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", 5e-6), language_lr),
+        "vision": _fallback(getattr(training_args, "vision_adamw_lr", 3e-6), vision_lr),
+        "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
+    }
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 60
+- 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", 5e-6), language_lr),
+        "vision": _fallback(getattr(training_args, "vision_adamw_lr", 3e-6), vision_lr),
+        "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
+    }
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 60
+- 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": 2298.6989257586497,
+    "epoch": 4.0,
+    "total_flos": 3.954132003103703e+18,
+    "train_loss": 0.9162792685289545,
+    "train_runtime": 34079.0084,
+    "train_samples_per_second": 1.768,
+    "train_steps_per_second": 0.029
+}

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 sha256:5ebb3937ff4588a9b1d7c7d3b9406b9a0882fa272261779d550a54a374b449a9
+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": 2298.6989257586497,
+    "epoch": 4.0,
+    "total_flos": 3.954132003103703e+18,
+    "train_loss": 0.9162792685289545,
+    "train_runtime": 34079.0084,
+    "train_samples_per_second": 1.768,
+    "train_steps_per_second": 0.029
+}

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": 0.36507540941238403,
+      "learning_rate": 9.803921568627452e-08,
+      "loss": 2.1478986740112305,
+      "step": 2
+    },
+    {
+      "epoch": 0.01593625498007968,
+      "grad_norm": 0.30089065432548523,
+      "learning_rate": 2.9411764705882356e-07,
+      "loss": 2.0989038944244385,
+      "step": 4
+    },
+    {
+      "epoch": 0.02390438247011952,
+      "grad_norm": 1.5660828351974487,
+      "learning_rate": 4.901960784313725e-07,
+      "loss": 2.3009233474731445,
+      "step": 6
+    },
+    {
+      "epoch": 0.03187250996015936,
+      "grad_norm": 0.2664785385131836,
+      "learning_rate": 6.862745098039217e-07,
+      "loss": 1.9238520860671997,
+      "step": 8
+    },
+    {
+      "epoch": 0.0398406374501992,
+      "grad_norm": 0.5795847177505493,
+      "learning_rate": 8.823529411764707e-07,
+      "loss": 1.5781251192092896,
+      "step": 10
+    },
+    {
+      "epoch": 0.04780876494023904,
+      "grad_norm": 0.4124312996864319,
+      "learning_rate": 1.0784313725490197e-06,
+      "loss": 1.835196852684021,
+      "step": 12
+    },
+    {
+      "epoch": 0.055776892430278883,
+      "grad_norm": 0.25381967425346375,
+      "learning_rate": 1.2745098039215686e-06,
+      "loss": 2.811845541000366,
+      "step": 14
+    },
+    {
+      "epoch": 0.06374501992031872,
+      "grad_norm": 1.212020754814148,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 4.502689838409424,
+      "step": 16
+    },
+    {
+      "epoch": 0.07171314741035857,
+      "grad_norm": 3.0406649112701416,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.8233565092086792,
+      "step": 18
+    },
+    {
+      "epoch": 0.0796812749003984,
+      "grad_norm": 0.17684955894947052,
+      "learning_rate": 1.8627450980392158e-06,
+      "loss": 1.6987965106964111,
+      "step": 20
+    },
+    {
+      "epoch": 0.08764940239043825,
+      "grad_norm": 0.36174970865249634,
+      "learning_rate": 2.058823529411765e-06,
+      "loss": 1.683405876159668,
+      "step": 22
+    },
+    {
+      "epoch": 0.09561752988047809,
+      "grad_norm": 0.27825862169265747,
+      "learning_rate": 2.254901960784314e-06,
+      "loss": 1.4908095598220825,
+      "step": 24
+    },
+    {
+      "epoch": 0.10358565737051793,
+      "grad_norm": 0.11050917953252792,
+      "learning_rate": 2.450980392156863e-06,
+      "loss": 1.5943338871002197,
+      "step": 26
+    },
+    {
+      "epoch": 0.11155378486055777,
+      "grad_norm": 0.35608208179473877,
+      "learning_rate": 2.647058823529412e-06,
+      "loss": 1.6743614673614502,
+      "step": 28
+    },
+    {
+      "epoch": 0.11952191235059761,
+      "grad_norm": 0.3636796474456787,
+      "learning_rate": 2.843137254901961e-06,
+      "loss": 1.4463095664978027,
+      "step": 30
+    },
+    {
+      "epoch": 0.12749003984063745,
+      "grad_norm": 0.221956267952919,
+      "learning_rate": 3.03921568627451e-06,
+      "loss": 1.2417314052581787,
+      "step": 32
+    },
+    {
+      "epoch": 0.13545816733067728,
+      "grad_norm": 0.39851754903793335,
+      "learning_rate": 3.2352941176470594e-06,
+      "loss": 1.3921197652816772,
+      "step": 34
+    },
+    {
+      "epoch": 0.14342629482071714,
+      "grad_norm": 0.23913101851940155,
+      "learning_rate": 3.431372549019608e-06,
+      "loss": 1.5064514875411987,
+      "step": 36
+    },
+    {
+      "epoch": 0.15139442231075698,
+      "grad_norm": 0.348177433013916,
+      "learning_rate": 3.6274509803921573e-06,
+      "loss": 1.3143336772918701,
+      "step": 38
+    },
+    {
+      "epoch": 0.1593625498007968,
+      "grad_norm": 0.1362006962299347,
+      "learning_rate": 3.8235294117647055e-06,
+      "loss": 1.408495545387268,
+      "step": 40
+    },
+    {
+      "epoch": 0.16733067729083664,
+      "grad_norm": 0.6190513968467712,
+      "learning_rate": 4.019607843137255e-06,
+      "loss": 0.7950257658958435,
+      "step": 42
+    },
+    {
+      "epoch": 0.1752988047808765,
+      "grad_norm": 0.16317594051361084,
+      "learning_rate": 4.215686274509805e-06,
+      "loss": 1.0343906879425049,
+      "step": 44
+    },
+    {
+      "epoch": 0.18326693227091634,
+      "grad_norm": 0.21713487803936005,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.9676719903945923,
+      "step": 46
+    },
+    {
+      "epoch": 0.19123505976095617,
+      "grad_norm": 0.3731115162372589,
+      "learning_rate": 4.607843137254902e-06,
+      "loss": 1.2459075450897217,
+      "step": 48
+    },
+    {
+      "epoch": 0.199203187250996,
+      "grad_norm": 0.3069813847541809,
+      "learning_rate": 4.803921568627452e-06,
+      "loss": 1.4362599849700928,
+      "step": 50
+    },
+    {
+      "epoch": 0.20717131474103587,
+      "grad_norm": 0.16431237757205963,
+      "learning_rate": 5e-06,
+      "loss": 1.3767913579940796,
+      "step": 52
+    },
+    {
+      "epoch": 0.2151394422310757,
+      "grad_norm": 0.6251493692398071,
+      "learning_rate": 4.999951098195543e-06,
+      "loss": 1.0581270456314087,
+      "step": 54
+    },
+    {
+      "epoch": 0.22310756972111553,
+      "grad_norm": 0.1892067939043045,
+      "learning_rate": 4.9998043949078495e-06,
+      "loss": 1.5613751411437988,
+      "step": 56
+    },
+    {
+      "epoch": 0.23107569721115537,
+      "grad_norm": 0.19491063058376312,
+      "learning_rate": 4.9995598965138565e-06,
+      "loss": 1.396912932395935,
+      "step": 58
+    },
+    {
+      "epoch": 0.23904382470119523,
+      "grad_norm": 0.1353502869606018,
+      "learning_rate": 4.9992176136414875e-06,
+      "loss": 0.7899325489997864,
+      "step": 60
+    },
+    {
+      "epoch": 0.24701195219123506,
+      "grad_norm": 0.13414904475212097,
+      "learning_rate": 4.998777561169186e-06,
+      "loss": 1.4000543355941772,
+      "step": 62
+    },
+    {
+      "epoch": 0.2549800796812749,
+      "grad_norm": 0.2815379798412323,
+      "learning_rate": 4.998239758225272e-06,
+      "loss": 1.1215482950210571,
+      "step": 64
+    },
+    {
+      "epoch": 0.26294820717131473,
+      "grad_norm": 0.15314121544361115,
+      "learning_rate": 4.99760422818711e-06,
+      "loss": 1.319429636001587,
+      "step": 66
+    },
+    {
+      "epoch": 0.27091633466135456,
+      "grad_norm": 0.28238752484321594,
+      "learning_rate": 4.9968709986800925e-06,
+      "loss": 0.7804682850837708,
+      "step": 68
+    },
+    {
+      "epoch": 0.2788844621513944,
+      "grad_norm": 0.239247664809227,
+      "learning_rate": 4.996040101576436e-06,
+      "loss": 1.620535135269165,
+      "step": 70
+    },
+    {
+      "epoch": 0.2868525896414343,
+      "grad_norm": 0.36936095356941223,
+      "learning_rate": 4.995111572993804e-06,
+      "loss": 0.7684857845306396,
+      "step": 72
+    },
+    {
+      "epoch": 0.2948207171314741,
+      "grad_norm": 0.8476793169975281,
+      "learning_rate": 4.994085453293725e-06,
+      "loss": 1.190945029258728,
+      "step": 74
+    },
+    {
+      "epoch": 0.30278884462151395,
+      "grad_norm": 0.22687865793704987,
+      "learning_rate": 4.992961787079848e-06,
+      "loss": 1.4628626108169556,
+      "step": 76
+    },
+    {
+      "epoch": 0.3107569721115538,
+      "grad_norm": 1.0330981016159058,
+      "learning_rate": 4.991740623196001e-06,
+      "loss": 0.9273925423622131,
+      "step": 78
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 0.11700116842985153,
+      "learning_rate": 4.990422014724068e-06,
+      "loss": 0.8137176036834717,
+      "step": 80
+    },
+    {
+      "epoch": 0.32669322709163345,
+      "grad_norm": 0.27189400792121887,
+      "learning_rate": 4.989006018981675e-06,
+      "loss": 1.3179572820663452,
+      "step": 82
+    },
+    {
+      "epoch": 0.3346613545816733,
+      "grad_norm": 0.19609802961349487,
+      "learning_rate": 4.987492697519712e-06,
+      "loss": 0.8398184180259705,
+      "step": 84
+    },
+    {
+      "epoch": 0.3426294820717131,
+      "grad_norm": 0.21447153389453888,
+      "learning_rate": 4.985882116119643e-06,
+      "loss": 1.3273674249649048,
+      "step": 86
+    },
+    {
+      "epoch": 0.350597609561753,
+      "grad_norm": 0.362120121717453,
+      "learning_rate": 4.9841743447906576e-06,
+      "loss": 0.8714478611946106,
+      "step": 88
+    },
+    {
+      "epoch": 0.35856573705179284,
+      "grad_norm": 0.12099381536245346,
+      "learning_rate": 4.982369457766621e-06,
+      "loss": 1.3452365398406982,
+      "step": 90
+    },
+    {
+      "epoch": 0.3665338645418327,
+      "grad_norm": 0.29390770196914673,
+      "learning_rate": 4.980467533502853e-06,
+      "loss": 1.1395965814590454,
+      "step": 92
+    },
+    {
+      "epoch": 0.3745019920318725,
+      "grad_norm": 0.14583678543567657,
+      "learning_rate": 4.978468654672709e-06,
+      "loss": 1.2588502168655396,
+      "step": 94
+    },
+    {
+      "epoch": 0.38247011952191234,
+      "grad_norm": 1.1907033920288086,
+      "learning_rate": 4.976372908163999e-06,
+      "loss": 1.14028799533844,
+      "step": 96
+    },
+    {
+      "epoch": 0.3904382470119522,
+      "grad_norm": 0.12643791735172272,
+      "learning_rate": 4.974180385075195e-06,
+      "loss": 1.2851067781448364,
+      "step": 98
+    },
+    {
+      "epoch": 0.398406374501992,
+      "grad_norm": 0.11285815387964249,
+      "learning_rate": 4.971891180711488e-06,
+      "loss": 0.8521233797073364,
+      "step": 100
+    },
+    {
+      "epoch": 0.4063745019920319,
+      "grad_norm": 0.1930067539215088,
+      "learning_rate": 4.9695053945806295e-06,
+      "loss": 1.2956879138946533,
+      "step": 102
+    },
+    {
+      "epoch": 0.41434262948207173,
+      "grad_norm": 0.10936727374792099,
+      "learning_rate": 4.9670231303886194e-06,
+      "loss": 0.7593114376068115,
+      "step": 104
+    },
+    {
+      "epoch": 0.42231075697211157,
+      "grad_norm": 0.584141731262207,
+      "learning_rate": 4.9644444960351865e-06,
+      "loss": 0.7490916848182678,
+      "step": 106
+    },
+    {
+      "epoch": 0.4302788844621514,
+      "grad_norm": 0.2863035202026367,
+      "learning_rate": 4.9617696036091095e-06,
+      "loss": 1.0160802602767944,
+      "step": 108
+    },
+    {
+      "epoch": 0.43824701195219123,
+      "grad_norm": 0.15232379734516144,
+      "learning_rate": 4.958998569383335e-06,
+      "loss": 1.2996617555618286,
+      "step": 110
+    },
+    {
+      "epoch": 0.44621513944223107,
+      "grad_norm": 0.39556685090065,
+      "learning_rate": 4.956131513809928e-06,
+      "loss": 0.8066137433052063,
+      "step": 112
+    },
+    {
+      "epoch": 0.4541832669322709,
+      "grad_norm": 0.6019495129585266,
+      "learning_rate": 4.953168561514838e-06,
+      "loss": 1.099776268005371,
+      "step": 114
+    },
+    {
+      "epoch": 0.46215139442231074,
+      "grad_norm": 0.16096602380275726,
+      "learning_rate": 4.950109841292475e-06,
+      "loss": 1.3010071516036987,
+      "step": 116
+    },
+    {
+      "epoch": 0.4701195219123506,
+      "grad_norm": 0.11458754539489746,
+      "learning_rate": 4.946955486100119e-06,
+      "loss": 1.3699376583099365,
+      "step": 118
+    },
+    {
+      "epoch": 0.47808764940239046,
+      "grad_norm": 0.15330001711845398,
+      "learning_rate": 4.943705633052134e-06,
+      "loss": 1.241147518157959,
+      "step": 120
+    },
+    {
+      "epoch": 0.4860557768924303,
+      "grad_norm": 0.1487206071615219,
+      "learning_rate": 4.940360423414013e-06,
+      "loss": 0.9461244940757751,
+      "step": 122
+    },
+    {
+      "epoch": 0.4940239043824701,
+      "grad_norm": 0.47019249200820923,
+      "learning_rate": 4.936920002596233e-06,
+      "loss": 1.0635651350021362,
+      "step": 124
+    },
+    {
+      "epoch": 0.50199203187251,
+      "grad_norm": 0.4726186990737915,
+      "learning_rate": 4.9333845201479375e-06,
+      "loss": 0.9114818572998047,
+      "step": 126
+    },
+    {
+      "epoch": 0.5099601593625498,
+      "grad_norm": 0.13533522188663483,
+      "learning_rate": 4.9297541297504345e-06,
+      "loss": 1.3086631298065186,
+      "step": 128
+    },
+    {
+      "epoch": 0.5179282868525896,
+      "grad_norm": 0.13124530017375946,
+      "learning_rate": 4.9260289892105164e-06,
+      "loss": 0.9271867871284485,
+      "step": 130
+    },
+    {
+      "epoch": 0.5258964143426295,
+      "grad_norm": 0.1354794055223465,
+      "learning_rate": 4.922209260453599e-06,
+      "loss": 0.8114712834358215,
+      "step": 132
+    },
+    {
+      "epoch": 0.5338645418326693,
+      "grad_norm": 0.22127960622310638,
+      "learning_rate": 4.9182951095166875e-06,
+      "loss": 0.8751158118247986,
+      "step": 134
+    },
+    {
+      "epoch": 0.5418326693227091,
+      "grad_norm": 0.27858051657676697,
+      "learning_rate": 4.914286706541153e-06,
+      "loss": 1.2887262105941772,
+      "step": 136
+    },
+    {
+      "epoch": 0.549800796812749,
+      "grad_norm": 0.14748907089233398,
+      "learning_rate": 4.910184225765341e-06,
+      "loss": 0.9257957339286804,
+      "step": 138
+    },
+    {
+      "epoch": 0.5577689243027888,
+      "grad_norm": 1.1639631986618042,
+      "learning_rate": 4.905987845516996e-06,
+      "loss": 1.06972074508667,
+      "step": 140
+    },
+    {
+      "epoch": 0.5657370517928287,
+      "grad_norm": 0.12395283579826355,
+      "learning_rate": 4.90169774820551e-06,
+      "loss": 0.9916914105415344,
+      "step": 142
+    },
+    {
+      "epoch": 0.5737051792828686,
+      "grad_norm": 0.26990726590156555,
+      "learning_rate": 4.897314120313996e-06,
+      "loss": 1.2373924255371094,
+      "step": 144
+    },
+    {
+      "epoch": 0.5816733067729084,
+      "grad_norm": 0.2367822676897049,
+      "learning_rate": 4.892837152391174e-06,
+      "loss": 1.4097868204116821,
+      "step": 146
+    },
+    {
+      "epoch": 0.5896414342629482,
+      "grad_norm": 0.20431344211101532,
+      "learning_rate": 4.888267039043101e-06,
+      "loss": 0.9128491282463074,
+      "step": 148
+    },
+    {
+      "epoch": 0.5976095617529881,
+      "grad_norm": 0.2742835581302643,
+      "learning_rate": 4.883603978924698e-06,
+      "loss": 0.9315645694732666,
+      "step": 150
+    },
+    {
+      "epoch": 0.6055776892430279,
+      "grad_norm": 0.4403739273548126,
+      "learning_rate": 4.878848174731126e-06,
+      "loss": 0.9307162165641785,
+      "step": 152
+    },
+    {
+      "epoch": 0.6135458167330677,
+      "grad_norm": 0.36071693897247314,
+      "learning_rate": 4.873999833188967e-06,
+      "loss": 1.1042546033859253,
+      "step": 154
+    },
+    {
+      "epoch": 0.6215139442231076,
+      "grad_norm": 2.229910373687744,
+      "learning_rate": 4.8690591650472455e-06,
+      "loss": 1.1711007356643677,
+      "step": 156
+    },
+    {
+      "epoch": 0.6294820717131474,
+      "grad_norm": 0.1784725934267044,
+      "learning_rate": 4.864026385068259e-06,
+      "loss": 1.131500005722046,
+      "step": 158
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": 0.13657332956790924,
+      "learning_rate": 4.858901712018251e-06,
+      "loss": 1.0008326768875122,
+      "step": 160
+    },
+    {
+      "epoch": 0.6454183266932271,
+      "grad_norm": 0.09326687455177307,
+      "learning_rate": 4.8536853686578965e-06,
+      "loss": 0.7472431063652039,
+      "step": 162
+    },
+    {
+      "epoch": 0.6533864541832669,
+      "grad_norm": 0.12042990326881409,
+      "learning_rate": 4.84837758173262e-06,
+      "loss": 1.1783264875411987,
+      "step": 164
+    },
+    {
+      "epoch": 0.6613545816733067,
+      "grad_norm": 0.3077879250049591,
+      "learning_rate": 4.8429785819627395e-06,
+      "loss": 0.87720787525177,
+      "step": 166
+    },
+    {
+      "epoch": 0.6693227091633466,
+      "grad_norm": 0.15068887174129486,
+      "learning_rate": 4.83748860403344e-06,
+      "loss": 1.2415030002593994,
+      "step": 168
+    },
+    {
+      "epoch": 0.6772908366533864,
+      "grad_norm": 0.6893270611763,
+      "learning_rate": 4.831907886584566e-06,
+      "loss": 0.9320418238639832,
+      "step": 170
+    },
+    {
+      "epoch": 0.6852589641434262,
+      "grad_norm": 0.29838675260543823,
+      "learning_rate": 4.8262366722002535e-06,
+      "loss": 0.8203558325767517,
+      "step": 172
+    },
+    {
+      "epoch": 0.6932270916334662,
+      "grad_norm": 0.1665155440568924,
+      "learning_rate": 4.820475207398386e-06,
+      "loss": 1.232407569885254,
+      "step": 174
+    },
+    {
+      "epoch": 0.701195219123506,
+      "grad_norm": 1.768316626548767,
+      "learning_rate": 4.8146237426198735e-06,
+      "loss": 0.7181666493415833,
+      "step": 176
+    },
+    {
+      "epoch": 0.7091633466135459,
+      "grad_norm": 0.39159202575683594,
+      "learning_rate": 4.808682532217772e-06,
+      "loss": 0.8964619636535645,
+      "step": 178
+    },
+    {
+      "epoch": 0.7171314741035857,
+      "grad_norm": 0.2547804117202759,
+      "learning_rate": 4.802651834446221e-06,
+      "loss": 1.0764801502227783,
+      "step": 180
+    },
+    {
+      "epoch": 0.7250996015936255,
+      "grad_norm": 0.05123830586671829,
+      "learning_rate": 4.796531911449226e-06,
+      "loss": 0.4317728281021118,
+      "step": 182
+    },
+    {
+      "epoch": 0.7330677290836654,
+      "grad_norm": 0.11170970648527145,
+      "learning_rate": 4.790323029249252e-06,
+      "loss": 1.2693806886672974,
+      "step": 184
+    },
+    {
+      "epoch": 0.7410358565737052,
+      "grad_norm": 0.18704238533973694,
+      "learning_rate": 4.784025457735675e-06,
+      "loss": 1.2701973915100098,
+      "step": 186
+    },
+    {
+      "epoch": 0.749003984063745,
+      "grad_norm": 0.1397540122270584,
+      "learning_rate": 4.777639470653035e-06,
+      "loss": 1.0848942995071411,
+      "step": 188
+    },
+    {
+      "epoch": 0.7569721115537849,
+      "grad_norm": 0.5312946438789368,
+      "learning_rate": 4.771165345589148e-06,
+      "loss": 0.8569958209991455,
+      "step": 190
+    },
+    {
+      "epoch": 0.7649402390438247,
+      "grad_norm": 0.306986927986145,
+      "learning_rate": 4.7646033639630355e-06,
+      "loss": 1.2206043004989624,
+      "step": 192
+    },
+    {
+      "epoch": 0.7729083665338645,
+      "grad_norm": 0.23638230562210083,
+      "learning_rate": 4.757953811012688e-06,
+      "loss": 0.8794302940368652,
+      "step": 194
+    },
+    {
+      "epoch": 0.7808764940239044,
+      "grad_norm": 0.17385224997997284,
+      "learning_rate": 4.7512169757826735e-06,
+      "loss": 0.5606666207313538,
+      "step": 196
+    },
+    {
+      "epoch": 0.7888446215139442,
+      "grad_norm": 0.3241356313228607,
+      "learning_rate": 4.74439315111157e-06,
+      "loss": 0.8000544905662537,
+      "step": 198
+    },
+    {
+      "epoch": 0.796812749003984,
+      "grad_norm": 0.16005879640579224,
+      "learning_rate": 4.737482633619234e-06,
+      "loss": 0.993906557559967,
+      "step": 200
+    },
+    {
+      "epoch": 0.8047808764940239,
+      "grad_norm": 0.07381737232208252,
+      "learning_rate": 4.730485723693912e-06,
+      "loss": 0.929846465587616,
+      "step": 202
+    },
+    {
+      "epoch": 0.8127490039840638,
+      "grad_norm": 0.20861877501010895,
+      "learning_rate": 4.723402725479177e-06,
+      "loss": 1.5461487770080566,
+      "step": 204
+    },
+    {
+      "epoch": 0.8207171314741036,
+      "grad_norm": 0.5194161534309387,
+      "learning_rate": 4.71623394686071e-06,
+      "loss": 1.2338072061538696,
+      "step": 206
+    },
+    {
+      "epoch": 0.8286852589641435,
+      "grad_norm": 0.3339504301548004,
+      "learning_rate": 4.708979699452923e-06,
+      "loss": 0.6025282740592957,
+      "step": 208
+    },
+    {
+      "epoch": 0.8366533864541833,
+      "grad_norm": 0.13407404720783234,
+      "learning_rate": 4.701640298585405e-06,
+      "loss": 1.2677758932113647,
+      "step": 210
+    },
+    {
+      "epoch": 0.8446215139442231,
+      "grad_norm": 0.18298420310020447,
+      "learning_rate": 4.694216063289219e-06,
+      "loss": 1.2246408462524414,
+      "step": 212
+    },
+    {
+      "epoch": 0.852589641434263,
+      "grad_norm": 0.15307551622390747,
+      "learning_rate": 4.686707316283033e-06,
+      "loss": 0.940060019493103,
+      "step": 214
+    },
+    {
+      "epoch": 0.8605577689243028,
+      "grad_norm": 0.4384134113788605,
+      "learning_rate": 4.679114383959095e-06,
+      "loss": 1.4186824560165405,
+      "step": 216
+    },
+    {
+      "epoch": 0.8685258964143426,
+      "grad_norm": 0.5803958773612976,
+      "learning_rate": 4.6714375963690415e-06,
+      "loss": 0.8482747673988342,
+      "step": 218
+    },
+    {
+      "epoch": 0.8764940239043825,
+      "grad_norm": 0.1442187875509262,
+      "learning_rate": 4.6636772872095545e-06,
+      "loss": 1.2409926652908325,
+      "step": 220
+    },
+    {
+      "epoch": 0.8844621513944223,
+      "grad_norm": 0.21851007640361786,
+      "learning_rate": 4.6558337938078505e-06,
+      "loss": 1.4906511306762695,
+      "step": 222
+    },
+    {
+      "epoch": 0.8924302788844621,
+      "grad_norm": 0.174688458442688,
+      "learning_rate": 4.647907457107025e-06,
+      "loss": 0.6975417137145996,
+      "step": 224
+    },
+    {
+      "epoch": 0.900398406374502,
+      "grad_norm": 0.1176387220621109,
+      "learning_rate": 4.639898621651226e-06,
+      "loss": 0.9766526818275452,
+      "step": 226
+    },
+    {
+      "epoch": 0.9083665338645418,
+      "grad_norm": 0.5311532616615295,
+      "learning_rate": 4.631807635570681e-06,
+      "loss": 1.0703117847442627,
+      "step": 228
+    },
+    {
+      "epoch": 0.9163346613545816,
+      "grad_norm": 0.2218572497367859,
+      "learning_rate": 4.623634850566563e-06,
+      "loss": 1.171491026878357,
+      "step": 230
+    },
+    {
+      "epoch": 0.9243027888446215,
+      "grad_norm": 0.22680677473545074,
+      "learning_rate": 4.615380621895701e-06,
+      "loss": 1.3510780334472656,
+      "step": 232
+    },
+    {
+      "epoch": 0.9322709163346613,
+      "grad_norm": 0.16424481570720673,
+      "learning_rate": 4.607045308355141e-06,
+      "loss": 0.7879006266593933,
+      "step": 234
+    },
+    {
+      "epoch": 0.9402390438247012,
+      "grad_norm": 0.11530027538537979,
+      "learning_rate": 4.598629272266549e-06,
+      "loss": 0.795449435710907,
+      "step": 236
+    },
+    {
+      "epoch": 0.9482071713147411,
+      "grad_norm": 0.6812359690666199,
+      "learning_rate": 4.590132879460458e-06,
+      "loss": 0.404697448015213,
+      "step": 238
+    },
+    {
+      "epoch": 0.9561752988047809,
+      "grad_norm": 0.2176714539527893,
+      "learning_rate": 4.5815564992603705e-06,
+      "loss": 0.8534306883811951,
+      "step": 240
+    },
+    {
+      "epoch": 0.9641434262948207,
+      "grad_norm": 0.2489551305770874,
+      "learning_rate": 4.572900504466702e-06,
+      "loss": 1.1137834787368774,
+      "step": 242
+    },
+    {
+      "epoch": 0.9721115537848606,
+      "grad_norm": 0.14749546349048615,
+      "learning_rate": 4.564165271340577e-06,
+      "loss": 1.2202308177947998,
+      "step": 244
+    },
+    {
+      "epoch": 0.9800796812749004,
+      "grad_norm": 0.14046330749988556,
+      "learning_rate": 4.555351179587472e-06,
+      "loss": 0.940899133682251,
+      "step": 246
+    },
+    {
+      "epoch": 0.9880478087649402,
+      "grad_norm": 0.15851272642612457,
+      "learning_rate": 4.546458612340714e-06,
+      "loss": 0.9538923501968384,
+      "step": 248
+    },
+    {
+      "epoch": 0.9960159362549801,
+      "grad_norm": 0.16326214373111725,
+      "learning_rate": 4.537487956144821e-06,
+      "loss": 0.9694409966468811,
+      "step": 250
+    },
+    {
+      "epoch": 1.00398406374502,
+      "grad_norm": 0.2218526154756546,
+      "learning_rate": 4.528439600938706e-06,
+      "loss": 0.8940787315368652,
+      "step": 252
+    },
+    {
+      "epoch": 1.0119521912350598,
+      "grad_norm": 0.11392181366682053,
+      "learning_rate": 4.519313940038721e-06,
+      "loss": 0.7144261002540588,
+      "step": 254
+    },
+    {
+      "epoch": 1.0199203187250996,
+      "grad_norm": 0.12673118710517883,
+      "learning_rate": 4.510111370121563e-06,
+      "loss": 1.1917835474014282,
+      "step": 256
+    },
+    {
+      "epoch": 1.0278884462151394,
+      "grad_norm": 0.17344379425048828,
+      "learning_rate": 4.500832291207033e-06,
+      "loss": 1.174926519393921,
+      "step": 258
+    },
+    {
+      "epoch": 1.0358565737051793,
+      "grad_norm": 0.3056865334510803,
+      "learning_rate": 4.491477106640646e-06,
+      "loss": 1.0975226163864136,
+      "step": 260
+    },
+    {
+      "epoch": 1.043824701195219,
+      "grad_norm": 0.17723745107650757,
+      "learning_rate": 4.482046223076092e-06,
+      "loss": 1.040866494178772,
+      "step": 262
+    },
+    {
+      "epoch": 1.051792828685259,
+      "grad_norm": 0.19307421147823334,
+      "learning_rate": 4.4725400504575725e-06,
+      "loss": 1.078101634979248,
+      "step": 264
+    },
+    {
+      "epoch": 1.0597609561752988,
+      "grad_norm": 0.2243003398180008,
+      "learning_rate": 4.462959002001971e-06,
+      "loss": 0.6358222365379333,
+      "step": 266
+    },
+    {
+      "epoch": 1.0677290836653386,
+      "grad_norm": 0.10301990807056427,
+      "learning_rate": 4.453303494180895e-06,
+      "loss": 0.9398614168167114,
+      "step": 268
+    },
+    {
+      "epoch": 1.0756972111553784,
+      "grad_norm": 0.13683800399303436,
+      "learning_rate": 4.443573946702573e-06,
+      "loss": 0.5699441432952881,
+      "step": 270
+    },
+    {
+      "epoch": 1.0836653386454183,
+      "grad_norm": 0.1332143247127533,
+      "learning_rate": 4.433770782493606e-06,
+      "loss": 1.2520045042037964,
+      "step": 272
+    },
+    {
+      "epoch": 1.091633466135458,
+      "grad_norm": 0.29650190472602844,
+      "learning_rate": 4.42389442768059e-06,
+      "loss": 0.609424889087677,
+      "step": 274
+    },
+    {
+      "epoch": 1.099601593625498,
+      "grad_norm": 0.26845359802246094,
+      "learning_rate": 4.413945311571586e-06,
+      "loss": 0.960149347782135,
+      "step": 276
+    },
+    {
+      "epoch": 1.1075697211155378,
+      "grad_norm": 0.1361047625541687,
+      "learning_rate": 4.40392386663747e-06,
+      "loss": 0.845086395740509,
+      "step": 278
+    },
+    {
+      "epoch": 1.1155378486055776,
+      "grad_norm": 0.19930897653102875,
+      "learning_rate": 4.393830528493118e-06,
+      "loss": 1.084862232208252,
+      "step": 280
+    },
+    {
+      "epoch": 1.1235059760956174,
+      "grad_norm": 0.5642545819282532,
+      "learning_rate": 4.3836657358784875e-06,
+      "loss": 1.2006343603134155,
+      "step": 282
+    },
+    {
+      "epoch": 1.1314741035856573,
+      "grad_norm": 0.33313703536987305,
+      "learning_rate": 4.373429930639534e-06,
+      "loss": 1.216106653213501,
+      "step": 284
+    },
+    {
+      "epoch": 1.139442231075697,
+      "grad_norm": 0.1351492553949356,
+      "learning_rate": 4.3631235577090085e-06,
+      "loss": 0.26553061604499817,
+      "step": 286
+    },
+    {
+      "epoch": 1.1474103585657371,
+      "grad_norm": 0.5928749442100525,
+      "learning_rate": 4.35274706508712e-06,
+      "loss": 0.775409996509552,
+      "step": 288
+    },
+    {
+      "epoch": 1.155378486055777,
+      "grad_norm": 1.4495903253555298,
+      "learning_rate": 4.342300903822057e-06,
+      "loss": 0.934550940990448,
+      "step": 290
+    },
+    {
+      "epoch": 1.1633466135458168,
+      "grad_norm": 0.1456296592950821,
+      "learning_rate": 4.331785527990384e-06,
+      "loss": 0.5133512616157532,
+      "step": 292
+    },
+    {
+      "epoch": 1.1713147410358566,
+      "grad_norm": 0.12180474400520325,
+      "learning_rate": 4.3212013946773045e-06,
+      "loss": 1.2214361429214478,
+      "step": 294
+    },
+    {
+      "epoch": 1.1792828685258965,
+      "grad_norm": 0.1378239244222641,
+      "learning_rate": 4.31054896395679e-06,
+      "loss": 1.2484345436096191,
+      "step": 296
+    },
+    {
+      "epoch": 1.1872509960159363,
+      "grad_norm": 0.2742413580417633,
+      "learning_rate": 4.299828698871581e-06,
+      "loss": 1.3978660106658936,
+      "step": 298
+    },
+    {
+      "epoch": 1.1952191235059761,
+      "grad_norm": 0.19852370023727417,
+      "learning_rate": 4.289041065413062e-06,
+      "loss": 0.5970309972763062,
+      "step": 300
+    },
+    {
+      "epoch": 1.203187250996016,
+      "grad_norm": 0.4067925810813904,
+      "learning_rate": 4.278186532501003e-06,
+      "loss": 0.894138514995575,
+      "step": 302
+    },
+    {
+      "epoch": 1.2111553784860558,
+      "grad_norm": 0.1865358054637909,
+      "learning_rate": 4.267265571963179e-06,
+      "loss": 0.5353958010673523,
+      "step": 304
+    },
+    {
+      "epoch": 1.2191235059760956,
+      "grad_norm": 0.15208090841770172,
+      "learning_rate": 4.256278658514858e-06,
+      "loss": 1.195402979850769,
+      "step": 306
+    },
+    {
+      "epoch": 1.2270916334661355,
+      "grad_norm": 0.26344433426856995,
+      "learning_rate": 4.245226269738165e-06,
+      "loss": 1.0176347494125366,
+      "step": 308
+    },
+    {
+      "epoch": 1.2350597609561753,
+      "grad_norm": 0.23767498135566711,
+      "learning_rate": 4.23410888606133e-06,
+      "loss": 1.1263632774353027,
+      "step": 310
+    },
+    {
+      "epoch": 1.2430278884462151,
+      "grad_norm": 0.403329461812973,
+      "learning_rate": 4.222926990737793e-06,
+      "loss": 1.0683237314224243,
+      "step": 312
+    },
+    {
+      "epoch": 1.250996015936255,
+      "grad_norm": 0.19358761608600616,
+      "learning_rate": 4.211681069825207e-06,
+      "loss": 0.864902675151825,
+      "step": 314
+    },
+    {
+      "epoch": 1.2589641434262948,
+      "grad_norm": 0.45990151166915894,
+      "learning_rate": 4.200371612164305e-06,
+      "loss": 0.7280765771865845,
+      "step": 316
+    },
+    {
+      "epoch": 1.2669322709163346,
+      "grad_norm": 0.2076907902956009,
+      "learning_rate": 4.1889991093576555e-06,
+      "loss": 0.609905481338501,
+      "step": 318
+    },
+    {
+      "epoch": 1.2749003984063745,
+      "grad_norm": 0.19576290249824524,
+      "learning_rate": 4.177564055748284e-06,
+      "loss": 0.48998862504959106,
+      "step": 320
+    },
+    {
+      "epoch": 1.2828685258964143,
+      "grad_norm": 0.26460185647010803,
+      "learning_rate": 4.166066948398199e-06,
+      "loss": 1.0001124143600464,
+      "step": 322
+    },
+    {
+      "epoch": 1.2908366533864541,
+      "grad_norm": 0.23232752084732056,
+      "learning_rate": 4.154508287066772e-06,
+      "loss": 0.9234213829040527,
+      "step": 324
+    },
+    {
+      "epoch": 1.298804780876494,
+      "grad_norm": 0.3292633295059204,
+      "learning_rate": 4.142888574189025e-06,
+      "loss": 1.310882568359375,
+      "step": 326
+    },
+    {
+      "epoch": 1.3067729083665338,
+      "grad_norm": 0.16180568933486938,
+      "learning_rate": 4.131208314853778e-06,
+      "loss": 0.6991411447525024,
+      "step": 328
+    },
+    {
+      "epoch": 1.3147410358565736,
+      "grad_norm": 0.3227066993713379,
+      "learning_rate": 4.119468016781707e-06,
+      "loss": 0.9130216240882874,
+      "step": 330
+    },
+    {
+      "epoch": 1.3227091633466135,
+      "grad_norm": 0.2901485860347748,
+      "learning_rate": 4.107668190303266e-06,
+      "loss": 0.9210165143013,
+      "step": 332
+    },
+    {
+      "epoch": 1.3306772908366533,
+      "grad_norm": 0.7312538623809814,
+      "learning_rate": 4.095809348336506e-06,
+      "loss": 0.6377519369125366,
+      "step": 334
+    },
+    {
+      "epoch": 1.3386454183266931,
+      "grad_norm": 0.4288463294506073,
+      "learning_rate": 4.083892006364777e-06,
+      "loss": 0.8995386362075806,
+      "step": 336
+    },
+    {
+      "epoch": 1.3466135458167332,
+      "grad_norm": 0.40529322624206543,
+      "learning_rate": 4.071916682414327e-06,
+      "loss": 1.1817045211791992,
+      "step": 338
+    },
+    {
+      "epoch": 1.354581673306773,
+      "grad_norm": 0.14130665361881256,
+      "learning_rate": 4.059883897031777e-06,
+      "loss": 1.1657414436340332,
+      "step": 340
+    },
+    {
+      "epoch": 1.3625498007968129,
+      "grad_norm": 0.17052190005779266,
+      "learning_rate": 4.0477941732615e-06,
+      "loss": 1.2001479864120483,
+      "step": 342
+    },
+    {
+      "epoch": 1.3705179282868527,
+      "grad_norm": 0.5133300423622131,
+      "learning_rate": 4.035648036622879e-06,
+      "loss": 1.1728051900863647,
+      "step": 344
+    },
+    {
+      "epoch": 1.3784860557768925,
+      "grad_norm": 0.9479273557662964,
+      "learning_rate": 4.023446015087469e-06,
+      "loss": 0.7141541838645935,
+      "step": 346
+    },
+    {
+      "epoch": 1.3864541832669324,
+      "grad_norm": 0.178302600979805,
+      "learning_rate": 4.0111886390560446e-06,
+      "loss": 1.1834806203842163,
+      "step": 348
+    },
+    {
+      "epoch": 1.3944223107569722,
+      "grad_norm": 0.9634085297584534,
+      "learning_rate": 3.998876441335544e-06,
+      "loss": 0.716385543346405,
+      "step": 350
+    },
+    {
+      "epoch": 1.402390438247012,
+      "grad_norm": 0.1601984202861786,
+      "learning_rate": 3.98650995711591e-06,
+      "loss": 1.224104881286621,
+      "step": 352
+    },
+    {
+      "epoch": 1.4103585657370519,
+      "grad_norm": 0.2518574595451355,
+      "learning_rate": 3.974089723946826e-06,
+      "loss": 1.160075068473816,
+      "step": 354
+    },
+    {
+      "epoch": 1.4183266932270917,
+      "grad_norm": 0.2955910861492157,
+      "learning_rate": 3.9616162817143465e-06,
+      "loss": 0.9143956899642944,
+      "step": 356
+    },
+    {
+      "epoch": 1.4262948207171315,
+      "grad_norm": 0.15328529477119446,
+      "learning_rate": 3.949090172617437e-06,
+      "loss": 1.1701505184173584,
+      "step": 358
+    },
+    {
+      "epoch": 1.4342629482071714,
+      "grad_norm": 0.32084110379219055,
+      "learning_rate": 3.936511941144397e-06,
+      "loss": 0.6246562600135803,
+      "step": 360
+    },
+    {
+      "epoch": 1.4422310756972112,
+      "grad_norm": 0.19887106120586395,
+      "learning_rate": 3.9238821340491936e-06,
+      "loss": 0.7575674653053284,
+      "step": 362
+    },
+    {
+      "epoch": 1.450199203187251,
+      "grad_norm": 0.5882703065872192,
+      "learning_rate": 3.911201300327703e-06,
+      "loss": 1.0714350938796997,
+      "step": 364
+    },
+    {
+      "epoch": 1.4581673306772909,
+      "grad_norm": 0.11301520466804504,
+      "learning_rate": 3.898469991193835e-06,
+      "loss": 1.157347559928894,
+      "step": 366
+    },
+    {
+      "epoch": 1.4661354581673307,
+      "grad_norm": 0.29773953557014465,
+      "learning_rate": 3.885688760055581e-06,
+      "loss": 0.6370880603790283,
+      "step": 368
+    },
+    {
+      "epoch": 1.4741035856573705,
+      "grad_norm": 0.18414317071437836,
+      "learning_rate": 3.872858162490956e-06,
+      "loss": 0.7134079933166504,
+      "step": 370
+    },
+    {
+      "epoch": 1.4820717131474104,
+      "grad_norm": 0.37900933623313904,
+      "learning_rate": 3.859978756223845e-06,
+      "loss": 1.287073016166687,
+      "step": 372
+    },
+    {
+      "epoch": 1.4900398406374502,
+      "grad_norm": 0.3501714766025543,
+      "learning_rate": 3.847051101099768e-06,
+      "loss": 1.1789612770080566,
+      "step": 374
+    },
+    {
+      "epoch": 1.49800796812749,
+      "grad_norm": 0.1395445317029953,
+      "learning_rate": 3.834075759061535e-06,
+      "loss": 1.1704124212265015,
+      "step": 376
+    },
+    {
+      "epoch": 1.5059760956175299,
+      "grad_norm": 0.3695407509803772,
+      "learning_rate": 3.8210532941248255e-06,
+      "loss": 0.9334000945091248,
+      "step": 378
+    },
+    {
+      "epoch": 1.5139442231075697,
+      "grad_norm": 0.34059756994247437,
+      "learning_rate": 3.8079842723536688e-06,
+      "loss": 1.1380053758621216,
+      "step": 380
+    },
+    {
+      "epoch": 1.5219123505976095,
+      "grad_norm": 0.11811260879039764,
+      "learning_rate": 3.7948692618358424e-06,
+      "loss": 0.8046299815177917,
+      "step": 382
+    },
+    {
+      "epoch": 1.5298804780876494,
+      "grad_norm": 0.13538780808448792,
+      "learning_rate": 3.781708832658169e-06,
+      "loss": 0.7898821830749512,
+      "step": 384
+    },
+    {
+      "epoch": 1.5378486055776892,
+      "grad_norm": 0.28071942925453186,
+      "learning_rate": 3.7685035568817492e-06,
+      "loss": 1.0728089809417725,
+      "step": 386
+    },
+    {
+      "epoch": 1.545816733067729,
+      "grad_norm": 0.26359888911247253,
+      "learning_rate": 3.7552540085170826e-06,
+      "loss": 1.1836777925491333,
+      "step": 388
+    },
+    {
+      "epoch": 1.5537848605577689,
+      "grad_norm": 0.31850743293762207,
+      "learning_rate": 3.7419607634991235e-06,
+      "loss": 0.5400734543800354,
+      "step": 390
+    },
+    {
+      "epoch": 1.5617529880478087,
+      "grad_norm": 0.35873132944107056,
+      "learning_rate": 3.7286243996622432e-06,
+      "loss": 0.6076874732971191,
+      "step": 392
+    },
+    {
+      "epoch": 1.5697211155378485,
+      "grad_norm": 0.6918613910675049,
+      "learning_rate": 3.715245496715116e-06,
+      "loss": 1.1702717542648315,
+      "step": 394
+    },
+    {
+      "epoch": 1.5776892430278884,
+      "grad_norm": 0.39108043909072876,
+      "learning_rate": 3.7018246362155134e-06,
+      "loss": 1.0692623853683472,
+      "step": 396
+    },
+    {
+      "epoch": 1.5856573705179282,
+      "grad_norm": 0.11517906934022903,
+      "learning_rate": 3.6883624015450344e-06,
+      "loss": 1.1680564880371094,
+      "step": 398
+    },
+    {
+      "epoch": 1.593625498007968,
+      "grad_norm": 0.2687815725803375,
+      "learning_rate": 3.6748593778837367e-06,
+      "loss": 0.5960079431533813,
+      "step": 400
+    },
+    {
+      "epoch": 1.6015936254980079,
+      "grad_norm": 0.17672830820083618,
+      "learning_rate": 3.661316152184708e-06,
+      "loss": 1.1508926153182983,
+      "step": 402
+    },
+    {
+      "epoch": 1.6095617529880477,
+      "grad_norm": 0.17908449470996857,
+      "learning_rate": 3.6477333131485483e-06,
+      "loss": 1.301782488822937,
+      "step": 404
+    },
+    {
+      "epoch": 1.6175298804780875,
+      "grad_norm": 0.4330017864704132,
+      "learning_rate": 3.634111451197781e-06,
+      "loss": 0.7402876615524292,
+      "step": 406
+    },
+    {
+      "epoch": 1.6254980079681274,
+      "grad_norm": 0.10258221626281738,
+      "learning_rate": 3.6204511584511865e-06,
+      "loss": 0.5856541991233826,
+      "step": 408
+    },
+    {
+      "epoch": 1.6334661354581672,
+      "grad_norm": 0.15880520641803741,
+      "learning_rate": 3.606753028698067e-06,
+      "loss": 0.8118333220481873,
+      "step": 410
+    },
+    {
+      "epoch": 1.641434262948207,
+      "grad_norm": 0.338400274515152,
+      "learning_rate": 3.593017657372436e-06,
+      "loss": 0.526035487651825,
+      "step": 412
+    },
+    {
+      "epoch": 1.6494023904382469,
+      "grad_norm": 0.12577082216739655,
+      "learning_rate": 3.5792456415271288e-06,
+      "loss": 0.8786559700965881,
+      "step": 414
+    },
+    {
+      "epoch": 1.6573705179282867,
+      "grad_norm": 0.18215803802013397,
+      "learning_rate": 3.565437579807858e-06,
+      "loss": 0.7458572387695312,
+      "step": 416
+    },
+    {
+      "epoch": 1.6653386454183265,
+      "grad_norm": 0.3652243912220001,
+      "learning_rate": 3.551594072427188e-06,
+      "loss": 1.067691683769226,
+      "step": 418
+    },
+    {
+      "epoch": 1.6733067729083664,
+      "grad_norm": 0.1905258148908615,
+      "learning_rate": 3.537715721138444e-06,
+      "loss": 1.164352536201477,
+      "step": 420
+    },
+    {
+      "epoch": 1.6812749003984062,
+      "grad_norm": 0.16650676727294922,
+      "learning_rate": 3.523803129209554e-06,
+      "loss": 1.0673019886016846,
+      "step": 422
+    },
+    {
+      "epoch": 1.6892430278884463,
+      "grad_norm": 0.213884636759758,
+      "learning_rate": 3.5098569013968314e-06,
+      "loss": 0.6284163594245911,
+      "step": 424
+    },
+    {
+      "epoch": 1.697211155378486,
+      "grad_norm": 0.19134126603603363,
+      "learning_rate": 3.49587764391868e-06,
+      "loss": 1.2433464527130127,
+      "step": 426
+    },
+    {
+      "epoch": 1.705179282868526,
+      "grad_norm": 0.13315454125404358,
+      "learning_rate": 3.4818659644292473e-06,
+      "loss": 1.181111454963684,
+      "step": 428
+    },
+    {
+      "epoch": 1.7131474103585658,
+      "grad_norm": 0.21014367043972015,
+      "learning_rate": 3.4678224719920085e-06,
+      "loss": 0.75547856092453,
+      "step": 430
+    },
+    {
+      "epoch": 1.7211155378486056,
+      "grad_norm": 0.25423720479011536,
+      "learning_rate": 3.4537477770532933e-06,
+      "loss": 0.9444085359573364,
+      "step": 432
+    },
+    {
+      "epoch": 1.7290836653386454,
+      "grad_norm": 0.3293650448322296,
+      "learning_rate": 3.4396424914157527e-06,
+      "loss": 0.6509208083152771,
+      "step": 434
+    },
+    {
+      "epoch": 1.7370517928286853,
+      "grad_norm": 0.29267174005508423,
+      "learning_rate": 3.4255072282117574e-06,
+      "loss": 0.36421462893486023,
+      "step": 436
+    },
+    {
+      "epoch": 1.745019920318725,
+      "grad_norm": 0.33871668577194214,
+      "learning_rate": 3.411342601876754e-06,
+      "loss": 0.736098051071167,
+      "step": 438
+    },
+    {
+      "epoch": 1.752988047808765,
+      "grad_norm": 0.6019716262817383,
+      "learning_rate": 3.3971492281225554e-06,
+      "loss": 0.6757362484931946,
+      "step": 440
+    },
+    {
+      "epoch": 1.7609561752988048,
+      "grad_norm": 0.45847344398498535,
+      "learning_rate": 3.382927723910572e-06,
+      "loss": 1.5645800828933716,
+      "step": 442
+    },
+    {
+      "epoch": 1.7689243027888446,
+      "grad_norm": 0.262884259223938,
+      "learning_rate": 3.3686787074249966e-06,
+      "loss": 0.8292508721351624,
+      "step": 444
+    },
+    {
+      "epoch": 1.7768924302788844,
+      "grad_norm": 0.12800410389900208,
+      "learning_rate": 3.354402798045935e-06,
+      "loss": 1.0583349466323853,
+      "step": 446
+    },
+    {
+      "epoch": 1.7848605577689243,
+      "grad_norm": 0.28849488496780396,
+      "learning_rate": 3.340100616322479e-06,
+      "loss": 1.1311969757080078,
+      "step": 448
+    },
+    {
+      "epoch": 1.792828685258964,
+      "grad_norm": 0.16964475810527802,
+      "learning_rate": 3.3257727839457356e-06,
+      "loss": 0.8914226293563843,
+      "step": 450
+    },
+    {
+      "epoch": 1.800796812749004,
+      "grad_norm": 0.1119479387998581,
+      "learning_rate": 3.311419923721798e-06,
+      "loss": 0.5656667351722717,
+      "step": 452
+    },
+    {
+      "epoch": 1.8087649402390438,
+      "grad_norm": 0.31310245394706726,
+      "learning_rate": 3.29704265954468e-06,
+      "loss": 1.0131810903549194,
+      "step": 454
+    },
+    {
+      "epoch": 1.8167330677290838,
+      "grad_norm": 0.3031913638114929,
+      "learning_rate": 3.282641616369193e-06,
+      "loss": 0.6895798444747925,
+      "step": 456
+    },
+    {
+      "epoch": 1.8247011952191237,
+      "grad_norm": 0.18734273314476013,
+      "learning_rate": 3.2682174201837773e-06,
+      "loss": 1.0674736499786377,
+      "step": 458
+    },
+    {
+      "epoch": 1.8326693227091635,
+      "grad_norm": 0.6715296506881714,
+      "learning_rate": 3.2537706979832955e-06,
+      "loss": 0.7272610068321228,
+      "step": 460
+    },
+    {
+      "epoch": 1.8406374501992033,
+      "grad_norm": 0.16952070593833923,
+      "learning_rate": 3.23930207774178e-06,
+      "loss": 0.7839730978012085,
+      "step": 462
+    },
+    {
+      "epoch": 1.8486055776892432,
+      "grad_norm": 0.11049998551607132,
+      "learning_rate": 3.2248121883851296e-06,
+      "loss": 0.11988221108913422,
+      "step": 464
+    },
+    {
+      "epoch": 1.856573705179283,
+      "grad_norm": 0.14067628979682922,
+      "learning_rate": 3.210301659763777e-06,
+      "loss": 1.1859278678894043,
+      "step": 466
+    },
+    {
+      "epoch": 1.8645418326693228,
+      "grad_norm": 0.28356078267097473,
+      "learning_rate": 3.1957711226253073e-06,
+      "loss": 0.5654076933860779,
+      "step": 468
+    },
+    {
+      "epoch": 1.8725099601593627,
+      "grad_norm": 0.26206132769584656,
+      "learning_rate": 3.181221208587041e-06,
+      "loss": 1.1874788999557495,
+      "step": 470
+    },
+    {
+      "epoch": 1.8804780876494025,
+      "grad_norm": 0.2839134633541107,
+      "learning_rate": 3.16665255010858e-06,
+      "loss": 1.0328947305679321,
+      "step": 472
+    },
+    {
+      "epoch": 1.8884462151394423,
+      "grad_norm": 0.2991686463356018,
+      "learning_rate": 3.152065780464311e-06,
+      "loss": 1.2463393211364746,
+      "step": 474
+    },
+    {
+      "epoch": 1.8964143426294822,
+      "grad_norm": 0.185896098613739,
+      "learning_rate": 3.1374615337158874e-06,
+      "loss": 0.9774811863899231,
+      "step": 476
+    },
+    {
+      "epoch": 1.904382470119522,
+      "grad_norm": 0.19690260291099548,
+      "learning_rate": 3.1228404446846577e-06,
+      "loss": 0.875652551651001,
+      "step": 478
+    },
+    {
+      "epoch": 1.9123505976095618,
+      "grad_norm": 0.7344804406166077,
+      "learning_rate": 3.1082031489240775e-06,
+      "loss": 0.5999815464019775,
+      "step": 480
+    },
+    {
+      "epoch": 1.9203187250996017,
+      "grad_norm": 0.2018146812915802,
+      "learning_rate": 3.093550282692081e-06,
+      "loss": 0.7411183714866638,
+      "step": 482
+    },
+    {
+      "epoch": 1.9282868525896415,
+      "grad_norm": 0.14856193959712982,
+      "learning_rate": 3.0788824829234206e-06,
+      "loss": 1.1458566188812256,
+      "step": 484
+    },
+    {
+      "epoch": 1.9362549800796813,
+      "grad_norm": 0.22270627319812775,
+      "learning_rate": 3.064200387201987e-06,
+      "loss": 1.1758733987808228,
+      "step": 486
+    },
+    {
+      "epoch": 1.9442231075697212,
+      "grad_norm": 0.22310347855091095,
+      "learning_rate": 3.0495046337330917e-06,
+      "loss": 1.1439220905303955,
+      "step": 488
+    },
+    {
+      "epoch": 1.952191235059761,
+      "grad_norm": 0.14515511691570282,
+      "learning_rate": 3.034795861315723e-06,
+      "loss": 1.1569921970367432,
+      "step": 490
+    },
+    {
+      "epoch": 1.9601593625498008,
+      "grad_norm": 0.19895517826080322,
+      "learning_rate": 3.020074709314781e-06,
+      "loss": 0.8201751112937927,
+      "step": 492
+    },
+    {
+      "epoch": 1.9681274900398407,
+      "grad_norm": 0.6536427140235901,
+      "learning_rate": 3.0053418176332844e-06,
+      "loss": 0.6143178343772888,
+      "step": 494
+    },
+    {
+      "epoch": 1.9760956175298805,
+      "grad_norm": 0.2805826961994171,
+      "learning_rate": 2.9905978266845565e-06,
+      "loss": 1.1290977001190186,
+      "step": 496
+    },
+    {
+      "epoch": 1.9840637450199203,
+      "grad_norm": 0.9473842978477478,
+      "learning_rate": 2.975843377364385e-06,
+      "loss": 0.8779794573783875,
+      "step": 498
+    },
+    {
+      "epoch": 1.9920318725099602,
+      "grad_norm": 0.15845194458961487,
+      "learning_rate": 2.961079111023167e-06,
+      "loss": 1.1883915662765503,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08591461181640625,
+      "learning_rate": 2.9463056694380263e-06,
+      "loss": 0.6186908483505249,
+      "step": 502
+    },
+    {
+      "epoch": 2.00796812749004,
+      "grad_norm": 0.1766180396080017,
+      "learning_rate": 2.9315236947849213e-06,
+      "loss": 0.682772159576416,
+      "step": 504
+    },
+    {
+      "epoch": 2.0159362549800797,
+      "grad_norm": 0.40233951807022095,
+      "learning_rate": 2.916733829610726e-06,
+      "loss": 0.6987518668174744,
+      "step": 506
+    },
+    {
+      "epoch": 2.0239043824701195,
+      "grad_norm": 0.0491398461163044,
+      "learning_rate": 2.901936716805302e-06,
+      "loss": 0.583588182926178,
+      "step": 508
+    },
+    {
+      "epoch": 2.0318725099601593,
+      "grad_norm": 0.1854499727487564,
+      "learning_rate": 2.887132999573554e-06,
+      "loss": 0.9084243774414062,
+      "step": 510
+    },
+    {
+      "epoch": 2.039840637450199,
+      "grad_norm": 1.4056905508041382,
+      "learning_rate": 2.8723233214074675e-06,
+      "loss": 0.7862600088119507,
+      "step": 512
+    },
+    {
+      "epoch": 2.047808764940239,
+      "grad_norm": 0.49783560633659363,
+      "learning_rate": 2.857508326058142e-06,
+      "loss": 0.2598005533218384,
+      "step": 514
+    },
+    {
+      "epoch": 2.055776892430279,
+      "grad_norm": 0.17493696510791779,
+      "learning_rate": 2.842688657507805e-06,
+      "loss": 0.9368789196014404,
+      "step": 516
+    },
+    {
+      "epoch": 2.0637450199203187,
+      "grad_norm": 3.7843520641326904,
+      "learning_rate": 2.8278649599418194e-06,
+      "loss": 0.5667819976806641,
+      "step": 518
+    },
+    {
+      "epoch": 2.0717131474103585,
+      "grad_norm": 0.3300062417984009,
+      "learning_rate": 2.813037877720683e-06,
+      "loss": 0.9266909956932068,
+      "step": 520
+    },
+    {
+      "epoch": 2.0796812749003983,
+      "grad_norm": 0.22610419988632202,
+      "learning_rate": 2.798208055352017e-06,
+      "loss": 1.0826575756072998,
+      "step": 522
+    },
+    {
+      "epoch": 2.087649402390438,
+      "grad_norm": 0.6533848643302917,
+      "learning_rate": 2.7833761374625546e-06,
+      "loss": 1.0334638357162476,
+      "step": 524
+    },
+    {
+      "epoch": 2.095617529880478,
+      "grad_norm": 0.701194167137146,
+      "learning_rate": 2.7685427687701172e-06,
+      "loss": 0.4522134065628052,
+      "step": 526
+    },
+    {
+      "epoch": 2.103585657370518,
+      "grad_norm": 0.18757887184619904,
+      "learning_rate": 2.753708594055588e-06,
+      "loss": 0.8463180661201477,
+      "step": 528
+    },
+    {
+      "epoch": 2.1115537848605577,
+      "grad_norm": 0.13783429563045502,
+      "learning_rate": 2.7388742581348893e-06,
+      "loss": 0.7611066102981567,
+      "step": 530
+    },
+    {
+      "epoch": 2.1195219123505975,
+      "grad_norm": 0.12442820519208908,
+      "learning_rate": 2.7240404058309487e-06,
+      "loss": 0.2651296854019165,
+      "step": 532
+    },
+    {
+      "epoch": 2.1274900398406373,
+      "grad_norm": 0.46111056208610535,
+      "learning_rate": 2.709207681945673e-06,
+      "loss": 0.8239482641220093,
+      "step": 534
+    },
+    {
+      "epoch": 2.135458167330677,
+      "grad_norm": 0.6820153594017029,
+      "learning_rate": 2.6943767312319167e-06,
+      "loss": 0.7330361604690552,
+      "step": 536
+    },
+    {
+      "epoch": 2.143426294820717,
+      "grad_norm": 0.36753934621810913,
+      "learning_rate": 2.679548198365462e-06,
+      "loss": 0.7063195705413818,
+      "step": 538
+    },
+    {
+      "epoch": 2.151394422310757,
+      "grad_norm": 0.2245899885892868,
+      "learning_rate": 2.6647227279169873e-06,
+      "loss": 0.9869629740715027,
+      "step": 540
+    },
+    {
+      "epoch": 2.1593625498007967,
+      "grad_norm": 0.24492686986923218,
+      "learning_rate": 2.6499009643240527e-06,
+      "loss": 0.9997462630271912,
+      "step": 542
+    },
+    {
+      "epoch": 2.1673306772908365,
+      "grad_norm": 0.17470212280750275,
+      "learning_rate": 2.6350835518630907e-06,
+      "loss": 0.9137216806411743,
+      "step": 544
+    },
+    {
+      "epoch": 2.1752988047808763,
+      "grad_norm": 0.1994341015815735,
+      "learning_rate": 2.620271134621397e-06,
+      "loss": 0.7038854956626892,
+      "step": 546
+    },
+    {
+      "epoch": 2.183266932270916,
+      "grad_norm": 0.5501155257225037,
+      "learning_rate": 2.605464356469131e-06,
+      "loss": 1.0640654563903809,
+      "step": 548
+    },
+    {
+      "epoch": 2.191235059760956,
+      "grad_norm": 0.22964413464069366,
+      "learning_rate": 2.5906638610313336e-06,
+      "loss": 1.1164069175720215,
+      "step": 550
+    },
+    {
+      "epoch": 2.199203187250996,
+      "grad_norm": 0.23910368978977203,
+      "learning_rate": 2.575870291659946e-06,
+      "loss": 0.7981907725334167,
+      "step": 552
+    },
+    {
+      "epoch": 2.2071713147410357,
+      "grad_norm": 0.29295814037323,
+      "learning_rate": 2.5610842914058446e-06,
+      "loss": 0.446155309677124,
+      "step": 554
+    },
+    {
+      "epoch": 2.2151394422310755,
+      "grad_norm": 0.17312096059322357,
+      "learning_rate": 2.5463065029908906e-06,
+      "loss": 0.700094997882843,
+      "step": 556
+    },
+    {
+      "epoch": 2.2231075697211153,
+      "grad_norm": 0.21850021183490753,
+      "learning_rate": 2.5315375687799896e-06,
+      "loss": 0.8777992725372314,
+      "step": 558
+    },
+    {
+      "epoch": 2.231075697211155,
+      "grad_norm": 0.1643497347831726,
+      "learning_rate": 2.5167781307531714e-06,
+      "loss": 1.0006399154663086,
+      "step": 560
+    },
+    {
+      "epoch": 2.239043824701195,
+      "grad_norm": 0.18887636065483093,
+      "learning_rate": 2.5020288304776822e-06,
+      "loss": 1.1018555164337158,
+      "step": 562
+    },
+    {
+      "epoch": 2.247011952191235,
+      "grad_norm": 0.8392075896263123,
+      "learning_rate": 2.487290309080097e-06,
+      "loss": 0.8930177092552185,
+      "step": 564
+    },
+    {
+      "epoch": 2.2549800796812747,
+      "grad_norm": 0.15411703288555145,
+      "learning_rate": 2.472563207218454e-06,
+      "loss": 0.7280173897743225,
+      "step": 566
+    },
+    {
+      "epoch": 2.2629482071713145,
+      "grad_norm": 0.16006462275981903,
+      "learning_rate": 2.457848165054402e-06,
+      "loss": 0.8207918405532837,
+      "step": 568
+    },
+    {
+      "epoch": 2.2709163346613543,
+      "grad_norm": 0.16222696006298065,
+      "learning_rate": 2.4431458222253755e-06,
+      "loss": 1.0905206203460693,
+      "step": 570
+    },
+    {
+      "epoch": 2.278884462151394,
+      "grad_norm": 0.8407166004180908,
+      "learning_rate": 2.4284568178167923e-06,
+      "loss": 0.6187630891799927,
+      "step": 572
+    },
+    {
+      "epoch": 2.2868525896414345,
+      "grad_norm": 0.21044810116291046,
+      "learning_rate": 2.413781790334272e-06,
+      "loss": 0.7563509345054626,
+      "step": 574
+    },
+    {
+      "epoch": 2.2948207171314743,
+      "grad_norm": 0.05672510713338852,
+      "learning_rate": 2.3991213776758776e-06,
+      "loss": 0.2623143494129181,
+      "step": 576
+    },
+    {
+      "epoch": 2.302788844621514,
+      "grad_norm": 0.24665121734142303,
+      "learning_rate": 2.3844762171043975e-06,
+      "loss": 0.6852317452430725,
+      "step": 578
+    },
+    {
+      "epoch": 2.310756972111554,
+      "grad_norm": 0.15142279863357544,
+      "learning_rate": 2.3698469452196328e-06,
+      "loss": 0.6712151169776917,
+      "step": 580
+    },
+    {
+      "epoch": 2.318725099601594,
+      "grad_norm": 0.3340560495853424,
+      "learning_rate": 2.355234197930735e-06,
+      "loss": 0.6551527380943298,
+      "step": 582
+    },
+    {
+      "epoch": 2.3266932270916336,
+      "grad_norm": 0.10578423738479614,
+      "learning_rate": 2.340638610428554e-06,
+      "loss": 0.8353914618492126,
+      "step": 584
+    },
+    {
+      "epoch": 2.3346613545816735,
+      "grad_norm": 0.164351686835289,
+      "learning_rate": 2.3260608171580412e-06,
+      "loss": 0.6742885112762451,
+      "step": 586
+    },
+    {
+      "epoch": 2.3426294820717133,
+      "grad_norm": 12.832938194274902,
+      "learning_rate": 2.311501451790658e-06,
+      "loss": 0.9225565791130066,
+      "step": 588
+    },
+    {
+      "epoch": 2.350597609561753,
+      "grad_norm": 0.7432026267051697,
+      "learning_rate": 2.2969611471968386e-06,
+      "loss": 1.0693492889404297,
+      "step": 590
+    },
+    {
+      "epoch": 2.358565737051793,
+      "grad_norm": 0.1554143875837326,
+      "learning_rate": 2.2824405354184776e-06,
+      "loss": 1.1116424798965454,
+      "step": 592
+    },
+    {
+      "epoch": 2.366533864541833,
+      "grad_norm": 0.7643561959266663,
+      "learning_rate": 2.267940247641458e-06,
+      "loss": 0.7770021557807922,
+      "step": 594
+    },
+    {
+      "epoch": 2.3745019920318726,
+      "grad_norm": 0.17631518840789795,
+      "learning_rate": 2.2534609141682135e-06,
+      "loss": 1.0330625772476196,
+      "step": 596
+    },
+    {
+      "epoch": 2.3824701195219125,
+      "grad_norm": 0.12926886975765228,
+      "learning_rate": 2.2390031643903286e-06,
+      "loss": 0.7804954051971436,
+      "step": 598
+    },
+    {
+      "epoch": 2.3904382470119523,
+      "grad_norm": 0.43368035554885864,
+      "learning_rate": 2.224567626761185e-06,
+      "loss": 0.9834002256393433,
+      "step": 600
+    },
+    {
+      "epoch": 2.398406374501992,
+      "grad_norm": 0.162871316075325,
+      "learning_rate": 2.2101549287686384e-06,
+      "loss": 1.0966094732284546,
+      "step": 602
+    },
+    {
+      "epoch": 2.406374501992032,
+      "grad_norm": 0.0719643086194992,
+      "learning_rate": 2.195765696907745e-06,
+      "loss": 0.6204472184181213,
+      "step": 604
+    },
+    {
+      "epoch": 2.414342629482072,
+      "grad_norm": 0.3520434498786926,
+      "learning_rate": 2.1814005566535303e-06,
+      "loss": 0.22512780129909515,
+      "step": 606
+    },
+    {
+      "epoch": 2.4223107569721116,
+      "grad_norm": 0.06715325266122818,
+      "learning_rate": 2.167060132433798e-06,
+      "loss": 0.6074760556221008,
+      "step": 608
+    },
+    {
+      "epoch": 2.4302788844621515,
+      "grad_norm": 0.10031144320964813,
+      "learning_rate": 2.1527450476019895e-06,
+      "loss": 1.0203115940093994,
+      "step": 610
+    },
+    {
+      "epoch": 2.4382470119521913,
+      "grad_norm": 0.36666399240493774,
+      "learning_rate": 2.138455924410085e-06,
+      "loss": 0.7576355934143066,
+      "step": 612
+    },
+    {
+      "epoch": 2.446215139442231,
+      "grad_norm": 0.44304245710372925,
+      "learning_rate": 2.1241933839815606e-06,
+      "loss": 0.6145632863044739,
+      "step": 614
+    },
+    {
+      "epoch": 2.454183266932271,
+      "grad_norm": 0.16212224960327148,
+      "learning_rate": 2.109958046284382e-06,
+      "loss": 0.9955238103866577,
+      "step": 616
+    },
+    {
+      "epoch": 2.462151394422311,
+      "grad_norm": 0.21524690091609955,
+      "learning_rate": 2.0957505301040604e-06,
+      "loss": 0.7642925977706909,
+      "step": 618
+    },
+    {
+      "epoch": 2.4701195219123506,
+      "grad_norm": 0.5468536019325256,
+      "learning_rate": 2.081571453016756e-06,
+      "loss": 0.8671405911445618,
+      "step": 620
+    },
+    {
+      "epoch": 2.4780876494023905,
+      "grad_norm": 0.4352398216724396,
+      "learning_rate": 2.067421431362427e-06,
+      "loss": 0.886379063129425,
+      "step": 622
+    },
+    {
+      "epoch": 2.4860557768924303,
+      "grad_norm": 0.20494049787521362,
+      "learning_rate": 2.053301080218044e-06,
+      "loss": 0.8346015214920044,
+      "step": 624
+    },
+    {
+      "epoch": 2.49402390438247,
+      "grad_norm": 0.5697457194328308,
+      "learning_rate": 2.039211013370853e-06,
+      "loss": 0.7564113736152649,
+      "step": 626
+    },
+    {
+      "epoch": 2.50199203187251,
+      "grad_norm": 0.24146224558353424,
+      "learning_rate": 2.025151843291693e-06,
+      "loss": 1.0702261924743652,
+      "step": 628
+    },
+    {
+      "epoch": 2.50996015936255,
+      "grad_norm": 0.4110378921031952,
+      "learning_rate": 2.0111241811083733e-06,
+      "loss": 0.5551565289497375,
+      "step": 630
+    },
+    {
+      "epoch": 2.5179282868525896,
+      "grad_norm": 0.6313554644584656,
+      "learning_rate": 1.9971286365791092e-06,
+      "loss": 0.51365065574646,
+      "step": 632
+    },
+    {
+      "epoch": 2.5258964143426295,
+      "grad_norm": 0.18522877991199493,
+      "learning_rate": 1.9831658180660197e-06,
+      "loss": 1.0828502178192139,
+      "step": 634
+    },
+    {
+      "epoch": 2.5338645418326693,
+      "grad_norm": 0.2894231677055359,
+      "learning_rate": 1.9692363325086774e-06,
+      "loss": 1.0256881713867188,
+      "step": 636
+    },
+    {
+      "epoch": 2.541832669322709,
+      "grad_norm": 0.9185420274734497,
+      "learning_rate": 1.95534078539773e-06,
+      "loss": 1.0182496309280396,
+      "step": 638
+    },
+    {
+      "epoch": 2.549800796812749,
+      "grad_norm": 0.09158791601657867,
+      "learning_rate": 1.9414797807485796e-06,
+      "loss": 0.8324208855628967,
+      "step": 640
+    },
+    {
+      "epoch": 2.557768924302789,
+      "grad_norm": 0.3643508553504944,
+      "learning_rate": 1.9276539210751295e-06,
+      "loss": 1.0580339431762695,
+      "step": 642
+    },
+    {
+      "epoch": 2.5657370517928286,
+      "grad_norm": 0.3601572513580322,
+      "learning_rate": 1.9138638073635886e-06,
+      "loss": 1.2165855169296265,
+      "step": 644
+    },
+    {
+      "epoch": 2.5737051792828685,
+      "grad_norm": 0.18631714582443237,
+      "learning_rate": 1.90011003904635e-06,
+      "loss": 0.6096924543380737,
+      "step": 646
+    },
+    {
+      "epoch": 2.5816733067729083,
+      "grad_norm": 0.18535248935222626,
+      "learning_rate": 1.886393213975939e-06,
+      "loss": 1.0994805097579956,
+      "step": 648
+    },
+    {
+      "epoch": 2.589641434262948,
+      "grad_norm": 0.28044986724853516,
+      "learning_rate": 1.8727139283990203e-06,
+      "loss": 0.8462460041046143,
+      "step": 650
+    },
+    {
+      "epoch": 2.597609561752988,
+      "grad_norm": 0.21029400825500488,
+      "learning_rate": 1.8590727769304789e-06,
+      "loss": 0.8882898092269897,
+      "step": 652
+    },
+    {
+      "epoch": 2.605577689243028,
+      "grad_norm": 0.1896900236606598,
+      "learning_rate": 1.8454703525275814e-06,
+      "loss": 0.708066999912262,
+      "step": 654
+    },
+    {
+      "epoch": 2.6135458167330676,
+      "grad_norm": 0.17034193873405457,
+      "learning_rate": 1.8319072464641912e-06,
+      "loss": 0.3668864369392395,
+      "step": 656
+    },
+    {
+      "epoch": 2.6215139442231075,
+      "grad_norm": 0.15018504858016968,
+      "learning_rate": 1.8183840483050741e-06,
+      "loss": 0.576996386051178,
+      "step": 658
+    },
+    {
+      "epoch": 2.6294820717131473,
+      "grad_norm": 0.23269203305244446,
+      "learning_rate": 1.8049013458802667e-06,
+      "loss": 0.9274337887763977,
+      "step": 660
+    },
+    {
+      "epoch": 2.637450199203187,
+      "grad_norm": 0.3903900980949402,
+      "learning_rate": 1.7914597252595267e-06,
+      "loss": 1.1220518350601196,
+      "step": 662
+    },
+    {
+      "epoch": 2.645418326693227,
+      "grad_norm": 0.4379798471927643,
+      "learning_rate": 1.7780597707268582e-06,
+      "loss": 0.6179613471031189,
+      "step": 664
+    },
+    {
+      "epoch": 2.653386454183267,
+      "grad_norm": 0.2553296983242035,
+      "learning_rate": 1.7647020647551105e-06,
+      "loss": 0.9994150400161743,
+      "step": 666
+    },
+    {
+      "epoch": 2.6613545816733066,
+      "grad_norm": 0.05387520045042038,
+      "learning_rate": 1.7513871879806605e-06,
+      "loss": 0.5990697145462036,
+      "step": 668
+    },
+    {
+      "epoch": 2.6693227091633465,
+      "grad_norm": 0.5788288116455078,
+      "learning_rate": 1.7381157191781766e-06,
+      "loss": 0.7859395742416382,
+      "step": 670
+    },
+    {
+      "epoch": 2.6772908366533863,
+      "grad_norm": 0.10587835311889648,
+      "learning_rate": 1.7248882352354571e-06,
+      "loss": 0.4548906981945038,
+      "step": 672
+    },
+    {
+      "epoch": 2.685258964143426,
+      "grad_norm": 0.1578235924243927,
+      "learning_rate": 1.7117053111283528e-06,
+      "loss": 1.0919955968856812,
+      "step": 674
+    },
+    {
+      "epoch": 2.6932270916334664,
+      "grad_norm": 1.8660527467727661,
+      "learning_rate": 1.6985675198957752e-06,
+      "loss": 0.7526142597198486,
+      "step": 676
+    },
+    {
+      "epoch": 2.7011952191235062,
+      "grad_norm": 0.2773953378200531,
+      "learning_rate": 1.6854754326147916e-06,
+      "loss": 0.6427589058876038,
+      "step": 678
+    },
+    {
+      "epoch": 2.709163346613546,
+      "grad_norm": 0.18345235288143158,
+      "learning_rate": 1.6724296183757925e-06,
+      "loss": 1.0830289125442505,
+      "step": 680
+    },
+    {
+      "epoch": 2.717131474103586,
+      "grad_norm": 0.1546901911497116,
+      "learning_rate": 1.6594306442577629e-06,
+      "loss": 1.1120257377624512,
+      "step": 682
+    },
+    {
+      "epoch": 2.7250996015936257,
+      "grad_norm": 0.23372378945350647,
+      "learning_rate": 1.6464790753036298e-06,
+      "loss": 0.7249743938446045,
+      "step": 684
+    },
+    {
+      "epoch": 2.7330677290836656,
+      "grad_norm": 0.1423330307006836,
+      "learning_rate": 1.6335754744956935e-06,
+      "loss": 0.4639202654361725,
+      "step": 686
+    },
+    {
+      "epoch": 2.7410358565737054,
+      "grad_norm": 0.18981285393238068,
+      "learning_rate": 1.6207204027311685e-06,
+      "loss": 1.097824215888977,
+      "step": 688
+    },
+    {
+      "epoch": 2.7490039840637452,
+      "grad_norm": 0.2816353142261505,
+      "learning_rate": 1.6079144187977925e-06,
+      "loss": 0.5818931460380554,
+      "step": 690
+    },
+    {
+      "epoch": 2.756972111553785,
+      "grad_norm": 0.18578679859638214,
+      "learning_rate": 1.595158079349542e-06,
+      "loss": 1.1433192491531372,
+      "step": 692
+    },
+    {
+      "epoch": 2.764940239043825,
+      "grad_norm": 0.25982242822647095,
+      "learning_rate": 1.5824519388824311e-06,
+      "loss": 0.9221243858337402,
+      "step": 694
+    },
+    {
+      "epoch": 2.7729083665338647,
+      "grad_norm": 0.313243567943573,
+      "learning_rate": 1.5697965497104117e-06,
+      "loss": 0.7722380757331848,
+      "step": 696
+    },
+    {
+      "epoch": 2.7808764940239046,
+      "grad_norm": 0.3970114588737488,
+      "learning_rate": 1.557192461941367e-06,
+      "loss": 0.9825866222381592,
+      "step": 698
+    },
+    {
+      "epoch": 2.7888446215139444,
+      "grad_norm": 0.1375483274459839,
+      "learning_rate": 1.5446402234531934e-06,
+      "loss": 1.1016637086868286,
+      "step": 700
+    },
+    {
+      "epoch": 2.7968127490039842,
+      "grad_norm": 0.2981008291244507,
+      "learning_rate": 1.5321403798699924e-06,
+      "loss": 0.692558765411377,
+      "step": 702
+    },
+    {
+      "epoch": 2.804780876494024,
+      "grad_norm": 0.2891223430633545,
+      "learning_rate": 1.5196934745383456e-06,
+      "loss": 1.3150120973587036,
+      "step": 704
+    },
+    {
+      "epoch": 2.812749003984064,
+      "grad_norm": 0.15468446910381317,
+      "learning_rate": 1.5073000485037044e-06,
+      "loss": 1.3187220096588135,
+      "step": 706
+    },
+    {
+      "epoch": 2.8207171314741037,
+      "grad_norm": 0.48310568928718567,
+      "learning_rate": 1.4949606404868638e-06,
+      "loss": 1.1436817646026611,
+      "step": 708
+    },
+    {
+      "epoch": 2.8286852589641436,
+      "grad_norm": 0.09301752597093582,
+      "learning_rate": 1.4826757868605519e-06,
+      "loss": 0.5754663348197937,
+      "step": 710
+    },
+    {
+      "epoch": 2.8366533864541834,
+      "grad_norm": 0.1893586367368698,
+      "learning_rate": 1.4704460216261125e-06,
+      "loss": 1.114943027496338,
+      "step": 712
+    },
+    {
+      "epoch": 2.8446215139442232,
+      "grad_norm": 0.892085075378418,
+      "learning_rate": 1.458271876390287e-06,
+      "loss": 0.6411311626434326,
+      "step": 714
+    },
+    {
+      "epoch": 2.852589641434263,
+      "grad_norm": 0.23233895003795624,
+      "learning_rate": 1.446153880342117e-06,
+      "loss": 1.0921809673309326,
+      "step": 716
+    },
+    {
+      "epoch": 2.860557768924303,
+      "grad_norm": 0.8313801288604736,
+      "learning_rate": 1.4340925602299337e-06,
+      "loss": 0.664229691028595,
+      "step": 718
+    },
+    {
+      "epoch": 2.8685258964143427,
+      "grad_norm": 0.14367663860321045,
+      "learning_rate": 1.4220884403384656e-06,
+      "loss": 0.6170852184295654,
+      "step": 720
+    },
+    {
+      "epoch": 2.8764940239043826,
+      "grad_norm": 0.2393234670162201,
+      "learning_rate": 1.4101420424660433e-06,
+      "loss": 0.7950517535209656,
+      "step": 722
+    },
+    {
+      "epoch": 2.8844621513944224,
+      "grad_norm": 0.11868282407522202,
+      "learning_rate": 1.3982538859019219e-06,
+      "loss": 0.6400004029273987,
+      "step": 724
+    },
+    {
+      "epoch": 2.8924302788844622,
+      "grad_norm": 0.17371788620948792,
+      "learning_rate": 1.3864244874037096e-06,
+      "loss": 1.056016445159912,
+      "step": 726
+    },
+    {
+      "epoch": 2.900398406374502,
+      "grad_norm": 0.13001227378845215,
+      "learning_rate": 1.3746543611749007e-06,
+      "loss": 0.6011821627616882,
+      "step": 728
+    },
+    {
+      "epoch": 2.908366533864542,
+      "grad_norm": 0.20077845454216003,
+      "learning_rate": 1.3629440188425285e-06,
+      "loss": 1.0083385705947876,
+      "step": 730
+    },
+    {
+      "epoch": 2.9163346613545817,
+      "grad_norm": 0.17687654495239258,
+      "learning_rate": 1.351293969434921e-06,
+      "loss": 0.4270380735397339,
+      "step": 732
+    },
+    {
+      "epoch": 2.9243027888446216,
+      "grad_norm": 0.4056450426578522,
+      "learning_rate": 1.3397047193595809e-06,
+      "loss": 1.1123888492584229,
+      "step": 734
+    },
+    {
+      "epoch": 2.9322709163346614,
+      "grad_norm": 0.6620773077011108,
+      "learning_rate": 1.3281767723811651e-06,
+      "loss": 0.43931594491004944,
+      "step": 736
+    },
+    {
+      "epoch": 2.9402390438247012,
+      "grad_norm": 0.38742882013320923,
+      "learning_rate": 1.3167106295995923e-06,
+      "loss": 0.9648318886756897,
+      "step": 738
+    },
+    {
+      "epoch": 2.948207171314741,
+      "grad_norm": 0.21989654004573822,
+      "learning_rate": 1.3053067894282624e-06,
+      "loss": 1.238889455795288,
+      "step": 740
+    },
+    {
+      "epoch": 2.956175298804781,
+      "grad_norm": 0.4380095303058624,
+      "learning_rate": 1.2939657475723844e-06,
+      "loss": 0.42800021171569824,
+      "step": 742
+    },
+    {
+      "epoch": 2.9641434262948207,
+      "grad_norm": 0.15024183690547943,
+      "learning_rate": 1.2826879970074346e-06,
+      "loss": 0.9620094895362854,
+      "step": 744
+    },
+    {
+      "epoch": 2.9721115537848606,
+      "grad_norm": 0.16157156229019165,
+      "learning_rate": 1.271474027957727e-06,
+      "loss": 0.9522150754928589,
+      "step": 746
+    },
+    {
+      "epoch": 2.9800796812749004,
+      "grad_norm": 0.23734919726848602,
+      "learning_rate": 1.2603243278751043e-06,
+      "loss": 0.5941182374954224,
+      "step": 748
+    },
+    {
+      "epoch": 2.9880478087649402,
+      "grad_norm": 0.22269928455352783,
+      "learning_rate": 1.249239381417746e-06,
+      "loss": 0.1700582355260849,
+      "step": 750
+    },
+    {
+      "epoch": 2.99601593625498,
+      "grad_norm": 0.1711830198764801,
+      "learning_rate": 1.238219670429104e-06,
+      "loss": 1.0743471384048462,
+      "step": 752
+    },
+    {
+      "epoch": 3.00398406374502,
+      "grad_norm": 0.13722623884677887,
+      "learning_rate": 1.2272656739169589e-06,
+      "loss": 0.5964380502700806,
+      "step": 754
+    },
+    {
+      "epoch": 3.0119521912350598,
+      "grad_norm": 0.22961658239364624,
+      "learning_rate": 1.2163778680325948e-06,
+      "loss": 0.6834949851036072,
+      "step": 756
+    },
+    {
+      "epoch": 3.0199203187250996,
+      "grad_norm": 0.2711966633796692,
+      "learning_rate": 1.2055567260501055e-06,
+      "loss": 0.3804636001586914,
+      "step": 758
+    },
+    {
+      "epoch": 3.0278884462151394,
+      "grad_norm": 0.5349511504173279,
+      "learning_rate": 1.1948027183458182e-06,
+      "loss": 0.7419881224632263,
+      "step": 760
+    },
+    {
+      "epoch": 3.0358565737051793,
+      "grad_norm": 0.21936191618442535,
+      "learning_rate": 1.18411631237785e-06,
+      "loss": 0.5301751494407654,
+      "step": 762
+    },
+    {
+      "epoch": 3.043824701195219,
+      "grad_norm": 0.16209813952445984,
+      "learning_rate": 1.173497972665788e-06,
+      "loss": 1.0582691431045532,
+      "step": 764
+    },
+    {
+      "epoch": 3.051792828685259,
+      "grad_norm": 0.11296246200799942,
+      "learning_rate": 1.1629481607704964e-06,
+      "loss": 0.16799992322921753,
+      "step": 766
+    },
+    {
+      "epoch": 3.0597609561752988,
+      "grad_norm": 0.1384953260421753,
+      "learning_rate": 1.1524673352740543e-06,
+      "loss": 0.6490381360054016,
+      "step": 768
+    },
+    {
+      "epoch": 3.0677290836653386,
+      "grad_norm": 0.3573448956012726,
+      "learning_rate": 1.1420559517598206e-06,
+      "loss": 0.8970813751220703,
+      "step": 770
+    },
+    {
+      "epoch": 3.0756972111553784,
+      "grad_norm": 0.20403094589710236,
+      "learning_rate": 1.13171446279263e-06,
+      "loss": 1.0503309965133667,
+      "step": 772
+    },
+    {
+      "epoch": 3.0836653386454183,
+      "grad_norm": 0.5975339412689209,
+      "learning_rate": 1.1214433178991258e-06,
+      "loss": 0.9140406250953674,
+      "step": 774
+    },
+    {
+      "epoch": 3.091633466135458,
+      "grad_norm": 0.0610031858086586,
+      "learning_rate": 1.111242963548212e-06,
+      "loss": 0.627947986125946,
+      "step": 776
+    },
+    {
+      "epoch": 3.099601593625498,
+      "grad_norm": 0.14743830263614655,
+      "learning_rate": 1.1011138431316538e-06,
+      "loss": 0.6517257690429688,
+      "step": 778
+    },
+    {
+      "epoch": 3.1075697211155378,
+      "grad_norm": 0.13844068348407745,
+      "learning_rate": 1.0910563969447969e-06,
+      "loss": 1.0392062664031982,
+      "step": 780
+    },
+    {
+      "epoch": 3.1155378486055776,
+      "grad_norm": 0.3827100694179535,
+      "learning_rate": 1.0810710621674355e-06,
+      "loss": 0.40662309527397156,
+      "step": 782
+    },
+    {
+      "epoch": 3.1235059760956174,
+      "grad_norm": 0.16287453472614288,
+      "learning_rate": 1.0711582728448034e-06,
+      "loss": 1.0952531099319458,
+      "step": 784
+    },
+    {
+      "epoch": 3.1314741035856573,
+      "grad_norm": 0.21308401226997375,
+      "learning_rate": 1.0613184598687088e-06,
+      "loss": 0.8335241675376892,
+      "step": 786
+    },
+    {
+      "epoch": 3.139442231075697,
+      "grad_norm": 0.42355456948280334,
+      "learning_rate": 1.0515520509588076e-06,
+      "loss": 0.6536455750465393,
+      "step": 788
+    },
+    {
+      "epoch": 3.147410358565737,
+      "grad_norm": 0.0891590565443039,
+      "learning_rate": 1.0418594706440022e-06,
+      "loss": 0.5871676802635193,
+      "step": 790
+    },
+    {
+      "epoch": 3.1553784860557768,
+      "grad_norm": 0.4792523980140686,
+      "learning_rate": 1.0322411402439982e-06,
+      "loss": 0.8735783100128174,
+      "step": 792
+    },
+    {
+      "epoch": 3.1633466135458166,
+      "grad_norm": 0.07262031733989716,
+      "learning_rate": 1.0226974778509846e-06,
+      "loss": 0.2604318857192993,
+      "step": 794
+    },
+    {
+      "epoch": 3.1713147410358564,
+      "grad_norm": 0.24448327720165253,
+      "learning_rate": 1.0132288983114611e-06,
+      "loss": 0.6942089200019836,
+      "step": 796
+    },
+    {
+      "epoch": 3.1792828685258963,
+      "grad_norm": 0.1413044035434723,
+      "learning_rate": 1.003835813208206e-06,
+      "loss": 0.5788269639015198,
+      "step": 798
+    },
+    {
+      "epoch": 3.187250996015936,
+      "grad_norm": 0.2534773349761963,
+      "learning_rate": 9.945186308423832e-07,
+      "loss": 0.901719868183136,
+      "step": 800
+    },
+    {
+      "epoch": 3.195219123505976,
+      "grad_norm": 0.1464780569076538,
+      "learning_rate": 9.852777562157983e-07,
+      "loss": 0.7941102981567383,
+      "step": 802
+    },
+    {
+      "epoch": 3.2031872509960158,
+      "grad_norm": 0.7416157126426697,
+      "learning_rate": 9.7611359101329e-07,
+      "loss": 0.7335487604141235,
+      "step": 804
+    },
+    {
+      "epoch": 3.2111553784860556,
+      "grad_norm": 0.37782636284828186,
+      "learning_rate": 9.670265335852725e-07,
+      "loss": 1.267388939857483,
+      "step": 806
+    },
+    {
+      "epoch": 3.2191235059760954,
+      "grad_norm": 1.360326886177063,
+      "learning_rate": 9.580169789304152e-07,
+      "loss": 0.5134503841400146,
+      "step": 808
+    },
+    {
+      "epoch": 3.2270916334661353,
+      "grad_norm": 0.16403120756149292,
+      "learning_rate": 9.490853186784801e-07,
+      "loss": 0.8042773604393005,
+      "step": 810
+    },
+    {
+      "epoch": 3.235059760956175,
+      "grad_norm": 0.49111008644104004,
+      "learning_rate": 9.402319410732911e-07,
+      "loss": 0.3888891041278839,
+      "step": 812
+    },
+    {
+      "epoch": 3.243027888446215,
+      "grad_norm": 0.16971656680107117,
+      "learning_rate": 9.314572309558617e-07,
+      "loss": 0.906256914138794,
+      "step": 814
+    },
+    {
+      "epoch": 3.2509960159362548,
+      "grad_norm": 0.39008116722106934,
+      "learning_rate": 9.227615697476674e-07,
+      "loss": 0.3999899923801422,
+      "step": 816
+    },
+    {
+      "epoch": 3.2589641434262946,
+      "grad_norm": 0.10503601282835007,
+      "learning_rate": 9.141453354340619e-07,
+      "loss": 1.0360020399093628,
+      "step": 818
+    },
+    {
+      "epoch": 3.2669322709163344,
+      "grad_norm": 0.6706594228744507,
+      "learning_rate": 9.056089025478495e-07,
+      "loss": 0.5925837755203247,
+      "step": 820
+    },
+    {
+      "epoch": 3.2749003984063743,
+      "grad_norm": 0.2793229818344116,
+      "learning_rate": 8.971526421530067e-07,
+      "loss": 0.8636225461959839,
+      "step": 822
+    },
+    {
+      "epoch": 3.2828685258964145,
+      "grad_norm": 0.5437958240509033,
+      "learning_rate": 8.887769218285469e-07,
+      "loss": 0.6271964311599731,
+      "step": 824
+    },
+    {
+      "epoch": 3.2908366533864544,
+      "grad_norm": 0.16260011494159698,
+      "learning_rate": 8.804821056525498e-07,
+      "loss": 1.0486832857131958,
+      "step": 826
+    },
+    {
+      "epoch": 3.298804780876494,
+      "grad_norm": 0.18559060990810394,
+      "learning_rate": 8.722685541863284e-07,
+      "loss": 1.0232266187667847,
+      "step": 828
+    },
+    {
+      "epoch": 3.306772908366534,
+      "grad_norm": 0.3313399851322174,
+      "learning_rate": 8.641366244587612e-07,
+      "loss": 0.996281087398529,
+      "step": 830
+    },
+    {
+      "epoch": 3.314741035856574,
+      "grad_norm": 0.5646917819976807,
+      "learning_rate": 8.560866699507703e-07,
+      "loss": 0.59163498878479,
+      "step": 832
+    },
+    {
+      "epoch": 3.3227091633466137,
+      "grad_norm": 0.4441075026988983,
+      "learning_rate": 8.481190405799569e-07,
+      "loss": 0.37602198123931885,
+      "step": 834
+    },
+    {
+      "epoch": 3.3306772908366535,
+      "grad_norm": 0.6061767935752869,
+      "learning_rate": 8.402340826853908e-07,
+      "loss": 0.6089810132980347,
+      "step": 836
+    },
+    {
+      "epoch": 3.3386454183266934,
+      "grad_norm": 0.30404508113861084,
+      "learning_rate": 8.324321390125548e-07,
+      "loss": 0.8452525734901428,
+      "step": 838
+    },
+    {
+      "epoch": 3.346613545816733,
+      "grad_norm": 0.9710149168968201,
+      "learning_rate": 8.247135486984487e-07,
+      "loss": 0.22593484818935394,
+      "step": 840
+    },
+    {
+      "epoch": 3.354581673306773,
+      "grad_norm": 0.31103479862213135,
+      "learning_rate": 8.170786472568451e-07,
+      "loss": 0.8221858143806458,
+      "step": 842
+    },
+    {
+      "epoch": 3.362549800796813,
+      "grad_norm": 0.5187264680862427,
+      "learning_rate": 8.095277665637061e-07,
+      "loss": 0.7228570580482483,
+      "step": 844
+    },
+    {
+      "epoch": 3.3705179282868527,
+      "grad_norm": 0.13890665769577026,
+      "learning_rate": 8.020612348427572e-07,
+      "loss": 1.0755844116210938,
+      "step": 846
+    },
+    {
+      "epoch": 3.3784860557768925,
+      "grad_norm": 0.1563568413257599,
+      "learning_rate": 7.946793766512195e-07,
+      "loss": 1.031057596206665,
+      "step": 848
+    },
+    {
+      "epoch": 3.3864541832669324,
+      "grad_norm": 0.39120933413505554,
+      "learning_rate": 7.873825128657034e-07,
+      "loss": 1.1692808866500854,
+      "step": 850
+    },
+    {
+      "epoch": 3.394422310756972,
+      "grad_norm": 0.14156459271907806,
+      "learning_rate": 7.801709606682573e-07,
+      "loss": 1.0264686346054077,
+      "step": 852
+    },
+    {
+      "epoch": 3.402390438247012,
+      "grad_norm": 0.21513643860816956,
+      "learning_rate": 7.730450335325852e-07,
+      "loss": 0.6073114275932312,
+      "step": 854
+    },
+    {
+      "epoch": 3.410358565737052,
+      "grad_norm": 0.2288302779197693,
+      "learning_rate": 7.660050412104153e-07,
+      "loss": 1.0001939535140991,
+      "step": 856
+    },
+    {
+      "epoch": 3.4183266932270917,
+      "grad_norm": 0.11735354363918304,
+      "learning_rate": 7.5905128971804e-07,
+      "loss": 1.1732920408248901,
+      "step": 858
+    },
+    {
+      "epoch": 3.4262948207171315,
+      "grad_norm": 0.35582444071769714,
+      "learning_rate": 7.521840813230098e-07,
+      "loss": 1.106850504875183,
+      "step": 860
+    },
+    {
+      "epoch": 3.4342629482071714,
+      "grad_norm": 0.21337585151195526,
+      "learning_rate": 7.454037145309986e-07,
+      "loss": 0.7733758091926575,
+      "step": 862
+    },
+    {
+      "epoch": 3.442231075697211,
+      "grad_norm": 0.34608328342437744,
+      "learning_rate": 7.38710484072826e-07,
+      "loss": 0.6272129416465759,
+      "step": 864
+    },
+    {
+      "epoch": 3.450199203187251,
+      "grad_norm": 0.24352410435676575,
+      "learning_rate": 7.321046808916427e-07,
+      "loss": 0.9221819043159485,
+      "step": 866
+    },
+    {
+      "epoch": 3.458167330677291,
+      "grad_norm": 0.1397869735956192,
+      "learning_rate": 7.255865921302902e-07,
+      "loss": 0.8171448707580566,
+      "step": 868
+    },
+    {
+      "epoch": 3.4661354581673307,
+      "grad_norm": 0.3466062843799591,
+      "learning_rate": 7.191565011188149e-07,
+      "loss": 0.570713996887207,
+      "step": 870
+    },
+    {
+      "epoch": 3.4741035856573705,
+      "grad_norm": 0.10642972588539124,
+      "learning_rate": 7.128146873621533e-07,
+      "loss": 0.6441148519515991,
+      "step": 872
+    },
+    {
+      "epoch": 3.4820717131474104,
+      "grad_norm": 0.08105063438415527,
+      "learning_rate": 7.065614265279819e-07,
+      "loss": 0.8004633784294128,
+      "step": 874
+    },
+    {
+      "epoch": 3.49003984063745,
+      "grad_norm": 0.14252963662147522,
+      "learning_rate": 7.00396990434734e-07,
+      "loss": 0.5975029468536377,
+      "step": 876
+    },
+    {
+      "epoch": 3.49800796812749,
+      "grad_norm": 0.19118371605873108,
+      "learning_rate": 6.943216470397872e-07,
+      "loss": 0.5780191421508789,
+      "step": 878
+    },
+    {
+      "epoch": 3.50597609561753,
+      "grad_norm": 0.08882622420787811,
+      "learning_rate": 6.883356604278116e-07,
+      "loss": 0.5070514678955078,
+      "step": 880
+    },
+    {
+      "epoch": 3.5139442231075697,
+      "grad_norm": 0.3662315309047699,
+      "learning_rate": 6.824392907992938e-07,
+      "loss": 0.7522435188293457,
+      "step": 882
+    },
+    {
+      "epoch": 3.5219123505976095,
+      "grad_norm": 0.3180921971797943,
+      "learning_rate": 6.76632794459224e-07,
+      "loss": 0.2688283324241638,
+      "step": 884
+    },
+    {
+      "epoch": 3.5298804780876494,
+      "grad_norm": 0.21487878262996674,
+      "learning_rate": 6.709164238059568e-07,
+      "loss": 0.8493873476982117,
+      "step": 886
+    },
+    {
+      "epoch": 3.537848605577689,
+      "grad_norm": 0.25673753023147583,
+      "learning_rate": 6.652904273202385e-07,
+      "loss": 1.03146493434906,
+      "step": 888
+    },
+    {
+      "epoch": 3.545816733067729,
+      "grad_norm": 0.22675621509552002,
+      "learning_rate": 6.597550495544071e-07,
+      "loss": 0.5393344163894653,
+      "step": 890
+    },
+    {
+      "epoch": 3.553784860557769,
+      "grad_norm": 0.3146322965621948,
+      "learning_rate": 6.54310531121762e-07,
+      "loss": 1.1090364456176758,
+      "step": 892
+    },
+    {
+      "epoch": 3.5617529880478087,
+      "grad_norm": 0.1820296347141266,
+      "learning_rate": 6.489571086861027e-07,
+      "loss": 1.1076128482818604,
+      "step": 894
+    },
+    {
+      "epoch": 3.5697211155378485,
+      "grad_norm": 0.18236935138702393,
+      "learning_rate": 6.436950149514448e-07,
+      "loss": 0.2818949520587921,
+      "step": 896
+    },
+    {
+      "epoch": 3.5776892430278884,
+      "grad_norm": 0.19373716413974762,
+      "learning_rate": 6.385244786519036e-07,
+      "loss": 0.7145392894744873,
+      "step": 898
+    },
+    {
+      "epoch": 3.585657370517928,
+      "grad_norm": 0.1788167804479599,
+      "learning_rate": 6.334457245417491e-07,
+      "loss": 0.28569626808166504,
+      "step": 900
+    },
+    {
+      "epoch": 3.593625498007968,
+      "grad_norm": 0.4483168423175812,
+      "learning_rate": 6.284589733856403e-07,
+      "loss": 0.104631207883358,
+      "step": 902
+    },
+    {
+      "epoch": 3.601593625498008,
+      "grad_norm": 0.21497026085853577,
+      "learning_rate": 6.235644419490253e-07,
+      "loss": 0.9116790890693665,
+      "step": 904
+    },
+    {
+      "epoch": 3.6095617529880477,
+      "grad_norm": 0.29076552391052246,
+      "learning_rate": 6.18762342988722e-07,
+      "loss": 0.7182366251945496,
+      "step": 906
+    },
+    {
+      "epoch": 3.6175298804780875,
+      "grad_norm": 0.2729831635951996,
+      "learning_rate": 6.140528852436666e-07,
+      "loss": 0.999624490737915,
+      "step": 908
+    },
+    {
+      "epoch": 3.6254980079681274,
+      "grad_norm": 1.2296032905578613,
+      "learning_rate": 6.094362734258438e-07,
+      "loss": 0.9347969889640808,
+      "step": 910
+    },
+    {
+      "epoch": 3.633466135458167,
+      "grad_norm": 0.11549732089042664,
+      "learning_rate": 6.049127082113853e-07,
+      "loss": 0.072967529296875,
+      "step": 912
+    },
+    {
+      "epoch": 3.641434262948207,
+      "grad_norm": 0.13338138163089752,
+      "learning_rate": 6.004823862318475e-07,
+      "loss": 0.8928102850914001,
+      "step": 914
+    },
+    {
+      "epoch": 3.649402390438247,
+      "grad_norm": 1.6068872213363647,
+      "learning_rate": 5.961455000656656e-07,
+      "loss": 0.8553287386894226,
+      "step": 916
+    },
+    {
+      "epoch": 3.6573705179282867,
+      "grad_norm": 0.3783324658870697,
+      "learning_rate": 5.919022382297808e-07,
+      "loss": 0.22164402902126312,
+      "step": 918
+    },
+    {
+      "epoch": 3.6653386454183265,
+      "grad_norm": 0.22376622259616852,
+      "learning_rate": 5.877527851714479e-07,
+      "loss": 1.0535707473754883,
+      "step": 920
+    },
+    {
+      "epoch": 3.6733067729083664,
+      "grad_norm": 0.16867855191230774,
+      "learning_rate": 5.836973212602144e-07,
+      "loss": 0.18693172931671143,
+      "step": 922
+    },
+    {
+      "epoch": 3.681274900398406,
+      "grad_norm": 0.323342502117157,
+      "learning_rate": 5.797360227800832e-07,
+      "loss": 1.1177575588226318,
+      "step": 924
+    },
+    {
+      "epoch": 3.6892430278884465,
+      "grad_norm": 0.7001636028289795,
+      "learning_rate": 5.758690619218493e-07,
+      "loss": 0.3386628031730652,
+      "step": 926
+    },
+    {
+      "epoch": 3.6972111553784863,
+      "grad_norm": 0.1657366007566452,
+      "learning_rate": 5.720966067756131e-07,
+      "loss": 0.6257779598236084,
+      "step": 928
+    },
+    {
+      "epoch": 3.705179282868526,
+      "grad_norm": 0.07795999944210052,
+      "learning_rate": 5.684188213234763e-07,
+      "loss": 0.9516653418540955,
+      "step": 930
+    },
+    {
+      "epoch": 3.713147410358566,
+      "grad_norm": 0.1383875459432602,
+      "learning_rate": 5.648358654324119e-07,
+      "loss": 1.0442441701889038,
+      "step": 932
+    },
+    {
+      "epoch": 3.721115537848606,
+      "grad_norm": 1.9287700653076172,
+      "learning_rate": 5.613478948473166e-07,
+      "loss": 0.6194300055503845,
+      "step": 934
+    },
+    {
+      "epoch": 3.7290836653386457,
+      "grad_norm": 0.16172027587890625,
+      "learning_rate": 5.579550611842395e-07,
+      "loss": 0.9539238214492798,
+      "step": 936
+    },
+    {
+      "epoch": 3.7370517928286855,
+      "grad_norm": 0.6292641758918762,
+      "learning_rate": 5.546575119237923e-07,
+      "loss": 0.8196353316307068,
+      "step": 938
+    },
+    {
+      "epoch": 3.7450199203187253,
+      "grad_norm": 0.14163076877593994,
+      "learning_rate": 5.514553904047394e-07,
+      "loss": 0.8597630858421326,
+      "step": 940
+    },
+    {
+      "epoch": 3.752988047808765,
+      "grad_norm": 0.5673378705978394,
+      "learning_rate": 5.483488358177647e-07,
+      "loss": 0.8270343542098999,
+      "step": 942
+    },
+    {
+      "epoch": 3.760956175298805,
+      "grad_norm": 0.20341992378234863,
+      "learning_rate": 5.453379831994238e-07,
+      "loss": 0.5761424899101257,
+      "step": 944
+    },
+    {
+      "epoch": 3.768924302788845,
+      "grad_norm": 0.1791536509990692,
+      "learning_rate": 5.424229634262735e-07,
+      "loss": 1.058624029159546,
+      "step": 946
+    },
+    {
+      "epoch": 3.7768924302788847,
+      "grad_norm": 0.1579664647579193,
+      "learning_rate": 5.396039032091826e-07,
+      "loss": 0.6653705835342407,
+      "step": 948
+    },
+    {
+      "epoch": 3.7848605577689245,
+      "grad_norm": 0.15775270760059357,
+      "learning_rate": 5.368809250878228e-07,
+      "loss": 1.0393195152282715,
+      "step": 950
+    },
+    {
+      "epoch": 3.7928286852589643,
+      "grad_norm": 0.22411321103572845,
+      "learning_rate": 5.342541474253438e-07,
+      "loss": 1.0520769357681274,
+      "step": 952
+    },
+    {
+      "epoch": 3.800796812749004,
+      "grad_norm": 0.13835610449314117,
+      "learning_rate": 5.317236844032285e-07,
+      "loss": 0.6255828142166138,
+      "step": 954
+    },
+    {
+      "epoch": 3.808764940239044,
+      "grad_norm": 0.2816826403141022,
+      "learning_rate": 5.292896460163282e-07,
+      "loss": 0.8512222170829773,
+      "step": 956
+    },
+    {
+      "epoch": 3.816733067729084,
+      "grad_norm": 10.575217247009277,
+      "learning_rate": 5.269521380680823e-07,
+      "loss": 0.6267296671867371,
+      "step": 958
+    },
+    {
+      "epoch": 3.8247011952191237,
+      "grad_norm": 1.148056149482727,
+      "learning_rate": 5.247112621659186e-07,
+      "loss": 0.806030809879303,
+      "step": 960
+    },
+    {
+      "epoch": 3.8326693227091635,
+      "grad_norm": 0.14214462041854858,
+      "learning_rate": 5.225671157168378e-07,
+      "loss": 0.6183053851127625,
+      "step": 962
+    },
+    {
+      "epoch": 3.8406374501992033,
+      "grad_norm": 0.3158741593360901,
+      "learning_rate": 5.205197919231773e-07,
+      "loss": 1.05531644821167,
+      "step": 964
+    },
+    {
+      "epoch": 3.848605577689243,
+      "grad_norm": 0.4142560064792633,
+      "learning_rate": 5.185693797785624e-07,
+      "loss": 0.42237982153892517,
+      "step": 966
+    },
+    {
+      "epoch": 3.856573705179283,
+      "grad_norm": 0.20964230597019196,
+      "learning_rate": 5.167159640640358e-07,
+      "loss": 0.603114664554596,
+      "step": 968
+    },
+    {
+      "epoch": 3.864541832669323,
+      "grad_norm": 0.37147626280784607,
+      "learning_rate": 5.149596253443733e-07,
+      "loss": 0.8410542607307434,
+      "step": 970
+    },
+    {
+      "epoch": 3.8725099601593627,
+      "grad_norm": 0.23301821947097778,
+      "learning_rate": 5.133004399645818e-07,
+      "loss": 0.626631498336792,
+      "step": 972
+    },
+    {
+      "epoch": 3.8804780876494025,
+      "grad_norm": 0.07937774062156677,
+      "learning_rate": 5.117384800465806e-07,
+      "loss": 0.49173229932785034,
+      "step": 974
+    },
+    {
+      "epoch": 3.8884462151394423,
+      "grad_norm": 0.1277993768453598,
+      "learning_rate": 5.102738134860656e-07,
+      "loss": 1.0443681478500366,
+      "step": 976
+    },
+    {
+      "epoch": 3.896414342629482,
+      "grad_norm": 0.2576330900192261,
+      "learning_rate": 5.089065039495598e-07,
+      "loss": 0.5926145911216736,
+      "step": 978
+    },
+    {
+      "epoch": 3.904382470119522,
+      "grad_norm": 0.6003551483154297,
+      "learning_rate": 5.076366108716438e-07,
+      "loss": 0.4315122067928314,
+      "step": 980
+    },
+    {
+      "epoch": 3.912350597609562,
+      "grad_norm": 0.19727757573127747,
+      "learning_rate": 5.064641894523737e-07,
+      "loss": 0.577692985534668,
+      "step": 982
+    },
+    {
+      "epoch": 3.9203187250996017,
+      "grad_norm": 0.22076201438903809,
+      "learning_rate": 5.053892906548811e-07,
+      "loss": 0.9802306294441223,
+      "step": 984
+    },
+    {
+      "epoch": 3.9282868525896415,
+      "grad_norm": 0.42418357729911804,
+      "learning_rate": 5.044119612031576e-07,
+      "loss": 0.14989471435546875,
+      "step": 986
+    },
+    {
+      "epoch": 3.9362549800796813,
+      "grad_norm": 0.34481361508369446,
+      "learning_rate": 5.035322435800248e-07,
+      "loss": 0.6541216969490051,
+      "step": 988
+    },
+    {
+      "epoch": 3.944223107569721,
+      "grad_norm": 0.17375615239143372,
+      "learning_rate": 5.027501760252857e-07,
+      "loss": 0.6517196297645569,
+      "step": 990
+    },
+    {
+      "epoch": 3.952191235059761,
+      "grad_norm": 0.37982651591300964,
+      "learning_rate": 5.02065792534065e-07,
+      "loss": 1.0831855535507202,
+      "step": 992
+    },
+    {
+      "epoch": 3.960159362549801,
+      "grad_norm": 0.03707882761955261,
+      "learning_rate": 5.014791228553294e-07,
+      "loss": 0.2668434679508209,
+      "step": 994
+    },
+    {
+      "epoch": 3.9681274900398407,
+      "grad_norm": 0.4722311198711395,
+      "learning_rate": 5.00990192490595e-07,
+      "loss": 0.966728687286377,
+      "step": 996
+    },
+    {
+      "epoch": 3.9760956175298805,
+      "grad_norm": 0.06797811388969421,
+      "learning_rate": 5.005990226928196e-07,
+      "loss": 0.6229426860809326,
+      "step": 998
+    },
+    {
+      "epoch": 3.9840637450199203,
+      "grad_norm": 0.22296170890331268,
+      "learning_rate": 5.003056304654774e-07,
+      "loss": 0.49053215980529785,
+      "step": 1000
+    },
+    {
+      "epoch": 3.99203187250996,
+      "grad_norm": 0.3212076723575592,
+      "learning_rate": 5.001100285618214e-07,
+      "loss": 1.0515018701553345,
+      "step": 1002
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.06559182703495026,
+      "learning_rate": 5.000122254843282e-07,
+      "loss": 0.3830489218235016,
+      "step": 1004
+    },
+    {
+      "epoch": 4.0,
+      "step": 1004,
+      "total_flos": 3.954132003103703e+18,
+      "train_loss": 0.9162792685289545,
+      "train_runtime": 34079.0084,
+      "train_samples_per_second": 1.768,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "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": 3.954132003103703e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da449856a02039da017acb91972f85a6f2a2d217b7b0f5ff9d1f0cd14011afb
+size 5649