+      "learning_rate": 1.3607641485848747e-06,
+      "loss": 0.7941989898681641,
+      "step": 594
+    },
+    {
+      "epoch": 2.3745019920318726,
+      "grad_norm": 0.5195335149765015,
+      "learning_rate": 1.352076548500928e-06,
+      "loss": 1.055949091911316,
+      "step": 596
+    },
+    {
+      "epoch": 2.3824701195219125,
+      "grad_norm": 0.7671335935592651,
+      "learning_rate": 1.343401898634197e-06,
+      "loss": 0.747549831867218,
+      "step": 598
+    },
+    {
+      "epoch": 2.3904382470119523,
+      "grad_norm": 5.928802490234375,
+      "learning_rate": 1.3347405760567109e-06,
+      "loss": 1.0375477075576782,
+      "step": 600
+    },
+    {
+      "epoch": 2.398406374501992,
+      "grad_norm": 1.452104926109314,
+      "learning_rate": 1.326092957261183e-06,
+      "loss": 1.0605626106262207,
+      "step": 602
+    },
+    {
+      "epoch": 2.406374501992032,
+      "grad_norm": 0.45336440205574036,
+      "learning_rate": 1.317459418144647e-06,
+      "loss": 0.6427274942398071,
+      "step": 604
+    },
+    {
+      "epoch": 2.414342629482072,
+      "grad_norm": 0.9673005938529968,
+      "learning_rate": 1.308840333992118e-06,
+      "loss": 0.2522476315498352,
+      "step": 606
+    },
+    {
+      "epoch": 2.4223107569721116,
+      "grad_norm": 0.3540583848953247,
+      "learning_rate": 1.3002360794602787e-06,
+      "loss": 0.6453299522399902,
+      "step": 608
+    },
+    {
+      "epoch": 2.4302788844621515,
+      "grad_norm": 0.20231011509895325,
+      "learning_rate": 1.2916470285611936e-06,
+      "loss": 0.9828154444694519,
+      "step": 610
+    },
+    {
+      "epoch": 2.4382470119521913,
+      "grad_norm": 0.3596932291984558,
+      "learning_rate": 1.283073554646051e-06,
+      "loss": 0.7582497000694275,
+      "step": 612
+    },
+    {
+      "epoch": 2.446215139442231,
+      "grad_norm": 0.47144603729248047,
+      "learning_rate": 1.274516030388936e-06,
+      "loss": 0.6129385232925415,
+      "step": 614
+    },
+    {
+      "epoch": 2.454183266932271,
+      "grad_norm": 0.6285446286201477,
+      "learning_rate": 1.2659748277706292e-06,
+      "loss": 0.9842470288276672,
+      "step": 616
+    },
+    {
+      "epoch": 2.462151394422311,
+      "grad_norm": 0.7511582970619202,
+      "learning_rate": 1.257450318062436e-06,
+      "loss": 0.8260526657104492,
+      "step": 618
+    },
+    {
+      "epoch": 2.4701195219123506,
+      "grad_norm": 1.097211480140686,
+      "learning_rate": 1.2489428718100534e-06,
+      "loss": 0.9079670310020447,
+      "step": 620
+    },
+    {
+      "epoch": 2.4780876494023905,
+      "grad_norm": 0.4593997895717621,
+      "learning_rate": 1.2404528588174562e-06,
+      "loss": 0.9143153429031372,
+      "step": 622
+    },
+    {
+      "epoch": 2.4860557768924303,
+      "grad_norm": 0.5682267546653748,
+      "learning_rate": 1.2319806481308265e-06,
+      "loss": 0.8137405514717102,
+      "step": 624
+    },
+    {
+      "epoch": 2.49402390438247,
+      "grad_norm": 3.3198330402374268,
+      "learning_rate": 1.2235266080225118e-06,
+      "loss": 0.705787718296051,
+      "step": 626
+    },
+    {
+      "epoch": 2.50199203187251,
+      "grad_norm": 0.6641273498535156,
+      "learning_rate": 1.2150911059750159e-06,
+      "loss": 1.0320712327957153,
+      "step": 628
+    },
+    {
+      "epoch": 2.50996015936255,
+      "grad_norm": 0.8049502372741699,
+      "learning_rate": 1.2066745086650239e-06,
+      "loss": 0.5817446708679199,
+      "step": 630
+    },
+    {
+      "epoch": 2.5179282868525896,
+      "grad_norm": 1.7005666494369507,
+      "learning_rate": 1.1982771819474656e-06,
+      "loss": 0.49497243762016296,
+      "step": 632
+    },
+    {
+      "epoch": 2.5258964143426295,
+      "grad_norm": 0.48148971796035767,
+      "learning_rate": 1.1898994908396118e-06,
+      "loss": 1.0635162591934204,
+      "step": 634
+    },
+    {
+      "epoch": 2.5338645418326693,
+      "grad_norm": 1.0913236141204834,
+      "learning_rate": 1.1815417995052062e-06,
+      "loss": 0.9964134693145752,
+      "step": 636
+    },
+    {
+      "epoch": 2.541832669322709,
+      "grad_norm": 1.4037988185882568,
+      "learning_rate": 1.173204471238638e-06,
+      "loss": 1.0414139032363892,
+      "step": 638
+    },
+    {
+      "epoch": 2.549800796812749,
+      "grad_norm": 0.8760337233543396,
+      "learning_rate": 1.1648878684491478e-06,
+      "loss": 0.8619127869606018,
+      "step": 640
+    },
+    {
+      "epoch": 2.557768924302789,
+      "grad_norm": 0.4692465662956238,
+      "learning_rate": 1.1565923526450775e-06,
+      "loss": 1.0320566892623901,
+      "step": 642
+    },
+    {
+      "epoch": 2.5657370517928286,
+      "grad_norm": 0.36346501111984253,
+      "learning_rate": 1.148318284418153e-06,
+      "loss": 1.2459909915924072,
+      "step": 644
+    },
+    {
+      "epoch": 2.5737051792828685,
+      "grad_norm": 0.4973103106021881,
+      "learning_rate": 1.1400660234278099e-06,
+      "loss": 0.5828899145126343,
+      "step": 646
+    },
+    {
+      "epoch": 2.5816733067729083,
+      "grad_norm": 0.5622968077659607,
+      "learning_rate": 1.1318359283855633e-06,
+      "loss": 1.0787078142166138,
+      "step": 648
+    },
+    {
+      "epoch": 2.589641434262948,
+      "grad_norm": 0.41192811727523804,
+      "learning_rate": 1.1236283570394122e-06,
+      "loss": 0.8327584862709045,
+      "step": 650
+    },
+    {
+      "epoch": 2.597609561752988,
+      "grad_norm": 4.0215840339660645,
+      "learning_rate": 1.1154436661582873e-06,
+      "loss": 0.997661828994751,
+      "step": 652
+    },
+    {
+      "epoch": 2.605577689243028,
+      "grad_norm": 0.40926310420036316,
+      "learning_rate": 1.1072822115165488e-06,
+      "loss": 0.6634190678596497,
+      "step": 654
+    },
+    {
+      "epoch": 2.6135458167330676,
+      "grad_norm": 0.556077241897583,
+      "learning_rate": 1.0991443478785146e-06,
+      "loss": 0.38381195068359375,
+      "step": 656
+    },
+    {
+      "epoch": 2.6215139442231075,
+      "grad_norm": 0.8958475589752197,
+      "learning_rate": 1.0910304289830445e-06,
+      "loss": 0.5694887042045593,
+      "step": 658
+    },
+    {
+      "epoch": 2.6294820717131473,
+      "grad_norm": 0.31501585245132446,
+      "learning_rate": 1.08294080752816e-06,
+      "loss": 0.9161617159843445,
+      "step": 660
+    },
+    {
+      "epoch": 2.637450199203187,
+      "grad_norm": 0.8538661003112793,
+      "learning_rate": 1.074875835155716e-06,
+      "loss": 1.10606050491333,
+      "step": 662
+    },
+    {
+      "epoch": 2.645418326693227,
+      "grad_norm": 0.8182650804519653,
+      "learning_rate": 1.0668358624361148e-06,
+      "loss": 0.672410249710083,
+      "step": 664
+    },
+    {
+      "epoch": 2.653386454183267,
+      "grad_norm": 1.2558993101119995,
+      "learning_rate": 1.0588212388530662e-06,
+      "loss": 0.969312310218811,
+      "step": 666
+    },
+    {
+      "epoch": 2.6613545816733066,
+      "grad_norm": 0.24255388975143433,
+      "learning_rate": 1.050832312788396e-06,
+      "loss": 0.5811322331428528,
+      "step": 668
+    },
+    {
+      "epoch": 2.6693227091633465,
+      "grad_norm": 0.8314858675003052,
+      "learning_rate": 1.042869431506906e-06,
+      "loss": 0.7844950556755066,
+      "step": 670
+    },
+    {
+      "epoch": 2.6772908366533863,
+      "grad_norm": 0.1939828097820282,
+      "learning_rate": 1.034932941141274e-06,
+      "loss": 0.44791269302368164,
+      "step": 672
+    },
+    {
+      "epoch": 2.685258964143426,
+      "grad_norm": 0.3819931745529175,
+      "learning_rate": 1.0270231866770115e-06,
+      "loss": 1.0550973415374756,
+      "step": 674
+    },
+    {
+      "epoch": 2.6932270916334664,
+      "grad_norm": 0.8612610101699829,
+      "learning_rate": 1.019140511937465e-06,
+      "loss": 0.7458590269088745,
+      "step": 676
+    },
+    {
+      "epoch": 2.7011952191235062,
+      "grad_norm": 0.5282925963401794,
+      "learning_rate": 1.011285259568875e-06,
+      "loss": 0.6542291641235352,
+      "step": 678
+    },
+    {
+      "epoch": 2.709163346613546,
+      "grad_norm": 0.45834335684776306,
+      "learning_rate": 1.0034577710254754e-06,
+      "loss": 1.0501289367675781,
+      "step": 680
+    },
+    {
+      "epoch": 2.717131474103586,
+      "grad_norm": 0.4280013144016266,
+      "learning_rate": 9.956583865546576e-07,
+      "loss": 1.0795950889587402,
+      "step": 682
+    },
+    {
+      "epoch": 2.7250996015936257,
+      "grad_norm": 0.4833294451236725,
+      "learning_rate": 9.878874451821777e-07,
+      "loss": 0.7288949489593506,
+      "step": 684
+    },
+    {
+      "epoch": 2.7330677290836656,
+      "grad_norm": 1.0351470708847046,
+      "learning_rate": 9.801452846974161e-07,
+      "loss": 0.5564233660697937,
+      "step": 686
+    },
+    {
+      "epoch": 2.7410358565737054,
+      "grad_norm": 0.41580677032470703,
+      "learning_rate": 9.724322416387011e-07,
+      "loss": 1.0649595260620117,
+      "step": 688
+    },
+    {
+      "epoch": 2.7490039840637452,
+      "grad_norm": 1.2443572282791138,
+      "learning_rate": 9.647486512786754e-07,
+      "loss": 0.5668457746505737,
+      "step": 690
+    },
+    {
+      "epoch": 2.756972111553785,
+      "grad_norm": 0.47028157114982605,
+      "learning_rate": 9.570948476097252e-07,
+      "loss": 1.165488839149475,
+      "step": 692
+    },
+    {
+      "epoch": 2.764940239043825,
+      "grad_norm": 1.4404064416885376,
+      "learning_rate": 9.494711633294586e-07,
+      "loss": 0.9548084735870361,
+      "step": 694
+    },
+    {
+      "epoch": 2.7729083665338647,
+      "grad_norm": 2.1831867694854736,
+      "learning_rate": 9.41877929826247e-07,
+      "loss": 0.8034579753875732,
+      "step": 696
+    },
+    {
+      "epoch": 2.7808764940239046,
+      "grad_norm": 0.36618274450302124,
+      "learning_rate": 9.343154771648201e-07,
+      "loss": 0.9508860111236572,
+      "step": 698
+    },
+    {
+      "epoch": 2.7888446215139444,
+      "grad_norm": 0.451259970664978,
+      "learning_rate": 9.267841340719161e-07,
+      "loss": 1.0815647840499878,
+      "step": 700
+    },
+    {
+      "epoch": 2.7968127490039842,
+      "grad_norm": 0.457039475440979,
+      "learning_rate": 9.192842279219954e-07,
+      "loss": 0.7261126041412354,
+      "step": 702
+    },
+    {
+      "epoch": 2.804780876494024,
+      "grad_norm": 0.9726790189743042,
+      "learning_rate": 9.118160847230074e-07,
+      "loss": 1.3043347597122192,
+      "step": 704
+    },
+    {
+      "epoch": 2.812749003984064,
+      "grad_norm": 0.2558709681034088,
+      "learning_rate": 9.043800291022225e-07,
+      "loss": 1.290697455406189,
+      "step": 706
+    },
+    {
+      "epoch": 2.8207171314741037,
+      "grad_norm": 0.5993645787239075,
+      "learning_rate": 8.969763842921183e-07,
+      "loss": 1.1300464868545532,
+      "step": 708
+    },
+    {
+      "epoch": 2.8286852589641436,
+      "grad_norm": 0.21556946635246277,
+      "learning_rate": 8.89605472116331e-07,
+      "loss": 0.5522478818893433,
+      "step": 710
+    },
+    {
+      "epoch": 2.8366533864541834,
+      "grad_norm": 0.5506062507629395,
+      "learning_rate": 8.822676129756673e-07,
+      "loss": 1.087594985961914,
+      "step": 712
+    },
+    {
+      "epoch": 2.8446215139442232,
+      "grad_norm": 0.34245195984840393,
+      "learning_rate": 8.749631258341722e-07,
+      "loss": 0.6451638340950012,
+      "step": 714
+    },
+    {
+      "epoch": 2.852589641434263,
+      "grad_norm": 0.330020934343338,
+      "learning_rate": 8.676923282052703e-07,
+      "loss": 1.0628772974014282,
+      "step": 716
+    },
+    {
+      "epoch": 2.860557768924303,
+      "grad_norm": 1.4934767484664917,
+      "learning_rate": 8.604555361379602e-07,
+      "loss": 0.6799197196960449,
+      "step": 718
+    },
+    {
+      "epoch": 2.8685258964143427,
+      "grad_norm": 0.47209084033966064,
+      "learning_rate": 8.532530642030793e-07,
+      "loss": 0.6012248396873474,
+      "step": 720
+    },
+    {
+      "epoch": 2.8764940239043826,
+      "grad_norm": 1.5172817707061768,
+      "learning_rate": 8.46085225479626e-07,
+      "loss": 0.8212974667549133,
+      "step": 722
+    },
+    {
+      "epoch": 2.8844621513944224,
+      "grad_norm": 0.3270165026187897,
+      "learning_rate": 8.389523315411531e-07,
+      "loss": 0.6892848610877991,
+      "step": 724
+    },
+    {
+      "epoch": 2.8924302788844622,
+      "grad_norm": 0.34172943234443665,
+      "learning_rate": 8.318546924422257e-07,
+      "loss": 1.040250539779663,
+      "step": 726
+    },
+    {
+      "epoch": 2.900398406374502,
+      "grad_norm": 0.3343369960784912,
+      "learning_rate": 8.247926167049404e-07,
+      "loss": 0.591463029384613,
+      "step": 728
+    },
+    {
+      "epoch": 2.908366533864542,
+      "grad_norm": 0.37521132826805115,
+      "learning_rate": 8.177664113055171e-07,
+      "loss": 1.0062123537063599,
+      "step": 730
+    },
+    {
+      "epoch": 2.9163346613545817,
+      "grad_norm": 0.31653112173080444,
+      "learning_rate": 8.107763816609526e-07,
+      "loss": 0.48367780447006226,
+      "step": 732
+    },
+    {
+      "epoch": 2.9243027888446216,
+      "grad_norm": 0.6464031338691711,
+      "learning_rate": 8.038228316157484e-07,
+      "loss": 1.0752416849136353,
+      "step": 734
+    },
+    {
+      "epoch": 2.9322709163346614,
+      "grad_norm": 1.5205926895141602,
+      "learning_rate": 7.96906063428699e-07,
+      "loss": 0.4515492022037506,
+      "step": 736
+    },
+    {
+      "epoch": 2.9402390438247012,
+      "grad_norm": 1.017087459564209,
+      "learning_rate": 7.900263777597554e-07,
+      "loss": 0.9680182337760925,
+      "step": 738
+    },
+    {
+      "epoch": 2.948207171314741,
+      "grad_norm": 0.33580952882766724,
+      "learning_rate": 7.831840736569573e-07,
+      "loss": 1.2022464275360107,
+      "step": 740
+    },
+    {
+      "epoch": 2.956175298804781,
+      "grad_norm": 0.9194537997245789,
+      "learning_rate": 7.763794485434306e-07,
+      "loss": 0.5004313588142395,
+      "step": 742
+    },
+    {
+      "epoch": 2.9641434262948207,
+      "grad_norm": 0.4175858199596405,
+      "learning_rate": 7.696127982044607e-07,
+      "loss": 0.9552463889122009,
+      "step": 744
+    },
+    {
+      "epoch": 2.9721115537848606,
+      "grad_norm": 0.7210242748260498,
+      "learning_rate": 7.628844167746361e-07,
+      "loss": 0.9815269112586975,
+      "step": 746
+    },
+    {
+      "epoch": 2.9800796812749004,
+      "grad_norm": 1.3052399158477783,
+      "learning_rate": 7.561945967250626e-07,
+      "loss": 0.5944569706916809,
+      "step": 748
+    },
+    {
+      "epoch": 2.9880478087649402,
+      "grad_norm": 0.40495985746383667,
+      "learning_rate": 7.495436288506475e-07,
+      "loss": 0.1485452651977539,
+      "step": 750
+    },
+    {
+      "epoch": 2.99601593625498,
+      "grad_norm": 0.40999165177345276,
+      "learning_rate": 7.429318022574623e-07,
+      "loss": 1.0614784955978394,
+      "step": 752
+    },
+    {
+      "epoch": 3.00398406374502,
+      "grad_norm": 0.4904988408088684,
+      "learning_rate": 7.363594043501752e-07,
+      "loss": 0.5685489177703857,
+      "step": 754
+    },
+    {
+      "epoch": 3.0119521912350598,
+      "grad_norm": 0.6486766338348389,
+      "learning_rate": 7.298267208195567e-07,
+      "loss": 0.6701474785804749,
+      "step": 756
+    },
+    {
+      "epoch": 3.0199203187250996,
+      "grad_norm": 0.38344699144363403,
+      "learning_rate": 7.233340356300632e-07,
+      "loss": 0.4652033746242523,
+      "step": 758
+    },
+    {
+      "epoch": 3.0278884462151394,
+      "grad_norm": 0.3574877679347992,
+      "learning_rate": 7.16881631007491e-07,
+      "loss": 0.7689741849899292,
+      "step": 760
+    },
+    {
+      "epoch": 3.0358565737051793,
+      "grad_norm": 0.7075855731964111,
+      "learning_rate": 7.1046978742671e-07,
+      "loss": 0.571841835975647,
+      "step": 762
+    },
+    {
+      "epoch": 3.043824701195219,
+      "grad_norm": 0.4493393898010254,
+      "learning_rate": 7.040987835994727e-07,
+      "loss": 1.018668532371521,
+      "step": 764
+    },
+    {
+      "epoch": 3.051792828685259,
+      "grad_norm": 1.3887406587600708,
+      "learning_rate": 6.977688964622978e-07,
+      "loss": 0.19836187362670898,
+      "step": 766
+    },
+    {
+      "epoch": 3.0597609561752988,
+      "grad_norm": 0.565453290939331,
+      "learning_rate": 6.914804011644326e-07,
+      "loss": 0.7899960875511169,
+      "step": 768
+    },
+    {
+      "epoch": 3.0677290836653386,
+      "grad_norm": 0.6862173676490784,
+      "learning_rate": 6.852335710558922e-07,
+      "loss": 0.9098981618881226,
+      "step": 770
+    },
+    {
+      "epoch": 3.0756972111553784,
+      "grad_norm": 0.5152872204780579,
+      "learning_rate": 6.790286776755779e-07,
+      "loss": 1.0554358959197998,
+      "step": 772
+    },
+    {
+      "epoch": 3.0836653386454183,
+      "grad_norm": 1.018154263496399,
+      "learning_rate": 6.728659907394755e-07,
+      "loss": 0.9298610091209412,
+      "step": 774
+    },
+    {
+      "epoch": 3.091633466135458,
+      "grad_norm": 0.14560498297214508,
+      "learning_rate": 6.667457781289271e-07,
+      "loss": 0.60512375831604,
+      "step": 776
+    },
+    {
+      "epoch": 3.099601593625498,
+      "grad_norm": 0.48420849442481995,
+      "learning_rate": 6.606683058789922e-07,
+      "loss": 0.6643580198287964,
+      "step": 778
+    },
+    {
+      "epoch": 3.1075697211155378,
+      "grad_norm": 0.40179142355918884,
+      "learning_rate": 6.546338381668782e-07,
+      "loss": 1.0011398792266846,
+      "step": 780
+    },
+    {
+      "epoch": 3.1155378486055776,
+      "grad_norm": 0.8947471380233765,
+      "learning_rate": 6.486426373004613e-07,
+      "loss": 0.41442957520484924,
+      "step": 782
+    },
+    {
+      "epoch": 3.1235059760956174,
+      "grad_norm": 0.4902297556400299,
+      "learning_rate": 6.42694963706882e-07,
+      "loss": 1.1005361080169678,
+      "step": 784
+    },
+    {
+      "epoch": 3.1314741035856573,
+      "grad_norm": 0.35919007658958435,
+      "learning_rate": 6.367910759212253e-07,
+      "loss": 0.8759674429893494,
+      "step": 786
+    },
+    {
+      "epoch": 3.139442231075697,
+      "grad_norm": 1.3167163133621216,
+      "learning_rate": 6.309312305752845e-07,
+      "loss": 0.718060314655304,
+      "step": 788
+    },
+    {
+      "epoch": 3.147410358565737,
+      "grad_norm": 0.24750226736068726,
+      "learning_rate": 6.251156823864013e-07,
+      "loss": 0.6157811284065247,
+      "step": 790
+    },
+    {
+      "epoch": 3.1553784860557768,
+      "grad_norm": 1.525368094444275,
+      "learning_rate": 6.19344684146399e-07,
+      "loss": 0.8752233982086182,
+      "step": 792
+    },
+    {
+      "epoch": 3.1633466135458166,
+      "grad_norm": 0.071062371134758,
+      "learning_rate": 6.136184867105907e-07,
+      "loss": 0.3096681237220764,
+      "step": 794
+    },
+    {
+      "epoch": 3.1713147410358564,
+      "grad_norm": 0.767979085445404,
+      "learning_rate": 6.079373389868767e-07,
+      "loss": 0.7163103818893433,
+      "step": 796
+    },
+    {
+      "epoch": 3.1792828685258963,
+      "grad_norm": 0.4465477168560028,
+      "learning_rate": 6.023014879249236e-07,
+      "loss": 0.5860901474952698,
+      "step": 798
+    },
+    {
+      "epoch": 3.187250996015936,
+      "grad_norm": 1.0776124000549316,
+      "learning_rate": 5.967111785054299e-07,
+      "loss": 0.9502109289169312,
+      "step": 800
+    },
+    {
+      "epoch": 3.195219123505976,
+      "grad_norm": 0.3106825649738312,
+      "learning_rate": 5.91166653729479e-07,
+      "loss": 0.7821487188339233,
+      "step": 802
+    },
+    {
+      "epoch": 3.2031872509960158,
+      "grad_norm": 5.8575263023376465,
+      "learning_rate": 5.85668154607974e-07,
+      "loss": 0.7681574821472168,
+      "step": 804
+    },
+    {
+      "epoch": 3.2111553784860556,
+      "grad_norm": 1.7226320505142212,
+      "learning_rate": 5.802159201511634e-07,
+      "loss": 1.3093531131744385,
+      "step": 806
+    },
+    {
+      "epoch": 3.2191235059760954,
+      "grad_norm": 0.9542534947395325,
+      "learning_rate": 5.748101873582492e-07,
+      "loss": 0.5746437907218933,
+      "step": 808
+    },
+    {
+      "epoch": 3.2270916334661353,
+      "grad_norm": 0.6066504716873169,
+      "learning_rate": 5.69451191207088e-07,
+      "loss": 0.8110766410827637,
+      "step": 810
+    },
+    {
+      "epoch": 3.235059760956175,
+      "grad_norm": 0.8804686665534973,
+      "learning_rate": 5.641391646439746e-07,
+      "loss": 0.42266717553138733,
+      "step": 812
+    },
+    {
+      "epoch": 3.243027888446215,
+      "grad_norm": 0.3170583248138428,
+      "learning_rate": 5.588743385735169e-07,
+      "loss": 0.9301043748855591,
+      "step": 814
+    },
+    {
+      "epoch": 3.2509960159362548,
+      "grad_norm": 3.740297317504883,
+      "learning_rate": 5.536569418486005e-07,
+      "loss": 0.4588174819946289,
+      "step": 816
+    },
+    {
+      "epoch": 3.2589641434262946,
+      "grad_norm": 0.40485963225364685,
+      "learning_rate": 5.484872012604372e-07,
+      "loss": 1.029528260231018,
+      "step": 818
+    },
+    {
+      "epoch": 3.2669322709163344,
+      "grad_norm": 1.3435243368148804,
+      "learning_rate": 5.433653415287097e-07,
+      "loss": 0.6181462407112122,
+      "step": 820
+    },
+    {
+      "epoch": 3.2749003984063743,
+      "grad_norm": 0.7431517243385315,
+      "learning_rate": 5.38291585291804e-07,
+      "loss": 0.8793559074401855,
+      "step": 822
+    },
+    {
+      "epoch": 3.2828685258964145,
+      "grad_norm": 0.7615469098091125,
+      "learning_rate": 5.332661530971281e-07,
+      "loss": 0.6390237808227539,
+      "step": 824
+    },
+    {
+      "epoch": 3.2908366533864544,
+      "grad_norm": 0.2795827388763428,
+      "learning_rate": 5.282892633915299e-07,
+      "loss": 1.0185526609420776,
+      "step": 826
+    },
+    {
+      "epoch": 3.298804780876494,
+      "grad_norm": 0.4049527943134308,
+      "learning_rate": 5.23361132511797e-07,
+      "loss": 1.022945523262024,
+      "step": 828
+    },
+    {
+      "epoch": 3.306772908366534,
+      "grad_norm": 0.4463924169540405,
+      "learning_rate": 5.184819746752567e-07,
+      "loss": 0.9758146405220032,
+      "step": 830
+    },
+    {
+      "epoch": 3.314741035856574,
+      "grad_norm": 1.3453718423843384,
+      "learning_rate": 5.136520019704622e-07,
+      "loss": 0.6447398662567139,
+      "step": 832
+    },
+    {
+      "epoch": 3.3227091633466137,
+      "grad_norm": 0.7485759258270264,
+      "learning_rate": 5.088714243479742e-07,
+      "loss": 0.3966885209083557,
+      "step": 834
+    },
+    {
+      "epoch": 3.3306772908366535,
+      "grad_norm": 2.261605739593506,
+      "learning_rate": 5.041404496112345e-07,
+      "loss": 0.6890445351600647,
+      "step": 836
+    },
+    {
+      "epoch": 3.3386454183266934,
+      "grad_norm": 0.7466967701911926,
+      "learning_rate": 4.994592834075328e-07,
+      "loss": 0.9410973191261292,
+      "step": 838
+    },
+    {
+      "epoch": 3.346613545816733,
+      "grad_norm": 1.0626827478408813,
+      "learning_rate": 4.948281292190692e-07,
+      "loss": 0.24332815408706665,
+      "step": 840
+    },
+    {
+      "epoch": 3.354581673306773,
+      "grad_norm": 0.5983356833457947,
+      "learning_rate": 4.90247188354107e-07,
+      "loss": 0.8691646456718445,
+      "step": 842
+    },
+    {
+      "epoch": 3.362549800796813,
+      "grad_norm": 0.5014941692352295,
+      "learning_rate": 4.857166599382236e-07,
+      "loss": 0.7781885862350464,
+      "step": 844
+    },
+    {
+      "epoch": 3.3705179282868527,
+      "grad_norm": 0.3870190382003784,
+      "learning_rate": 4.812367409056543e-07,
+      "loss": 1.034981608390808,
+      "step": 846
+    },
+    {
+      "epoch": 3.3784860557768925,
+      "grad_norm": 0.40831807255744934,
+      "learning_rate": 4.7680762599073167e-07,
+      "loss": 1.0040619373321533,
+      "step": 848
+    },
+    {
+      "epoch": 3.3864541832669324,
+      "grad_norm": 1.0064787864685059,
+      "learning_rate": 4.72429507719422e-07,
+      "loss": 1.1909987926483154,
+      "step": 850
+    },
+    {
+      "epoch": 3.394422310756972,
+      "grad_norm": 0.34172093868255615,
+      "learning_rate": 4.681025764009543e-07,
+      "loss": 1.0179778337478638,
+      "step": 852
+    },
+    {
+      "epoch": 3.402390438247012,
+      "grad_norm": 0.6938625574111938,
+      "learning_rate": 4.638270201195511e-07,
+      "loss": 0.6021140813827515,
+      "step": 854
+    },
+    {
+      "epoch": 3.410358565737052,
+      "grad_norm": 0.6337777972221375,
+      "learning_rate": 4.5960302472624914e-07,
+      "loss": 0.9684332013130188,
+      "step": 856
+    },
+    {
+      "epoch": 3.4183266932270917,
+      "grad_norm": 0.36189448833465576,
+      "learning_rate": 4.554307738308239e-07,
+      "loss": 1.1349108219146729,
+      "step": 858
+    },
+    {
+      "epoch": 3.4262948207171315,
+      "grad_norm": 1.1650807857513428,
+      "learning_rate": 4.513104487938059e-07,
+      "loss": 1.068455696105957,
+      "step": 860
+    },
+    {
+      "epoch": 3.4342629482071714,
+      "grad_norm": 0.4551082253456116,
+      "learning_rate": 4.4724222871859915e-07,
+      "loss": 0.7791970372200012,
+      "step": 862
+    },
+    {
+      "epoch": 3.442231075697211,
+      "grad_norm": 2.264080047607422,
+      "learning_rate": 4.4322629044369557e-07,
+      "loss": 0.7574501633644104,
+      "step": 864
+    },
+    {
+      "epoch": 3.450199203187251,
+      "grad_norm": 0.4233779013156891,
+      "learning_rate": 4.392628085349856e-07,
+      "loss": 0.947033166885376,
+      "step": 866
+    },
+    {
+      "epoch": 3.458167330677291,
+      "grad_norm": 0.6929165720939636,
+      "learning_rate": 4.3535195527817413e-07,
+      "loss": 0.8224045634269714,
+      "step": 868
+    },
+    {
+      "epoch": 3.4661354581673307,
+      "grad_norm": 0.4947459399700165,
+      "learning_rate": 4.3149390067128893e-07,
+      "loss": 0.5549885630607605,
+      "step": 870
+    },
+    {
+      "epoch": 3.4741035856573705,
+      "grad_norm": 0.18183910846710205,
+      "learning_rate": 4.2768881241729196e-07,
+      "loss": 0.6329528093338013,
+      "step": 872
+    },
+    {
+      "epoch": 3.4820717131474104,
+      "grad_norm": 0.28913554549217224,
+      "learning_rate": 4.239368559167891e-07,
+      "loss": 0.760714590549469,
+      "step": 874
+    },
+    {
+      "epoch": 3.49003984063745,
+      "grad_norm": 0.44314852356910706,
+      "learning_rate": 4.2023819426084043e-07,
+      "loss": 0.6140300631523132,
+      "step": 876
+    },
+    {
+      "epoch": 3.49800796812749,
+      "grad_norm": 0.6128693222999573,
+      "learning_rate": 4.165929882238723e-07,
+      "loss": 0.5876585245132446,
+      "step": 878
+    },
+    {
+      "epoch": 3.50597609561753,
+      "grad_norm": 0.18565566837787628,
+      "learning_rate": 4.130013962566869e-07,
+      "loss": 0.5421848297119141,
+      "step": 880
+    },
+    {
+      "epoch": 3.5139442231075697,
+      "grad_norm": 0.5768609046936035,
+      "learning_rate": 4.094635744795763e-07,
+      "loss": 0.8825575709342957,
+      "step": 882
+    },
+    {
+      "epoch": 3.5219123505976095,
+      "grad_norm": 0.9254052042961121,
+      "learning_rate": 4.059796766755343e-07,
+      "loss": 0.308013379573822,
+      "step": 884
+    },
+    {
+      "epoch": 3.5298804780876494,
+      "grad_norm": 1.7089602947235107,
+      "learning_rate": 4.0254985428357405e-07,
+      "loss": 0.9074363708496094,
+      "step": 886
+    },
+    {
+      "epoch": 3.537848605577689,
+      "grad_norm": 0.46798571944236755,
+      "learning_rate": 3.9917425639214304e-07,
+      "loss": 0.9869987368583679,
+      "step": 888
+    },
+    {
+      "epoch": 3.545816733067729,
+      "grad_norm": 1.8204545974731445,
+      "learning_rate": 3.9585302973264424e-07,
+      "loss": 0.5235753059387207,
+      "step": 890
+    },
+    {
+      "epoch": 3.553784860557769,
+      "grad_norm": 0.8664906620979309,
+      "learning_rate": 3.9258631867305723e-07,
+      "loss": 1.2101613283157349,
+      "step": 892
+    },
+    {
+      "epoch": 3.5617529880478087,
+      "grad_norm": 0.4034668207168579,
+      "learning_rate": 3.893742652116616e-07,
+      "loss": 1.0782972574234009,
+      "step": 894
+    },
+    {
+      "epoch": 3.5697211155378485,
+      "grad_norm": 0.37115031480789185,
+      "learning_rate": 3.8621700897086686e-07,
+      "loss": 0.25802165269851685,
+      "step": 896
+    },
+    {
+      "epoch": 3.5776892430278884,
+      "grad_norm": 0.4131646156311035,
+      "learning_rate": 3.8311468719114215e-07,
+      "loss": 0.6915317177772522,
+      "step": 898
+    },
+    {
+      "epoch": 3.585657370517928,
+      "grad_norm": 0.5455676913261414,
+      "learning_rate": 3.8006743472504945e-07,
+      "loss": 0.3316478133201599,
+      "step": 900
+    },
+    {
+      "epoch": 3.593625498007968,
+      "grad_norm": 0.9060930609703064,
+      "learning_rate": 3.7707538403138413e-07,
+      "loss": 0.11103206127882004,
+      "step": 902
+    },
+    {
+      "epoch": 3.601593625498008,
+      "grad_norm": 0.5972309708595276,
+      "learning_rate": 3.7413866516941513e-07,
+      "loss": 0.8609724640846252,
+      "step": 904
+    },
+    {
+      "epoch": 3.6095617529880477,
+      "grad_norm": 2.9889116287231445,
+      "learning_rate": 3.712574057932332e-07,
+      "loss": 0.7271422147750854,
+      "step": 906
+    },
+    {
+      "epoch": 3.6175298804780875,
+      "grad_norm": 0.5200643539428711,
+      "learning_rate": 3.684317311461999e-07,
+      "loss": 0.9715712070465088,
+      "step": 908
+    },
+    {
+      "epoch": 3.6254980079681274,
+      "grad_norm": 1.3307124376296997,
+      "learning_rate": 3.656617640555063e-07,
+      "loss": 0.9659046530723572,
+      "step": 910
+    },
+    {
+      "epoch": 3.633466135458167,
+      "grad_norm": 0.22726085782051086,
+      "learning_rate": 3.6294762492683114e-07,
+      "loss": 0.06467059254646301,
+      "step": 912
+    },
+    {
+      "epoch": 3.641434262948207,
+      "grad_norm": 0.4885714054107666,
+      "learning_rate": 3.6028943173910846e-07,
+      "loss": 0.8727531433105469,
+      "step": 914
+    },
+    {
+      "epoch": 3.649402390438247,
+      "grad_norm": 1.1886482238769531,
+      "learning_rate": 3.5768730003939934e-07,
+      "loss": 0.8834037184715271,
+      "step": 916
+    },
+    {
+      "epoch": 3.6573705179282867,
+      "grad_norm": 6.707517147064209,
+      "learning_rate": 3.551413429378685e-07,
+      "loss": 0.28755173087120056,
+      "step": 918
+    },
+    {
+      "epoch": 3.6653386454183265,
+      "grad_norm": 0.6478546857833862,
+      "learning_rate": 3.526516711028687e-07,
+      "loss": 1.0173288583755493,
+      "step": 920
+    },
+    {
+      "epoch": 3.6733067729083664,
+      "grad_norm": 0.3290223479270935,
+      "learning_rate": 3.502183927561286e-07,
+      "loss": 0.20666202902793884,
+      "step": 922
+    },
+    {
+      "epoch": 3.681274900398406,
+      "grad_norm": 0.8621473908424377,
+      "learning_rate": 3.478416136680499e-07,
+      "loss": 1.1904857158660889,
+      "step": 924
+    },
+    {
+      "epoch": 3.6892430278884465,
+      "grad_norm": 6.629832744598389,
+      "learning_rate": 3.455214371531096e-07,
+      "loss": 0.448214590549469,
+      "step": 926
+    },
+    {
+      "epoch": 3.6972111553784863,
+      "grad_norm": 0.4641083776950836,
+      "learning_rate": 3.432579640653678e-07,
+      "loss": 0.6058546304702759,
+      "step": 928
+    },
+    {
+      "epoch": 3.705179282868526,
+      "grad_norm": 0.16589830815792084,
+      "learning_rate": 3.4105129279408574e-07,
+      "loss": 0.9167323112487793,
+      "step": 930
+    },
+    {
+      "epoch": 3.713147410358566,
+      "grad_norm": 0.8476380109786987,
+      "learning_rate": 3.389015192594471e-07,
+      "loss": 1.018453598022461,
+      "step": 932
+    },
+    {
+      "epoch": 3.721115537848606,
+      "grad_norm": 1.218807578086853,
+      "learning_rate": 3.3680873690839e-07,
+      "loss": 0.6338685154914856,
+      "step": 934
+    },
+    {
+      "epoch": 3.7290836653386457,
+      "grad_norm": 0.4406608045101166,
+      "learning_rate": 3.347730367105437e-07,
+      "loss": 0.9283577799797058,
+      "step": 936
+    },
+    {
+      "epoch": 3.7370517928286855,
+      "grad_norm": 1.626468539237976,
+      "learning_rate": 3.327945071542754e-07,
+      "loss": 0.9253164529800415,
+      "step": 938
+    },
+    {
+      "epoch": 3.7450199203187253,
+      "grad_norm": 0.49745914340019226,
+      "learning_rate": 3.308732342428437e-07,
+      "loss": 0.8693242073059082,
+      "step": 940
+    },
+    {
+      "epoch": 3.752988047808765,
+      "grad_norm": 1.1181275844573975,
+      "learning_rate": 3.2900930149065883e-07,
+      "loss": 0.9114285111427307,
+      "step": 942
+    },
+    {
+      "epoch": 3.760956175298805,
+      "grad_norm": 0.4131788909435272,
+      "learning_rate": 3.2720278991965424e-07,
+      "loss": 0.5458086729049683,
+      "step": 944
+    },
+    {
+      "epoch": 3.768924302788845,
+      "grad_norm": 0.3882419466972351,
+      "learning_rate": 3.2545377805576414e-07,
+      "loss": 1.0222781896591187,
+      "step": 946
+    },
+    {
+      "epoch": 3.7768924302788847,
+      "grad_norm": 0.4516999423503876,
+      "learning_rate": 3.2376234192550955e-07,
+      "loss": 0.6500365138053894,
+      "step": 948
+    },
+    {
+      "epoch": 3.7848605577689245,
+      "grad_norm": 0.7559425234794617,
+      "learning_rate": 3.221285550526936e-07,
+      "loss": 0.9952846765518188,
+      "step": 950
+    },
+    {
+      "epoch": 3.7928286852589643,
+      "grad_norm": 0.43123456835746765,
+      "learning_rate": 3.205524884552062e-07,
+      "loss": 1.0094038248062134,
+      "step": 952
+    },
+    {
+      "epoch": 3.800796812749004,
+      "grad_norm": 0.43853896856307983,
+      "learning_rate": 3.1903421064193714e-07,
+      "loss": 0.6855465769767761,
+      "step": 954
+    },
+    {
+      "epoch": 3.808764940239044,
+      "grad_norm": 0.9686547517776489,
+      "learning_rate": 3.1757378760979694e-07,
+      "loss": 0.8955079317092896,
+      "step": 956
+    },
+    {
+      "epoch": 3.816733067729084,
+      "grad_norm": 1.594388484954834,
+      "learning_rate": 3.161712828408494e-07,
+      "loss": 0.6716915965080261,
+      "step": 958
+    },
+    {
+      "epoch": 3.8247011952191237,
+      "grad_norm": 1.1490174531936646,
+      "learning_rate": 3.1482675729955115e-07,
+      "loss": 0.8457735776901245,
+      "step": 960
+    },
+    {
+      "epoch": 3.8326693227091635,
+      "grad_norm": 0.44997137784957886,
+      "learning_rate": 3.135402694301026e-07,
+      "loss": 0.6334148645401001,
+      "step": 962
+    },
+    {
+      "epoch": 3.8406374501992033,
+      "grad_norm": 0.7384113073348999,
+      "learning_rate": 3.123118751539064e-07,
+      "loss": 1.0639876127243042,
+      "step": 964
+    },
+    {
+      "epoch": 3.848605577689243,
+      "grad_norm": 0.7392749786376953,
+      "learning_rate": 3.111416278671374e-07,
+      "loss": 0.40739232301712036,
+      "step": 966
+    },
+    {
+      "epoch": 3.856573705179283,
+      "grad_norm": 0.3943544030189514,
+      "learning_rate": 3.1002957843842143e-07,
+      "loss": 0.5916213393211365,
+      "step": 968
+    },
+    {
+      "epoch": 3.864541832669323,
+      "grad_norm": 1.1247427463531494,
+      "learning_rate": 3.0897577520662403e-07,
+      "loss": 0.8500593304634094,
+      "step": 970
+    },
+    {
+      "epoch": 3.8725099601593627,
+      "grad_norm": 0.3284965753555298,
+      "learning_rate": 3.0798026397874904e-07,
+      "loss": 0.631747841835022,
+      "step": 972
+    },
+    {
+      "epoch": 3.8804780876494025,
+      "grad_norm": 0.27052104473114014,
+      "learning_rate": 3.070430880279484e-07,
+      "loss": 0.5036011934280396,
+      "step": 974
+    },
+    {
+      "epoch": 3.8884462151394423,
+      "grad_norm": 0.4196729063987732,
+      "learning_rate": 3.0616428809163936e-07,
+      "loss": 1.0151411294937134,
+      "step": 976
+    },
+    {
+      "epoch": 3.896414342629482,
+      "grad_norm": 0.604816198348999,
+      "learning_rate": 3.053439023697359e-07,
+      "loss": 0.5701797008514404,
+      "step": 978
+    },
+    {
+      "epoch": 3.904382470119522,
+      "grad_norm": 0.21591706573963165,
+      "learning_rate": 3.0458196652298623e-07,
+      "loss": 0.46466773748397827,
+      "step": 980
+    },
+    {
+      "epoch": 3.912350597609562,
+      "grad_norm": 0.5833430886268616,
+      "learning_rate": 3.038785136714242e-07,
+      "loss": 0.5528253316879272,
+      "step": 982
+    },
+    {
+      "epoch": 3.9203187250996017,
+      "grad_norm": 0.3425147235393524,
+      "learning_rate": 3.0323357439292857e-07,
+      "loss": 0.9604100584983826,
+      "step": 984
+    },
+    {
+      "epoch": 3.9282868525896415,
+      "grad_norm": 0.6084439754486084,
+      "learning_rate": 3.026471767218946e-07,
+      "loss": 0.1784566193819046,
+      "step": 986
+    },
+    {
+      "epoch": 3.9362549800796813,
+      "grad_norm": 0.6684430241584778,
+      "learning_rate": 3.0211934614801484e-07,
+      "loss": 0.6319288611412048,
+      "step": 988
+    },
+    {
+      "epoch": 3.944223107569721,
+      "grad_norm": 0.1623208075761795,
+      "learning_rate": 3.016501056151714e-07,
+      "loss": 0.6323052048683167,
+      "step": 990
+    },
+    {
+      "epoch": 3.952191235059761,
+      "grad_norm": 0.598673939704895,
+      "learning_rate": 3.01239475520439e-07,
+      "loss": 1.1039389371871948,
+      "step": 992
+    },
+    {
+      "epoch": 3.960159362549801,
+      "grad_norm": 0.10632996261119843,
+      "learning_rate": 3.008874737131976e-07,
+      "loss": 0.30895280838012695,
+      "step": 994
+    },
+    {
+      "epoch": 3.9681274900398407,
+      "grad_norm": 0.7597146034240723,
+      "learning_rate": 3.00594115494357e-07,
+      "loss": 0.9472017884254456,
+      "step": 996
+    },
+    {
+      "epoch": 3.9760956175298805,
+      "grad_norm": 0.3815767765045166,
+      "learning_rate": 3.0035941361569174e-07,
+      "loss": 0.6094083189964294,
+      "step": 998
+    },
+    {
+      "epoch": 3.9840637450199203,
+      "grad_norm": 1.381508708000183,
+      "learning_rate": 3.0018337827928646e-07,
+      "loss": 0.5018728971481323,
+      "step": 1000
+    },
+    {
+      "epoch": 3.99203187250996,
+      "grad_norm": 0.7763594388961792,
+      "learning_rate": 3.0006601713709283e-07,
+      "loss": 1.0228667259216309,
+      "step": 1002
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.1577903777360916,
+      "learning_rate": 3.000073352905969e-07,
+      "loss": 0.34115365147590637,
+      "step": 1004
+    },
+    {
+      "epoch": 4.0,
+      "step": 1004,
+      "total_flos": 4.038502240003031e+18,
+      "train_loss": 0.9239894755600221,
+      "train_runtime": 10281.2731,
+      "train_samples_per_second": 5.859,
+      "train_steps_per_second": 0.098
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1004,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 99999,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.038502240003031e+18,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32de5b9e45d3dff237cf7eface5a5493a0d389e79f4252e73da00de0411d72d
+size 5649