Upload LoRA adapter for continued training

adapter/README.md

@@ -5,8 +5,8 @@ model_name: cmlm-lora
 tags:
 - generated_from_trainer
 - unsloth
-- trl
 - sft
+- trl
 licence: license
 ---
 

adapter/checkpoint-3000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter/checkpoint-3000/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d2b0fb3ab25b445cb474e79b5babefa0c98406259748405530e47ed80eae20
+size 25587104

adapter/checkpoint-3000/chat_template.jinja

@@ -0,0 +1,158 @@
+{%- 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 %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- 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 merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|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 %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if 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 mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<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 %}
+    {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, tool calling #}

adapter/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456cf6ab7427c756b89c97f67d2018c353976a00a098fafd5815d0b23176589c
+size 51282443

adapter/checkpoint-3000/processor_config.json

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

adapter/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

adapter/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1f0a1f7ba55e2ed5c5558cf96123eb17e4f8dd413115d8e6dd3ba8f6dc0403
+size 1465

adapter/checkpoint-3000/tokenizer.json

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

adapter/checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "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": false,
+  "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": "<|vision_pad|>",
+  "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|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

adapter/checkpoint-3000/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.01756764274441715,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.855880914805717e-05,
+      "grad_norm": 1.5575445890426636,
+      "learning_rate": 1.8e-05,
+      "loss": 0.7678159713745117,
+      "step": 10
+    },
+    {
+      "epoch": 0.00011711761829611434,
+      "grad_norm": 1.0704400539398193,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7586987972259521,
+      "step": 20
+    },
+    {
+      "epoch": 0.0001756764274441715,
+      "grad_norm": 0.6421218514442444,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6814639568328857,
+      "step": 30
+    },
+    {
+      "epoch": 0.00023423523659222867,
+      "grad_norm": 0.938690721988678,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.6233416557312011,
+      "step": 40
+    },
+    {
+      "epoch": 0.00029279404574028583,
+      "grad_norm": 1.166359543800354,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5837168216705322,
+      "step": 50
+    },
+    {
+      "epoch": 0.000351352854888343,
+      "grad_norm": 0.7864418029785156,
+      "learning_rate": 0.000118,
+      "loss": 0.49336514472961424,
+      "step": 60
+    },
+    {
+      "epoch": 0.00040991166403640014,
+      "grad_norm": 0.723896861076355,
+      "learning_rate": 0.000138,
+      "loss": 0.6541348457336426,
+      "step": 70
+    },
+    {
+      "epoch": 0.00046847047318445735,
+      "grad_norm": 0.5491677522659302,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.6446280479431152,
+      "step": 80
+    },
+    {
+      "epoch": 0.0005270292823325145,
+      "grad_norm": 1.032065510749817,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.493870210647583,
+      "step": 90
+    },
+    {
+      "epoch": 0.0005855880914805717,
+      "grad_norm": 0.7324640154838562,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.63213210105896,
+      "step": 100
+    },
+    {
+      "epoch": 0.0006441469006286288,
+      "grad_norm": 0.8503096103668213,
+      "learning_rate": 0.00019953846153846153,
+      "loss": 0.6286506652832031,
+      "step": 110
+    },
+    {
+      "epoch": 0.000702705709776686,
+      "grad_norm": 0.8664548993110657,
+      "learning_rate": 0.00019902564102564104,
+      "loss": 0.48207850456237794,
+      "step": 120
+    },
+    {
+      "epoch": 0.0007612645189247431,
+      "grad_norm": 0.6782843470573425,
+      "learning_rate": 0.00019851282051282053,
+      "loss": 0.6306986331939697,
+      "step": 130
+    },
+    {
+      "epoch": 0.0008198233280728003,
+      "grad_norm": 1.2085249423980713,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.5556919574737549,
+      "step": 140
+    },
+    {
+      "epoch": 0.0008783821372208574,
+      "grad_norm": 0.8503999710083008,
+      "learning_rate": 0.0001974871794871795,
+      "loss": 0.6409926414489746,
+      "step": 150
+    },
+    {
+      "epoch": 0.0009369409463689147,
+      "grad_norm": 0.7704036235809326,
+      "learning_rate": 0.000196974358974359,
+      "loss": 0.5393772125244141,
+      "step": 160
+    },
+    {
+      "epoch": 0.0009954997555169719,
+      "grad_norm": 0.7071548104286194,
+      "learning_rate": 0.00019646153846153847,
+      "loss": 0.6072579860687256,
+      "step": 170
+    },
+    {
+      "epoch": 0.001054058564665029,
+      "grad_norm": 0.6557785272598267,
+      "learning_rate": 0.00019594871794871796,
+      "loss": 0.49915218353271484,
+      "step": 180
+    },
+    {
+      "epoch": 0.0011126173738130862,
+      "grad_norm": 0.6428221464157104,
+      "learning_rate": 0.00019543589743589745,
+      "loss": 0.6393180370330811,
+      "step": 190
+    },
+    {
+      "epoch": 0.0011711761829611433,
+      "grad_norm": 0.8832526803016663,
+      "learning_rate": 0.00019492307692307693,
+      "loss": 0.6467752456665039,
+      "step": 200
+    },
+    {
+      "epoch": 0.0012297349921092005,
+      "grad_norm": 0.8874967694282532,
+      "learning_rate": 0.00019441025641025642,
+      "loss": 0.6200666904449463,
+      "step": 210
+    },
+    {
+      "epoch": 0.0012882938012572576,
+      "grad_norm": 0.8451365828514099,
+      "learning_rate": 0.0001938974358974359,
+      "loss": 0.5980692386627198,
+      "step": 220
+    },
+    {
+      "epoch": 0.0013468526104053148,
+      "grad_norm": 1.3747062683105469,
+      "learning_rate": 0.0001933846153846154,
+      "loss": 0.5997383117675781,
+      "step": 230
+    },
+    {
+      "epoch": 0.001405411419553372,
+      "grad_norm": 0.7659091949462891,
+      "learning_rate": 0.00019287179487179488,
+      "loss": 0.6244289875030518,
+      "step": 240
+    },
+    {
+      "epoch": 0.001463970228701429,
+      "grad_norm": 0.7551876902580261,
+      "learning_rate": 0.00019235897435897437,
+      "loss": 0.5602375507354737,
+      "step": 250
+    },
+    {
+      "epoch": 0.0015225290378494862,
+      "grad_norm": 0.8756004571914673,
+      "learning_rate": 0.00019184615384615385,
+      "loss": 0.5726509094238281,
+      "step": 260
+    },
+    {
+      "epoch": 0.0015810878469975434,
+      "grad_norm": 0.9010286927223206,
+      "learning_rate": 0.00019133333333333334,
+      "loss": 0.564607048034668,
+      "step": 270
+    },
+    {
+      "epoch": 0.0016396466561456006,
+      "grad_norm": 0.768795907497406,
+      "learning_rate": 0.00019082051282051283,
+      "loss": 0.6172872066497803,
+      "step": 280
+    },
+    {
+      "epoch": 0.0016982054652936577,
+      "grad_norm": 0.8452103137969971,
+      "learning_rate": 0.0001903076923076923,
+      "loss": 0.5882416248321534,
+      "step": 290
+    },
+    {
+      "epoch": 0.0017567642744417149,
+      "grad_norm": 0.8099432587623596,
+      "learning_rate": 0.0001897948717948718,
+      "loss": 0.5674912452697753,
+      "step": 300
+    },
+    {
+      "epoch": 0.001815323083589772,
+      "grad_norm": 0.7150252461433411,
+      "learning_rate": 0.00018928205128205129,
+      "loss": 0.5736612796783447,
+      "step": 310
+    },
+    {
+      "epoch": 0.0018738818927378294,
+      "grad_norm": 1.098449945449829,
+      "learning_rate": 0.0001887692307692308,
+      "loss": 0.6177639484405517,
+      "step": 320
+    },
+    {
+      "epoch": 0.0019324407018858865,
+      "grad_norm": 0.7274444103240967,
+      "learning_rate": 0.00018825641025641029,
+      "loss": 0.6690079212188721,
+      "step": 330
+    },
+    {
+      "epoch": 0.0019909995110339437,
+      "grad_norm": 0.7714038491249084,
+      "learning_rate": 0.00018774358974358975,
+      "loss": 0.5143749237060546,
+      "step": 340
+    },
+    {
+      "epoch": 0.0020495583201820006,
+      "grad_norm": 0.9286389946937561,
+      "learning_rate": 0.00018723076923076923,
+      "loss": 0.5226009368896485,
+      "step": 350
+    },
+    {
+      "epoch": 0.002108117129330058,
+      "grad_norm": 0.9736594557762146,
+      "learning_rate": 0.00018671794871794872,
+      "loss": 0.5954864501953125,
+      "step": 360
+    },
+    {
+      "epoch": 0.002166675938478115,
+      "grad_norm": 0.7701608538627625,
+      "learning_rate": 0.0001862051282051282,
+      "loss": 0.564179515838623,
+      "step": 370
+    },
+    {
+      "epoch": 0.0022252347476261723,
+      "grad_norm": 0.8563699126243591,
+      "learning_rate": 0.0001856923076923077,
+      "loss": 0.587281608581543,
+      "step": 380
+    },
+    {
+      "epoch": 0.0022837935567742293,
+      "grad_norm": 1.017929196357727,
+      "learning_rate": 0.00018517948717948718,
+      "loss": 0.579550313949585,
+      "step": 390
+    },
+    {
+      "epoch": 0.0023423523659222866,
+      "grad_norm": 0.6563118696212769,
+      "learning_rate": 0.00018466666666666666,
+      "loss": 0.5135430335998535,
+      "step": 400
+    },
+    {
+      "epoch": 0.0024009111750703436,
+      "grad_norm": 0.7011086344718933,
+      "learning_rate": 0.00018415384615384618,
+      "loss": 0.6544422149658203,
+      "step": 410
+    },
+    {
+      "epoch": 0.002459469984218401,
+      "grad_norm": 0.991001546382904,
+      "learning_rate": 0.00018364102564102567,
+      "loss": 0.6101119518280029,
+      "step": 420
+    },
+    {
+      "epoch": 0.0025180287933664583,
+      "grad_norm": 0.7023338675498962,
+      "learning_rate": 0.00018312820512820515,
+      "loss": 0.5026431560516358,
+      "step": 430
+    },
+    {
+      "epoch": 0.0025765876025145153,
+      "grad_norm": 0.9078162908554077,
+      "learning_rate": 0.00018261538461538464,
+      "loss": 0.5121633052825928,
+      "step": 440
+    },
+    {
+      "epoch": 0.0026351464116625726,
+      "grad_norm": 0.7449192404747009,
+      "learning_rate": 0.00018210256410256412,
+      "loss": 0.6154009819030761,
+      "step": 450
+    },
+    {
+      "epoch": 0.0026937052208106296,
+      "grad_norm": 0.6876159906387329,
+      "learning_rate": 0.00018158974358974358,
+      "loss": 0.5338088989257812,
+      "step": 460
+    },
+    {
+      "epoch": 0.002752264029958687,
+      "grad_norm": 0.9204329252243042,
+      "learning_rate": 0.00018107692307692307,
+      "loss": 0.5554272174835205,
+      "step": 470
+    },
+    {
+      "epoch": 0.002810822839106744,
+      "grad_norm": 0.7362950444221497,
+      "learning_rate": 0.00018056410256410256,
+      "loss": 0.6131524085998535,
+      "step": 480
+    },
+    {
+      "epoch": 0.0028693816482548012,
+      "grad_norm": 0.9833507537841797,
+      "learning_rate": 0.00018005128205128204,
+      "loss": 0.5537636756896973,
+      "step": 490
+    },
+    {
+      "epoch": 0.002927940457402858,
+      "grad_norm": 0.7546113133430481,
+      "learning_rate": 0.00017953846153846156,
+      "loss": 0.6003861904144288,
+      "step": 500
+    },
+    {
+      "epoch": 0.0029864992665509156,
+      "grad_norm": 0.7838321924209595,
+      "learning_rate": 0.00017902564102564104,
+      "loss": 0.6598413944244385,
+      "step": 510
+    },
+    {
+      "epoch": 0.0030450580756989725,
+      "grad_norm": 0.7242461442947388,
+      "learning_rate": 0.00017851282051282053,
+      "loss": 0.5558955669403076,
+      "step": 520
+    },
+    {
+      "epoch": 0.00310361688484703,
+      "grad_norm": 1.1162296533584595,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.6460456371307373,
+      "step": 530
+    },
+    {
+      "epoch": 0.003162175693995087,
+      "grad_norm": 0.7049973011016846,
+      "learning_rate": 0.0001774871794871795,
+      "loss": 0.6043939113616943,
+      "step": 540
+    },
+    {
+      "epoch": 0.003220734503143144,
+      "grad_norm": 0.8112305998802185,
+      "learning_rate": 0.000176974358974359,
+      "loss": 0.4545936584472656,
+      "step": 550
+    },
+    {
+      "epoch": 0.003279293312291201,
+      "grad_norm": 0.6234564781188965,
+      "learning_rate": 0.00017646153846153848,
+      "loss": 0.6101226329803466,
+      "step": 560
+    },
+    {
+      "epoch": 0.0033378521214392585,
+      "grad_norm": 0.9512666463851929,
+      "learning_rate": 0.00017594871794871796,
+      "loss": 0.6055888175964356,
+      "step": 570
+    },
+    {
+      "epoch": 0.0033964109305873154,
+      "grad_norm": 0.8533800840377808,
+      "learning_rate": 0.00017543589743589742,
+      "loss": 0.6529808044433594,
+      "step": 580
+    },
+    {
+      "epoch": 0.003454969739735373,
+      "grad_norm": 0.896560549736023,
+      "learning_rate": 0.00017492307692307694,
+      "loss": 0.5882085800170899,
+      "step": 590
+    },
+    {
+      "epoch": 0.0035135285488834297,
+      "grad_norm": 0.8455023765563965,
+      "learning_rate": 0.00017441025641025642,
+      "loss": 0.518503999710083,
+      "step": 600
+    },
+    {
+      "epoch": 0.003572087358031487,
+      "grad_norm": 0.7477754950523376,
+      "learning_rate": 0.0001738974358974359,
+      "loss": 0.6013938426971436,
+      "step": 610
+    },
+    {
+      "epoch": 0.003630646167179544,
+      "grad_norm": 0.8402391672134399,
+      "learning_rate": 0.0001733846153846154,
+      "loss": 0.6162835597991944,
+      "step": 620
+    },
+    {
+      "epoch": 0.0036892049763276014,
+      "grad_norm": 1.0327485799789429,
+      "learning_rate": 0.00017287179487179488,
+      "loss": 0.6443416595458984,
+      "step": 630
+    },
+    {
+      "epoch": 0.003747763785475659,
+      "grad_norm": 1.0342403650283813,
+      "learning_rate": 0.00017235897435897437,
+      "loss": 0.5222865581512451,
+      "step": 640
+    },
+    {
+      "epoch": 0.0038063225946237157,
+      "grad_norm": 0.9043326377868652,
+      "learning_rate": 0.00017184615384615386,
+      "loss": 0.6140403747558594,
+      "step": 650
+    },
+    {
+      "epoch": 0.003864881403771773,
+      "grad_norm": 0.8706991076469421,
+      "learning_rate": 0.00017133333333333334,
+      "loss": 0.6201248645782471,
+      "step": 660
+    },
+    {
+      "epoch": 0.0039234402129198305,
+      "grad_norm": 0.7702825665473938,
+      "learning_rate": 0.00017082051282051283,
+      "loss": 0.5698607921600342,
+      "step": 670
+    },
+    {
+      "epoch": 0.003981999022067887,
+      "grad_norm": 0.7835186719894409,
+      "learning_rate": 0.00017030769230769231,
+      "loss": 0.5464808464050293,
+      "step": 680
+    },
+    {
+      "epoch": 0.004040557831215944,
+      "grad_norm": 0.7293221950531006,
+      "learning_rate": 0.0001697948717948718,
+      "loss": 0.6055557250976562,
+      "step": 690
+    },
+    {
+      "epoch": 0.004099116640364001,
+      "grad_norm": 0.8519648313522339,
+      "learning_rate": 0.0001692820512820513,
+      "loss": 0.594606876373291,
+      "step": 700
+    },
+    {
+      "epoch": 0.004157675449512059,
+      "grad_norm": 0.8359381556510925,
+      "learning_rate": 0.00016876923076923077,
+      "loss": 0.6676365852355957,
+      "step": 710
+    },
+    {
+      "epoch": 0.004216234258660116,
+      "grad_norm": 0.9601361155509949,
+      "learning_rate": 0.00016825641025641026,
+      "loss": 0.5267905235290528,
+      "step": 720
+    },
+    {
+      "epoch": 0.004274793067808173,
+      "grad_norm": 0.5900155901908875,
+      "learning_rate": 0.00016774358974358975,
+      "loss": 0.5860335826873779,
+      "step": 730
+    },
+    {
+      "epoch": 0.00433335187695623,
+      "grad_norm": 0.7671850323677063,
+      "learning_rate": 0.00016723076923076923,
+      "loss": 0.5898273468017579,
+      "step": 740
+    },
+    {
+      "epoch": 0.004391910686104288,
+      "grad_norm": 0.9657745361328125,
+      "learning_rate": 0.00016671794871794872,
+      "loss": 0.6093048572540283,
+      "step": 750
+    },
+    {
+      "epoch": 0.004450469495252345,
+      "grad_norm": 0.7431370615959167,
+      "learning_rate": 0.0001662051282051282,
+      "loss": 0.6279802799224854,
+      "step": 760
+    },
+    {
+      "epoch": 0.004509028304400402,
+      "grad_norm": 0.9329614639282227,
+      "learning_rate": 0.0001656923076923077,
+      "loss": 0.5990581512451172,
+      "step": 770
+    },
+    {
+      "epoch": 0.0045675871135484585,
+      "grad_norm": 0.6032372713088989,
+      "learning_rate": 0.00016517948717948718,
+      "loss": 0.5825644493103027,
+      "step": 780
+    },
+    {
+      "epoch": 0.004626145922696516,
+      "grad_norm": 0.6884028911590576,
+      "learning_rate": 0.00016466666666666667,
+      "loss": 0.555311632156372,
+      "step": 790
+    },
+    {
+      "epoch": 0.004684704731844573,
+      "grad_norm": 0.7366816997528076,
+      "learning_rate": 0.00016415384615384618,
+      "loss": 0.6074917793273926,
+      "step": 800
+    },
+    {
+      "epoch": 0.00474326354099263,
+      "grad_norm": 0.776561439037323,
+      "learning_rate": 0.00016364102564102567,
+      "loss": 0.5682147026062012,
+      "step": 810
+    },
+    {
+      "epoch": 0.004801822350140687,
+      "grad_norm": 0.8783098459243774,
+      "learning_rate": 0.00016312820512820515,
+      "loss": 0.6519593715667724,
+      "step": 820
+    },
+    {
+      "epoch": 0.004860381159288745,
+      "grad_norm": 0.8319303393363953,
+      "learning_rate": 0.0001626153846153846,
+      "loss": 0.6276237487792968,
+      "step": 830
+    },
+    {
+      "epoch": 0.004918939968436802,
+      "grad_norm": 0.7415748238563538,
+      "learning_rate": 0.0001621025641025641,
+      "loss": 0.6673260688781738,
+      "step": 840
+    },
+    {
+      "epoch": 0.004977498777584859,
+      "grad_norm": 1.0244334936141968,
+      "learning_rate": 0.00016158974358974359,
+      "loss": 0.6164275169372558,
+      "step": 850
+    },
+    {
+      "epoch": 0.005036057586732917,
+      "grad_norm": 1.0644179582595825,
+      "learning_rate": 0.00016107692307692307,
+      "loss": 0.5958343505859375,
+      "step": 860
+    },
+    {
+      "epoch": 0.0050946163958809736,
+      "grad_norm": 0.7661171555519104,
+      "learning_rate": 0.00016056410256410256,
+      "loss": 0.5362070083618165,
+      "step": 870
+    },
+    {
+      "epoch": 0.0051531752050290305,
+      "grad_norm": 1.014600157737732,
+      "learning_rate": 0.00016005128205128205,
+      "loss": 0.537624454498291,
+      "step": 880
+    },
+    {
+      "epoch": 0.0052117340141770874,
+      "grad_norm": 0.7331597805023193,
+      "learning_rate": 0.00015953846153846156,
+      "loss": 0.5774639129638672,
+      "step": 890
+    },
+    {
+      "epoch": 0.005270292823325145,
+      "grad_norm": 0.7434748411178589,
+      "learning_rate": 0.00015902564102564105,
+      "loss": 0.5845869064331055,
+      "step": 900
+    },
+    {
+      "epoch": 0.005328851632473202,
+      "grad_norm": 0.7248567342758179,
+      "learning_rate": 0.00015851282051282053,
+      "loss": 0.590050458908081,
+      "step": 910
+    },
+    {
+      "epoch": 0.005387410441621259,
+      "grad_norm": 0.9382026791572571,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.6036070823669434,
+      "step": 920
+    },
+    {
+      "epoch": 0.005445969250769316,
+      "grad_norm": 0.9255577325820923,
+      "learning_rate": 0.0001574871794871795,
+      "loss": 0.4737861633300781,
+      "step": 930
+    },
+    {
+      "epoch": 0.005504528059917374,
+      "grad_norm": 0.9797175526618958,
+      "learning_rate": 0.000156974358974359,
+      "loss": 0.5388136386871338,
+      "step": 940
+    },
+    {
+      "epoch": 0.005563086869065431,
+      "grad_norm": 0.7894104719161987,
+      "learning_rate": 0.00015646153846153845,
+      "loss": 0.529002571105957,
+      "step": 950
+    },
+    {
+      "epoch": 0.005621645678213488,
+      "grad_norm": 0.8898355960845947,
+      "learning_rate": 0.00015594871794871794,
+      "loss": 0.5382211685180665,
+      "step": 960
+    },
+    {
+      "epoch": 0.005680204487361545,
+      "grad_norm": 0.7389085292816162,
+      "learning_rate": 0.00015543589743589742,
+      "loss": 0.5379764080047608,
+      "step": 970
+    },
+    {
+      "epoch": 0.0057387632965096025,
+      "grad_norm": 0.8882327675819397,
+      "learning_rate": 0.00015492307692307694,
+      "loss": 0.5847358226776123,
+      "step": 980
+    },
+    {
+      "epoch": 0.005797322105657659,
+      "grad_norm": 1.1310079097747803,
+      "learning_rate": 0.00015441025641025642,
+      "loss": 0.5858294486999511,
+      "step": 990
+    },
+    {
+      "epoch": 0.005855880914805716,
+      "grad_norm": 1.0356104373931885,
+      "learning_rate": 0.0001538974358974359,
+      "loss": 0.5417033195495605,
+      "step": 1000
+    },
+    {
+      "epoch": 0.005914439723953773,
+      "grad_norm": 0.7012810707092285,
+      "learning_rate": 0.0001533846153846154,
+      "loss": 0.6806005477905274,
+      "step": 1010
+    },
+    {
+      "epoch": 0.005972998533101831,
+      "grad_norm": 0.9496027231216431,
+      "learning_rate": 0.00015287179487179488,
+      "loss": 0.521822738647461,
+      "step": 1020
+    },
+    {
+      "epoch": 0.006031557342249888,
+      "grad_norm": 0.7196470499038696,
+      "learning_rate": 0.00015235897435897437,
+      "loss": 0.5730608940124512,
+      "step": 1030
+    },
+    {
+      "epoch": 0.006090116151397945,
+      "grad_norm": 0.7311615347862244,
+      "learning_rate": 0.00015184615384615386,
+      "loss": 0.6122246742248535,
+      "step": 1040
+    },
+    {
+      "epoch": 0.006148674960546002,
+      "grad_norm": 0.7351731657981873,
+      "learning_rate": 0.00015133333333333334,
+      "loss": 0.5122735023498535,
+      "step": 1050
+    },
+    {
+      "epoch": 0.00620723376969406,
+      "grad_norm": 0.8649750351905823,
+      "learning_rate": 0.00015082051282051283,
+      "loss": 0.6370734691619873,
+      "step": 1060
+    },
+    {
+      "epoch": 0.006265792578842117,
+      "grad_norm": 0.7295814752578735,
+      "learning_rate": 0.00015030769230769232,
+      "loss": 0.5188347816467285,
+      "step": 1070
+    },
+    {
+      "epoch": 0.006324351387990174,
+      "grad_norm": 0.7717416882514954,
+      "learning_rate": 0.0001497948717948718,
+      "loss": 0.5114748001098632,
+      "step": 1080
+    },
+    {
+      "epoch": 0.006382910197138231,
+      "grad_norm": 0.5910501480102539,
+      "learning_rate": 0.0001492820512820513,
+      "loss": 0.46537189483642577,
+      "step": 1090
+    },
+    {
+      "epoch": 0.006441469006286288,
+      "grad_norm": 0.7533769011497498,
+      "learning_rate": 0.00014876923076923078,
+      "loss": 0.5796781539916992,
+      "step": 1100
+    },
+    {
+      "epoch": 0.006500027815434345,
+      "grad_norm": 0.9167582988739014,
+      "learning_rate": 0.00014825641025641026,
+      "loss": 0.6297817230224609,
+      "step": 1110
+    },
+    {
+      "epoch": 0.006558586624582402,
+      "grad_norm": 1.1386590003967285,
+      "learning_rate": 0.00014774358974358975,
+      "loss": 0.592150354385376,
+      "step": 1120
+    },
+    {
+      "epoch": 0.00661714543373046,
+      "grad_norm": 0.7550930380821228,
+      "learning_rate": 0.00014723076923076924,
+      "loss": 0.5509029865264893,
+      "step": 1130
+    },
+    {
+      "epoch": 0.006675704242878517,
+      "grad_norm": 0.6492360234260559,
+      "learning_rate": 0.00014671794871794872,
+      "loss": 0.5187190055847168,
+      "step": 1140
+    },
+    {
+      "epoch": 0.006734263052026574,
+      "grad_norm": 0.7233424782752991,
+      "learning_rate": 0.0001462051282051282,
+      "loss": 0.5804600238800048,
+      "step": 1150
+    },
+    {
+      "epoch": 0.006792821861174631,
+      "grad_norm": 1.0428144931793213,
+      "learning_rate": 0.0001456923076923077,
+      "loss": 0.5116332530975342,
+      "step": 1160
+    },
+    {
+      "epoch": 0.006851380670322689,
+      "grad_norm": 0.7919323444366455,
+      "learning_rate": 0.00014517948717948718,
+      "loss": 0.6416738986968994,
+      "step": 1170
+    },
+    {
+      "epoch": 0.006909939479470746,
+      "grad_norm": 0.8511198163032532,
+      "learning_rate": 0.0001446666666666667,
+      "loss": 0.579420518875122,
+      "step": 1180
+    },
+    {
+      "epoch": 0.0069684982886188025,
+      "grad_norm": 0.6856178641319275,
+      "learning_rate": 0.00014415384615384615,
+      "loss": 0.5805029392242431,
+      "step": 1190
+    },
+    {
+      "epoch": 0.0070270570977668595,
+      "grad_norm": 0.7397869229316711,
+      "learning_rate": 0.00014364102564102564,
+      "loss": 0.5604559898376464,
+      "step": 1200
+    },
+    {
+      "epoch": 0.007085615906914917,
+      "grad_norm": 0.7105910778045654,
+      "learning_rate": 0.00014312820512820513,
+      "loss": 0.5608997821807862,
+      "step": 1210
+    },
+    {
+      "epoch": 0.007144174716062974,
+      "grad_norm": 0.7479007244110107,
+      "learning_rate": 0.00014261538461538461,
+      "loss": 0.6052242279052734,
+      "step": 1220
+    },
+    {
+      "epoch": 0.007202733525211031,
+      "grad_norm": 1.1256407499313354,
+      "learning_rate": 0.0001421025641025641,
+      "loss": 0.6259459495544434,
+      "step": 1230
+    },
+    {
+      "epoch": 0.007261292334359088,
+      "grad_norm": 0.6991755962371826,
+      "learning_rate": 0.0001415897435897436,
+      "loss": 0.5524515151977539,
+      "step": 1240
+    },
+    {
+      "epoch": 0.007319851143507146,
+      "grad_norm": 1.053760051727295,
+      "learning_rate": 0.00014107692307692307,
+      "loss": 0.5364514827728272,
+      "step": 1250
+    },
+    {
+      "epoch": 0.007378409952655203,
+      "grad_norm": 0.983850359916687,
+      "learning_rate": 0.00014056410256410256,
+      "loss": 0.5353530883789063,
+      "step": 1260
+    },
+    {
+      "epoch": 0.00743696876180326,
+      "grad_norm": 0.6570679545402527,
+      "learning_rate": 0.00014005128205128207,
+      "loss": 0.5768649101257324,
+      "step": 1270
+    },
+    {
+      "epoch": 0.007495527570951318,
+      "grad_norm": 0.6319562792778015,
+      "learning_rate": 0.00013953846153846156,
+      "loss": 0.587717342376709,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0075540863800993745,
+      "grad_norm": 0.8129682540893555,
+      "learning_rate": 0.00013902564102564105,
+      "loss": 0.561523723602295,
+      "step": 1290
+    },
+    {
+      "epoch": 0.0076126451892474314,
+      "grad_norm": 0.884220540523529,
+      "learning_rate": 0.00013851282051282053,
+      "loss": 0.513004207611084,
+      "step": 1300
+    },
+    {
+      "epoch": 0.007671203998395488,
+      "grad_norm": 0.7594801783561707,
+      "learning_rate": 0.000138,
+      "loss": 0.5956247806549072,
+      "step": 1310
+    },
+    {
+      "epoch": 0.007729762807543546,
+      "grad_norm": 0.8838579654693604,
+      "learning_rate": 0.00013748717948717948,
+      "loss": 0.6295031547546387,
+      "step": 1320
+    },
+    {
+      "epoch": 0.007788321616691603,
+      "grad_norm": 0.7182386517524719,
+      "learning_rate": 0.00013697435897435897,
+      "loss": 0.5618526458740234,
+      "step": 1330
+    },
+    {
+      "epoch": 0.007846880425839661,
+      "grad_norm": 0.7297655940055847,
+      "learning_rate": 0.00013646153846153845,
+      "loss": 0.5208499908447266,
+      "step": 1340
+    },
+    {
+      "epoch": 0.007905439234987717,
+      "grad_norm": 0.62089604139328,
+      "learning_rate": 0.00013594871794871794,
+      "loss": 0.5239852428436279,
+      "step": 1350
+    },
+    {
+      "epoch": 0.007963998044135775,
+      "grad_norm": 0.7171675562858582,
+      "learning_rate": 0.00013543589743589745,
+      "loss": 0.5648018836975097,
+      "step": 1360
+    },
+    {
+      "epoch": 0.008022556853283831,
+      "grad_norm": 0.9089975357055664,
+      "learning_rate": 0.00013492307692307694,
+      "loss": 0.5615391254425048,
+      "step": 1370
+    },
+    {
+      "epoch": 0.008081115662431889,
+      "grad_norm": 0.7600458860397339,
+      "learning_rate": 0.00013441025641025643,
+      "loss": 0.604154634475708,
+      "step": 1380
+    },
+    {
+      "epoch": 0.008139674471579946,
+      "grad_norm": 0.7462561726570129,
+      "learning_rate": 0.0001338974358974359,
+      "loss": 0.6301332950592041,
+      "step": 1390
+    },
+    {
+      "epoch": 0.008198233280728003,
+      "grad_norm": 0.7292648553848267,
+      "learning_rate": 0.0001333846153846154,
+      "loss": 0.5153694152832031,
+      "step": 1400
+    },
+    {
+      "epoch": 0.00825679208987606,
+      "grad_norm": 0.8180534243583679,
+      "learning_rate": 0.00013287179487179489,
+      "loss": 0.647784423828125,
+      "step": 1410
+    },
+    {
+      "epoch": 0.008315350899024118,
+      "grad_norm": 0.6629355549812317,
+      "learning_rate": 0.00013235897435897437,
+      "loss": 0.5387883186340332,
+      "step": 1420
+    },
+    {
+      "epoch": 0.008373909708172174,
+      "grad_norm": 1.1468173265457153,
+      "learning_rate": 0.00013184615384615383,
+      "loss": 0.6159374713897705,
+      "step": 1430
+    },
+    {
+      "epoch": 0.008432468517320232,
+      "grad_norm": 0.9131197929382324,
+      "learning_rate": 0.00013133333333333332,
+      "loss": 0.5780044078826905,
+      "step": 1440
+    },
+    {
+      "epoch": 0.008491027326468288,
+      "grad_norm": 0.8688338398933411,
+      "learning_rate": 0.00013082051282051283,
+      "loss": 0.5893913745880127,
+      "step": 1450
+    },
+    {
+      "epoch": 0.008549586135616346,
+      "grad_norm": 0.6430419683456421,
+      "learning_rate": 0.00013030769230769232,
+      "loss": 0.5053946495056152,
+      "step": 1460
+    },
+    {
+      "epoch": 0.008608144944764404,
+      "grad_norm": 0.81430584192276,
+      "learning_rate": 0.0001297948717948718,
+      "loss": 0.587185287475586,
+      "step": 1470
+    },
+    {
+      "epoch": 0.00866670375391246,
+      "grad_norm": 0.7069384455680847,
+      "learning_rate": 0.0001292820512820513,
+      "loss": 0.6119993686676025,
+      "step": 1480
+    },
+    {
+      "epoch": 0.008725262563060518,
+      "grad_norm": 0.8512614965438843,
+      "learning_rate": 0.00012876923076923078,
+      "loss": 0.5506554126739502,
+      "step": 1490
+    },
+    {
+      "epoch": 0.008783821372208575,
+      "grad_norm": 0.6660640835762024,
+      "learning_rate": 0.00012825641025641026,
+      "loss": 0.5566682338714599,
+      "step": 1500
+    },
+    {
+      "epoch": 0.008842380181356631,
+      "grad_norm": 0.7649056315422058,
+      "learning_rate": 0.00012774358974358975,
+      "loss": 0.5694420814514161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.00890093899050469,
+      "grad_norm": 0.909599781036377,
+      "learning_rate": 0.00012723076923076924,
+      "loss": 0.6355206489562988,
+      "step": 1520
+    },
+    {
+      "epoch": 0.008959497799652747,
+      "grad_norm": 0.7873692512512207,
+      "learning_rate": 0.00012671794871794872,
+      "loss": 0.510439395904541,
+      "step": 1530
+    },
+    {
+      "epoch": 0.009018056608800803,
+      "grad_norm": 0.7628417611122131,
+      "learning_rate": 0.0001262051282051282,
+      "loss": 0.5399933338165284,
+      "step": 1540
+    },
+    {
+      "epoch": 0.009076615417948861,
+      "grad_norm": 0.8505508899688721,
+      "learning_rate": 0.0001256923076923077,
+      "loss": 0.6154933452606202,
+      "step": 1550
+    },
+    {
+      "epoch": 0.009135174227096917,
+      "grad_norm": 0.794605553150177,
+      "learning_rate": 0.00012517948717948718,
+      "loss": 0.6099573612213135,
+      "step": 1560
+    },
+    {
+      "epoch": 0.009193733036244975,
+      "grad_norm": 0.818773090839386,
+      "learning_rate": 0.00012466666666666667,
+      "loss": 0.5245619297027588,
+      "step": 1570
+    },
+    {
+      "epoch": 0.009252291845393033,
+      "grad_norm": 0.6100147366523743,
+      "learning_rate": 0.00012415384615384616,
+      "loss": 0.5743139743804931,
+      "step": 1580
+    },
+    {
+      "epoch": 0.009310850654541089,
+      "grad_norm": 0.911518394947052,
+      "learning_rate": 0.00012364102564102564,
+      "loss": 0.5403082370758057,
+      "step": 1590
+    },
+    {
+      "epoch": 0.009369409463689147,
+      "grad_norm": 0.7002453804016113,
+      "learning_rate": 0.00012312820512820513,
+      "loss": 0.5670140743255615,
+      "step": 1600
+    },
+    {
+      "epoch": 0.009427968272837204,
+      "grad_norm": 0.6926924586296082,
+      "learning_rate": 0.00012261538461538462,
+      "loss": 0.5283169746398926,
+      "step": 1610
+    },
+    {
+      "epoch": 0.00948652708198526,
+      "grad_norm": 0.8910185098648071,
+      "learning_rate": 0.0001221025641025641,
+      "loss": 0.5464873313903809,
+      "step": 1620
+    },
+    {
+      "epoch": 0.009545085891133318,
+      "grad_norm": 0.9428623914718628,
+      "learning_rate": 0.0001215897435897436,
+      "loss": 0.6371686935424805,
+      "step": 1630
+    },
+    {
+      "epoch": 0.009603644700281374,
+      "grad_norm": 0.9594399333000183,
+      "learning_rate": 0.00012107692307692309,
+      "loss": 0.5639693737030029,
+      "step": 1640
+    },
+    {
+      "epoch": 0.009662203509429432,
+      "grad_norm": 0.9431197643280029,
+      "learning_rate": 0.00012056410256410258,
+      "loss": 0.4942180633544922,
+      "step": 1650
+    },
+    {
+      "epoch": 0.00972076231857749,
+      "grad_norm": 0.778407096862793,
+      "learning_rate": 0.00012005128205128206,
+      "loss": 0.5874770641326904,
+      "step": 1660
+    },
+    {
+      "epoch": 0.009779321127725546,
+      "grad_norm": 0.7874659299850464,
+      "learning_rate": 0.00011953846153846155,
+      "loss": 0.5451854228973388,
+      "step": 1670
+    },
+    {
+      "epoch": 0.009837879936873604,
+      "grad_norm": 0.7366560697555542,
+      "learning_rate": 0.00011902564102564102,
+      "loss": 0.5593300342559815,
+      "step": 1680
+    },
+    {
+      "epoch": 0.009896438746021662,
+      "grad_norm": 0.762984573841095,
+      "learning_rate": 0.00011851282051282051,
+      "loss": 0.571781587600708,
+      "step": 1690
+    },
+    {
+      "epoch": 0.009954997555169718,
+      "grad_norm": 0.7820915579795837,
+      "learning_rate": 0.000118,
+      "loss": 0.6361937522888184,
+      "step": 1700
+    },
+    {
+      "epoch": 0.010013556364317775,
+      "grad_norm": 0.885874330997467,
+      "learning_rate": 0.0001174871794871795,
+      "loss": 0.5583993911743164,
+      "step": 1710
+    },
+    {
+      "epoch": 0.010072115173465833,
+      "grad_norm": 0.7336756587028503,
+      "learning_rate": 0.00011697435897435898,
+      "loss": 0.5345401763916016,
+      "step": 1720
+    },
+    {
+      "epoch": 0.01013067398261389,
+      "grad_norm": 1.1266441345214844,
+      "learning_rate": 0.00011646153846153847,
+      "loss": 0.5590295314788818,
+      "step": 1730
+    },
+    {
+      "epoch": 0.010189232791761947,
+      "grad_norm": 0.6986821889877319,
+      "learning_rate": 0.00011594871794871795,
+      "loss": 0.626862907409668,
+      "step": 1740
+    },
+    {
+      "epoch": 0.010247791600910003,
+      "grad_norm": 0.6808388233184814,
+      "learning_rate": 0.00011543589743589744,
+      "loss": 0.45256743431091306,
+      "step": 1750
+    },
+    {
+      "epoch": 0.010306350410058061,
+      "grad_norm": 0.8917853236198425,
+      "learning_rate": 0.00011492307692307693,
+      "loss": 0.5677892684936523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.010364909219206119,
+      "grad_norm": 0.84018474817276,
+      "learning_rate": 0.00011441025641025643,
+      "loss": 0.6715295314788818,
+      "step": 1770
+    },
+    {
+      "epoch": 0.010423468028354175,
+      "grad_norm": 0.8711966276168823,
+      "learning_rate": 0.00011389743589743591,
+      "loss": 0.49718570709228516,
+      "step": 1780
+    },
+    {
+      "epoch": 0.010482026837502233,
+      "grad_norm": 0.8351517915725708,
+      "learning_rate": 0.0001133846153846154,
+      "loss": 0.5668165683746338,
+      "step": 1790
+    },
+    {
+      "epoch": 0.01054058564665029,
+      "grad_norm": 0.9627017378807068,
+      "learning_rate": 0.00011287179487179486,
+      "loss": 0.5853204727172852,
+      "step": 1800
+    },
+    {
+      "epoch": 0.010599144455798347,
+      "grad_norm": 0.642246425151825,
+      "learning_rate": 0.00011235897435897436,
+      "loss": 0.5551766872406005,
+      "step": 1810
+    },
+    {
+      "epoch": 0.010657703264946404,
+      "grad_norm": 0.9542229771614075,
+      "learning_rate": 0.00011184615384615385,
+      "loss": 0.6531394958496094,
+      "step": 1820
+    },
+    {
+      "epoch": 0.01071626207409446,
+      "grad_norm": 0.7595056891441345,
+      "learning_rate": 0.00011133333333333333,
+      "loss": 0.5438894748687744,
+      "step": 1830
+    },
+    {
+      "epoch": 0.010774820883242518,
+      "grad_norm": 0.8346898555755615,
+      "learning_rate": 0.00011082051282051282,
+      "loss": 0.516790771484375,
+      "step": 1840
+    },
+    {
+      "epoch": 0.010833379692390576,
+      "grad_norm": 0.7261139750480652,
+      "learning_rate": 0.0001103076923076923,
+      "loss": 0.5511853694915771,
+      "step": 1850
+    },
+    {
+      "epoch": 0.010891938501538632,
+      "grad_norm": 0.7773726582527161,
+      "learning_rate": 0.0001097948717948718,
+      "loss": 0.6048900604248046,
+      "step": 1860
+    },
+    {
+      "epoch": 0.01095049731068669,
+      "grad_norm": 0.7758798599243164,
+      "learning_rate": 0.00010928205128205129,
+      "loss": 0.4920170783996582,
+      "step": 1870
+    },
+    {
+      "epoch": 0.011009056119834748,
+      "grad_norm": 0.7595053315162659,
+      "learning_rate": 0.00010876923076923078,
+      "loss": 0.5262623786926269,
+      "step": 1880
+    },
+    {
+      "epoch": 0.011067614928982804,
+      "grad_norm": 0.662896454334259,
+      "learning_rate": 0.00010825641025641027,
+      "loss": 0.5706700325012207,
+      "step": 1890
+    },
+    {
+      "epoch": 0.011126173738130862,
+      "grad_norm": 0.8547627329826355,
+      "learning_rate": 0.00010774358974358975,
+      "loss": 0.5571642398834229,
+      "step": 1900
+    },
+    {
+      "epoch": 0.011184732547278918,
+      "grad_norm": 0.9618740081787109,
+      "learning_rate": 0.00010723076923076924,
+      "loss": 0.5785984039306641,
+      "step": 1910
+    },
+    {
+      "epoch": 0.011243291356426975,
+      "grad_norm": 0.8090870976448059,
+      "learning_rate": 0.00010671794871794871,
+      "loss": 0.6467090606689453,
+      "step": 1920
+    },
+    {
+      "epoch": 0.011301850165575033,
+      "grad_norm": 0.8532423377037048,
+      "learning_rate": 0.0001062051282051282,
+      "loss": 0.5037952423095703,
+      "step": 1930
+    },
+    {
+      "epoch": 0.01136040897472309,
+      "grad_norm": 0.8701047897338867,
+      "learning_rate": 0.00010569230769230769,
+      "loss": 0.6252214908599854,
+      "step": 1940
+    },
+    {
+      "epoch": 0.011418967783871147,
+      "grad_norm": 0.8058343529701233,
+      "learning_rate": 0.00010517948717948719,
+      "loss": 0.49949493408203127,
+      "step": 1950
+    },
+    {
+      "epoch": 0.011477526593019205,
+      "grad_norm": 0.7899404764175415,
+      "learning_rate": 0.00010466666666666667,
+      "loss": 0.5413167476654053,
+      "step": 1960
+    },
+    {
+      "epoch": 0.011536085402167261,
+      "grad_norm": 0.7027344107627869,
+      "learning_rate": 0.00010415384615384616,
+      "loss": 0.45540223121643064,
+      "step": 1970
+    },
+    {
+      "epoch": 0.011594644211315319,
+      "grad_norm": 0.8737793564796448,
+      "learning_rate": 0.00010364102564102565,
+      "loss": 0.5688265800476074,
+      "step": 1980
+    },
+    {
+      "epoch": 0.011653203020463377,
+      "grad_norm": 0.9242916703224182,
+      "learning_rate": 0.00010312820512820513,
+      "loss": 0.5170233726501465,
+      "step": 1990
+    },
+    {
+      "epoch": 0.011711761829611433,
+      "grad_norm": 0.6759135127067566,
+      "learning_rate": 0.00010261538461538462,
+      "loss": 0.6288806438446045,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01177032063875949,
+      "grad_norm": 0.7091163396835327,
+      "learning_rate": 0.00010210256410256412,
+      "loss": 0.5844020843505859,
+      "step": 2010
+    },
+    {
+      "epoch": 0.011828879447907547,
+      "grad_norm": 0.9295818209648132,
+      "learning_rate": 0.0001015897435897436,
+      "loss": 0.5282711982727051,
+      "step": 2020
+    },
+    {
+      "epoch": 0.011887438257055604,
+      "grad_norm": 0.6938250064849854,
+      "learning_rate": 0.00010107692307692309,
+      "loss": 0.6149167537689209,
+      "step": 2030
+    },
+    {
+      "epoch": 0.011945997066203662,
+      "grad_norm": 0.7174298763275146,
+      "learning_rate": 0.00010056410256410256,
+      "loss": 0.5130744934082031,
+      "step": 2040
+    },
+    {
+      "epoch": 0.012004555875351718,
+      "grad_norm": 0.9726197123527527,
+      "learning_rate": 0.00010005128205128205,
+      "loss": 0.6236517429351807,
+      "step": 2050
+    },
+    {
+      "epoch": 0.012063114684499776,
+      "grad_norm": 0.7376599311828613,
+      "learning_rate": 9.953846153846155e-05,
+      "loss": 0.4681741714477539,
+      "step": 2060
+    },
+    {
+      "epoch": 0.012121673493647834,
+      "grad_norm": 0.8139657378196716,
+      "learning_rate": 9.902564102564102e-05,
+      "loss": 0.4887677192687988,
+      "step": 2070
+    },
+    {
+      "epoch": 0.01218023230279589,
+      "grad_norm": 0.9429419636726379,
+      "learning_rate": 9.851282051282051e-05,
+      "loss": 0.5326910018920898,
+      "step": 2080
+    },
+    {
+      "epoch": 0.012238791111943948,
+      "grad_norm": 0.9702481627464294,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5095866680145263,
+      "step": 2090
+    },
+    {
+      "epoch": 0.012297349921092004,
+      "grad_norm": 0.6909214854240417,
+      "learning_rate": 9.74871794871795e-05,
+      "loss": 0.5370609283447265,
+      "step": 2100
+    },
+    {
+      "epoch": 0.012355908730240062,
+      "grad_norm": 1.2493647336959839,
+      "learning_rate": 9.697435897435898e-05,
+      "loss": 0.5658076763153076,
+      "step": 2110
+    },
+    {
+      "epoch": 0.01241446753938812,
+      "grad_norm": 0.7158144116401672,
+      "learning_rate": 9.646153846153847e-05,
+      "loss": 0.5293547153472901,
+      "step": 2120
+    },
+    {
+      "epoch": 0.012473026348536176,
+      "grad_norm": 0.8394598364830017,
+      "learning_rate": 9.594871794871796e-05,
+      "loss": 0.48808741569519043,
+      "step": 2130
+    },
+    {
+      "epoch": 0.012531585157684233,
+      "grad_norm": 0.9504506587982178,
+      "learning_rate": 9.543589743589744e-05,
+      "loss": 0.5906731605529785,
+      "step": 2140
+    },
+    {
+      "epoch": 0.012590143966832291,
+      "grad_norm": 0.7592800855636597,
+      "learning_rate": 9.492307692307693e-05,
+      "loss": 0.5167060852050781,
+      "step": 2150
+    },
+    {
+      "epoch": 0.012648702775980347,
+      "grad_norm": 0.8858376145362854,
+      "learning_rate": 9.441025641025642e-05,
+      "loss": 0.5447789669036865,
+      "step": 2160
+    },
+    {
+      "epoch": 0.012707261585128405,
+      "grad_norm": 0.8264896273612976,
+      "learning_rate": 9.38974358974359e-05,
+      "loss": 0.4619621753692627,
+      "step": 2170
+    },
+    {
+      "epoch": 0.012765820394276463,
+      "grad_norm": 0.7801193594932556,
+      "learning_rate": 9.338461538461539e-05,
+      "loss": 0.5282919883728028,
+      "step": 2180
+    },
+    {
+      "epoch": 0.012824379203424519,
+      "grad_norm": 0.7734062671661377,
+      "learning_rate": 9.287179487179488e-05,
+      "loss": 0.6420894622802734,
+      "step": 2190
+    },
+    {
+      "epoch": 0.012882938012572577,
+      "grad_norm": 0.844348132610321,
+      "learning_rate": 9.235897435897436e-05,
+      "loss": 0.602821159362793,
+      "step": 2200
+    },
+    {
+      "epoch": 0.012941496821720633,
+      "grad_norm": 0.8861480355262756,
+      "learning_rate": 9.184615384615385e-05,
+      "loss": 0.5366893291473389,
+      "step": 2210
+    },
+    {
+      "epoch": 0.01300005563086869,
+      "grad_norm": 0.8071720600128174,
+      "learning_rate": 9.133333333333334e-05,
+      "loss": 0.4816866874694824,
+      "step": 2220
+    },
+    {
+      "epoch": 0.013058614440016748,
+      "grad_norm": 0.7975764870643616,
+      "learning_rate": 9.082051282051282e-05,
+      "loss": 0.6320478439331054,
+      "step": 2230
+    },
+    {
+      "epoch": 0.013117173249164804,
+      "grad_norm": 0.7712560296058655,
+      "learning_rate": 9.030769230769232e-05,
+      "loss": 0.607432746887207,
+      "step": 2240
+    },
+    {
+      "epoch": 0.013175732058312862,
+      "grad_norm": 0.7562223076820374,
+      "learning_rate": 8.979487179487181e-05,
+      "loss": 0.4568962097167969,
+      "step": 2250
+    },
+    {
+      "epoch": 0.01323429086746092,
+      "grad_norm": 0.7949206233024597,
+      "learning_rate": 8.928205128205128e-05,
+      "loss": 0.5890951156616211,
+      "step": 2260
+    },
+    {
+      "epoch": 0.013292849676608976,
+      "grad_norm": 0.8863471150398254,
+      "learning_rate": 8.876923076923077e-05,
+      "loss": 0.4792426109313965,
+      "step": 2270
+    },
+    {
+      "epoch": 0.013351408485757034,
+      "grad_norm": 0.9258952736854553,
+      "learning_rate": 8.825641025641025e-05,
+      "loss": 0.6157923698425293,
+      "step": 2280
+    },
+    {
+      "epoch": 0.01340996729490509,
+      "grad_norm": 0.7849915027618408,
+      "learning_rate": 8.774358974358975e-05,
+      "loss": 0.5654351234436035,
+      "step": 2290
+    },
+    {
+      "epoch": 0.013468526104053148,
+      "grad_norm": 0.7935325503349304,
+      "learning_rate": 8.723076923076924e-05,
+      "loss": 0.5722135543823242,
+      "step": 2300
+    },
+    {
+      "epoch": 0.013527084913201206,
+      "grad_norm": 0.8465309739112854,
+      "learning_rate": 8.671794871794873e-05,
+      "loss": 0.5128249645233154,
+      "step": 2310
+    },
+    {
+      "epoch": 0.013585643722349262,
+      "grad_norm": 0.8264815211296082,
+      "learning_rate": 8.62051282051282e-05,
+      "loss": 0.6118460655212402,
+      "step": 2320
+    },
+    {
+      "epoch": 0.01364420253149732,
+      "grad_norm": 0.6705726385116577,
+      "learning_rate": 8.56923076923077e-05,
+      "loss": 0.5447952747344971,
+      "step": 2330
+    },
+    {
+      "epoch": 0.013702761340645377,
+      "grad_norm": 0.921404242515564,
+      "learning_rate": 8.517948717948719e-05,
+      "loss": 0.542200756072998,
+      "step": 2340
+    },
+    {
+      "epoch": 0.013761320149793433,
+      "grad_norm": 0.5786399245262146,
+      "learning_rate": 8.466666666666667e-05,
+      "loss": 0.5167455673217773,
+      "step": 2350
+    },
+    {
+      "epoch": 0.013819878958941491,
+      "grad_norm": 0.8080707788467407,
+      "learning_rate": 8.415384615384616e-05,
+      "loss": 0.495404052734375,
+      "step": 2360
+    },
+    {
+      "epoch": 0.013878437768089549,
+      "grad_norm": 0.7522940635681152,
+      "learning_rate": 8.364102564102565e-05,
+      "loss": 0.5303984165191651,
+      "step": 2370
+    },
+    {
+      "epoch": 0.013936996577237605,
+      "grad_norm": 0.9101510643959045,
+      "learning_rate": 8.312820512820513e-05,
+      "loss": 0.5638332843780518,
+      "step": 2380
+    },
+    {
+      "epoch": 0.013995555386385663,
+      "grad_norm": 0.6749529838562012,
+      "learning_rate": 8.261538461538462e-05,
+      "loss": 0.5651543617248536,
+      "step": 2390
+    },
+    {
+      "epoch": 0.014054114195533719,
+      "grad_norm": 0.9458379149436951,
+      "learning_rate": 8.21025641025641e-05,
+      "loss": 0.5108407497406006,
+      "step": 2400
+    },
+    {
+      "epoch": 0.014112673004681777,
+      "grad_norm": 1.089971899986267,
+      "learning_rate": 8.158974358974359e-05,
+      "loss": 0.49324331283569334,
+      "step": 2410
+    },
+    {
+      "epoch": 0.014171231813829835,
+      "grad_norm": 0.7607450485229492,
+      "learning_rate": 8.107692307692308e-05,
+      "loss": 0.6479440212249756,
+      "step": 2420
+    },
+    {
+      "epoch": 0.01422979062297789,
+      "grad_norm": 0.9622839093208313,
+      "learning_rate": 8.056410256410257e-05,
+      "loss": 0.5628427982330322,
+      "step": 2430
+    },
+    {
+      "epoch": 0.014288349432125948,
+      "grad_norm": 0.8064730167388916,
+      "learning_rate": 8.005128205128205e-05,
+      "loss": 0.4927206993103027,
+      "step": 2440
+    },
+    {
+      "epoch": 0.014346908241274006,
+      "grad_norm": 0.7792487144470215,
+      "learning_rate": 7.953846153846154e-05,
+      "loss": 0.6291625022888183,
+      "step": 2450
+    },
+    {
+      "epoch": 0.014405467050422062,
+      "grad_norm": 1.0805375576019287,
+      "learning_rate": 7.902564102564103e-05,
+      "loss": 0.5925718307495117,
+      "step": 2460
+    },
+    {
+      "epoch": 0.01446402585957012,
+      "grad_norm": 0.5765560865402222,
+      "learning_rate": 7.851282051282051e-05,
+      "loss": 0.5485690593719482,
+      "step": 2470
+    },
+    {
+      "epoch": 0.014522584668718176,
+      "grad_norm": 0.8152871131896973,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.5624689102172852,
+      "step": 2480
+    },
+    {
+      "epoch": 0.014581143477866234,
+      "grad_norm": 0.8335279226303101,
+      "learning_rate": 7.74871794871795e-05,
+      "loss": 0.5260688304901123,
+      "step": 2490
+    },
+    {
+      "epoch": 0.014639702287014292,
+      "grad_norm": 0.7680035829544067,
+      "learning_rate": 7.697435897435897e-05,
+      "loss": 0.4830802917480469,
+      "step": 2500
+    },
+    {
+      "epoch": 0.014698261096162348,
+      "grad_norm": 0.9397810697555542,
+      "learning_rate": 7.646153846153846e-05,
+      "loss": 0.5444638729095459,
+      "step": 2510
+    },
+    {
+      "epoch": 0.014756819905310406,
+      "grad_norm": 0.7944267392158508,
+      "learning_rate": 7.594871794871794e-05,
+      "loss": 0.6039426326751709,
+      "step": 2520
+    },
+    {
+      "epoch": 0.014815378714458463,
+      "grad_norm": 0.8528501987457275,
+      "learning_rate": 7.543589743589744e-05,
+      "loss": 0.5764337539672851,
+      "step": 2530
+    },
+    {
+      "epoch": 0.01487393752360652,
+      "grad_norm": 0.9321673512458801,
+      "learning_rate": 7.492307692307693e-05,
+      "loss": 0.5600544929504394,
+      "step": 2540
+    },
+    {
+      "epoch": 0.014932496332754577,
+      "grad_norm": 0.8647655248641968,
+      "learning_rate": 7.441025641025642e-05,
+      "loss": 0.6365120887756348,
+      "step": 2550
+    },
+    {
+      "epoch": 0.014991055141902635,
+      "grad_norm": 0.9241213798522949,
+      "learning_rate": 7.389743589743589e-05,
+      "loss": 0.5070790767669677,
+      "step": 2560
+    },
+    {
+      "epoch": 0.015049613951050691,
+      "grad_norm": 0.6943749785423279,
+      "learning_rate": 7.338461538461539e-05,
+      "loss": 0.5472688674926758,
+      "step": 2570
+    },
+    {
+      "epoch": 0.015108172760198749,
+      "grad_norm": 0.7544350624084473,
+      "learning_rate": 7.287179487179488e-05,
+      "loss": 0.5143001079559326,
+      "step": 2580
+    },
+    {
+      "epoch": 0.015166731569346805,
+      "grad_norm": 0.8759540319442749,
+      "learning_rate": 7.235897435897436e-05,
+      "loss": 0.5885789871215821,
+      "step": 2590
+    },
+    {
+      "epoch": 0.015225290378494863,
+      "grad_norm": 0.8004186153411865,
+      "learning_rate": 7.184615384615385e-05,
+      "loss": 0.5833802223205566,
+      "step": 2600
+    },
+    {
+      "epoch": 0.01528384918764292,
+      "grad_norm": 0.8919973969459534,
+      "learning_rate": 7.133333333333334e-05,
+      "loss": 0.7211344242095947,
+      "step": 2610
+    },
+    {
+      "epoch": 0.015342407996790977,
+      "grad_norm": 0.6915315985679626,
+      "learning_rate": 7.082051282051282e-05,
+      "loss": 0.5526168823242188,
+      "step": 2620
+    },
+    {
+      "epoch": 0.015400966805939035,
+      "grad_norm": 0.9145429134368896,
+      "learning_rate": 7.030769230769231e-05,
+      "loss": 0.4407088279724121,
+      "step": 2630
+    },
+    {
+      "epoch": 0.015459525615087092,
+      "grad_norm": 0.674967885017395,
+      "learning_rate": 6.97948717948718e-05,
+      "loss": 0.4634512424468994,
+      "step": 2640
+    },
+    {
+      "epoch": 0.015518084424235148,
+      "grad_norm": 0.6875638365745544,
+      "learning_rate": 6.928205128205128e-05,
+      "loss": 0.47414402961730956,
+      "step": 2650
+    },
+    {
+      "epoch": 0.015576643233383206,
+      "grad_norm": 0.9719008803367615,
+      "learning_rate": 6.876923076923077e-05,
+      "loss": 0.5467365264892579,
+      "step": 2660
+    },
+    {
+      "epoch": 0.015635202042531264,
+      "grad_norm": 0.7496704459190369,
+      "learning_rate": 6.825641025641027e-05,
+      "loss": 0.5100692749023438,
+      "step": 2670
+    },
+    {
+      "epoch": 0.015693760851679322,
+      "grad_norm": 0.6996882557868958,
+      "learning_rate": 6.774358974358974e-05,
+      "loss": 0.5840377330780029,
+      "step": 2680
+    },
+    {
+      "epoch": 0.015752319660827376,
+      "grad_norm": 0.8965880274772644,
+      "learning_rate": 6.723076923076923e-05,
+      "loss": 0.5683030605316162,
+      "step": 2690
+    },
+    {
+      "epoch": 0.015810878469975434,
+      "grad_norm": 0.9862522482872009,
+      "learning_rate": 6.671794871794872e-05,
+      "loss": 0.5894110679626465,
+      "step": 2700
+    },
+    {
+      "epoch": 0.015869437279123492,
+      "grad_norm": 0.9664445519447327,
+      "learning_rate": 6.62051282051282e-05,
+      "loss": 0.5402120590209961,
+      "step": 2710
+    },
+    {
+      "epoch": 0.01592799608827155,
+      "grad_norm": 0.8799305558204651,
+      "learning_rate": 6.56923076923077e-05,
+      "loss": 0.5548243045806884,
+      "step": 2720
+    },
+    {
+      "epoch": 0.015986554897419607,
+      "grad_norm": 0.6217681169509888,
+      "learning_rate": 6.517948717948719e-05,
+      "loss": 0.48618650436401367,
+      "step": 2730
+    },
+    {
+      "epoch": 0.016045113706567662,
+      "grad_norm": 0.7473154664039612,
+      "learning_rate": 6.466666666666666e-05,
+      "loss": 0.5558083057403564,
+      "step": 2740
+    },
+    {
+      "epoch": 0.01610367251571572,
+      "grad_norm": 0.8467188477516174,
+      "learning_rate": 6.415384615384615e-05,
+      "loss": 0.5468488216400147,
+      "step": 2750
+    },
+    {
+      "epoch": 0.016162231324863777,
+      "grad_norm": 0.8353908658027649,
+      "learning_rate": 6.364102564102565e-05,
+      "loss": 0.55488600730896,
+      "step": 2760
+    },
+    {
+      "epoch": 0.016220790134011835,
+      "grad_norm": 1.0089359283447266,
+      "learning_rate": 6.312820512820514e-05,
+      "loss": 0.4439121723175049,
+      "step": 2770
+    },
+    {
+      "epoch": 0.016279348943159893,
+      "grad_norm": 0.8033394813537598,
+      "learning_rate": 6.261538461538462e-05,
+      "loss": 0.592630672454834,
+      "step": 2780
+    },
+    {
+      "epoch": 0.01633790775230795,
+      "grad_norm": 0.7081058621406555,
+      "learning_rate": 6.210256410256411e-05,
+      "loss": 0.5640474319458008,
+      "step": 2790
+    },
+    {
+      "epoch": 0.016396466561456005,
+      "grad_norm": 0.9237245321273804,
+      "learning_rate": 6.15897435897436e-05,
+      "loss": 0.6005640983581543,
+      "step": 2800
+    },
+    {
+      "epoch": 0.016455025370604063,
+      "grad_norm": 0.8360455632209778,
+      "learning_rate": 6.107692307692308e-05,
+      "loss": 0.5373104572296142,
+      "step": 2810
+    },
+    {
+      "epoch": 0.01651358417975212,
+      "grad_norm": 0.8988027572631836,
+      "learning_rate": 6.056410256410257e-05,
+      "loss": 0.5758774757385254,
+      "step": 2820
+    },
+    {
+      "epoch": 0.01657214298890018,
+      "grad_norm": 0.9521508812904358,
+      "learning_rate": 6.0051282051282054e-05,
+      "loss": 0.5425063133239746,
+      "step": 2830
+    },
+    {
+      "epoch": 0.016630701798048236,
+      "grad_norm": 1.0230766534805298,
+      "learning_rate": 5.953846153846154e-05,
+      "loss": 0.617734146118164,
+      "step": 2840
+    },
+    {
+      "epoch": 0.01668926060719629,
+      "grad_norm": 0.8182085752487183,
+      "learning_rate": 5.9025641025641034e-05,
+      "loss": 0.49785604476928713,
+      "step": 2850
+    },
+    {
+      "epoch": 0.01674781941634435,
+      "grad_norm": 0.819509744644165,
+      "learning_rate": 5.851282051282052e-05,
+      "loss": 0.5303618907928467,
+      "step": 2860
+    },
+    {
+      "epoch": 0.016806378225492406,
+      "grad_norm": 0.9338365197181702,
+      "learning_rate": 5.8e-05,
+      "loss": 0.5084160327911377,
+      "step": 2870
+    },
+    {
+      "epoch": 0.016864937034640464,
+      "grad_norm": 0.9572207927703857,
+      "learning_rate": 5.748717948717949e-05,
+      "loss": 0.5966866493225098,
+      "step": 2880
+    },
+    {
+      "epoch": 0.016923495843788522,
+      "grad_norm": 0.66383296251297,
+      "learning_rate": 5.6974358974358973e-05,
+      "loss": 0.5305398941040039,
+      "step": 2890
+    },
+    {
+      "epoch": 0.016982054652936576,
+      "grad_norm": 1.0674878358840942,
+      "learning_rate": 5.646153846153847e-05,
+      "loss": 0.556536340713501,
+      "step": 2900
+    },
+    {
+      "epoch": 0.017040613462084634,
+      "grad_norm": 0.7483784556388855,
+      "learning_rate": 5.594871794871795e-05,
+      "loss": 0.49668869972229,
+      "step": 2910
+    },
+    {
+      "epoch": 0.017099172271232692,
+      "grad_norm": 1.0706493854522705,
+      "learning_rate": 5.5435897435897447e-05,
+      "loss": 0.49158105850219724,
+      "step": 2920
+    },
+    {
+      "epoch": 0.01715773108038075,
+      "grad_norm": 0.7071096897125244,
+      "learning_rate": 5.492307692307692e-05,
+      "loss": 0.5811544895172119,
+      "step": 2930
+    },
+    {
+      "epoch": 0.017216289889528807,
+      "grad_norm": 0.8249266147613525,
+      "learning_rate": 5.441025641025641e-05,
+      "loss": 0.5450833797454834,
+      "step": 2940
+    },
+    {
+      "epoch": 0.017274848698676865,
+      "grad_norm": 0.684613823890686,
+      "learning_rate": 5.38974358974359e-05,
+      "loss": 0.5169521808624268,
+      "step": 2950
+    },
+    {
+      "epoch": 0.01733340750782492,
+      "grad_norm": 1.1294605731964111,
+      "learning_rate": 5.3384615384615386e-05,
+      "loss": 0.6362704277038574,
+      "step": 2960
+    },
+    {
+      "epoch": 0.017391966316972977,
+      "grad_norm": 0.7923810482025146,
+      "learning_rate": 5.287179487179488e-05,
+      "loss": 0.498931360244751,
+      "step": 2970
+    },
+    {
+      "epoch": 0.017450525126121035,
+      "grad_norm": 0.8153409957885742,
+      "learning_rate": 5.2358974358974366e-05,
+      "loss": 0.5227402687072754,
+      "step": 2980
+    },
+    {
+      "epoch": 0.017509083935269093,
+      "grad_norm": 0.8139829635620117,
+      "learning_rate": 5.1846153846153845e-05,
+      "loss": 0.5427112102508544,
+      "step": 2990
+    },
+    {
+      "epoch": 0.01756764274441715,
+      "grad_norm": 0.7023552060127258,
+      "learning_rate": 5.133333333333333e-05,
+      "loss": 0.5183414459228516,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.82859251162583e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

adapter/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b31c165767a8418547683b7b0bb98466ae2cea43d76fd57aefee2b75c80453
+size 5713

adapter/checkpoint-3500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter/checkpoint-3500/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/checkpoint-3500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78a73ce5366882903388c23e51289f2d393f5b945986f7f30733d89f4c3eaf5
+size 25587104

adapter/checkpoint-3500/chat_template.jinja

@@ -0,0 +1,158 @@
+{%- 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 %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- 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 merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|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 %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if 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 mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<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 %}
+    {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, tool calling #}

adapter/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a79db1bd15c4c803976a4c1c9241830d0bae2cbe3bd4f86475db021ad619ef
+size 51282443

adapter/checkpoint-3500/processor_config.json

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

adapter/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

adapter/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f981a7717a67543ab81b4b2ac95f0e2abc0b0a8764ef5ce0b995c16051aa90
+size 1465

adapter/checkpoint-3500/tokenizer.json

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

adapter/checkpoint-3500/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "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": false,
+  "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": "<|vision_pad|>",
+  "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|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

adapter/checkpoint-3500/trainer_state.json

@@ -0,0 +1,2484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.020495583201820006,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.855880914805717e-05,
+      "grad_norm": 1.5575445890426636,
+      "learning_rate": 1.8e-05,
+      "loss": 0.7678159713745117,
+      "step": 10
+    },
+    {
+      "epoch": 0.00011711761829611434,
+      "grad_norm": 1.0704400539398193,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7586987972259521,
+      "step": 20
+    },
+    {
+      "epoch": 0.0001756764274441715,
+      "grad_norm": 0.6421218514442444,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6814639568328857,
+      "step": 30
+    },
+    {
+      "epoch": 0.00023423523659222867,
+      "grad_norm": 0.938690721988678,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.6233416557312011,
+      "step": 40
+    },
+    {
+      "epoch": 0.00029279404574028583,
+      "grad_norm": 1.166359543800354,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5837168216705322,
+      "step": 50
+    },
+    {
+      "epoch": 0.000351352854888343,
+      "grad_norm": 0.7864418029785156,
+      "learning_rate": 0.000118,
+      "loss": 0.49336514472961424,
+      "step": 60
+    },
+    {
+      "epoch": 0.00040991166403640014,
+      "grad_norm": 0.723896861076355,
+      "learning_rate": 0.000138,
+      "loss": 0.6541348457336426,
+      "step": 70
+    },
+    {
+      "epoch": 0.00046847047318445735,
+      "grad_norm": 0.5491677522659302,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.6446280479431152,
+      "step": 80
+    },
+    {
+      "epoch": 0.0005270292823325145,
+      "grad_norm": 1.032065510749817,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.493870210647583,
+      "step": 90
+    },
+    {
+      "epoch": 0.0005855880914805717,
+      "grad_norm": 0.7324640154838562,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.63213210105896,
+      "step": 100
+    },
+    {
+      "epoch": 0.0006441469006286288,
+      "grad_norm": 0.8503096103668213,
+      "learning_rate": 0.00019953846153846153,
+      "loss": 0.6286506652832031,
+      "step": 110
+    },
+    {
+      "epoch": 0.000702705709776686,
+      "grad_norm": 0.8664548993110657,
+      "learning_rate": 0.00019902564102564104,
+      "loss": 0.48207850456237794,
+      "step": 120
+    },
+    {
+      "epoch": 0.0007612645189247431,
+      "grad_norm": 0.6782843470573425,
+      "learning_rate": 0.00019851282051282053,
+      "loss": 0.6306986331939697,
+      "step": 130
+    },
+    {
+      "epoch": 0.0008198233280728003,
+      "grad_norm": 1.2085249423980713,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.5556919574737549,
+      "step": 140
+    },
+    {
+      "epoch": 0.0008783821372208574,
+      "grad_norm": 0.8503999710083008,
+      "learning_rate": 0.0001974871794871795,
+      "loss": 0.6409926414489746,
+      "step": 150
+    },
+    {
+      "epoch": 0.0009369409463689147,
+      "grad_norm": 0.7704036235809326,
+      "learning_rate": 0.000196974358974359,
+      "loss": 0.5393772125244141,
+      "step": 160
+    },
+    {
+      "epoch": 0.0009954997555169719,
+      "grad_norm": 0.7071548104286194,
+      "learning_rate": 0.00019646153846153847,
+      "loss": 0.6072579860687256,
+      "step": 170
+    },
+    {
+      "epoch": 0.001054058564665029,
+      "grad_norm": 0.6557785272598267,
+      "learning_rate": 0.00019594871794871796,
+      "loss": 0.49915218353271484,
+      "step": 180
+    },
+    {
+      "epoch": 0.0011126173738130862,
+      "grad_norm": 0.6428221464157104,
+      "learning_rate": 0.00019543589743589745,
+      "loss": 0.6393180370330811,
+      "step": 190
+    },
+    {
+      "epoch": 0.0011711761829611433,
+      "grad_norm": 0.8832526803016663,
+      "learning_rate": 0.00019492307692307693,
+      "loss": 0.6467752456665039,
+      "step": 200
+    },
+    {
+      "epoch": 0.0012297349921092005,
+      "grad_norm": 0.8874967694282532,
+      "learning_rate": 0.00019441025641025642,
+      "loss": 0.6200666904449463,
+      "step": 210
+    },
+    {
+      "epoch": 0.0012882938012572576,
+      "grad_norm": 0.8451365828514099,
+      "learning_rate": 0.0001938974358974359,
+      "loss": 0.5980692386627198,
+      "step": 220
+    },
+    {
+      "epoch": 0.0013468526104053148,
+      "grad_norm": 1.3747062683105469,
+      "learning_rate": 0.0001933846153846154,
+      "loss": 0.5997383117675781,
+      "step": 230
+    },
+    {
+      "epoch": 0.001405411419553372,
+      "grad_norm": 0.7659091949462891,
+      "learning_rate": 0.00019287179487179488,
+      "loss": 0.6244289875030518,
+      "step": 240
+    },
+    {
+      "epoch": 0.001463970228701429,
+      "grad_norm": 0.7551876902580261,
+      "learning_rate": 0.00019235897435897437,
+      "loss": 0.5602375507354737,
+      "step": 250
+    },
+    {
+      "epoch": 0.0015225290378494862,
+      "grad_norm": 0.8756004571914673,
+      "learning_rate": 0.00019184615384615385,
+      "loss": 0.5726509094238281,
+      "step": 260
+    },
+    {
+      "epoch": 0.0015810878469975434,
+      "grad_norm": 0.9010286927223206,
+      "learning_rate": 0.00019133333333333334,
+      "loss": 0.564607048034668,
+      "step": 270
+    },
+    {
+      "epoch": 0.0016396466561456006,
+      "grad_norm": 0.768795907497406,
+      "learning_rate": 0.00019082051282051283,
+      "loss": 0.6172872066497803,
+      "step": 280
+    },
+    {
+      "epoch": 0.0016982054652936577,
+      "grad_norm": 0.8452103137969971,
+      "learning_rate": 0.0001903076923076923,
+      "loss": 0.5882416248321534,
+      "step": 290
+    },
+    {
+      "epoch": 0.0017567642744417149,
+      "grad_norm": 0.8099432587623596,
+      "learning_rate": 0.0001897948717948718,
+      "loss": 0.5674912452697753,
+      "step": 300
+    },
+    {
+      "epoch": 0.001815323083589772,
+      "grad_norm": 0.7150252461433411,
+      "learning_rate": 0.00018928205128205129,
+      "loss": 0.5736612796783447,
+      "step": 310
+    },
+    {
+      "epoch": 0.0018738818927378294,
+      "grad_norm": 1.098449945449829,
+      "learning_rate": 0.0001887692307692308,
+      "loss": 0.6177639484405517,
+      "step": 320
+    },
+    {
+      "epoch": 0.0019324407018858865,
+      "grad_norm": 0.7274444103240967,
+      "learning_rate": 0.00018825641025641029,
+      "loss": 0.6690079212188721,
+      "step": 330
+    },
+    {
+      "epoch": 0.0019909995110339437,
+      "grad_norm": 0.7714038491249084,
+      "learning_rate": 0.00018774358974358975,
+      "loss": 0.5143749237060546,
+      "step": 340
+    },
+    {
+      "epoch": 0.0020495583201820006,
+      "grad_norm": 0.9286389946937561,
+      "learning_rate": 0.00018723076923076923,
+      "loss": 0.5226009368896485,
+      "step": 350
+    },
+    {
+      "epoch": 0.002108117129330058,
+      "grad_norm": 0.9736594557762146,
+      "learning_rate": 0.00018671794871794872,
+      "loss": 0.5954864501953125,
+      "step": 360
+    },
+    {
+      "epoch": 0.002166675938478115,
+      "grad_norm": 0.7701608538627625,
+      "learning_rate": 0.0001862051282051282,
+      "loss": 0.564179515838623,
+      "step": 370
+    },
+    {
+      "epoch": 0.0022252347476261723,
+      "grad_norm": 0.8563699126243591,
+      "learning_rate": 0.0001856923076923077,
+      "loss": 0.587281608581543,
+      "step": 380
+    },
+    {
+      "epoch": 0.0022837935567742293,
+      "grad_norm": 1.017929196357727,
+      "learning_rate": 0.00018517948717948718,
+      "loss": 0.579550313949585,
+      "step": 390
+    },
+    {
+      "epoch": 0.0023423523659222866,
+      "grad_norm": 0.6563118696212769,
+      "learning_rate": 0.00018466666666666666,
+      "loss": 0.5135430335998535,
+      "step": 400
+    },
+    {
+      "epoch": 0.0024009111750703436,
+      "grad_norm": 0.7011086344718933,
+      "learning_rate": 0.00018415384615384618,
+      "loss": 0.6544422149658203,
+      "step": 410
+    },
+    {
+      "epoch": 0.002459469984218401,
+      "grad_norm": 0.991001546382904,
+      "learning_rate": 0.00018364102564102567,
+      "loss": 0.6101119518280029,
+      "step": 420
+    },
+    {
+      "epoch": 0.0025180287933664583,
+      "grad_norm": 0.7023338675498962,
+      "learning_rate": 0.00018312820512820515,
+      "loss": 0.5026431560516358,
+      "step": 430
+    },
+    {
+      "epoch": 0.0025765876025145153,
+      "grad_norm": 0.9078162908554077,
+      "learning_rate": 0.00018261538461538464,
+      "loss": 0.5121633052825928,
+      "step": 440
+    },
+    {
+      "epoch": 0.0026351464116625726,
+      "grad_norm": 0.7449192404747009,
+      "learning_rate": 0.00018210256410256412,
+      "loss": 0.6154009819030761,
+      "step": 450
+    },
+    {
+      "epoch": 0.0026937052208106296,
+      "grad_norm": 0.6876159906387329,
+      "learning_rate": 0.00018158974358974358,
+      "loss": 0.5338088989257812,
+      "step": 460
+    },
+    {
+      "epoch": 0.002752264029958687,
+      "grad_norm": 0.9204329252243042,
+      "learning_rate": 0.00018107692307692307,
+      "loss": 0.5554272174835205,
+      "step": 470
+    },
+    {
+      "epoch": 0.002810822839106744,
+      "grad_norm": 0.7362950444221497,
+      "learning_rate": 0.00018056410256410256,
+      "loss": 0.6131524085998535,
+      "step": 480
+    },
+    {
+      "epoch": 0.0028693816482548012,
+      "grad_norm": 0.9833507537841797,
+      "learning_rate": 0.00018005128205128204,
+      "loss": 0.5537636756896973,
+      "step": 490
+    },
+    {
+      "epoch": 0.002927940457402858,
+      "grad_norm": 0.7546113133430481,
+      "learning_rate": 0.00017953846153846156,
+      "loss": 0.6003861904144288,
+      "step": 500
+    },
+    {
+      "epoch": 0.0029864992665509156,
+      "grad_norm": 0.7838321924209595,
+      "learning_rate": 0.00017902564102564104,
+      "loss": 0.6598413944244385,
+      "step": 510
+    },
+    {
+      "epoch": 0.0030450580756989725,
+      "grad_norm": 0.7242461442947388,
+      "learning_rate": 0.00017851282051282053,
+      "loss": 0.5558955669403076,
+      "step": 520
+    },
+    {
+      "epoch": 0.00310361688484703,
+      "grad_norm": 1.1162296533584595,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.6460456371307373,
+      "step": 530
+    },
+    {
+      "epoch": 0.003162175693995087,
+      "grad_norm": 0.7049973011016846,
+      "learning_rate": 0.0001774871794871795,
+      "loss": 0.6043939113616943,
+      "step": 540
+    },
+    {
+      "epoch": 0.003220734503143144,
+      "grad_norm": 0.8112305998802185,
+      "learning_rate": 0.000176974358974359,
+      "loss": 0.4545936584472656,
+      "step": 550
+    },
+    {
+      "epoch": 0.003279293312291201,
+      "grad_norm": 0.6234564781188965,
+      "learning_rate": 0.00017646153846153848,
+      "loss": 0.6101226329803466,
+      "step": 560
+    },
+    {
+      "epoch": 0.0033378521214392585,
+      "grad_norm": 0.9512666463851929,
+      "learning_rate": 0.00017594871794871796,
+      "loss": 0.6055888175964356,
+      "step": 570
+    },
+    {
+      "epoch": 0.0033964109305873154,
+      "grad_norm": 0.8533800840377808,
+      "learning_rate": 0.00017543589743589742,
+      "loss": 0.6529808044433594,
+      "step": 580
+    },
+    {
+      "epoch": 0.003454969739735373,
+      "grad_norm": 0.896560549736023,
+      "learning_rate": 0.00017492307692307694,
+      "loss": 0.5882085800170899,
+      "step": 590
+    },
+    {
+      "epoch": 0.0035135285488834297,
+      "grad_norm": 0.8455023765563965,
+      "learning_rate": 0.00017441025641025642,
+      "loss": 0.518503999710083,
+      "step": 600
+    },
+    {
+      "epoch": 0.003572087358031487,
+      "grad_norm": 0.7477754950523376,
+      "learning_rate": 0.0001738974358974359,
+      "loss": 0.6013938426971436,
+      "step": 610
+    },
+    {
+      "epoch": 0.003630646167179544,
+      "grad_norm": 0.8402391672134399,
+      "learning_rate": 0.0001733846153846154,
+      "loss": 0.6162835597991944,
+      "step": 620
+    },
+    {
+      "epoch": 0.0036892049763276014,
+      "grad_norm": 1.0327485799789429,
+      "learning_rate": 0.00017287179487179488,
+      "loss": 0.6443416595458984,
+      "step": 630
+    },
+    {
+      "epoch": 0.003747763785475659,
+      "grad_norm": 1.0342403650283813,
+      "learning_rate": 0.00017235897435897437,
+      "loss": 0.5222865581512451,
+      "step": 640
+    },
+    {
+      "epoch": 0.0038063225946237157,
+      "grad_norm": 0.9043326377868652,
+      "learning_rate": 0.00017184615384615386,
+      "loss": 0.6140403747558594,
+      "step": 650
+    },
+    {
+      "epoch": 0.003864881403771773,
+      "grad_norm": 0.8706991076469421,
+      "learning_rate": 0.00017133333333333334,
+      "loss": 0.6201248645782471,
+      "step": 660
+    },
+    {
+      "epoch": 0.0039234402129198305,
+      "grad_norm": 0.7702825665473938,
+      "learning_rate": 0.00017082051282051283,
+      "loss": 0.5698607921600342,
+      "step": 670
+    },
+    {
+      "epoch": 0.003981999022067887,
+      "grad_norm": 0.7835186719894409,
+      "learning_rate": 0.00017030769230769231,
+      "loss": 0.5464808464050293,
+      "step": 680
+    },
+    {
+      "epoch": 0.004040557831215944,
+      "grad_norm": 0.7293221950531006,
+      "learning_rate": 0.0001697948717948718,
+      "loss": 0.6055557250976562,
+      "step": 690
+    },
+    {
+      "epoch": 0.004099116640364001,
+      "grad_norm": 0.8519648313522339,
+      "learning_rate": 0.0001692820512820513,
+      "loss": 0.594606876373291,
+      "step": 700
+    },
+    {
+      "epoch": 0.004157675449512059,
+      "grad_norm": 0.8359381556510925,
+      "learning_rate": 0.00016876923076923077,
+      "loss": 0.6676365852355957,
+      "step": 710
+    },
+    {
+      "epoch": 0.004216234258660116,
+      "grad_norm": 0.9601361155509949,
+      "learning_rate": 0.00016825641025641026,
+      "loss": 0.5267905235290528,
+      "step": 720
+    },
+    {
+      "epoch": 0.004274793067808173,
+      "grad_norm": 0.5900155901908875,
+      "learning_rate": 0.00016774358974358975,
+      "loss": 0.5860335826873779,
+      "step": 730
+    },
+    {
+      "epoch": 0.00433335187695623,
+      "grad_norm": 0.7671850323677063,
+      "learning_rate": 0.00016723076923076923,
+      "loss": 0.5898273468017579,
+      "step": 740
+    },
+    {
+      "epoch": 0.004391910686104288,
+      "grad_norm": 0.9657745361328125,
+      "learning_rate": 0.00016671794871794872,
+      "loss": 0.6093048572540283,
+      "step": 750
+    },
+    {
+      "epoch": 0.004450469495252345,
+      "grad_norm": 0.7431370615959167,
+      "learning_rate": 0.0001662051282051282,
+      "loss": 0.6279802799224854,
+      "step": 760
+    },
+    {
+      "epoch": 0.004509028304400402,
+      "grad_norm": 0.9329614639282227,
+      "learning_rate": 0.0001656923076923077,
+      "loss": 0.5990581512451172,
+      "step": 770
+    },
+    {
+      "epoch": 0.0045675871135484585,
+      "grad_norm": 0.6032372713088989,
+      "learning_rate": 0.00016517948717948718,
+      "loss": 0.5825644493103027,
+      "step": 780
+    },
+    {
+      "epoch": 0.004626145922696516,
+      "grad_norm": 0.6884028911590576,
+      "learning_rate": 0.00016466666666666667,
+      "loss": 0.555311632156372,
+      "step": 790
+    },
+    {
+      "epoch": 0.004684704731844573,
+      "grad_norm": 0.7366816997528076,
+      "learning_rate": 0.00016415384615384618,
+      "loss": 0.6074917793273926,
+      "step": 800
+    },
+    {
+      "epoch": 0.00474326354099263,
+      "grad_norm": 0.776561439037323,
+      "learning_rate": 0.00016364102564102567,
+      "loss": 0.5682147026062012,
+      "step": 810
+    },
+    {
+      "epoch": 0.004801822350140687,
+      "grad_norm": 0.8783098459243774,
+      "learning_rate": 0.00016312820512820515,
+      "loss": 0.6519593715667724,
+      "step": 820
+    },
+    {
+      "epoch": 0.004860381159288745,
+      "grad_norm": 0.8319303393363953,
+      "learning_rate": 0.0001626153846153846,
+      "loss": 0.6276237487792968,
+      "step": 830
+    },
+    {
+      "epoch": 0.004918939968436802,
+      "grad_norm": 0.7415748238563538,
+      "learning_rate": 0.0001621025641025641,
+      "loss": 0.6673260688781738,
+      "step": 840
+    },
+    {
+      "epoch": 0.004977498777584859,
+      "grad_norm": 1.0244334936141968,
+      "learning_rate": 0.00016158974358974359,
+      "loss": 0.6164275169372558,
+      "step": 850
+    },
+    {
+      "epoch": 0.005036057586732917,
+      "grad_norm": 1.0644179582595825,
+      "learning_rate": 0.00016107692307692307,
+      "loss": 0.5958343505859375,
+      "step": 860
+    },
+    {
+      "epoch": 0.0050946163958809736,
+      "grad_norm": 0.7661171555519104,
+      "learning_rate": 0.00016056410256410256,
+      "loss": 0.5362070083618165,
+      "step": 870
+    },
+    {
+      "epoch": 0.0051531752050290305,
+      "grad_norm": 1.014600157737732,
+      "learning_rate": 0.00016005128205128205,
+      "loss": 0.537624454498291,
+      "step": 880
+    },
+    {
+      "epoch": 0.0052117340141770874,
+      "grad_norm": 0.7331597805023193,
+      "learning_rate": 0.00015953846153846156,
+      "loss": 0.5774639129638672,
+      "step": 890
+    },
+    {
+      "epoch": 0.005270292823325145,
+      "grad_norm": 0.7434748411178589,
+      "learning_rate": 0.00015902564102564105,
+      "loss": 0.5845869064331055,
+      "step": 900
+    },
+    {
+      "epoch": 0.005328851632473202,
+      "grad_norm": 0.7248567342758179,
+      "learning_rate": 0.00015851282051282053,
+      "loss": 0.590050458908081,
+      "step": 910
+    },
+    {
+      "epoch": 0.005387410441621259,
+      "grad_norm": 0.9382026791572571,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.6036070823669434,
+      "step": 920
+    },
+    {
+      "epoch": 0.005445969250769316,
+      "grad_norm": 0.9255577325820923,
+      "learning_rate": 0.0001574871794871795,
+      "loss": 0.4737861633300781,
+      "step": 930
+    },
+    {
+      "epoch": 0.005504528059917374,
+      "grad_norm": 0.9797175526618958,
+      "learning_rate": 0.000156974358974359,
+      "loss": 0.5388136386871338,
+      "step": 940
+    },
+    {
+      "epoch": 0.005563086869065431,
+      "grad_norm": 0.7894104719161987,
+      "learning_rate": 0.00015646153846153845,
+      "loss": 0.529002571105957,
+      "step": 950
+    },
+    {
+      "epoch": 0.005621645678213488,
+      "grad_norm": 0.8898355960845947,
+      "learning_rate": 0.00015594871794871794,
+      "loss": 0.5382211685180665,
+      "step": 960
+    },
+    {
+      "epoch": 0.005680204487361545,
+      "grad_norm": 0.7389085292816162,
+      "learning_rate": 0.00015543589743589742,
+      "loss": 0.5379764080047608,
+      "step": 970
+    },
+    {
+      "epoch": 0.0057387632965096025,
+      "grad_norm": 0.8882327675819397,
+      "learning_rate": 0.00015492307692307694,
+      "loss": 0.5847358226776123,
+      "step": 980
+    },
+    {
+      "epoch": 0.005797322105657659,
+      "grad_norm": 1.1310079097747803,
+      "learning_rate": 0.00015441025641025642,
+      "loss": 0.5858294486999511,
+      "step": 990
+    },
+    {
+      "epoch": 0.005855880914805716,
+      "grad_norm": 1.0356104373931885,
+      "learning_rate": 0.0001538974358974359,
+      "loss": 0.5417033195495605,
+      "step": 1000
+    },
+    {
+      "epoch": 0.005914439723953773,
+      "grad_norm": 0.7012810707092285,
+      "learning_rate": 0.0001533846153846154,
+      "loss": 0.6806005477905274,
+      "step": 1010
+    },
+    {
+      "epoch": 0.005972998533101831,
+      "grad_norm": 0.9496027231216431,
+      "learning_rate": 0.00015287179487179488,
+      "loss": 0.521822738647461,
+      "step": 1020
+    },
+    {
+      "epoch": 0.006031557342249888,
+      "grad_norm": 0.7196470499038696,
+      "learning_rate": 0.00015235897435897437,
+      "loss": 0.5730608940124512,
+      "step": 1030
+    },
+    {
+      "epoch": 0.006090116151397945,
+      "grad_norm": 0.7311615347862244,
+      "learning_rate": 0.00015184615384615386,
+      "loss": 0.6122246742248535,
+      "step": 1040
+    },
+    {
+      "epoch": 0.006148674960546002,
+      "grad_norm": 0.7351731657981873,
+      "learning_rate": 0.00015133333333333334,
+      "loss": 0.5122735023498535,
+      "step": 1050
+    },
+    {
+      "epoch": 0.00620723376969406,
+      "grad_norm": 0.8649750351905823,
+      "learning_rate": 0.00015082051282051283,
+      "loss": 0.6370734691619873,
+      "step": 1060
+    },
+    {
+      "epoch": 0.006265792578842117,
+      "grad_norm": 0.7295814752578735,
+      "learning_rate": 0.00015030769230769232,
+      "loss": 0.5188347816467285,
+      "step": 1070
+    },
+    {
+      "epoch": 0.006324351387990174,
+      "grad_norm": 0.7717416882514954,
+      "learning_rate": 0.0001497948717948718,
+      "loss": 0.5114748001098632,
+      "step": 1080
+    },
+    {
+      "epoch": 0.006382910197138231,
+      "grad_norm": 0.5910501480102539,
+      "learning_rate": 0.0001492820512820513,
+      "loss": 0.46537189483642577,
+      "step": 1090
+    },
+    {
+      "epoch": 0.006441469006286288,
+      "grad_norm": 0.7533769011497498,
+      "learning_rate": 0.00014876923076923078,
+      "loss": 0.5796781539916992,
+      "step": 1100
+    },
+    {
+      "epoch": 0.006500027815434345,
+      "grad_norm": 0.9167582988739014,
+      "learning_rate": 0.00014825641025641026,
+      "loss": 0.6297817230224609,
+      "step": 1110
+    },
+    {
+      "epoch": 0.006558586624582402,
+      "grad_norm": 1.1386590003967285,
+      "learning_rate": 0.00014774358974358975,
+      "loss": 0.592150354385376,
+      "step": 1120
+    },
+    {
+      "epoch": 0.00661714543373046,
+      "grad_norm": 0.7550930380821228,
+      "learning_rate": 0.00014723076923076924,
+      "loss": 0.5509029865264893,
+      "step": 1130
+    },
+    {
+      "epoch": 0.006675704242878517,
+      "grad_norm": 0.6492360234260559,
+      "learning_rate": 0.00014671794871794872,
+      "loss": 0.5187190055847168,
+      "step": 1140
+    },
+    {
+      "epoch": 0.006734263052026574,
+      "grad_norm": 0.7233424782752991,
+      "learning_rate": 0.0001462051282051282,
+      "loss": 0.5804600238800048,
+      "step": 1150
+    },
+    {
+      "epoch": 0.006792821861174631,
+      "grad_norm": 1.0428144931793213,
+      "learning_rate": 0.0001456923076923077,
+      "loss": 0.5116332530975342,
+      "step": 1160
+    },
+    {
+      "epoch": 0.006851380670322689,
+      "grad_norm": 0.7919323444366455,
+      "learning_rate": 0.00014517948717948718,
+      "loss": 0.6416738986968994,
+      "step": 1170
+    },
+    {
+      "epoch": 0.006909939479470746,
+      "grad_norm": 0.8511198163032532,
+      "learning_rate": 0.0001446666666666667,
+      "loss": 0.579420518875122,
+      "step": 1180
+    },
+    {
+      "epoch": 0.0069684982886188025,
+      "grad_norm": 0.6856178641319275,
+      "learning_rate": 0.00014415384615384615,
+      "loss": 0.5805029392242431,
+      "step": 1190
+    },
+    {
+      "epoch": 0.0070270570977668595,
+      "grad_norm": 0.7397869229316711,
+      "learning_rate": 0.00014364102564102564,
+      "loss": 0.5604559898376464,
+      "step": 1200
+    },
+    {
+      "epoch": 0.007085615906914917,
+      "grad_norm": 0.7105910778045654,
+      "learning_rate": 0.00014312820512820513,
+      "loss": 0.5608997821807862,
+      "step": 1210
+    },
+    {
+      "epoch": 0.007144174716062974,
+      "grad_norm": 0.7479007244110107,
+      "learning_rate": 0.00014261538461538461,
+      "loss": 0.6052242279052734,
+      "step": 1220
+    },
+    {
+      "epoch": 0.007202733525211031,
+      "grad_norm": 1.1256407499313354,
+      "learning_rate": 0.0001421025641025641,
+      "loss": 0.6259459495544434,
+      "step": 1230
+    },
+    {
+      "epoch": 0.007261292334359088,
+      "grad_norm": 0.6991755962371826,
+      "learning_rate": 0.0001415897435897436,
+      "loss": 0.5524515151977539,
+      "step": 1240
+    },
+    {
+      "epoch": 0.007319851143507146,
+      "grad_norm": 1.053760051727295,
+      "learning_rate": 0.00014107692307692307,
+      "loss": 0.5364514827728272,
+      "step": 1250
+    },
+    {
+      "epoch": 0.007378409952655203,
+      "grad_norm": 0.983850359916687,
+      "learning_rate": 0.00014056410256410256,
+      "loss": 0.5353530883789063,
+      "step": 1260
+    },
+    {
+      "epoch": 0.00743696876180326,
+      "grad_norm": 0.6570679545402527,
+      "learning_rate": 0.00014005128205128207,
+      "loss": 0.5768649101257324,
+      "step": 1270
+    },
+    {
+      "epoch": 0.007495527570951318,
+      "grad_norm": 0.6319562792778015,
+      "learning_rate": 0.00013953846153846156,
+      "loss": 0.587717342376709,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0075540863800993745,
+      "grad_norm": 0.8129682540893555,
+      "learning_rate": 0.00013902564102564105,
+      "loss": 0.561523723602295,
+      "step": 1290
+    },
+    {
+      "epoch": 0.0076126451892474314,
+      "grad_norm": 0.884220540523529,
+      "learning_rate": 0.00013851282051282053,
+      "loss": 0.513004207611084,
+      "step": 1300
+    },
+    {
+      "epoch": 0.007671203998395488,
+      "grad_norm": 0.7594801783561707,
+      "learning_rate": 0.000138,
+      "loss": 0.5956247806549072,
+      "step": 1310
+    },
+    {
+      "epoch": 0.007729762807543546,
+      "grad_norm": 0.8838579654693604,
+      "learning_rate": 0.00013748717948717948,
+      "loss": 0.6295031547546387,
+      "step": 1320
+    },
+    {
+      "epoch": 0.007788321616691603,
+      "grad_norm": 0.7182386517524719,
+      "learning_rate": 0.00013697435897435897,
+      "loss": 0.5618526458740234,
+      "step": 1330
+    },
+    {
+      "epoch": 0.007846880425839661,
+      "grad_norm": 0.7297655940055847,
+      "learning_rate": 0.00013646153846153845,
+      "loss": 0.5208499908447266,
+      "step": 1340
+    },
+    {
+      "epoch": 0.007905439234987717,
+      "grad_norm": 0.62089604139328,
+      "learning_rate": 0.00013594871794871794,
+      "loss": 0.5239852428436279,
+      "step": 1350
+    },
+    {
+      "epoch": 0.007963998044135775,
+      "grad_norm": 0.7171675562858582,
+      "learning_rate": 0.00013543589743589745,
+      "loss": 0.5648018836975097,
+      "step": 1360
+    },
+    {
+      "epoch": 0.008022556853283831,
+      "grad_norm": 0.9089975357055664,
+      "learning_rate": 0.00013492307692307694,
+      "loss": 0.5615391254425048,
+      "step": 1370
+    },
+    {
+      "epoch": 0.008081115662431889,
+      "grad_norm": 0.7600458860397339,
+      "learning_rate": 0.00013441025641025643,
+      "loss": 0.604154634475708,
+      "step": 1380
+    },
+    {
+      "epoch": 0.008139674471579946,
+      "grad_norm": 0.7462561726570129,
+      "learning_rate": 0.0001338974358974359,
+      "loss": 0.6301332950592041,
+      "step": 1390
+    },
+    {
+      "epoch": 0.008198233280728003,
+      "grad_norm": 0.7292648553848267,
+      "learning_rate": 0.0001333846153846154,
+      "loss": 0.5153694152832031,
+      "step": 1400
+    },
+    {
+      "epoch": 0.00825679208987606,
+      "grad_norm": 0.8180534243583679,
+      "learning_rate": 0.00013287179487179489,
+      "loss": 0.647784423828125,
+      "step": 1410
+    },
+    {
+      "epoch": 0.008315350899024118,
+      "grad_norm": 0.6629355549812317,
+      "learning_rate": 0.00013235897435897437,
+      "loss": 0.5387883186340332,
+      "step": 1420
+    },
+    {
+      "epoch": 0.008373909708172174,
+      "grad_norm": 1.1468173265457153,
+      "learning_rate": 0.00013184615384615383,
+      "loss": 0.6159374713897705,
+      "step": 1430
+    },
+    {
+      "epoch": 0.008432468517320232,
+      "grad_norm": 0.9131197929382324,
+      "learning_rate": 0.00013133333333333332,
+      "loss": 0.5780044078826905,
+      "step": 1440
+    },
+    {
+      "epoch": 0.008491027326468288,
+      "grad_norm": 0.8688338398933411,
+      "learning_rate": 0.00013082051282051283,
+      "loss": 0.5893913745880127,
+      "step": 1450
+    },
+    {
+      "epoch": 0.008549586135616346,
+      "grad_norm": 0.6430419683456421,
+      "learning_rate": 0.00013030769230769232,
+      "loss": 0.5053946495056152,
+      "step": 1460
+    },
+    {
+      "epoch": 0.008608144944764404,
+      "grad_norm": 0.81430584192276,
+      "learning_rate": 0.0001297948717948718,
+      "loss": 0.587185287475586,
+      "step": 1470
+    },
+    {
+      "epoch": 0.00866670375391246,
+      "grad_norm": 0.7069384455680847,
+      "learning_rate": 0.0001292820512820513,
+      "loss": 0.6119993686676025,
+      "step": 1480
+    },
+    {
+      "epoch": 0.008725262563060518,
+      "grad_norm": 0.8512614965438843,
+      "learning_rate": 0.00012876923076923078,
+      "loss": 0.5506554126739502,
+      "step": 1490
+    },
+    {
+      "epoch": 0.008783821372208575,
+      "grad_norm": 0.6660640835762024,
+      "learning_rate": 0.00012825641025641026,
+      "loss": 0.5566682338714599,
+      "step": 1500
+    },
+    {
+      "epoch": 0.008842380181356631,
+      "grad_norm": 0.7649056315422058,
+      "learning_rate": 0.00012774358974358975,
+      "loss": 0.5694420814514161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.00890093899050469,
+      "grad_norm": 0.909599781036377,
+      "learning_rate": 0.00012723076923076924,
+      "loss": 0.6355206489562988,
+      "step": 1520
+    },
+    {
+      "epoch": 0.008959497799652747,
+      "grad_norm": 0.7873692512512207,
+      "learning_rate": 0.00012671794871794872,
+      "loss": 0.510439395904541,
+      "step": 1530
+    },
+    {
+      "epoch": 0.009018056608800803,
+      "grad_norm": 0.7628417611122131,
+      "learning_rate": 0.0001262051282051282,
+      "loss": 0.5399933338165284,
+      "step": 1540
+    },
+    {
+      "epoch": 0.009076615417948861,
+      "grad_norm": 0.8505508899688721,
+      "learning_rate": 0.0001256923076923077,
+      "loss": 0.6154933452606202,
+      "step": 1550
+    },
+    {
+      "epoch": 0.009135174227096917,
+      "grad_norm": 0.794605553150177,
+      "learning_rate": 0.00012517948717948718,
+      "loss": 0.6099573612213135,
+      "step": 1560
+    },
+    {
+      "epoch": 0.009193733036244975,
+      "grad_norm": 0.818773090839386,
+      "learning_rate": 0.00012466666666666667,
+      "loss": 0.5245619297027588,
+      "step": 1570
+    },
+    {
+      "epoch": 0.009252291845393033,
+      "grad_norm": 0.6100147366523743,
+      "learning_rate": 0.00012415384615384616,
+      "loss": 0.5743139743804931,
+      "step": 1580
+    },
+    {
+      "epoch": 0.009310850654541089,
+      "grad_norm": 0.911518394947052,
+      "learning_rate": 0.00012364102564102564,
+      "loss": 0.5403082370758057,
+      "step": 1590
+    },
+    {
+      "epoch": 0.009369409463689147,
+      "grad_norm": 0.7002453804016113,
+      "learning_rate": 0.00012312820512820513,
+      "loss": 0.5670140743255615,
+      "step": 1600
+    },
+    {
+      "epoch": 0.009427968272837204,
+      "grad_norm": 0.6926924586296082,
+      "learning_rate": 0.00012261538461538462,
+      "loss": 0.5283169746398926,
+      "step": 1610
+    },
+    {
+      "epoch": 0.00948652708198526,
+      "grad_norm": 0.8910185098648071,
+      "learning_rate": 0.0001221025641025641,
+      "loss": 0.5464873313903809,
+      "step": 1620
+    },
+    {
+      "epoch": 0.009545085891133318,
+      "grad_norm": 0.9428623914718628,
+      "learning_rate": 0.0001215897435897436,
+      "loss": 0.6371686935424805,
+      "step": 1630
+    },
+    {
+      "epoch": 0.009603644700281374,
+      "grad_norm": 0.9594399333000183,
+      "learning_rate": 0.00012107692307692309,
+      "loss": 0.5639693737030029,
+      "step": 1640
+    },
+    {
+      "epoch": 0.009662203509429432,
+      "grad_norm": 0.9431197643280029,
+      "learning_rate": 0.00012056410256410258,
+      "loss": 0.4942180633544922,
+      "step": 1650
+    },
+    {
+      "epoch": 0.00972076231857749,
+      "grad_norm": 0.778407096862793,
+      "learning_rate": 0.00012005128205128206,
+      "loss": 0.5874770641326904,
+      "step": 1660
+    },
+    {
+      "epoch": 0.009779321127725546,
+      "grad_norm": 0.7874659299850464,
+      "learning_rate": 0.00011953846153846155,
+      "loss": 0.5451854228973388,
+      "step": 1670
+    },
+    {
+      "epoch": 0.009837879936873604,
+      "grad_norm": 0.7366560697555542,
+      "learning_rate": 0.00011902564102564102,
+      "loss": 0.5593300342559815,
+      "step": 1680
+    },
+    {
+      "epoch": 0.009896438746021662,
+      "grad_norm": 0.762984573841095,
+      "learning_rate": 0.00011851282051282051,
+      "loss": 0.571781587600708,
+      "step": 1690
+    },
+    {
+      "epoch": 0.009954997555169718,
+      "grad_norm": 0.7820915579795837,
+      "learning_rate": 0.000118,
+      "loss": 0.6361937522888184,
+      "step": 1700
+    },
+    {
+      "epoch": 0.010013556364317775,
+      "grad_norm": 0.885874330997467,
+      "learning_rate": 0.0001174871794871795,
+      "loss": 0.5583993911743164,
+      "step": 1710
+    },
+    {
+      "epoch": 0.010072115173465833,
+      "grad_norm": 0.7336756587028503,
+      "learning_rate": 0.00011697435897435898,
+      "loss": 0.5345401763916016,
+      "step": 1720
+    },
+    {
+      "epoch": 0.01013067398261389,
+      "grad_norm": 1.1266441345214844,
+      "learning_rate": 0.00011646153846153847,
+      "loss": 0.5590295314788818,
+      "step": 1730
+    },
+    {
+      "epoch": 0.010189232791761947,
+      "grad_norm": 0.6986821889877319,
+      "learning_rate": 0.00011594871794871795,
+      "loss": 0.626862907409668,
+      "step": 1740
+    },
+    {
+      "epoch": 0.010247791600910003,
+      "grad_norm": 0.6808388233184814,
+      "learning_rate": 0.00011543589743589744,
+      "loss": 0.45256743431091306,
+      "step": 1750
+    },
+    {
+      "epoch": 0.010306350410058061,
+      "grad_norm": 0.8917853236198425,
+      "learning_rate": 0.00011492307692307693,
+      "loss": 0.5677892684936523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.010364909219206119,
+      "grad_norm": 0.84018474817276,
+      "learning_rate": 0.00011441025641025643,
+      "loss": 0.6715295314788818,
+      "step": 1770
+    },
+    {
+      "epoch": 0.010423468028354175,
+      "grad_norm": 0.8711966276168823,
+      "learning_rate": 0.00011389743589743591,
+      "loss": 0.49718570709228516,
+      "step": 1780
+    },
+    {
+      "epoch": 0.010482026837502233,
+      "grad_norm": 0.8351517915725708,
+      "learning_rate": 0.0001133846153846154,
+      "loss": 0.5668165683746338,
+      "step": 1790
+    },
+    {
+      "epoch": 0.01054058564665029,
+      "grad_norm": 0.9627017378807068,
+      "learning_rate": 0.00011287179487179486,
+      "loss": 0.5853204727172852,
+      "step": 1800
+    },
+    {
+      "epoch": 0.010599144455798347,
+      "grad_norm": 0.642246425151825,
+      "learning_rate": 0.00011235897435897436,
+      "loss": 0.5551766872406005,
+      "step": 1810
+    },
+    {
+      "epoch": 0.010657703264946404,
+      "grad_norm": 0.9542229771614075,
+      "learning_rate": 0.00011184615384615385,
+      "loss": 0.6531394958496094,
+      "step": 1820
+    },
+    {
+      "epoch": 0.01071626207409446,
+      "grad_norm": 0.7595056891441345,
+      "learning_rate": 0.00011133333333333333,
+      "loss": 0.5438894748687744,
+      "step": 1830
+    },
+    {
+      "epoch": 0.010774820883242518,
+      "grad_norm": 0.8346898555755615,
+      "learning_rate": 0.00011082051282051282,
+      "loss": 0.516790771484375,
+      "step": 1840
+    },
+    {
+      "epoch": 0.010833379692390576,
+      "grad_norm": 0.7261139750480652,
+      "learning_rate": 0.0001103076923076923,
+      "loss": 0.5511853694915771,
+      "step": 1850
+    },
+    {
+      "epoch": 0.010891938501538632,
+      "grad_norm": 0.7773726582527161,
+      "learning_rate": 0.0001097948717948718,
+      "loss": 0.6048900604248046,
+      "step": 1860
+    },
+    {
+      "epoch": 0.01095049731068669,
+      "grad_norm": 0.7758798599243164,
+      "learning_rate": 0.00010928205128205129,
+      "loss": 0.4920170783996582,
+      "step": 1870
+    },
+    {
+      "epoch": 0.011009056119834748,
+      "grad_norm": 0.7595053315162659,
+      "learning_rate": 0.00010876923076923078,
+      "loss": 0.5262623786926269,
+      "step": 1880
+    },
+    {
+      "epoch": 0.011067614928982804,
+      "grad_norm": 0.662896454334259,
+      "learning_rate": 0.00010825641025641027,
+      "loss": 0.5706700325012207,
+      "step": 1890
+    },
+    {
+      "epoch": 0.011126173738130862,
+      "grad_norm": 0.8547627329826355,
+      "learning_rate": 0.00010774358974358975,
+      "loss": 0.5571642398834229,
+      "step": 1900
+    },
+    {
+      "epoch": 0.011184732547278918,
+      "grad_norm": 0.9618740081787109,
+      "learning_rate": 0.00010723076923076924,
+      "loss": 0.5785984039306641,
+      "step": 1910
+    },
+    {
+      "epoch": 0.011243291356426975,
+      "grad_norm": 0.8090870976448059,
+      "learning_rate": 0.00010671794871794871,
+      "loss": 0.6467090606689453,
+      "step": 1920
+    },
+    {
+      "epoch": 0.011301850165575033,
+      "grad_norm": 0.8532423377037048,
+      "learning_rate": 0.0001062051282051282,
+      "loss": 0.5037952423095703,
+      "step": 1930
+    },
+    {
+      "epoch": 0.01136040897472309,
+      "grad_norm": 0.8701047897338867,
+      "learning_rate": 0.00010569230769230769,
+      "loss": 0.6252214908599854,
+      "step": 1940
+    },
+    {
+      "epoch": 0.011418967783871147,
+      "grad_norm": 0.8058343529701233,
+      "learning_rate": 0.00010517948717948719,
+      "loss": 0.49949493408203127,
+      "step": 1950
+    },
+    {
+      "epoch": 0.011477526593019205,
+      "grad_norm": 0.7899404764175415,
+      "learning_rate": 0.00010466666666666667,
+      "loss": 0.5413167476654053,
+      "step": 1960
+    },
+    {
+      "epoch": 0.011536085402167261,
+      "grad_norm": 0.7027344107627869,
+      "learning_rate": 0.00010415384615384616,
+      "loss": 0.45540223121643064,
+      "step": 1970
+    },
+    {
+      "epoch": 0.011594644211315319,
+      "grad_norm": 0.8737793564796448,
+      "learning_rate": 0.00010364102564102565,
+      "loss": 0.5688265800476074,
+      "step": 1980
+    },
+    {
+      "epoch": 0.011653203020463377,
+      "grad_norm": 0.9242916703224182,
+      "learning_rate": 0.00010312820512820513,
+      "loss": 0.5170233726501465,
+      "step": 1990
+    },
+    {
+      "epoch": 0.011711761829611433,
+      "grad_norm": 0.6759135127067566,
+      "learning_rate": 0.00010261538461538462,
+      "loss": 0.6288806438446045,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01177032063875949,
+      "grad_norm": 0.7091163396835327,
+      "learning_rate": 0.00010210256410256412,
+      "loss": 0.5844020843505859,
+      "step": 2010
+    },
+    {
+      "epoch": 0.011828879447907547,
+      "grad_norm": 0.9295818209648132,
+      "learning_rate": 0.0001015897435897436,
+      "loss": 0.5282711982727051,
+      "step": 2020
+    },
+    {
+      "epoch": 0.011887438257055604,
+      "grad_norm": 0.6938250064849854,
+      "learning_rate": 0.00010107692307692309,
+      "loss": 0.6149167537689209,
+      "step": 2030
+    },
+    {
+      "epoch": 0.011945997066203662,
+      "grad_norm": 0.7174298763275146,
+      "learning_rate": 0.00010056410256410256,
+      "loss": 0.5130744934082031,
+      "step": 2040
+    },
+    {
+      "epoch": 0.012004555875351718,
+      "grad_norm": 0.9726197123527527,
+      "learning_rate": 0.00010005128205128205,
+      "loss": 0.6236517429351807,
+      "step": 2050
+    },
+    {
+      "epoch": 0.012063114684499776,
+      "grad_norm": 0.7376599311828613,
+      "learning_rate": 9.953846153846155e-05,
+      "loss": 0.4681741714477539,
+      "step": 2060
+    },
+    {
+      "epoch": 0.012121673493647834,
+      "grad_norm": 0.8139657378196716,
+      "learning_rate": 9.902564102564102e-05,
+      "loss": 0.4887677192687988,
+      "step": 2070
+    },
+    {
+      "epoch": 0.01218023230279589,
+      "grad_norm": 0.9429419636726379,
+      "learning_rate": 9.851282051282051e-05,
+      "loss": 0.5326910018920898,
+      "step": 2080
+    },
+    {
+      "epoch": 0.012238791111943948,
+      "grad_norm": 0.9702481627464294,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5095866680145263,
+      "step": 2090
+    },
+    {
+      "epoch": 0.012297349921092004,
+      "grad_norm": 0.6909214854240417,
+      "learning_rate": 9.74871794871795e-05,
+      "loss": 0.5370609283447265,
+      "step": 2100
+    },
+    {
+      "epoch": 0.012355908730240062,
+      "grad_norm": 1.2493647336959839,
+      "learning_rate": 9.697435897435898e-05,
+      "loss": 0.5658076763153076,
+      "step": 2110
+    },
+    {
+      "epoch": 0.01241446753938812,
+      "grad_norm": 0.7158144116401672,
+      "learning_rate": 9.646153846153847e-05,
+      "loss": 0.5293547153472901,
+      "step": 2120
+    },
+    {
+      "epoch": 0.012473026348536176,
+      "grad_norm": 0.8394598364830017,
+      "learning_rate": 9.594871794871796e-05,
+      "loss": 0.48808741569519043,
+      "step": 2130
+    },
+    {
+      "epoch": 0.012531585157684233,
+      "grad_norm": 0.9504506587982178,
+      "learning_rate": 9.543589743589744e-05,
+      "loss": 0.5906731605529785,
+      "step": 2140
+    },
+    {
+      "epoch": 0.012590143966832291,
+      "grad_norm": 0.7592800855636597,
+      "learning_rate": 9.492307692307693e-05,
+      "loss": 0.5167060852050781,
+      "step": 2150
+    },
+    {
+      "epoch": 0.012648702775980347,
+      "grad_norm": 0.8858376145362854,
+      "learning_rate": 9.441025641025642e-05,
+      "loss": 0.5447789669036865,
+      "step": 2160
+    },
+    {
+      "epoch": 0.012707261585128405,
+      "grad_norm": 0.8264896273612976,
+      "learning_rate": 9.38974358974359e-05,
+      "loss": 0.4619621753692627,
+      "step": 2170
+    },
+    {
+      "epoch": 0.012765820394276463,
+      "grad_norm": 0.7801193594932556,
+      "learning_rate": 9.338461538461539e-05,
+      "loss": 0.5282919883728028,
+      "step": 2180
+    },
+    {
+      "epoch": 0.012824379203424519,
+      "grad_norm": 0.7734062671661377,
+      "learning_rate": 9.287179487179488e-05,
+      "loss": 0.6420894622802734,
+      "step": 2190
+    },
+    {
+      "epoch": 0.012882938012572577,
+      "grad_norm": 0.844348132610321,
+      "learning_rate": 9.235897435897436e-05,
+      "loss": 0.602821159362793,
+      "step": 2200
+    },
+    {
+      "epoch": 0.012941496821720633,
+      "grad_norm": 0.8861480355262756,
+      "learning_rate": 9.184615384615385e-05,
+      "loss": 0.5366893291473389,
+      "step": 2210
+    },
+    {
+      "epoch": 0.01300005563086869,
+      "grad_norm": 0.8071720600128174,
+      "learning_rate": 9.133333333333334e-05,
+      "loss": 0.4816866874694824,
+      "step": 2220
+    },
+    {
+      "epoch": 0.013058614440016748,
+      "grad_norm": 0.7975764870643616,
+      "learning_rate": 9.082051282051282e-05,
+      "loss": 0.6320478439331054,
+      "step": 2230
+    },
+    {
+      "epoch": 0.013117173249164804,
+      "grad_norm": 0.7712560296058655,
+      "learning_rate": 9.030769230769232e-05,
+      "loss": 0.607432746887207,
+      "step": 2240
+    },
+    {
+      "epoch": 0.013175732058312862,
+      "grad_norm": 0.7562223076820374,
+      "learning_rate": 8.979487179487181e-05,
+      "loss": 0.4568962097167969,
+      "step": 2250
+    },
+    {
+      "epoch": 0.01323429086746092,
+      "grad_norm": 0.7949206233024597,
+      "learning_rate": 8.928205128205128e-05,
+      "loss": 0.5890951156616211,
+      "step": 2260
+    },
+    {
+      "epoch": 0.013292849676608976,
+      "grad_norm": 0.8863471150398254,
+      "learning_rate": 8.876923076923077e-05,
+      "loss": 0.4792426109313965,
+      "step": 2270
+    },
+    {
+      "epoch": 0.013351408485757034,
+      "grad_norm": 0.9258952736854553,
+      "learning_rate": 8.825641025641025e-05,
+      "loss": 0.6157923698425293,
+      "step": 2280
+    },
+    {
+      "epoch": 0.01340996729490509,
+      "grad_norm": 0.7849915027618408,
+      "learning_rate": 8.774358974358975e-05,
+      "loss": 0.5654351234436035,
+      "step": 2290
+    },
+    {
+      "epoch": 0.013468526104053148,
+      "grad_norm": 0.7935325503349304,
+      "learning_rate": 8.723076923076924e-05,
+      "loss": 0.5722135543823242,
+      "step": 2300
+    },
+    {
+      "epoch": 0.013527084913201206,
+      "grad_norm": 0.8465309739112854,
+      "learning_rate": 8.671794871794873e-05,
+      "loss": 0.5128249645233154,
+      "step": 2310
+    },
+    {
+      "epoch": 0.013585643722349262,
+      "grad_norm": 0.8264815211296082,
+      "learning_rate": 8.62051282051282e-05,
+      "loss": 0.6118460655212402,
+      "step": 2320
+    },
+    {
+      "epoch": 0.01364420253149732,
+      "grad_norm": 0.6705726385116577,
+      "learning_rate": 8.56923076923077e-05,
+      "loss": 0.5447952747344971,
+      "step": 2330
+    },
+    {
+      "epoch": 0.013702761340645377,
+      "grad_norm": 0.921404242515564,
+      "learning_rate": 8.517948717948719e-05,
+      "loss": 0.542200756072998,
+      "step": 2340
+    },
+    {
+      "epoch": 0.013761320149793433,
+      "grad_norm": 0.5786399245262146,
+      "learning_rate": 8.466666666666667e-05,
+      "loss": 0.5167455673217773,
+      "step": 2350
+    },
+    {
+      "epoch": 0.013819878958941491,
+      "grad_norm": 0.8080707788467407,
+      "learning_rate": 8.415384615384616e-05,
+      "loss": 0.495404052734375,
+      "step": 2360
+    },
+    {
+      "epoch": 0.013878437768089549,
+      "grad_norm": 0.7522940635681152,
+      "learning_rate": 8.364102564102565e-05,
+      "loss": 0.5303984165191651,
+      "step": 2370
+    },
+    {
+      "epoch": 0.013936996577237605,
+      "grad_norm": 0.9101510643959045,
+      "learning_rate": 8.312820512820513e-05,
+      "loss": 0.5638332843780518,
+      "step": 2380
+    },
+    {
+      "epoch": 0.013995555386385663,
+      "grad_norm": 0.6749529838562012,
+      "learning_rate": 8.261538461538462e-05,
+      "loss": 0.5651543617248536,
+      "step": 2390
+    },
+    {
+      "epoch": 0.014054114195533719,
+      "grad_norm": 0.9458379149436951,
+      "learning_rate": 8.21025641025641e-05,
+      "loss": 0.5108407497406006,
+      "step": 2400
+    },
+    {
+      "epoch": 0.014112673004681777,
+      "grad_norm": 1.089971899986267,
+      "learning_rate": 8.158974358974359e-05,
+      "loss": 0.49324331283569334,
+      "step": 2410
+    },
+    {
+      "epoch": 0.014171231813829835,
+      "grad_norm": 0.7607450485229492,
+      "learning_rate": 8.107692307692308e-05,
+      "loss": 0.6479440212249756,
+      "step": 2420
+    },
+    {
+      "epoch": 0.01422979062297789,
+      "grad_norm": 0.9622839093208313,
+      "learning_rate": 8.056410256410257e-05,
+      "loss": 0.5628427982330322,
+      "step": 2430
+    },
+    {
+      "epoch": 0.014288349432125948,
+      "grad_norm": 0.8064730167388916,
+      "learning_rate": 8.005128205128205e-05,
+      "loss": 0.4927206993103027,
+      "step": 2440
+    },
+    {
+      "epoch": 0.014346908241274006,
+      "grad_norm": 0.7792487144470215,
+      "learning_rate": 7.953846153846154e-05,
+      "loss": 0.6291625022888183,
+      "step": 2450
+    },
+    {
+      "epoch": 0.014405467050422062,
+      "grad_norm": 1.0805375576019287,
+      "learning_rate": 7.902564102564103e-05,
+      "loss": 0.5925718307495117,
+      "step": 2460
+    },
+    {
+      "epoch": 0.01446402585957012,
+      "grad_norm": 0.5765560865402222,
+      "learning_rate": 7.851282051282051e-05,
+      "loss": 0.5485690593719482,
+      "step": 2470
+    },
+    {
+      "epoch": 0.014522584668718176,
+      "grad_norm": 0.8152871131896973,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.5624689102172852,
+      "step": 2480
+    },
+    {
+      "epoch": 0.014581143477866234,
+      "grad_norm": 0.8335279226303101,
+      "learning_rate": 7.74871794871795e-05,
+      "loss": 0.5260688304901123,
+      "step": 2490
+    },
+    {
+      "epoch": 0.014639702287014292,
+      "grad_norm": 0.7680035829544067,
+      "learning_rate": 7.697435897435897e-05,
+      "loss": 0.4830802917480469,
+      "step": 2500
+    },
+    {
+      "epoch": 0.014698261096162348,
+      "grad_norm": 0.9397810697555542,
+      "learning_rate": 7.646153846153846e-05,
+      "loss": 0.5444638729095459,
+      "step": 2510
+    },
+    {
+      "epoch": 0.014756819905310406,
+      "grad_norm": 0.7944267392158508,
+      "learning_rate": 7.594871794871794e-05,
+      "loss": 0.6039426326751709,
+      "step": 2520
+    },
+    {
+      "epoch": 0.014815378714458463,
+      "grad_norm": 0.8528501987457275,
+      "learning_rate": 7.543589743589744e-05,
+      "loss": 0.5764337539672851,
+      "step": 2530
+    },
+    {
+      "epoch": 0.01487393752360652,
+      "grad_norm": 0.9321673512458801,
+      "learning_rate": 7.492307692307693e-05,
+      "loss": 0.5600544929504394,
+      "step": 2540
+    },
+    {
+      "epoch": 0.014932496332754577,
+      "grad_norm": 0.8647655248641968,
+      "learning_rate": 7.441025641025642e-05,
+      "loss": 0.6365120887756348,
+      "step": 2550
+    },
+    {
+      "epoch": 0.014991055141902635,
+      "grad_norm": 0.9241213798522949,
+      "learning_rate": 7.389743589743589e-05,
+      "loss": 0.5070790767669677,
+      "step": 2560
+    },
+    {
+      "epoch": 0.015049613951050691,
+      "grad_norm": 0.6943749785423279,
+      "learning_rate": 7.338461538461539e-05,
+      "loss": 0.5472688674926758,
+      "step": 2570
+    },
+    {
+      "epoch": 0.015108172760198749,
+      "grad_norm": 0.7544350624084473,
+      "learning_rate": 7.287179487179488e-05,
+      "loss": 0.5143001079559326,
+      "step": 2580
+    },
+    {
+      "epoch": 0.015166731569346805,
+      "grad_norm": 0.8759540319442749,
+      "learning_rate": 7.235897435897436e-05,
+      "loss": 0.5885789871215821,
+      "step": 2590
+    },
+    {
+      "epoch": 0.015225290378494863,
+      "grad_norm": 0.8004186153411865,
+      "learning_rate": 7.184615384615385e-05,
+      "loss": 0.5833802223205566,
+      "step": 2600
+    },
+    {
+      "epoch": 0.01528384918764292,
+      "grad_norm": 0.8919973969459534,
+      "learning_rate": 7.133333333333334e-05,
+      "loss": 0.7211344242095947,
+      "step": 2610
+    },
+    {
+      "epoch": 0.015342407996790977,
+      "grad_norm": 0.6915315985679626,
+      "learning_rate": 7.082051282051282e-05,
+      "loss": 0.5526168823242188,
+      "step": 2620
+    },
+    {
+      "epoch": 0.015400966805939035,
+      "grad_norm": 0.9145429134368896,
+      "learning_rate": 7.030769230769231e-05,
+      "loss": 0.4407088279724121,
+      "step": 2630
+    },
+    {
+      "epoch": 0.015459525615087092,
+      "grad_norm": 0.674967885017395,
+      "learning_rate": 6.97948717948718e-05,
+      "loss": 0.4634512424468994,
+      "step": 2640
+    },
+    {
+      "epoch": 0.015518084424235148,
+      "grad_norm": 0.6875638365745544,
+      "learning_rate": 6.928205128205128e-05,
+      "loss": 0.47414402961730956,
+      "step": 2650
+    },
+    {
+      "epoch": 0.015576643233383206,
+      "grad_norm": 0.9719008803367615,
+      "learning_rate": 6.876923076923077e-05,
+      "loss": 0.5467365264892579,
+      "step": 2660
+    },
+    {
+      "epoch": 0.015635202042531264,
+      "grad_norm": 0.7496704459190369,
+      "learning_rate": 6.825641025641027e-05,
+      "loss": 0.5100692749023438,
+      "step": 2670
+    },
+    {
+      "epoch": 0.015693760851679322,
+      "grad_norm": 0.6996882557868958,
+      "learning_rate": 6.774358974358974e-05,
+      "loss": 0.5840377330780029,
+      "step": 2680
+    },
+    {
+      "epoch": 0.015752319660827376,
+      "grad_norm": 0.8965880274772644,
+      "learning_rate": 6.723076923076923e-05,
+      "loss": 0.5683030605316162,
+      "step": 2690
+    },
+    {
+      "epoch": 0.015810878469975434,
+      "grad_norm": 0.9862522482872009,
+      "learning_rate": 6.671794871794872e-05,
+      "loss": 0.5894110679626465,
+      "step": 2700
+    },
+    {
+      "epoch": 0.015869437279123492,
+      "grad_norm": 0.9664445519447327,
+      "learning_rate": 6.62051282051282e-05,
+      "loss": 0.5402120590209961,
+      "step": 2710
+    },
+    {
+      "epoch": 0.01592799608827155,
+      "grad_norm": 0.8799305558204651,
+      "learning_rate": 6.56923076923077e-05,
+      "loss": 0.5548243045806884,
+      "step": 2720
+    },
+    {
+      "epoch": 0.015986554897419607,
+      "grad_norm": 0.6217681169509888,
+      "learning_rate": 6.517948717948719e-05,
+      "loss": 0.48618650436401367,
+      "step": 2730
+    },
+    {
+      "epoch": 0.016045113706567662,
+      "grad_norm": 0.7473154664039612,
+      "learning_rate": 6.466666666666666e-05,
+      "loss": 0.5558083057403564,
+      "step": 2740
+    },
+    {
+      "epoch": 0.01610367251571572,
+      "grad_norm": 0.8467188477516174,
+      "learning_rate": 6.415384615384615e-05,
+      "loss": 0.5468488216400147,
+      "step": 2750
+    },
+    {
+      "epoch": 0.016162231324863777,
+      "grad_norm": 0.8353908658027649,
+      "learning_rate": 6.364102564102565e-05,
+      "loss": 0.55488600730896,
+      "step": 2760
+    },
+    {
+      "epoch": 0.016220790134011835,
+      "grad_norm": 1.0089359283447266,
+      "learning_rate": 6.312820512820514e-05,
+      "loss": 0.4439121723175049,
+      "step": 2770
+    },
+    {
+      "epoch": 0.016279348943159893,
+      "grad_norm": 0.8033394813537598,
+      "learning_rate": 6.261538461538462e-05,
+      "loss": 0.592630672454834,
+      "step": 2780
+    },
+    {
+      "epoch": 0.01633790775230795,
+      "grad_norm": 0.7081058621406555,
+      "learning_rate": 6.210256410256411e-05,
+      "loss": 0.5640474319458008,
+      "step": 2790
+    },
+    {
+      "epoch": 0.016396466561456005,
+      "grad_norm": 0.9237245321273804,
+      "learning_rate": 6.15897435897436e-05,
+      "loss": 0.6005640983581543,
+      "step": 2800
+    },
+    {
+      "epoch": 0.016455025370604063,
+      "grad_norm": 0.8360455632209778,
+      "learning_rate": 6.107692307692308e-05,
+      "loss": 0.5373104572296142,
+      "step": 2810
+    },
+    {
+      "epoch": 0.01651358417975212,
+      "grad_norm": 0.8988027572631836,
+      "learning_rate": 6.056410256410257e-05,
+      "loss": 0.5758774757385254,
+      "step": 2820
+    },
+    {
+      "epoch": 0.01657214298890018,
+      "grad_norm": 0.9521508812904358,
+      "learning_rate": 6.0051282051282054e-05,
+      "loss": 0.5425063133239746,
+      "step": 2830
+    },
+    {
+      "epoch": 0.016630701798048236,
+      "grad_norm": 1.0230766534805298,
+      "learning_rate": 5.953846153846154e-05,
+      "loss": 0.617734146118164,
+      "step": 2840
+    },
+    {
+      "epoch": 0.01668926060719629,
+      "grad_norm": 0.8182085752487183,
+      "learning_rate": 5.9025641025641034e-05,
+      "loss": 0.49785604476928713,
+      "step": 2850
+    },
+    {
+      "epoch": 0.01674781941634435,
+      "grad_norm": 0.819509744644165,
+      "learning_rate": 5.851282051282052e-05,
+      "loss": 0.5303618907928467,
+      "step": 2860
+    },
+    {
+      "epoch": 0.016806378225492406,
+      "grad_norm": 0.9338365197181702,
+      "learning_rate": 5.8e-05,
+      "loss": 0.5084160327911377,
+      "step": 2870
+    },
+    {
+      "epoch": 0.016864937034640464,
+      "grad_norm": 0.9572207927703857,
+      "learning_rate": 5.748717948717949e-05,
+      "loss": 0.5966866493225098,
+      "step": 2880
+    },
+    {
+      "epoch": 0.016923495843788522,
+      "grad_norm": 0.66383296251297,
+      "learning_rate": 5.6974358974358973e-05,
+      "loss": 0.5305398941040039,
+      "step": 2890
+    },
+    {
+      "epoch": 0.016982054652936576,
+      "grad_norm": 1.0674878358840942,
+      "learning_rate": 5.646153846153847e-05,
+      "loss": 0.556536340713501,
+      "step": 2900
+    },
+    {
+      "epoch": 0.017040613462084634,
+      "grad_norm": 0.7483784556388855,
+      "learning_rate": 5.594871794871795e-05,
+      "loss": 0.49668869972229,
+      "step": 2910
+    },
+    {
+      "epoch": 0.017099172271232692,
+      "grad_norm": 1.0706493854522705,
+      "learning_rate": 5.5435897435897447e-05,
+      "loss": 0.49158105850219724,
+      "step": 2920
+    },
+    {
+      "epoch": 0.01715773108038075,
+      "grad_norm": 0.7071096897125244,
+      "learning_rate": 5.492307692307692e-05,
+      "loss": 0.5811544895172119,
+      "step": 2930
+    },
+    {
+      "epoch": 0.017216289889528807,
+      "grad_norm": 0.8249266147613525,
+      "learning_rate": 5.441025641025641e-05,
+      "loss": 0.5450833797454834,
+      "step": 2940
+    },
+    {
+      "epoch": 0.017274848698676865,
+      "grad_norm": 0.684613823890686,
+      "learning_rate": 5.38974358974359e-05,
+      "loss": 0.5169521808624268,
+      "step": 2950
+    },
+    {
+      "epoch": 0.01733340750782492,
+      "grad_norm": 1.1294605731964111,
+      "learning_rate": 5.3384615384615386e-05,
+      "loss": 0.6362704277038574,
+      "step": 2960
+    },
+    {
+      "epoch": 0.017391966316972977,
+      "grad_norm": 0.7923810482025146,
+      "learning_rate": 5.287179487179488e-05,
+      "loss": 0.498931360244751,
+      "step": 2970
+    },
+    {
+      "epoch": 0.017450525126121035,
+      "grad_norm": 0.8153409957885742,
+      "learning_rate": 5.2358974358974366e-05,
+      "loss": 0.5227402687072754,
+      "step": 2980
+    },
+    {
+      "epoch": 0.017509083935269093,
+      "grad_norm": 0.8139829635620117,
+      "learning_rate": 5.1846153846153845e-05,
+      "loss": 0.5427112102508544,
+      "step": 2990
+    },
+    {
+      "epoch": 0.01756764274441715,
+      "grad_norm": 0.7023552060127258,
+      "learning_rate": 5.133333333333333e-05,
+      "loss": 0.5183414459228516,
+      "step": 3000
+    },
+    {
+      "epoch": 0.017626201553565205,
+      "grad_norm": 1.1172661781311035,
+      "learning_rate": 5.0820512820512825e-05,
+      "loss": 0.5479337692260742,
+      "step": 3010
+    },
+    {
+      "epoch": 0.017684760362713263,
+      "grad_norm": 0.9706581234931946,
+      "learning_rate": 5.030769230769231e-05,
+      "loss": 0.5230507373809814,
+      "step": 3020
+    },
+    {
+      "epoch": 0.01774331917186132,
+      "grad_norm": 0.9869327545166016,
+      "learning_rate": 4.979487179487179e-05,
+      "loss": 0.5095770359039307,
+      "step": 3030
+    },
+    {
+      "epoch": 0.01780187798100938,
+      "grad_norm": 1.0374623537063599,
+      "learning_rate": 4.9282051282051285e-05,
+      "loss": 0.5869725704193115,
+      "step": 3040
+    },
+    {
+      "epoch": 0.017860436790157436,
+      "grad_norm": 1.1641126871109009,
+      "learning_rate": 4.876923076923077e-05,
+      "loss": 0.6153728008270264,
+      "step": 3050
+    },
+    {
+      "epoch": 0.017918995599305494,
+      "grad_norm": 0.9592261910438538,
+      "learning_rate": 4.825641025641026e-05,
+      "loss": 0.4673551082611084,
+      "step": 3060
+    },
+    {
+      "epoch": 0.01797755440845355,
+      "grad_norm": 0.9529333114624023,
+      "learning_rate": 4.7743589743589744e-05,
+      "loss": 0.5785486698150635,
+      "step": 3070
+    },
+    {
+      "epoch": 0.018036113217601606,
+      "grad_norm": 0.9785205125808716,
+      "learning_rate": 4.723076923076923e-05,
+      "loss": 0.6254173278808594,
+      "step": 3080
+    },
+    {
+      "epoch": 0.018094672026749664,
+      "grad_norm": 0.7712920308113098,
+      "learning_rate": 4.671794871794872e-05,
+      "loss": 0.5232354640960694,
+      "step": 3090
+    },
+    {
+      "epoch": 0.018153230835897722,
+      "grad_norm": 0.9690357446670532,
+      "learning_rate": 4.6205128205128204e-05,
+      "loss": 0.6493497371673584,
+      "step": 3100
+    },
+    {
+      "epoch": 0.01821178964504578,
+      "grad_norm": 0.7151793241500854,
+      "learning_rate": 4.56923076923077e-05,
+      "loss": 0.4791082859039307,
+      "step": 3110
+    },
+    {
+      "epoch": 0.018270348454193834,
+      "grad_norm": 1.0174742937088013,
+      "learning_rate": 4.5179487179487184e-05,
+      "loss": 0.6347029685974122,
+      "step": 3120
+    },
+    {
+      "epoch": 0.018328907263341892,
+      "grad_norm": 0.8618830442428589,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 0.5541427135467529,
+      "step": 3130
+    },
+    {
+      "epoch": 0.01838746607248995,
+      "grad_norm": 0.9328573942184448,
+      "learning_rate": 4.415384615384616e-05,
+      "loss": 0.49029951095581054,
+      "step": 3140
+    },
+    {
+      "epoch": 0.018446024881638007,
+      "grad_norm": 1.0293370485305786,
+      "learning_rate": 4.3641025641025643e-05,
+      "loss": 0.49523158073425294,
+      "step": 3150
+    },
+    {
+      "epoch": 0.018504583690786065,
+      "grad_norm": 0.8024817109107971,
+      "learning_rate": 4.312820512820513e-05,
+      "loss": 0.6391828536987305,
+      "step": 3160
+    },
+    {
+      "epoch": 0.01856314249993412,
+      "grad_norm": 0.7935349941253662,
+      "learning_rate": 4.2615384615384617e-05,
+      "loss": 0.535066032409668,
+      "step": 3170
+    },
+    {
+      "epoch": 0.018621701309082177,
+      "grad_norm": 1.0129835605621338,
+      "learning_rate": 4.210256410256411e-05,
+      "loss": 0.5176414012908935,
+      "step": 3180
+    },
+    {
+      "epoch": 0.018680260118230235,
+      "grad_norm": 0.7804064154624939,
+      "learning_rate": 4.158974358974359e-05,
+      "loss": 0.5758108615875244,
+      "step": 3190
+    },
+    {
+      "epoch": 0.018738818927378293,
+      "grad_norm": 1.0611324310302734,
+      "learning_rate": 4.1076923076923076e-05,
+      "loss": 0.5137322902679443,
+      "step": 3200
+    },
+    {
+      "epoch": 0.01879737773652635,
+      "grad_norm": 0.9809267520904541,
+      "learning_rate": 4.056410256410257e-05,
+      "loss": 0.5527653217315673,
+      "step": 3210
+    },
+    {
+      "epoch": 0.01885593654567441,
+      "grad_norm": 0.7737221717834473,
+      "learning_rate": 4.005128205128205e-05,
+      "loss": 0.622959041595459,
+      "step": 3220
+    },
+    {
+      "epoch": 0.018914495354822463,
+      "grad_norm": 0.6540891528129578,
+      "learning_rate": 3.953846153846154e-05,
+      "loss": 0.49772024154663086,
+      "step": 3230
+    },
+    {
+      "epoch": 0.01897305416397052,
+      "grad_norm": 0.861090362071991,
+      "learning_rate": 3.902564102564103e-05,
+      "loss": 0.576954984664917,
+      "step": 3240
+    },
+    {
+      "epoch": 0.01903161297311858,
+      "grad_norm": 0.929144024848938,
+      "learning_rate": 3.8512820512820516e-05,
+      "loss": 0.6221125602722168,
+      "step": 3250
+    },
+    {
+      "epoch": 0.019090171782266636,
+      "grad_norm": 0.7518307566642761,
+      "learning_rate": 3.8e-05,
+      "loss": 0.6510417938232422,
+      "step": 3260
+    },
+    {
+      "epoch": 0.019148730591414694,
+      "grad_norm": 0.7619118094444275,
+      "learning_rate": 3.748717948717949e-05,
+      "loss": 0.5681602954864502,
+      "step": 3270
+    },
+    {
+      "epoch": 0.01920728940056275,
+      "grad_norm": 0.926790714263916,
+      "learning_rate": 3.6974358974358975e-05,
+      "loss": 0.5376785278320313,
+      "step": 3280
+    },
+    {
+      "epoch": 0.019265848209710806,
+      "grad_norm": 0.871703565120697,
+      "learning_rate": 3.646153846153846e-05,
+      "loss": 0.5535645008087158,
+      "step": 3290
+    },
+    {
+      "epoch": 0.019324407018858864,
+      "grad_norm": 0.9614275693893433,
+      "learning_rate": 3.5948717948717955e-05,
+      "loss": 0.49208922386169435,
+      "step": 3300
+    },
+    {
+      "epoch": 0.019382965828006922,
+      "grad_norm": 0.9823223352432251,
+      "learning_rate": 3.5435897435897435e-05,
+      "loss": 0.5003201961517334,
+      "step": 3310
+    },
+    {
+      "epoch": 0.01944152463715498,
+      "grad_norm": 0.8970009088516235,
+      "learning_rate": 3.492307692307693e-05,
+      "loss": 0.5308861255645752,
+      "step": 3320
+    },
+    {
+      "epoch": 0.019500083446303038,
+      "grad_norm": 0.7754250764846802,
+      "learning_rate": 3.4410256410256415e-05,
+      "loss": 0.5034646034240723,
+      "step": 3330
+    },
+    {
+      "epoch": 0.019558642255451092,
+      "grad_norm": 0.7612975835800171,
+      "learning_rate": 3.3897435897435894e-05,
+      "loss": 0.5634318351745605,
+      "step": 3340
+    },
+    {
+      "epoch": 0.01961720106459915,
+      "grad_norm": 0.8280472755432129,
+      "learning_rate": 3.338461538461539e-05,
+      "loss": 0.6287012577056885,
+      "step": 3350
+    },
+    {
+      "epoch": 0.019675759873747208,
+      "grad_norm": 0.8421421647071838,
+      "learning_rate": 3.2871794871794874e-05,
+      "loss": 0.5922800540924072,
+      "step": 3360
+    },
+    {
+      "epoch": 0.019734318682895265,
+      "grad_norm": 0.9054791927337646,
+      "learning_rate": 3.235897435897436e-05,
+      "loss": 0.5123564243316651,
+      "step": 3370
+    },
+    {
+      "epoch": 0.019792877492043323,
+      "grad_norm": 0.7409724593162537,
+      "learning_rate": 3.184615384615385e-05,
+      "loss": 0.5477404594421387,
+      "step": 3380
+    },
+    {
+      "epoch": 0.019851436301191377,
+      "grad_norm": 1.0175254344940186,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 0.5544933795928955,
+      "step": 3390
+    },
+    {
+      "epoch": 0.019909995110339435,
+      "grad_norm": 0.6535821557044983,
+      "learning_rate": 3.082051282051282e-05,
+      "loss": 0.5649590492248535,
+      "step": 3400
+    },
+    {
+      "epoch": 0.019968553919487493,
+      "grad_norm": 0.8674274682998657,
+      "learning_rate": 3.030769230769231e-05,
+      "loss": 0.565241003036499,
+      "step": 3410
+    },
+    {
+      "epoch": 0.02002711272863555,
+      "grad_norm": 0.8033132553100586,
+      "learning_rate": 2.9794871794871797e-05,
+      "loss": 0.515103816986084,
+      "step": 3420
+    },
+    {
+      "epoch": 0.02008567153778361,
+      "grad_norm": 1.0296214818954468,
+      "learning_rate": 2.9282051282051283e-05,
+      "loss": 0.5208463668823242,
+      "step": 3430
+    },
+    {
+      "epoch": 0.020144230346931667,
+      "grad_norm": 0.8400964736938477,
+      "learning_rate": 2.876923076923077e-05,
+      "loss": 0.5142516136169434,
+      "step": 3440
+    },
+    {
+      "epoch": 0.02020278915607972,
+      "grad_norm": 0.8163658976554871,
+      "learning_rate": 2.825641025641026e-05,
+      "loss": 0.5436674118041992,
+      "step": 3450
+    },
+    {
+      "epoch": 0.02026134796522778,
+      "grad_norm": 0.8809291124343872,
+      "learning_rate": 2.7743589743589743e-05,
+      "loss": 0.5333271026611328,
+      "step": 3460
+    },
+    {
+      "epoch": 0.020319906774375836,
+      "grad_norm": 0.8439704179763794,
+      "learning_rate": 2.7230769230769233e-05,
+      "loss": 0.5213183403015137,
+      "step": 3470
+    },
+    {
+      "epoch": 0.020378465583523894,
+      "grad_norm": 0.8002095222473145,
+      "learning_rate": 2.671794871794872e-05,
+      "loss": 0.4625570297241211,
+      "step": 3480
+    },
+    {
+      "epoch": 0.020437024392671952,
+      "grad_norm": 0.899154007434845,
+      "learning_rate": 2.6205128205128206e-05,
+      "loss": 0.4710862636566162,
+      "step": 3490
+    },
+    {
+      "epoch": 0.020495583201820006,
+      "grad_norm": 0.9485552906990051,
+      "learning_rate": 2.5692307692307692e-05,
+      "loss": 0.47341165542602537,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.96240571456978e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

adapter/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b31c165767a8418547683b7b0bb98466ae2cea43d76fd57aefee2b75c80453
+size 5713

adapter/checkpoint-4000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3.5-0.8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3.5-0.8B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter/checkpoint-4000/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-0.8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/checkpoint-4000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51eeed04284d061c6f6cd1b340925e6f461d11447030a73d2e2f1b6539ae8eaf
+size 25587104

adapter/checkpoint-4000/chat_template.jinja

@@ -0,0 +1,158 @@
+{%- 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 %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- 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 merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|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 %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if 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 mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<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 %}
+    {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, tool calling #}

adapter/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac66fa1ec3c3f2789ed25bc19ed53cea8e04f74540b4ca9535735cac9de5649f
+size 51282443

adapter/checkpoint-4000/processor_config.json

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

adapter/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

adapter/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1783515d13d2c7f566c1258dc98c98181fd931bd6b4838fe28d3a212a9d460b
+size 1465

adapter/checkpoint-4000/tokenizer.json

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

adapter/checkpoint-4000/tokenizer_config.json

@@ -0,0 +1,299 @@
+{
+  "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": false,
+  "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": "<|vision_pad|>",
+  "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|>",
+  "added_tokens_decoder": {
+    "248044": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248045": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248046": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248047": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248048": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248049": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248050": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248051": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248052": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248053": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248054": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248055": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248056": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248057": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248058": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248059": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248060": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248061": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248062": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248063": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248064": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248065": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248066": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248067": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248068": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248069": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "248070": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248071": {
+      "content": "<|audio_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248072": {
+      "content": "<tts_pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248073": {
+      "content": "<tts_text_bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248074": {
+      "content": "<tts_text_eod>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248075": {
+      "content": "<tts_text_bos_single>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "248076": {
+      "content": "<|audio_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

adapter/checkpoint-4000/trainer_state.json

@@ -0,0 +1,2834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.023423523659222865,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.855880914805717e-05,
+      "grad_norm": 1.5575445890426636,
+      "learning_rate": 1.8e-05,
+      "loss": 0.7678159713745117,
+      "step": 10
+    },
+    {
+      "epoch": 0.00011711761829611434,
+      "grad_norm": 1.0704400539398193,
+      "learning_rate": 3.8e-05,
+      "loss": 0.7586987972259521,
+      "step": 20
+    },
+    {
+      "epoch": 0.0001756764274441715,
+      "grad_norm": 0.6421218514442444,
+      "learning_rate": 5.8e-05,
+      "loss": 0.6814639568328857,
+      "step": 30
+    },
+    {
+      "epoch": 0.00023423523659222867,
+      "grad_norm": 0.938690721988678,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.6233416557312011,
+      "step": 40
+    },
+    {
+      "epoch": 0.00029279404574028583,
+      "grad_norm": 1.166359543800354,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5837168216705322,
+      "step": 50
+    },
+    {
+      "epoch": 0.000351352854888343,
+      "grad_norm": 0.7864418029785156,
+      "learning_rate": 0.000118,
+      "loss": 0.49336514472961424,
+      "step": 60
+    },
+    {
+      "epoch": 0.00040991166403640014,
+      "grad_norm": 0.723896861076355,
+      "learning_rate": 0.000138,
+      "loss": 0.6541348457336426,
+      "step": 70
+    },
+    {
+      "epoch": 0.00046847047318445735,
+      "grad_norm": 0.5491677522659302,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.6446280479431152,
+      "step": 80
+    },
+    {
+      "epoch": 0.0005270292823325145,
+      "grad_norm": 1.032065510749817,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.493870210647583,
+      "step": 90
+    },
+    {
+      "epoch": 0.0005855880914805717,
+      "grad_norm": 0.7324640154838562,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.63213210105896,
+      "step": 100
+    },
+    {
+      "epoch": 0.0006441469006286288,
+      "grad_norm": 0.8503096103668213,
+      "learning_rate": 0.00019953846153846153,
+      "loss": 0.6286506652832031,
+      "step": 110
+    },
+    {
+      "epoch": 0.000702705709776686,
+      "grad_norm": 0.8664548993110657,
+      "learning_rate": 0.00019902564102564104,
+      "loss": 0.48207850456237794,
+      "step": 120
+    },
+    {
+      "epoch": 0.0007612645189247431,
+      "grad_norm": 0.6782843470573425,
+      "learning_rate": 0.00019851282051282053,
+      "loss": 0.6306986331939697,
+      "step": 130
+    },
+    {
+      "epoch": 0.0008198233280728003,
+      "grad_norm": 1.2085249423980713,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.5556919574737549,
+      "step": 140
+    },
+    {
+      "epoch": 0.0008783821372208574,
+      "grad_norm": 0.8503999710083008,
+      "learning_rate": 0.0001974871794871795,
+      "loss": 0.6409926414489746,
+      "step": 150
+    },
+    {
+      "epoch": 0.0009369409463689147,
+      "grad_norm": 0.7704036235809326,
+      "learning_rate": 0.000196974358974359,
+      "loss": 0.5393772125244141,
+      "step": 160
+    },
+    {
+      "epoch": 0.0009954997555169719,
+      "grad_norm": 0.7071548104286194,
+      "learning_rate": 0.00019646153846153847,
+      "loss": 0.6072579860687256,
+      "step": 170
+    },
+    {
+      "epoch": 0.001054058564665029,
+      "grad_norm": 0.6557785272598267,
+      "learning_rate": 0.00019594871794871796,
+      "loss": 0.49915218353271484,
+      "step": 180
+    },
+    {
+      "epoch": 0.0011126173738130862,
+      "grad_norm": 0.6428221464157104,
+      "learning_rate": 0.00019543589743589745,
+      "loss": 0.6393180370330811,
+      "step": 190
+    },
+    {
+      "epoch": 0.0011711761829611433,
+      "grad_norm": 0.8832526803016663,
+      "learning_rate": 0.00019492307692307693,
+      "loss": 0.6467752456665039,
+      "step": 200
+    },
+    {
+      "epoch": 0.0012297349921092005,
+      "grad_norm": 0.8874967694282532,
+      "learning_rate": 0.00019441025641025642,
+      "loss": 0.6200666904449463,
+      "step": 210
+    },
+    {
+      "epoch": 0.0012882938012572576,
+      "grad_norm": 0.8451365828514099,
+      "learning_rate": 0.0001938974358974359,
+      "loss": 0.5980692386627198,
+      "step": 220
+    },
+    {
+      "epoch": 0.0013468526104053148,
+      "grad_norm": 1.3747062683105469,
+      "learning_rate": 0.0001933846153846154,
+      "loss": 0.5997383117675781,
+      "step": 230
+    },
+    {
+      "epoch": 0.001405411419553372,
+      "grad_norm": 0.7659091949462891,
+      "learning_rate": 0.00019287179487179488,
+      "loss": 0.6244289875030518,
+      "step": 240
+    },
+    {
+      "epoch": 0.001463970228701429,
+      "grad_norm": 0.7551876902580261,
+      "learning_rate": 0.00019235897435897437,
+      "loss": 0.5602375507354737,
+      "step": 250
+    },
+    {
+      "epoch": 0.0015225290378494862,
+      "grad_norm": 0.8756004571914673,
+      "learning_rate": 0.00019184615384615385,
+      "loss": 0.5726509094238281,
+      "step": 260
+    },
+    {
+      "epoch": 0.0015810878469975434,
+      "grad_norm": 0.9010286927223206,
+      "learning_rate": 0.00019133333333333334,
+      "loss": 0.564607048034668,
+      "step": 270
+    },
+    {
+      "epoch": 0.0016396466561456006,
+      "grad_norm": 0.768795907497406,
+      "learning_rate": 0.00019082051282051283,
+      "loss": 0.6172872066497803,
+      "step": 280
+    },
+    {
+      "epoch": 0.0016982054652936577,
+      "grad_norm": 0.8452103137969971,
+      "learning_rate": 0.0001903076923076923,
+      "loss": 0.5882416248321534,
+      "step": 290
+    },
+    {
+      "epoch": 0.0017567642744417149,
+      "grad_norm": 0.8099432587623596,
+      "learning_rate": 0.0001897948717948718,
+      "loss": 0.5674912452697753,
+      "step": 300
+    },
+    {
+      "epoch": 0.001815323083589772,
+      "grad_norm": 0.7150252461433411,
+      "learning_rate": 0.00018928205128205129,
+      "loss": 0.5736612796783447,
+      "step": 310
+    },
+    {
+      "epoch": 0.0018738818927378294,
+      "grad_norm": 1.098449945449829,
+      "learning_rate": 0.0001887692307692308,
+      "loss": 0.6177639484405517,
+      "step": 320
+    },
+    {
+      "epoch": 0.0019324407018858865,
+      "grad_norm": 0.7274444103240967,
+      "learning_rate": 0.00018825641025641029,
+      "loss": 0.6690079212188721,
+      "step": 330
+    },
+    {
+      "epoch": 0.0019909995110339437,
+      "grad_norm": 0.7714038491249084,
+      "learning_rate": 0.00018774358974358975,
+      "loss": 0.5143749237060546,
+      "step": 340
+    },
+    {
+      "epoch": 0.0020495583201820006,
+      "grad_norm": 0.9286389946937561,
+      "learning_rate": 0.00018723076923076923,
+      "loss": 0.5226009368896485,
+      "step": 350
+    },
+    {
+      "epoch": 0.002108117129330058,
+      "grad_norm": 0.9736594557762146,
+      "learning_rate": 0.00018671794871794872,
+      "loss": 0.5954864501953125,
+      "step": 360
+    },
+    {
+      "epoch": 0.002166675938478115,
+      "grad_norm": 0.7701608538627625,
+      "learning_rate": 0.0001862051282051282,
+      "loss": 0.564179515838623,
+      "step": 370
+    },
+    {
+      "epoch": 0.0022252347476261723,
+      "grad_norm": 0.8563699126243591,
+      "learning_rate": 0.0001856923076923077,
+      "loss": 0.587281608581543,
+      "step": 380
+    },
+    {
+      "epoch": 0.0022837935567742293,
+      "grad_norm": 1.017929196357727,
+      "learning_rate": 0.00018517948717948718,
+      "loss": 0.579550313949585,
+      "step": 390
+    },
+    {
+      "epoch": 0.0023423523659222866,
+      "grad_norm": 0.6563118696212769,
+      "learning_rate": 0.00018466666666666666,
+      "loss": 0.5135430335998535,
+      "step": 400
+    },
+    {
+      "epoch": 0.0024009111750703436,
+      "grad_norm": 0.7011086344718933,
+      "learning_rate": 0.00018415384615384618,
+      "loss": 0.6544422149658203,
+      "step": 410
+    },
+    {
+      "epoch": 0.002459469984218401,
+      "grad_norm": 0.991001546382904,
+      "learning_rate": 0.00018364102564102567,
+      "loss": 0.6101119518280029,
+      "step": 420
+    },
+    {
+      "epoch": 0.0025180287933664583,
+      "grad_norm": 0.7023338675498962,
+      "learning_rate": 0.00018312820512820515,
+      "loss": 0.5026431560516358,
+      "step": 430
+    },
+    {
+      "epoch": 0.0025765876025145153,
+      "grad_norm": 0.9078162908554077,
+      "learning_rate": 0.00018261538461538464,
+      "loss": 0.5121633052825928,
+      "step": 440
+    },
+    {
+      "epoch": 0.0026351464116625726,
+      "grad_norm": 0.7449192404747009,
+      "learning_rate": 0.00018210256410256412,
+      "loss": 0.6154009819030761,
+      "step": 450
+    },
+    {
+      "epoch": 0.0026937052208106296,
+      "grad_norm": 0.6876159906387329,
+      "learning_rate": 0.00018158974358974358,
+      "loss": 0.5338088989257812,
+      "step": 460
+    },
+    {
+      "epoch": 0.002752264029958687,
+      "grad_norm": 0.9204329252243042,
+      "learning_rate": 0.00018107692307692307,
+      "loss": 0.5554272174835205,
+      "step": 470
+    },
+    {
+      "epoch": 0.002810822839106744,
+      "grad_norm": 0.7362950444221497,
+      "learning_rate": 0.00018056410256410256,
+      "loss": 0.6131524085998535,
+      "step": 480
+    },
+    {
+      "epoch": 0.0028693816482548012,
+      "grad_norm": 0.9833507537841797,
+      "learning_rate": 0.00018005128205128204,
+      "loss": 0.5537636756896973,
+      "step": 490
+    },
+    {
+      "epoch": 0.002927940457402858,
+      "grad_norm": 0.7546113133430481,
+      "learning_rate": 0.00017953846153846156,
+      "loss": 0.6003861904144288,
+      "step": 500
+    },
+    {
+      "epoch": 0.0029864992665509156,
+      "grad_norm": 0.7838321924209595,
+      "learning_rate": 0.00017902564102564104,
+      "loss": 0.6598413944244385,
+      "step": 510
+    },
+    {
+      "epoch": 0.0030450580756989725,
+      "grad_norm": 0.7242461442947388,
+      "learning_rate": 0.00017851282051282053,
+      "loss": 0.5558955669403076,
+      "step": 520
+    },
+    {
+      "epoch": 0.00310361688484703,
+      "grad_norm": 1.1162296533584595,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.6460456371307373,
+      "step": 530
+    },
+    {
+      "epoch": 0.003162175693995087,
+      "grad_norm": 0.7049973011016846,
+      "learning_rate": 0.0001774871794871795,
+      "loss": 0.6043939113616943,
+      "step": 540
+    },
+    {
+      "epoch": 0.003220734503143144,
+      "grad_norm": 0.8112305998802185,
+      "learning_rate": 0.000176974358974359,
+      "loss": 0.4545936584472656,
+      "step": 550
+    },
+    {
+      "epoch": 0.003279293312291201,
+      "grad_norm": 0.6234564781188965,
+      "learning_rate": 0.00017646153846153848,
+      "loss": 0.6101226329803466,
+      "step": 560
+    },
+    {
+      "epoch": 0.0033378521214392585,
+      "grad_norm": 0.9512666463851929,
+      "learning_rate": 0.00017594871794871796,
+      "loss": 0.6055888175964356,
+      "step": 570
+    },
+    {
+      "epoch": 0.0033964109305873154,
+      "grad_norm": 0.8533800840377808,
+      "learning_rate": 0.00017543589743589742,
+      "loss": 0.6529808044433594,
+      "step": 580
+    },
+    {
+      "epoch": 0.003454969739735373,
+      "grad_norm": 0.896560549736023,
+      "learning_rate": 0.00017492307692307694,
+      "loss": 0.5882085800170899,
+      "step": 590
+    },
+    {
+      "epoch": 0.0035135285488834297,
+      "grad_norm": 0.8455023765563965,
+      "learning_rate": 0.00017441025641025642,
+      "loss": 0.518503999710083,
+      "step": 600
+    },
+    {
+      "epoch": 0.003572087358031487,
+      "grad_norm": 0.7477754950523376,
+      "learning_rate": 0.0001738974358974359,
+      "loss": 0.6013938426971436,
+      "step": 610
+    },
+    {
+      "epoch": 0.003630646167179544,
+      "grad_norm": 0.8402391672134399,
+      "learning_rate": 0.0001733846153846154,
+      "loss": 0.6162835597991944,
+      "step": 620
+    },
+    {
+      "epoch": 0.0036892049763276014,
+      "grad_norm": 1.0327485799789429,
+      "learning_rate": 0.00017287179487179488,
+      "loss": 0.6443416595458984,
+      "step": 630
+    },
+    {
+      "epoch": 0.003747763785475659,
+      "grad_norm": 1.0342403650283813,
+      "learning_rate": 0.00017235897435897437,
+      "loss": 0.5222865581512451,
+      "step": 640
+    },
+    {
+      "epoch": 0.0038063225946237157,
+      "grad_norm": 0.9043326377868652,
+      "learning_rate": 0.00017184615384615386,
+      "loss": 0.6140403747558594,
+      "step": 650
+    },
+    {
+      "epoch": 0.003864881403771773,
+      "grad_norm": 0.8706991076469421,
+      "learning_rate": 0.00017133333333333334,
+      "loss": 0.6201248645782471,
+      "step": 660
+    },
+    {
+      "epoch": 0.0039234402129198305,
+      "grad_norm": 0.7702825665473938,
+      "learning_rate": 0.00017082051282051283,
+      "loss": 0.5698607921600342,
+      "step": 670
+    },
+    {
+      "epoch": 0.003981999022067887,
+      "grad_norm": 0.7835186719894409,
+      "learning_rate": 0.00017030769230769231,
+      "loss": 0.5464808464050293,
+      "step": 680
+    },
+    {
+      "epoch": 0.004040557831215944,
+      "grad_norm": 0.7293221950531006,
+      "learning_rate": 0.0001697948717948718,
+      "loss": 0.6055557250976562,
+      "step": 690
+    },
+    {
+      "epoch": 0.004099116640364001,
+      "grad_norm": 0.8519648313522339,
+      "learning_rate": 0.0001692820512820513,
+      "loss": 0.594606876373291,
+      "step": 700
+    },
+    {
+      "epoch": 0.004157675449512059,
+      "grad_norm": 0.8359381556510925,
+      "learning_rate": 0.00016876923076923077,
+      "loss": 0.6676365852355957,
+      "step": 710
+    },
+    {
+      "epoch": 0.004216234258660116,
+      "grad_norm": 0.9601361155509949,
+      "learning_rate": 0.00016825641025641026,
+      "loss": 0.5267905235290528,
+      "step": 720
+    },
+    {
+      "epoch": 0.004274793067808173,
+      "grad_norm": 0.5900155901908875,
+      "learning_rate": 0.00016774358974358975,
+      "loss": 0.5860335826873779,
+      "step": 730
+    },
+    {
+      "epoch": 0.00433335187695623,
+      "grad_norm": 0.7671850323677063,
+      "learning_rate": 0.00016723076923076923,
+      "loss": 0.5898273468017579,
+      "step": 740
+    },
+    {
+      "epoch": 0.004391910686104288,
+      "grad_norm": 0.9657745361328125,
+      "learning_rate": 0.00016671794871794872,
+      "loss": 0.6093048572540283,
+      "step": 750
+    },
+    {
+      "epoch": 0.004450469495252345,
+      "grad_norm": 0.7431370615959167,
+      "learning_rate": 0.0001662051282051282,
+      "loss": 0.6279802799224854,
+      "step": 760
+    },
+    {
+      "epoch": 0.004509028304400402,
+      "grad_norm": 0.9329614639282227,
+      "learning_rate": 0.0001656923076923077,
+      "loss": 0.5990581512451172,
+      "step": 770
+    },
+    {
+      "epoch": 0.0045675871135484585,
+      "grad_norm": 0.6032372713088989,
+      "learning_rate": 0.00016517948717948718,
+      "loss": 0.5825644493103027,
+      "step": 780
+    },
+    {
+      "epoch": 0.004626145922696516,
+      "grad_norm": 0.6884028911590576,
+      "learning_rate": 0.00016466666666666667,
+      "loss": 0.555311632156372,
+      "step": 790
+    },
+    {
+      "epoch": 0.004684704731844573,
+      "grad_norm": 0.7366816997528076,
+      "learning_rate": 0.00016415384615384618,
+      "loss": 0.6074917793273926,
+      "step": 800
+    },
+    {
+      "epoch": 0.00474326354099263,
+      "grad_norm": 0.776561439037323,
+      "learning_rate": 0.00016364102564102567,
+      "loss": 0.5682147026062012,
+      "step": 810
+    },
+    {
+      "epoch": 0.004801822350140687,
+      "grad_norm": 0.8783098459243774,
+      "learning_rate": 0.00016312820512820515,
+      "loss": 0.6519593715667724,
+      "step": 820
+    },
+    {
+      "epoch": 0.004860381159288745,
+      "grad_norm": 0.8319303393363953,
+      "learning_rate": 0.0001626153846153846,
+      "loss": 0.6276237487792968,
+      "step": 830
+    },
+    {
+      "epoch": 0.004918939968436802,
+      "grad_norm": 0.7415748238563538,
+      "learning_rate": 0.0001621025641025641,
+      "loss": 0.6673260688781738,
+      "step": 840
+    },
+    {
+      "epoch": 0.004977498777584859,
+      "grad_norm": 1.0244334936141968,
+      "learning_rate": 0.00016158974358974359,
+      "loss": 0.6164275169372558,
+      "step": 850
+    },
+    {
+      "epoch": 0.005036057586732917,
+      "grad_norm": 1.0644179582595825,
+      "learning_rate": 0.00016107692307692307,
+      "loss": 0.5958343505859375,
+      "step": 860
+    },
+    {
+      "epoch": 0.0050946163958809736,
+      "grad_norm": 0.7661171555519104,
+      "learning_rate": 0.00016056410256410256,
+      "loss": 0.5362070083618165,
+      "step": 870
+    },
+    {
+      "epoch": 0.0051531752050290305,
+      "grad_norm": 1.014600157737732,
+      "learning_rate": 0.00016005128205128205,
+      "loss": 0.537624454498291,
+      "step": 880
+    },
+    {
+      "epoch": 0.0052117340141770874,
+      "grad_norm": 0.7331597805023193,
+      "learning_rate": 0.00015953846153846156,
+      "loss": 0.5774639129638672,
+      "step": 890
+    },
+    {
+      "epoch": 0.005270292823325145,
+      "grad_norm": 0.7434748411178589,
+      "learning_rate": 0.00015902564102564105,
+      "loss": 0.5845869064331055,
+      "step": 900
+    },
+    {
+      "epoch": 0.005328851632473202,
+      "grad_norm": 0.7248567342758179,
+      "learning_rate": 0.00015851282051282053,
+      "loss": 0.590050458908081,
+      "step": 910
+    },
+    {
+      "epoch": 0.005387410441621259,
+      "grad_norm": 0.9382026791572571,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.6036070823669434,
+      "step": 920
+    },
+    {
+      "epoch": 0.005445969250769316,
+      "grad_norm": 0.9255577325820923,
+      "learning_rate": 0.0001574871794871795,
+      "loss": 0.4737861633300781,
+      "step": 930
+    },
+    {
+      "epoch": 0.005504528059917374,
+      "grad_norm": 0.9797175526618958,
+      "learning_rate": 0.000156974358974359,
+      "loss": 0.5388136386871338,
+      "step": 940
+    },
+    {
+      "epoch": 0.005563086869065431,
+      "grad_norm": 0.7894104719161987,
+      "learning_rate": 0.00015646153846153845,
+      "loss": 0.529002571105957,
+      "step": 950
+    },
+    {
+      "epoch": 0.005621645678213488,
+      "grad_norm": 0.8898355960845947,
+      "learning_rate": 0.00015594871794871794,
+      "loss": 0.5382211685180665,
+      "step": 960
+    },
+    {
+      "epoch": 0.005680204487361545,
+      "grad_norm": 0.7389085292816162,
+      "learning_rate": 0.00015543589743589742,
+      "loss": 0.5379764080047608,
+      "step": 970
+    },
+    {
+      "epoch": 0.0057387632965096025,
+      "grad_norm": 0.8882327675819397,
+      "learning_rate": 0.00015492307692307694,
+      "loss": 0.5847358226776123,
+      "step": 980
+    },
+    {
+      "epoch": 0.005797322105657659,
+      "grad_norm": 1.1310079097747803,
+      "learning_rate": 0.00015441025641025642,
+      "loss": 0.5858294486999511,
+      "step": 990
+    },
+    {
+      "epoch": 0.005855880914805716,
+      "grad_norm": 1.0356104373931885,
+      "learning_rate": 0.0001538974358974359,
+      "loss": 0.5417033195495605,
+      "step": 1000
+    },
+    {
+      "epoch": 0.005914439723953773,
+      "grad_norm": 0.7012810707092285,
+      "learning_rate": 0.0001533846153846154,
+      "loss": 0.6806005477905274,
+      "step": 1010
+    },
+    {
+      "epoch": 0.005972998533101831,
+      "grad_norm": 0.9496027231216431,
+      "learning_rate": 0.00015287179487179488,
+      "loss": 0.521822738647461,
+      "step": 1020
+    },
+    {
+      "epoch": 0.006031557342249888,
+      "grad_norm": 0.7196470499038696,
+      "learning_rate": 0.00015235897435897437,
+      "loss": 0.5730608940124512,
+      "step": 1030
+    },
+    {
+      "epoch": 0.006090116151397945,
+      "grad_norm": 0.7311615347862244,
+      "learning_rate": 0.00015184615384615386,
+      "loss": 0.6122246742248535,
+      "step": 1040
+    },
+    {
+      "epoch": 0.006148674960546002,
+      "grad_norm": 0.7351731657981873,
+      "learning_rate": 0.00015133333333333334,
+      "loss": 0.5122735023498535,
+      "step": 1050
+    },
+    {
+      "epoch": 0.00620723376969406,
+      "grad_norm": 0.8649750351905823,
+      "learning_rate": 0.00015082051282051283,
+      "loss": 0.6370734691619873,
+      "step": 1060
+    },
+    {
+      "epoch": 0.006265792578842117,
+      "grad_norm": 0.7295814752578735,
+      "learning_rate": 0.00015030769230769232,
+      "loss": 0.5188347816467285,
+      "step": 1070
+    },
+    {
+      "epoch": 0.006324351387990174,
+      "grad_norm": 0.7717416882514954,
+      "learning_rate": 0.0001497948717948718,
+      "loss": 0.5114748001098632,
+      "step": 1080
+    },
+    {
+      "epoch": 0.006382910197138231,
+      "grad_norm": 0.5910501480102539,
+      "learning_rate": 0.0001492820512820513,
+      "loss": 0.46537189483642577,
+      "step": 1090
+    },
+    {
+      "epoch": 0.006441469006286288,
+      "grad_norm": 0.7533769011497498,
+      "learning_rate": 0.00014876923076923078,
+      "loss": 0.5796781539916992,
+      "step": 1100
+    },
+    {
+      "epoch": 0.006500027815434345,
+      "grad_norm": 0.9167582988739014,
+      "learning_rate": 0.00014825641025641026,
+      "loss": 0.6297817230224609,
+      "step": 1110
+    },
+    {
+      "epoch": 0.006558586624582402,
+      "grad_norm": 1.1386590003967285,
+      "learning_rate": 0.00014774358974358975,
+      "loss": 0.592150354385376,
+      "step": 1120
+    },
+    {
+      "epoch": 0.00661714543373046,
+      "grad_norm": 0.7550930380821228,
+      "learning_rate": 0.00014723076923076924,
+      "loss": 0.5509029865264893,
+      "step": 1130
+    },
+    {
+      "epoch": 0.006675704242878517,
+      "grad_norm": 0.6492360234260559,
+      "learning_rate": 0.00014671794871794872,
+      "loss": 0.5187190055847168,
+      "step": 1140
+    },
+    {
+      "epoch": 0.006734263052026574,
+      "grad_norm": 0.7233424782752991,
+      "learning_rate": 0.0001462051282051282,
+      "loss": 0.5804600238800048,
+      "step": 1150
+    },
+    {
+      "epoch": 0.006792821861174631,
+      "grad_norm": 1.0428144931793213,
+      "learning_rate": 0.0001456923076923077,
+      "loss": 0.5116332530975342,
+      "step": 1160
+    },
+    {
+      "epoch": 0.006851380670322689,
+      "grad_norm": 0.7919323444366455,
+      "learning_rate": 0.00014517948717948718,
+      "loss": 0.6416738986968994,
+      "step": 1170
+    },
+    {
+      "epoch": 0.006909939479470746,
+      "grad_norm": 0.8511198163032532,
+      "learning_rate": 0.0001446666666666667,
+      "loss": 0.579420518875122,
+      "step": 1180
+    },
+    {
+      "epoch": 0.0069684982886188025,
+      "grad_norm": 0.6856178641319275,
+      "learning_rate": 0.00014415384615384615,
+      "loss": 0.5805029392242431,
+      "step": 1190
+    },
+    {
+      "epoch": 0.0070270570977668595,
+      "grad_norm": 0.7397869229316711,
+      "learning_rate": 0.00014364102564102564,
+      "loss": 0.5604559898376464,
+      "step": 1200
+    },
+    {
+      "epoch": 0.007085615906914917,
+      "grad_norm": 0.7105910778045654,
+      "learning_rate": 0.00014312820512820513,
+      "loss": 0.5608997821807862,
+      "step": 1210
+    },
+    {
+      "epoch": 0.007144174716062974,
+      "grad_norm": 0.7479007244110107,
+      "learning_rate": 0.00014261538461538461,
+      "loss": 0.6052242279052734,
+      "step": 1220
+    },
+    {
+      "epoch": 0.007202733525211031,
+      "grad_norm": 1.1256407499313354,
+      "learning_rate": 0.0001421025641025641,
+      "loss": 0.6259459495544434,
+      "step": 1230
+    },
+    {
+      "epoch": 0.007261292334359088,
+      "grad_norm": 0.6991755962371826,
+      "learning_rate": 0.0001415897435897436,
+      "loss": 0.5524515151977539,
+      "step": 1240
+    },
+    {
+      "epoch": 0.007319851143507146,
+      "grad_norm": 1.053760051727295,
+      "learning_rate": 0.00014107692307692307,
+      "loss": 0.5364514827728272,
+      "step": 1250
+    },
+    {
+      "epoch": 0.007378409952655203,
+      "grad_norm": 0.983850359916687,
+      "learning_rate": 0.00014056410256410256,
+      "loss": 0.5353530883789063,
+      "step": 1260
+    },
+    {
+      "epoch": 0.00743696876180326,
+      "grad_norm": 0.6570679545402527,
+      "learning_rate": 0.00014005128205128207,
+      "loss": 0.5768649101257324,
+      "step": 1270
+    },
+    {
+      "epoch": 0.007495527570951318,
+      "grad_norm": 0.6319562792778015,
+      "learning_rate": 0.00013953846153846156,
+      "loss": 0.587717342376709,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0075540863800993745,
+      "grad_norm": 0.8129682540893555,
+      "learning_rate": 0.00013902564102564105,
+      "loss": 0.561523723602295,
+      "step": 1290
+    },
+    {
+      "epoch": 0.0076126451892474314,
+      "grad_norm": 0.884220540523529,
+      "learning_rate": 0.00013851282051282053,
+      "loss": 0.513004207611084,
+      "step": 1300
+    },
+    {
+      "epoch": 0.007671203998395488,
+      "grad_norm": 0.7594801783561707,
+      "learning_rate": 0.000138,
+      "loss": 0.5956247806549072,
+      "step": 1310
+    },
+    {
+      "epoch": 0.007729762807543546,
+      "grad_norm": 0.8838579654693604,
+      "learning_rate": 0.00013748717948717948,
+      "loss": 0.6295031547546387,
+      "step": 1320
+    },
+    {
+      "epoch": 0.007788321616691603,
+      "grad_norm": 0.7182386517524719,
+      "learning_rate": 0.00013697435897435897,
+      "loss": 0.5618526458740234,
+      "step": 1330
+    },
+    {
+      "epoch": 0.007846880425839661,
+      "grad_norm": 0.7297655940055847,
+      "learning_rate": 0.00013646153846153845,
+      "loss": 0.5208499908447266,
+      "step": 1340
+    },
+    {
+      "epoch": 0.007905439234987717,
+      "grad_norm": 0.62089604139328,
+      "learning_rate": 0.00013594871794871794,
+      "loss": 0.5239852428436279,
+      "step": 1350
+    },
+    {
+      "epoch": 0.007963998044135775,
+      "grad_norm": 0.7171675562858582,
+      "learning_rate": 0.00013543589743589745,
+      "loss": 0.5648018836975097,
+      "step": 1360
+    },
+    {
+      "epoch": 0.008022556853283831,
+      "grad_norm": 0.9089975357055664,
+      "learning_rate": 0.00013492307692307694,
+      "loss": 0.5615391254425048,
+      "step": 1370
+    },
+    {
+      "epoch": 0.008081115662431889,
+      "grad_norm": 0.7600458860397339,
+      "learning_rate": 0.00013441025641025643,
+      "loss": 0.604154634475708,
+      "step": 1380
+    },
+    {
+      "epoch": 0.008139674471579946,
+      "grad_norm": 0.7462561726570129,
+      "learning_rate": 0.0001338974358974359,
+      "loss": 0.6301332950592041,
+      "step": 1390
+    },
+    {
+      "epoch": 0.008198233280728003,
+      "grad_norm": 0.7292648553848267,
+      "learning_rate": 0.0001333846153846154,
+      "loss": 0.5153694152832031,
+      "step": 1400
+    },
+    {
+      "epoch": 0.00825679208987606,
+      "grad_norm": 0.8180534243583679,
+      "learning_rate": 0.00013287179487179489,
+      "loss": 0.647784423828125,
+      "step": 1410
+    },
+    {
+      "epoch": 0.008315350899024118,
+      "grad_norm": 0.6629355549812317,
+      "learning_rate": 0.00013235897435897437,
+      "loss": 0.5387883186340332,
+      "step": 1420
+    },
+    {
+      "epoch": 0.008373909708172174,
+      "grad_norm": 1.1468173265457153,
+      "learning_rate": 0.00013184615384615383,
+      "loss": 0.6159374713897705,
+      "step": 1430
+    },
+    {
+      "epoch": 0.008432468517320232,
+      "grad_norm": 0.9131197929382324,
+      "learning_rate": 0.00013133333333333332,
+      "loss": 0.5780044078826905,
+      "step": 1440
+    },
+    {
+      "epoch": 0.008491027326468288,
+      "grad_norm": 0.8688338398933411,
+      "learning_rate": 0.00013082051282051283,
+      "loss": 0.5893913745880127,
+      "step": 1450
+    },
+    {
+      "epoch": 0.008549586135616346,
+      "grad_norm": 0.6430419683456421,
+      "learning_rate": 0.00013030769230769232,
+      "loss": 0.5053946495056152,
+      "step": 1460
+    },
+    {
+      "epoch": 0.008608144944764404,
+      "grad_norm": 0.81430584192276,
+      "learning_rate": 0.0001297948717948718,
+      "loss": 0.587185287475586,
+      "step": 1470
+    },
+    {
+      "epoch": 0.00866670375391246,
+      "grad_norm": 0.7069384455680847,
+      "learning_rate": 0.0001292820512820513,
+      "loss": 0.6119993686676025,
+      "step": 1480
+    },
+    {
+      "epoch": 0.008725262563060518,
+      "grad_norm": 0.8512614965438843,
+      "learning_rate": 0.00012876923076923078,
+      "loss": 0.5506554126739502,
+      "step": 1490
+    },
+    {
+      "epoch": 0.008783821372208575,
+      "grad_norm": 0.6660640835762024,
+      "learning_rate": 0.00012825641025641026,
+      "loss": 0.5566682338714599,
+      "step": 1500
+    },
+    {
+      "epoch": 0.008842380181356631,
+      "grad_norm": 0.7649056315422058,
+      "learning_rate": 0.00012774358974358975,
+      "loss": 0.5694420814514161,
+      "step": 1510
+    },
+    {
+      "epoch": 0.00890093899050469,
+      "grad_norm": 0.909599781036377,
+      "learning_rate": 0.00012723076923076924,
+      "loss": 0.6355206489562988,
+      "step": 1520
+    },
+    {
+      "epoch": 0.008959497799652747,
+      "grad_norm": 0.7873692512512207,
+      "learning_rate": 0.00012671794871794872,
+      "loss": 0.510439395904541,
+      "step": 1530
+    },
+    {
+      "epoch": 0.009018056608800803,
+      "grad_norm": 0.7628417611122131,
+      "learning_rate": 0.0001262051282051282,
+      "loss": 0.5399933338165284,
+      "step": 1540
+    },
+    {
+      "epoch": 0.009076615417948861,
+      "grad_norm": 0.8505508899688721,
+      "learning_rate": 0.0001256923076923077,
+      "loss": 0.6154933452606202,
+      "step": 1550
+    },
+    {
+      "epoch": 0.009135174227096917,
+      "grad_norm": 0.794605553150177,
+      "learning_rate": 0.00012517948717948718,
+      "loss": 0.6099573612213135,
+      "step": 1560
+    },
+    {
+      "epoch": 0.009193733036244975,
+      "grad_norm": 0.818773090839386,
+      "learning_rate": 0.00012466666666666667,
+      "loss": 0.5245619297027588,
+      "step": 1570
+    },
+    {
+      "epoch": 0.009252291845393033,
+      "grad_norm": 0.6100147366523743,
+      "learning_rate": 0.00012415384615384616,
+      "loss": 0.5743139743804931,
+      "step": 1580
+    },
+    {
+      "epoch": 0.009310850654541089,
+      "grad_norm": 0.911518394947052,
+      "learning_rate": 0.00012364102564102564,
+      "loss": 0.5403082370758057,
+      "step": 1590
+    },
+    {
+      "epoch": 0.009369409463689147,
+      "grad_norm": 0.7002453804016113,
+      "learning_rate": 0.00012312820512820513,
+      "loss": 0.5670140743255615,
+      "step": 1600
+    },
+    {
+      "epoch": 0.009427968272837204,
+      "grad_norm": 0.6926924586296082,
+      "learning_rate": 0.00012261538461538462,
+      "loss": 0.5283169746398926,
+      "step": 1610
+    },
+    {
+      "epoch": 0.00948652708198526,
+      "grad_norm": 0.8910185098648071,
+      "learning_rate": 0.0001221025641025641,
+      "loss": 0.5464873313903809,
+      "step": 1620
+    },
+    {
+      "epoch": 0.009545085891133318,
+      "grad_norm": 0.9428623914718628,
+      "learning_rate": 0.0001215897435897436,
+      "loss": 0.6371686935424805,
+      "step": 1630
+    },
+    {
+      "epoch": 0.009603644700281374,
+      "grad_norm": 0.9594399333000183,
+      "learning_rate": 0.00012107692307692309,
+      "loss": 0.5639693737030029,
+      "step": 1640
+    },
+    {
+      "epoch": 0.009662203509429432,
+      "grad_norm": 0.9431197643280029,
+      "learning_rate": 0.00012056410256410258,
+      "loss": 0.4942180633544922,
+      "step": 1650
+    },
+    {
+      "epoch": 0.00972076231857749,
+      "grad_norm": 0.778407096862793,
+      "learning_rate": 0.00012005128205128206,
+      "loss": 0.5874770641326904,
+      "step": 1660
+    },
+    {
+      "epoch": 0.009779321127725546,
+      "grad_norm": 0.7874659299850464,
+      "learning_rate": 0.00011953846153846155,
+      "loss": 0.5451854228973388,
+      "step": 1670
+    },
+    {
+      "epoch": 0.009837879936873604,
+      "grad_norm": 0.7366560697555542,
+      "learning_rate": 0.00011902564102564102,
+      "loss": 0.5593300342559815,
+      "step": 1680
+    },
+    {
+      "epoch": 0.009896438746021662,
+      "grad_norm": 0.762984573841095,
+      "learning_rate": 0.00011851282051282051,
+      "loss": 0.571781587600708,
+      "step": 1690
+    },
+    {
+      "epoch": 0.009954997555169718,
+      "grad_norm": 0.7820915579795837,
+      "learning_rate": 0.000118,
+      "loss": 0.6361937522888184,
+      "step": 1700
+    },
+    {
+      "epoch": 0.010013556364317775,
+      "grad_norm": 0.885874330997467,
+      "learning_rate": 0.0001174871794871795,
+      "loss": 0.5583993911743164,
+      "step": 1710
+    },
+    {
+      "epoch": 0.010072115173465833,
+      "grad_norm": 0.7336756587028503,
+      "learning_rate": 0.00011697435897435898,
+      "loss": 0.5345401763916016,
+      "step": 1720
+    },
+    {
+      "epoch": 0.01013067398261389,
+      "grad_norm": 1.1266441345214844,
+      "learning_rate": 0.00011646153846153847,
+      "loss": 0.5590295314788818,
+      "step": 1730
+    },
+    {
+      "epoch": 0.010189232791761947,
+      "grad_norm": 0.6986821889877319,
+      "learning_rate": 0.00011594871794871795,
+      "loss": 0.626862907409668,
+      "step": 1740
+    },
+    {
+      "epoch": 0.010247791600910003,
+      "grad_norm": 0.6808388233184814,
+      "learning_rate": 0.00011543589743589744,
+      "loss": 0.45256743431091306,
+      "step": 1750
+    },
+    {
+      "epoch": 0.010306350410058061,
+      "grad_norm": 0.8917853236198425,
+      "learning_rate": 0.00011492307692307693,
+      "loss": 0.5677892684936523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.010364909219206119,
+      "grad_norm": 0.84018474817276,
+      "learning_rate": 0.00011441025641025643,
+      "loss": 0.6715295314788818,
+      "step": 1770
+    },
+    {
+      "epoch": 0.010423468028354175,
+      "grad_norm": 0.8711966276168823,
+      "learning_rate": 0.00011389743589743591,
+      "loss": 0.49718570709228516,
+      "step": 1780
+    },
+    {
+      "epoch": 0.010482026837502233,
+      "grad_norm": 0.8351517915725708,
+      "learning_rate": 0.0001133846153846154,
+      "loss": 0.5668165683746338,
+      "step": 1790
+    },
+    {
+      "epoch": 0.01054058564665029,
+      "grad_norm": 0.9627017378807068,
+      "learning_rate": 0.00011287179487179486,
+      "loss": 0.5853204727172852,
+      "step": 1800
+    },
+    {
+      "epoch": 0.010599144455798347,
+      "grad_norm": 0.642246425151825,
+      "learning_rate": 0.00011235897435897436,
+      "loss": 0.5551766872406005,
+      "step": 1810
+    },
+    {
+      "epoch": 0.010657703264946404,
+      "grad_norm": 0.9542229771614075,
+      "learning_rate": 0.00011184615384615385,
+      "loss": 0.6531394958496094,
+      "step": 1820
+    },
+    {
+      "epoch": 0.01071626207409446,
+      "grad_norm": 0.7595056891441345,
+      "learning_rate": 0.00011133333333333333,
+      "loss": 0.5438894748687744,
+      "step": 1830
+    },
+    {
+      "epoch": 0.010774820883242518,
+      "grad_norm": 0.8346898555755615,
+      "learning_rate": 0.00011082051282051282,
+      "loss": 0.516790771484375,
+      "step": 1840
+    },
+    {
+      "epoch": 0.010833379692390576,
+      "grad_norm": 0.7261139750480652,
+      "learning_rate": 0.0001103076923076923,
+      "loss": 0.5511853694915771,
+      "step": 1850
+    },
+    {
+      "epoch": 0.010891938501538632,
+      "grad_norm": 0.7773726582527161,
+      "learning_rate": 0.0001097948717948718,
+      "loss": 0.6048900604248046,
+      "step": 1860
+    },
+    {
+      "epoch": 0.01095049731068669,
+      "grad_norm": 0.7758798599243164,
+      "learning_rate": 0.00010928205128205129,
+      "loss": 0.4920170783996582,
+      "step": 1870
+    },
+    {
+      "epoch": 0.011009056119834748,
+      "grad_norm": 0.7595053315162659,
+      "learning_rate": 0.00010876923076923078,
+      "loss": 0.5262623786926269,
+      "step": 1880
+    },
+    {
+      "epoch": 0.011067614928982804,
+      "grad_norm": 0.662896454334259,
+      "learning_rate": 0.00010825641025641027,
+      "loss": 0.5706700325012207,
+      "step": 1890
+    },
+    {
+      "epoch": 0.011126173738130862,
+      "grad_norm": 0.8547627329826355,
+      "learning_rate": 0.00010774358974358975,
+      "loss": 0.5571642398834229,
+      "step": 1900
+    },
+    {
+      "epoch": 0.011184732547278918,
+      "grad_norm": 0.9618740081787109,
+      "learning_rate": 0.00010723076923076924,
+      "loss": 0.5785984039306641,
+      "step": 1910
+    },
+    {
+      "epoch": 0.011243291356426975,
+      "grad_norm": 0.8090870976448059,
+      "learning_rate": 0.00010671794871794871,
+      "loss": 0.6467090606689453,
+      "step": 1920
+    },
+    {
+      "epoch": 0.011301850165575033,
+      "grad_norm": 0.8532423377037048,
+      "learning_rate": 0.0001062051282051282,
+      "loss": 0.5037952423095703,
+      "step": 1930
+    },
+    {
+      "epoch": 0.01136040897472309,
+      "grad_norm": 0.8701047897338867,
+      "learning_rate": 0.00010569230769230769,
+      "loss": 0.6252214908599854,
+      "step": 1940
+    },
+    {
+      "epoch": 0.011418967783871147,
+      "grad_norm": 0.8058343529701233,
+      "learning_rate": 0.00010517948717948719,
+      "loss": 0.49949493408203127,
+      "step": 1950
+    },
+    {
+      "epoch": 0.011477526593019205,
+      "grad_norm": 0.7899404764175415,
+      "learning_rate": 0.00010466666666666667,
+      "loss": 0.5413167476654053,
+      "step": 1960
+    },
+    {
+      "epoch": 0.011536085402167261,
+      "grad_norm": 0.7027344107627869,
+      "learning_rate": 0.00010415384615384616,
+      "loss": 0.45540223121643064,
+      "step": 1970
+    },
+    {
+      "epoch": 0.011594644211315319,
+      "grad_norm": 0.8737793564796448,
+      "learning_rate": 0.00010364102564102565,
+      "loss": 0.5688265800476074,
+      "step": 1980
+    },
+    {
+      "epoch": 0.011653203020463377,
+      "grad_norm": 0.9242916703224182,
+      "learning_rate": 0.00010312820512820513,
+      "loss": 0.5170233726501465,
+      "step": 1990
+    },
+    {
+      "epoch": 0.011711761829611433,
+      "grad_norm": 0.6759135127067566,
+      "learning_rate": 0.00010261538461538462,
+      "loss": 0.6288806438446045,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01177032063875949,
+      "grad_norm": 0.7091163396835327,
+      "learning_rate": 0.00010210256410256412,
+      "loss": 0.5844020843505859,
+      "step": 2010
+    },
+    {
+      "epoch": 0.011828879447907547,
+      "grad_norm": 0.9295818209648132,
+      "learning_rate": 0.0001015897435897436,
+      "loss": 0.5282711982727051,
+      "step": 2020
+    },
+    {
+      "epoch": 0.011887438257055604,
+      "grad_norm": 0.6938250064849854,
+      "learning_rate": 0.00010107692307692309,
+      "loss": 0.6149167537689209,
+      "step": 2030
+    },
+    {
+      "epoch": 0.011945997066203662,
+      "grad_norm": 0.7174298763275146,
+      "learning_rate": 0.00010056410256410256,
+      "loss": 0.5130744934082031,
+      "step": 2040
+    },
+    {
+      "epoch": 0.012004555875351718,
+      "grad_norm": 0.9726197123527527,
+      "learning_rate": 0.00010005128205128205,
+      "loss": 0.6236517429351807,
+      "step": 2050
+    },
+    {
+      "epoch": 0.012063114684499776,
+      "grad_norm": 0.7376599311828613,
+      "learning_rate": 9.953846153846155e-05,
+      "loss": 0.4681741714477539,
+      "step": 2060
+    },
+    {
+      "epoch": 0.012121673493647834,
+      "grad_norm": 0.8139657378196716,
+      "learning_rate": 9.902564102564102e-05,
+      "loss": 0.4887677192687988,
+      "step": 2070
+    },
+    {
+      "epoch": 0.01218023230279589,
+      "grad_norm": 0.9429419636726379,
+      "learning_rate": 9.851282051282051e-05,
+      "loss": 0.5326910018920898,
+      "step": 2080
+    },
+    {
+      "epoch": 0.012238791111943948,
+      "grad_norm": 0.9702481627464294,
+      "learning_rate": 9.8e-05,
+      "loss": 0.5095866680145263,
+      "step": 2090
+    },
+    {
+      "epoch": 0.012297349921092004,
+      "grad_norm": 0.6909214854240417,
+      "learning_rate": 9.74871794871795e-05,
+      "loss": 0.5370609283447265,
+      "step": 2100
+    },
+    {
+      "epoch": 0.012355908730240062,
+      "grad_norm": 1.2493647336959839,
+      "learning_rate": 9.697435897435898e-05,
+      "loss": 0.5658076763153076,
+      "step": 2110
+    },
+    {
+      "epoch": 0.01241446753938812,
+      "grad_norm": 0.7158144116401672,
+      "learning_rate": 9.646153846153847e-05,
+      "loss": 0.5293547153472901,
+      "step": 2120
+    },
+    {
+      "epoch": 0.012473026348536176,
+      "grad_norm": 0.8394598364830017,
+      "learning_rate": 9.594871794871796e-05,
+      "loss": 0.48808741569519043,
+      "step": 2130
+    },
+    {
+      "epoch": 0.012531585157684233,
+      "grad_norm": 0.9504506587982178,
+      "learning_rate": 9.543589743589744e-05,
+      "loss": 0.5906731605529785,
+      "step": 2140
+    },
+    {
+      "epoch": 0.012590143966832291,
+      "grad_norm": 0.7592800855636597,
+      "learning_rate": 9.492307692307693e-05,
+      "loss": 0.5167060852050781,
+      "step": 2150
+    },
+    {
+      "epoch": 0.012648702775980347,
+      "grad_norm": 0.8858376145362854,
+      "learning_rate": 9.441025641025642e-05,
+      "loss": 0.5447789669036865,
+      "step": 2160
+    },
+    {
+      "epoch": 0.012707261585128405,
+      "grad_norm": 0.8264896273612976,
+      "learning_rate": 9.38974358974359e-05,
+      "loss": 0.4619621753692627,
+      "step": 2170
+    },
+    {
+      "epoch": 0.012765820394276463,
+      "grad_norm": 0.7801193594932556,
+      "learning_rate": 9.338461538461539e-05,
+      "loss": 0.5282919883728028,
+      "step": 2180
+    },
+    {
+      "epoch": 0.012824379203424519,
+      "grad_norm": 0.7734062671661377,
+      "learning_rate": 9.287179487179488e-05,
+      "loss": 0.6420894622802734,
+      "step": 2190
+    },
+    {
+      "epoch": 0.012882938012572577,
+      "grad_norm": 0.844348132610321,
+      "learning_rate": 9.235897435897436e-05,
+      "loss": 0.602821159362793,
+      "step": 2200
+    },
+    {
+      "epoch": 0.012941496821720633,
+      "grad_norm": 0.8861480355262756,
+      "learning_rate": 9.184615384615385e-05,
+      "loss": 0.5366893291473389,
+      "step": 2210
+    },
+    {
+      "epoch": 0.01300005563086869,
+      "grad_norm": 0.8071720600128174,
+      "learning_rate": 9.133333333333334e-05,
+      "loss": 0.4816866874694824,
+      "step": 2220
+    },
+    {
+      "epoch": 0.013058614440016748,
+      "grad_norm": 0.7975764870643616,
+      "learning_rate": 9.082051282051282e-05,
+      "loss": 0.6320478439331054,
+      "step": 2230
+    },
+    {
+      "epoch": 0.013117173249164804,
+      "grad_norm": 0.7712560296058655,
+      "learning_rate": 9.030769230769232e-05,
+      "loss": 0.607432746887207,
+      "step": 2240
+    },
+    {
+      "epoch": 0.013175732058312862,
+      "grad_norm": 0.7562223076820374,
+      "learning_rate": 8.979487179487181e-05,
+      "loss": 0.4568962097167969,
+      "step": 2250
+    },
+    {
+      "epoch": 0.01323429086746092,
+      "grad_norm": 0.7949206233024597,
+      "learning_rate": 8.928205128205128e-05,
+      "loss": 0.5890951156616211,
+      "step": 2260
+    },
+    {
+      "epoch": 0.013292849676608976,
+      "grad_norm": 0.8863471150398254,
+      "learning_rate": 8.876923076923077e-05,
+      "loss": 0.4792426109313965,
+      "step": 2270
+    },
+    {
+      "epoch": 0.013351408485757034,
+      "grad_norm": 0.9258952736854553,
+      "learning_rate": 8.825641025641025e-05,
+      "loss": 0.6157923698425293,
+      "step": 2280
+    },
+    {
+      "epoch": 0.01340996729490509,
+      "grad_norm": 0.7849915027618408,
+      "learning_rate": 8.774358974358975e-05,
+      "loss": 0.5654351234436035,
+      "step": 2290
+    },
+    {
+      "epoch": 0.013468526104053148,
+      "grad_norm": 0.7935325503349304,
+      "learning_rate": 8.723076923076924e-05,
+      "loss": 0.5722135543823242,
+      "step": 2300
+    },
+    {
+      "epoch": 0.013527084913201206,
+      "grad_norm": 0.8465309739112854,
+      "learning_rate": 8.671794871794873e-05,
+      "loss": 0.5128249645233154,
+      "step": 2310
+    },
+    {
+      "epoch": 0.013585643722349262,
+      "grad_norm": 0.8264815211296082,
+      "learning_rate": 8.62051282051282e-05,
+      "loss": 0.6118460655212402,
+      "step": 2320
+    },
+    {
+      "epoch": 0.01364420253149732,
+      "grad_norm": 0.6705726385116577,
+      "learning_rate": 8.56923076923077e-05,
+      "loss": 0.5447952747344971,
+      "step": 2330
+    },
+    {
+      "epoch": 0.013702761340645377,
+      "grad_norm": 0.921404242515564,
+      "learning_rate": 8.517948717948719e-05,
+      "loss": 0.542200756072998,
+      "step": 2340
+    },
+    {
+      "epoch": 0.013761320149793433,
+      "grad_norm": 0.5786399245262146,
+      "learning_rate": 8.466666666666667e-05,
+      "loss": 0.5167455673217773,
+      "step": 2350
+    },
+    {
+      "epoch": 0.013819878958941491,
+      "grad_norm": 0.8080707788467407,
+      "learning_rate": 8.415384615384616e-05,
+      "loss": 0.495404052734375,
+      "step": 2360
+    },
+    {
+      "epoch": 0.013878437768089549,
+      "grad_norm": 0.7522940635681152,
+      "learning_rate": 8.364102564102565e-05,
+      "loss": 0.5303984165191651,
+      "step": 2370
+    },
+    {
+      "epoch": 0.013936996577237605,
+      "grad_norm": 0.9101510643959045,
+      "learning_rate": 8.312820512820513e-05,
+      "loss": 0.5638332843780518,
+      "step": 2380
+    },
+    {
+      "epoch": 0.013995555386385663,
+      "grad_norm": 0.6749529838562012,
+      "learning_rate": 8.261538461538462e-05,
+      "loss": 0.5651543617248536,
+      "step": 2390
+    },
+    {
+      "epoch": 0.014054114195533719,
+      "grad_norm": 0.9458379149436951,
+      "learning_rate": 8.21025641025641e-05,
+      "loss": 0.5108407497406006,
+      "step": 2400
+    },
+    {
+      "epoch": 0.014112673004681777,
+      "grad_norm": 1.089971899986267,
+      "learning_rate": 8.158974358974359e-05,
+      "loss": 0.49324331283569334,
+      "step": 2410
+    },
+    {
+      "epoch": 0.014171231813829835,
+      "grad_norm": 0.7607450485229492,
+      "learning_rate": 8.107692307692308e-05,
+      "loss": 0.6479440212249756,
+      "step": 2420
+    },
+    {
+      "epoch": 0.01422979062297789,
+      "grad_norm": 0.9622839093208313,
+      "learning_rate": 8.056410256410257e-05,
+      "loss": 0.5628427982330322,
+      "step": 2430
+    },
+    {
+      "epoch": 0.014288349432125948,
+      "grad_norm": 0.8064730167388916,
+      "learning_rate": 8.005128205128205e-05,
+      "loss": 0.4927206993103027,
+      "step": 2440
+    },
+    {
+      "epoch": 0.014346908241274006,
+      "grad_norm": 0.7792487144470215,
+      "learning_rate": 7.953846153846154e-05,
+      "loss": 0.6291625022888183,
+      "step": 2450
+    },
+    {
+      "epoch": 0.014405467050422062,
+      "grad_norm": 1.0805375576019287,
+      "learning_rate": 7.902564102564103e-05,
+      "loss": 0.5925718307495117,
+      "step": 2460
+    },
+    {
+      "epoch": 0.01446402585957012,
+      "grad_norm": 0.5765560865402222,
+      "learning_rate": 7.851282051282051e-05,
+      "loss": 0.5485690593719482,
+      "step": 2470
+    },
+    {
+      "epoch": 0.014522584668718176,
+      "grad_norm": 0.8152871131896973,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.5624689102172852,
+      "step": 2480
+    },
+    {
+      "epoch": 0.014581143477866234,
+      "grad_norm": 0.8335279226303101,
+      "learning_rate": 7.74871794871795e-05,
+      "loss": 0.5260688304901123,
+      "step": 2490
+    },
+    {
+      "epoch": 0.014639702287014292,
+      "grad_norm": 0.7680035829544067,
+      "learning_rate": 7.697435897435897e-05,
+      "loss": 0.4830802917480469,
+      "step": 2500
+    },
+    {
+      "epoch": 0.014698261096162348,
+      "grad_norm": 0.9397810697555542,
+      "learning_rate": 7.646153846153846e-05,
+      "loss": 0.5444638729095459,
+      "step": 2510
+    },
+    {
+      "epoch": 0.014756819905310406,
+      "grad_norm": 0.7944267392158508,
+      "learning_rate": 7.594871794871794e-05,
+      "loss": 0.6039426326751709,
+      "step": 2520
+    },
+    {
+      "epoch": 0.014815378714458463,
+      "grad_norm": 0.8528501987457275,
+      "learning_rate": 7.543589743589744e-05,
+      "loss": 0.5764337539672851,
+      "step": 2530
+    },
+    {
+      "epoch": 0.01487393752360652,
+      "grad_norm": 0.9321673512458801,
+      "learning_rate": 7.492307692307693e-05,
+      "loss": 0.5600544929504394,
+      "step": 2540
+    },
+    {
+      "epoch": 0.014932496332754577,
+      "grad_norm": 0.8647655248641968,
+      "learning_rate": 7.441025641025642e-05,
+      "loss": 0.6365120887756348,
+      "step": 2550
+    },
+    {
+      "epoch": 0.014991055141902635,
+      "grad_norm": 0.9241213798522949,
+      "learning_rate": 7.389743589743589e-05,
+      "loss": 0.5070790767669677,
+      "step": 2560
+    },
+    {
+      "epoch": 0.015049613951050691,
+      "grad_norm": 0.6943749785423279,
+      "learning_rate": 7.338461538461539e-05,
+      "loss": 0.5472688674926758,
+      "step": 2570
+    },
+    {
+      "epoch": 0.015108172760198749,
+      "grad_norm": 0.7544350624084473,
+      "learning_rate": 7.287179487179488e-05,
+      "loss": 0.5143001079559326,
+      "step": 2580
+    },
+    {
+      "epoch": 0.015166731569346805,
+      "grad_norm": 0.8759540319442749,
+      "learning_rate": 7.235897435897436e-05,
+      "loss": 0.5885789871215821,
+      "step": 2590
+    },
+    {
+      "epoch": 0.015225290378494863,
+      "grad_norm": 0.8004186153411865,
+      "learning_rate": 7.184615384615385e-05,
+      "loss": 0.5833802223205566,
+      "step": 2600
+    },
+    {
+      "epoch": 0.01528384918764292,
+      "grad_norm": 0.8919973969459534,
+      "learning_rate": 7.133333333333334e-05,
+      "loss": 0.7211344242095947,
+      "step": 2610
+    },
+    {
+      "epoch": 0.015342407996790977,
+      "grad_norm": 0.6915315985679626,
+      "learning_rate": 7.082051282051282e-05,
+      "loss": 0.5526168823242188,
+      "step": 2620
+    },
+    {
+      "epoch": 0.015400966805939035,
+      "grad_norm": 0.9145429134368896,
+      "learning_rate": 7.030769230769231e-05,
+      "loss": 0.4407088279724121,
+      "step": 2630
+    },
+    {
+      "epoch": 0.015459525615087092,
+      "grad_norm": 0.674967885017395,
+      "learning_rate": 6.97948717948718e-05,
+      "loss": 0.4634512424468994,
+      "step": 2640
+    },
+    {
+      "epoch": 0.015518084424235148,
+      "grad_norm": 0.6875638365745544,
+      "learning_rate": 6.928205128205128e-05,
+      "loss": 0.47414402961730956,
+      "step": 2650
+    },
+    {
+      "epoch": 0.015576643233383206,
+      "grad_norm": 0.9719008803367615,
+      "learning_rate": 6.876923076923077e-05,
+      "loss": 0.5467365264892579,
+      "step": 2660
+    },
+    {
+      "epoch": 0.015635202042531264,
+      "grad_norm": 0.7496704459190369,
+      "learning_rate": 6.825641025641027e-05,
+      "loss": 0.5100692749023438,
+      "step": 2670
+    },
+    {
+      "epoch": 0.015693760851679322,
+      "grad_norm": 0.6996882557868958,
+      "learning_rate": 6.774358974358974e-05,
+      "loss": 0.5840377330780029,
+      "step": 2680
+    },
+    {
+      "epoch": 0.015752319660827376,
+      "grad_norm": 0.8965880274772644,
+      "learning_rate": 6.723076923076923e-05,
+      "loss": 0.5683030605316162,
+      "step": 2690
+    },
+    {
+      "epoch": 0.015810878469975434,
+      "grad_norm": 0.9862522482872009,
+      "learning_rate": 6.671794871794872e-05,
+      "loss": 0.5894110679626465,
+      "step": 2700
+    },
+    {
+      "epoch": 0.015869437279123492,
+      "grad_norm": 0.9664445519447327,
+      "learning_rate": 6.62051282051282e-05,
+      "loss": 0.5402120590209961,
+      "step": 2710
+    },
+    {
+      "epoch": 0.01592799608827155,
+      "grad_norm": 0.8799305558204651,
+      "learning_rate": 6.56923076923077e-05,
+      "loss": 0.5548243045806884,
+      "step": 2720
+    },
+    {
+      "epoch": 0.015986554897419607,
+      "grad_norm": 0.6217681169509888,
+      "learning_rate": 6.517948717948719e-05,
+      "loss": 0.48618650436401367,
+      "step": 2730
+    },
+    {
+      "epoch": 0.016045113706567662,
+      "grad_norm": 0.7473154664039612,
+      "learning_rate": 6.466666666666666e-05,
+      "loss": 0.5558083057403564,
+      "step": 2740
+    },
+    {
+      "epoch": 0.01610367251571572,
+      "grad_norm": 0.8467188477516174,
+      "learning_rate": 6.415384615384615e-05,
+      "loss": 0.5468488216400147,
+      "step": 2750
+    },
+    {
+      "epoch": 0.016162231324863777,
+      "grad_norm": 0.8353908658027649,
+      "learning_rate": 6.364102564102565e-05,
+      "loss": 0.55488600730896,
+      "step": 2760
+    },
+    {
+      "epoch": 0.016220790134011835,
+      "grad_norm": 1.0089359283447266,
+      "learning_rate": 6.312820512820514e-05,
+      "loss": 0.4439121723175049,
+      "step": 2770
+    },
+    {
+      "epoch": 0.016279348943159893,
+      "grad_norm": 0.8033394813537598,
+      "learning_rate": 6.261538461538462e-05,
+      "loss": 0.592630672454834,
+      "step": 2780
+    },
+    {
+      "epoch": 0.01633790775230795,
+      "grad_norm": 0.7081058621406555,
+      "learning_rate": 6.210256410256411e-05,
+      "loss": 0.5640474319458008,
+      "step": 2790
+    },
+    {
+      "epoch": 0.016396466561456005,
+      "grad_norm": 0.9237245321273804,
+      "learning_rate": 6.15897435897436e-05,
+      "loss": 0.6005640983581543,
+      "step": 2800
+    },
+    {
+      "epoch": 0.016455025370604063,
+      "grad_norm": 0.8360455632209778,
+      "learning_rate": 6.107692307692308e-05,
+      "loss": 0.5373104572296142,
+      "step": 2810
+    },
+    {
+      "epoch": 0.01651358417975212,
+      "grad_norm": 0.8988027572631836,
+      "learning_rate": 6.056410256410257e-05,
+      "loss": 0.5758774757385254,
+      "step": 2820
+    },
+    {
+      "epoch": 0.01657214298890018,
+      "grad_norm": 0.9521508812904358,
+      "learning_rate": 6.0051282051282054e-05,
+      "loss": 0.5425063133239746,
+      "step": 2830
+    },
+    {
+      "epoch": 0.016630701798048236,
+      "grad_norm": 1.0230766534805298,
+      "learning_rate": 5.953846153846154e-05,
+      "loss": 0.617734146118164,
+      "step": 2840
+    },
+    {
+      "epoch": 0.01668926060719629,
+      "grad_norm": 0.8182085752487183,
+      "learning_rate": 5.9025641025641034e-05,
+      "loss": 0.49785604476928713,
+      "step": 2850
+    },
+    {
+      "epoch": 0.01674781941634435,
+      "grad_norm": 0.819509744644165,
+      "learning_rate": 5.851282051282052e-05,
+      "loss": 0.5303618907928467,
+      "step": 2860
+    },
+    {
+      "epoch": 0.016806378225492406,
+      "grad_norm": 0.9338365197181702,
+      "learning_rate": 5.8e-05,
+      "loss": 0.5084160327911377,
+      "step": 2870
+    },
+    {
+      "epoch": 0.016864937034640464,
+      "grad_norm": 0.9572207927703857,
+      "learning_rate": 5.748717948717949e-05,
+      "loss": 0.5966866493225098,
+      "step": 2880
+    },
+    {
+      "epoch": 0.016923495843788522,
+      "grad_norm": 0.66383296251297,
+      "learning_rate": 5.6974358974358973e-05,
+      "loss": 0.5305398941040039,
+      "step": 2890
+    },
+    {
+      "epoch": 0.016982054652936576,
+      "grad_norm": 1.0674878358840942,
+      "learning_rate": 5.646153846153847e-05,
+      "loss": 0.556536340713501,
+      "step": 2900
+    },
+    {
+      "epoch": 0.017040613462084634,
+      "grad_norm": 0.7483784556388855,
+      "learning_rate": 5.594871794871795e-05,
+      "loss": 0.49668869972229,
+      "step": 2910
+    },
+    {
+      "epoch": 0.017099172271232692,
+      "grad_norm": 1.0706493854522705,
+      "learning_rate": 5.5435897435897447e-05,
+      "loss": 0.49158105850219724,
+      "step": 2920
+    },
+    {
+      "epoch": 0.01715773108038075,
+      "grad_norm": 0.7071096897125244,
+      "learning_rate": 5.492307692307692e-05,
+      "loss": 0.5811544895172119,
+      "step": 2930
+    },
+    {
+      "epoch": 0.017216289889528807,
+      "grad_norm": 0.8249266147613525,
+      "learning_rate": 5.441025641025641e-05,
+      "loss": 0.5450833797454834,
+      "step": 2940
+    },
+    {
+      "epoch": 0.017274848698676865,
+      "grad_norm": 0.684613823890686,
+      "learning_rate": 5.38974358974359e-05,
+      "loss": 0.5169521808624268,
+      "step": 2950
+    },
+    {
+      "epoch": 0.01733340750782492,
+      "grad_norm": 1.1294605731964111,
+      "learning_rate": 5.3384615384615386e-05,
+      "loss": 0.6362704277038574,
+      "step": 2960
+    },
+    {
+      "epoch": 0.017391966316972977,
+      "grad_norm": 0.7923810482025146,
+      "learning_rate": 5.287179487179488e-05,
+      "loss": 0.498931360244751,
+      "step": 2970
+    },
+    {
+      "epoch": 0.017450525126121035,
+      "grad_norm": 0.8153409957885742,
+      "learning_rate": 5.2358974358974366e-05,
+      "loss": 0.5227402687072754,
+      "step": 2980
+    },
+    {
+      "epoch": 0.017509083935269093,
+      "grad_norm": 0.8139829635620117,
+      "learning_rate": 5.1846153846153845e-05,
+      "loss": 0.5427112102508544,
+      "step": 2990
+    },
+    {
+      "epoch": 0.01756764274441715,
+      "grad_norm": 0.7023552060127258,
+      "learning_rate": 5.133333333333333e-05,
+      "loss": 0.5183414459228516,
+      "step": 3000
+    },
+    {
+      "epoch": 0.017626201553565205,
+      "grad_norm": 1.1172661781311035,
+      "learning_rate": 5.0820512820512825e-05,
+      "loss": 0.5479337692260742,
+      "step": 3010
+    },
+    {
+      "epoch": 0.017684760362713263,
+      "grad_norm": 0.9706581234931946,
+      "learning_rate": 5.030769230769231e-05,
+      "loss": 0.5230507373809814,
+      "step": 3020
+    },
+    {
+      "epoch": 0.01774331917186132,
+      "grad_norm": 0.9869327545166016,
+      "learning_rate": 4.979487179487179e-05,
+      "loss": 0.5095770359039307,
+      "step": 3030
+    },
+    {
+      "epoch": 0.01780187798100938,
+      "grad_norm": 1.0374623537063599,
+      "learning_rate": 4.9282051282051285e-05,
+      "loss": 0.5869725704193115,
+      "step": 3040
+    },
+    {
+      "epoch": 0.017860436790157436,
+      "grad_norm": 1.1641126871109009,
+      "learning_rate": 4.876923076923077e-05,
+      "loss": 0.6153728008270264,
+      "step": 3050
+    },
+    {
+      "epoch": 0.017918995599305494,
+      "grad_norm": 0.9592261910438538,
+      "learning_rate": 4.825641025641026e-05,
+      "loss": 0.4673551082611084,
+      "step": 3060
+    },
+    {
+      "epoch": 0.01797755440845355,
+      "grad_norm": 0.9529333114624023,
+      "learning_rate": 4.7743589743589744e-05,
+      "loss": 0.5785486698150635,
+      "step": 3070
+    },
+    {
+      "epoch": 0.018036113217601606,
+      "grad_norm": 0.9785205125808716,
+      "learning_rate": 4.723076923076923e-05,
+      "loss": 0.6254173278808594,
+      "step": 3080
+    },
+    {
+      "epoch": 0.018094672026749664,
+      "grad_norm": 0.7712920308113098,
+      "learning_rate": 4.671794871794872e-05,
+      "loss": 0.5232354640960694,
+      "step": 3090
+    },
+    {
+      "epoch": 0.018153230835897722,
+      "grad_norm": 0.9690357446670532,
+      "learning_rate": 4.6205128205128204e-05,
+      "loss": 0.6493497371673584,
+      "step": 3100
+    },
+    {
+      "epoch": 0.01821178964504578,
+      "grad_norm": 0.7151793241500854,
+      "learning_rate": 4.56923076923077e-05,
+      "loss": 0.4791082859039307,
+      "step": 3110
+    },
+    {
+      "epoch": 0.018270348454193834,
+      "grad_norm": 1.0174742937088013,
+      "learning_rate": 4.5179487179487184e-05,
+      "loss": 0.6347029685974122,
+      "step": 3120
+    },
+    {
+      "epoch": 0.018328907263341892,
+      "grad_norm": 0.8618830442428589,
+      "learning_rate": 4.466666666666667e-05,
+      "loss": 0.5541427135467529,
+      "step": 3130
+    },
+    {
+      "epoch": 0.01838746607248995,
+      "grad_norm": 0.9328573942184448,
+      "learning_rate": 4.415384615384616e-05,
+      "loss": 0.49029951095581054,
+      "step": 3140
+    },
+    {
+      "epoch": 0.018446024881638007,
+      "grad_norm": 1.0293370485305786,
+      "learning_rate": 4.3641025641025643e-05,
+      "loss": 0.49523158073425294,
+      "step": 3150
+    },
+    {
+      "epoch": 0.018504583690786065,
+      "grad_norm": 0.8024817109107971,
+      "learning_rate": 4.312820512820513e-05,
+      "loss": 0.6391828536987305,
+      "step": 3160
+    },
+    {
+      "epoch": 0.01856314249993412,
+      "grad_norm": 0.7935349941253662,
+      "learning_rate": 4.2615384615384617e-05,
+      "loss": 0.535066032409668,
+      "step": 3170
+    },
+    {
+      "epoch": 0.018621701309082177,
+      "grad_norm": 1.0129835605621338,
+      "learning_rate": 4.210256410256411e-05,
+      "loss": 0.5176414012908935,
+      "step": 3180
+    },
+    {
+      "epoch": 0.018680260118230235,
+      "grad_norm": 0.7804064154624939,
+      "learning_rate": 4.158974358974359e-05,
+      "loss": 0.5758108615875244,
+      "step": 3190
+    },
+    {
+      "epoch": 0.018738818927378293,
+      "grad_norm": 1.0611324310302734,
+      "learning_rate": 4.1076923076923076e-05,
+      "loss": 0.5137322902679443,
+      "step": 3200
+    },
+    {
+      "epoch": 0.01879737773652635,
+      "grad_norm": 0.9809267520904541,
+      "learning_rate": 4.056410256410257e-05,
+      "loss": 0.5527653217315673,
+      "step": 3210
+    },
+    {
+      "epoch": 0.01885593654567441,
+      "grad_norm": 0.7737221717834473,
+      "learning_rate": 4.005128205128205e-05,
+      "loss": 0.622959041595459,
+      "step": 3220
+    },
+    {
+      "epoch": 0.018914495354822463,
+      "grad_norm": 0.6540891528129578,
+      "learning_rate": 3.953846153846154e-05,
+      "loss": 0.49772024154663086,
+      "step": 3230
+    },
+    {
+      "epoch": 0.01897305416397052,
+      "grad_norm": 0.861090362071991,
+      "learning_rate": 3.902564102564103e-05,
+      "loss": 0.576954984664917,
+      "step": 3240
+    },
+    {
+      "epoch": 0.01903161297311858,
+      "grad_norm": 0.929144024848938,
+      "learning_rate": 3.8512820512820516e-05,
+      "loss": 0.6221125602722168,
+      "step": 3250
+    },
+    {
+      "epoch": 0.019090171782266636,
+      "grad_norm": 0.7518307566642761,
+      "learning_rate": 3.8e-05,
+      "loss": 0.6510417938232422,
+      "step": 3260
+    },
+    {
+      "epoch": 0.019148730591414694,
+      "grad_norm": 0.7619118094444275,
+      "learning_rate": 3.748717948717949e-05,
+      "loss": 0.5681602954864502,
+      "step": 3270
+    },
+    {
+      "epoch": 0.01920728940056275,
+      "grad_norm": 0.926790714263916,
+      "learning_rate": 3.6974358974358975e-05,
+      "loss": 0.5376785278320313,
+      "step": 3280
+    },
+    {
+      "epoch": 0.019265848209710806,
+      "grad_norm": 0.871703565120697,
+      "learning_rate": 3.646153846153846e-05,
+      "loss": 0.5535645008087158,
+      "step": 3290
+    },
+    {
+      "epoch": 0.019324407018858864,
+      "grad_norm": 0.9614275693893433,
+      "learning_rate": 3.5948717948717955e-05,
+      "loss": 0.49208922386169435,
+      "step": 3300
+    },
+    {
+      "epoch": 0.019382965828006922,
+      "grad_norm": 0.9823223352432251,
+      "learning_rate": 3.5435897435897435e-05,
+      "loss": 0.5003201961517334,
+      "step": 3310
+    },
+    {
+      "epoch": 0.01944152463715498,
+      "grad_norm": 0.8970009088516235,
+      "learning_rate": 3.492307692307693e-05,
+      "loss": 0.5308861255645752,
+      "step": 3320
+    },
+    {
+      "epoch": 0.019500083446303038,
+      "grad_norm": 0.7754250764846802,
+      "learning_rate": 3.4410256410256415e-05,
+      "loss": 0.5034646034240723,
+      "step": 3330
+    },
+    {
+      "epoch": 0.019558642255451092,
+      "grad_norm": 0.7612975835800171,
+      "learning_rate": 3.3897435897435894e-05,
+      "loss": 0.5634318351745605,
+      "step": 3340
+    },
+    {
+      "epoch": 0.01961720106459915,
+      "grad_norm": 0.8280472755432129,
+      "learning_rate": 3.338461538461539e-05,
+      "loss": 0.6287012577056885,
+      "step": 3350
+    },
+    {
+      "epoch": 0.019675759873747208,
+      "grad_norm": 0.8421421647071838,
+      "learning_rate": 3.2871794871794874e-05,
+      "loss": 0.5922800540924072,
+      "step": 3360
+    },
+    {
+      "epoch": 0.019734318682895265,
+      "grad_norm": 0.9054791927337646,
+      "learning_rate": 3.235897435897436e-05,
+      "loss": 0.5123564243316651,
+      "step": 3370
+    },
+    {
+      "epoch": 0.019792877492043323,
+      "grad_norm": 0.7409724593162537,
+      "learning_rate": 3.184615384615385e-05,
+      "loss": 0.5477404594421387,
+      "step": 3380
+    },
+    {
+      "epoch": 0.019851436301191377,
+      "grad_norm": 1.0175254344940186,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 0.5544933795928955,
+      "step": 3390
+    },
+    {
+      "epoch": 0.019909995110339435,
+      "grad_norm": 0.6535821557044983,
+      "learning_rate": 3.082051282051282e-05,
+      "loss": 0.5649590492248535,
+      "step": 3400
+    },
+    {
+      "epoch": 0.019968553919487493,
+      "grad_norm": 0.8674274682998657,
+      "learning_rate": 3.030769230769231e-05,
+      "loss": 0.565241003036499,
+      "step": 3410
+    },
+    {
+      "epoch": 0.02002711272863555,
+      "grad_norm": 0.8033132553100586,
+      "learning_rate": 2.9794871794871797e-05,
+      "loss": 0.515103816986084,
+      "step": 3420
+    },
+    {
+      "epoch": 0.02008567153778361,
+      "grad_norm": 1.0296214818954468,
+      "learning_rate": 2.9282051282051283e-05,
+      "loss": 0.5208463668823242,
+      "step": 3430
+    },
+    {
+      "epoch": 0.020144230346931667,
+      "grad_norm": 0.8400964736938477,
+      "learning_rate": 2.876923076923077e-05,
+      "loss": 0.5142516136169434,
+      "step": 3440
+    },
+    {
+      "epoch": 0.02020278915607972,
+      "grad_norm": 0.8163658976554871,
+      "learning_rate": 2.825641025641026e-05,
+      "loss": 0.5436674118041992,
+      "step": 3450
+    },
+    {
+      "epoch": 0.02026134796522778,
+      "grad_norm": 0.8809291124343872,
+      "learning_rate": 2.7743589743589743e-05,
+      "loss": 0.5333271026611328,
+      "step": 3460
+    },
+    {
+      "epoch": 0.020319906774375836,
+      "grad_norm": 0.8439704179763794,
+      "learning_rate": 2.7230769230769233e-05,
+      "loss": 0.5213183403015137,
+      "step": 3470
+    },
+    {
+      "epoch": 0.020378465583523894,
+      "grad_norm": 0.8002095222473145,
+      "learning_rate": 2.671794871794872e-05,
+      "loss": 0.4625570297241211,
+      "step": 3480
+    },
+    {
+      "epoch": 0.020437024392671952,
+      "grad_norm": 0.899154007434845,
+      "learning_rate": 2.6205128205128206e-05,
+      "loss": 0.4710862636566162,
+      "step": 3490
+    },
+    {
+      "epoch": 0.020495583201820006,
+      "grad_norm": 0.9485552906990051,
+      "learning_rate": 2.5692307692307692e-05,
+      "loss": 0.47341165542602537,
+      "step": 3500
+    },
+    {
+      "epoch": 0.020554142010968064,
+      "grad_norm": 1.1024211645126343,
+      "learning_rate": 2.5179487179487182e-05,
+      "loss": 0.5134012222290039,
+      "step": 3510
+    },
+    {
+      "epoch": 0.020612700820116122,
+      "grad_norm": 0.876735508441925,
+      "learning_rate": 2.466666666666667e-05,
+      "loss": 0.5757248878479004,
+      "step": 3520
+    },
+    {
+      "epoch": 0.02067125962926418,
+      "grad_norm": 0.7668870091438293,
+      "learning_rate": 2.4153846153846155e-05,
+      "loss": 0.44100046157836914,
+      "step": 3530
+    },
+    {
+      "epoch": 0.020729818438412238,
+      "grad_norm": 0.889595091342926,
+      "learning_rate": 2.3641025641025642e-05,
+      "loss": 0.509488582611084,
+      "step": 3540
+    },
+    {
+      "epoch": 0.020788377247560292,
+      "grad_norm": 0.9260969758033752,
+      "learning_rate": 2.312820512820513e-05,
+      "loss": 0.5279482841491699,
+      "step": 3550
+    },
+    {
+      "epoch": 0.02084693605670835,
+      "grad_norm": 0.8012005686759949,
+      "learning_rate": 2.2615384615384615e-05,
+      "loss": 0.5833855628967285,
+      "step": 3560
+    },
+    {
+      "epoch": 0.020905494865856408,
+      "grad_norm": 0.7497194409370422,
+      "learning_rate": 2.21025641025641e-05,
+      "loss": 0.5504710674285889,
+      "step": 3570
+    },
+    {
+      "epoch": 0.020964053675004465,
+      "grad_norm": 0.7818493247032166,
+      "learning_rate": 2.158974358974359e-05,
+      "loss": 0.49176998138427735,
+      "step": 3580
+    },
+    {
+      "epoch": 0.021022612484152523,
+      "grad_norm": 0.9991495609283447,
+      "learning_rate": 2.1076923076923078e-05,
+      "loss": 0.5877357482910156,
+      "step": 3590
+    },
+    {
+      "epoch": 0.02108117129330058,
+      "grad_norm": 0.7078049778938293,
+      "learning_rate": 2.0564102564102568e-05,
+      "loss": 0.505121898651123,
+      "step": 3600
+    },
+    {
+      "epoch": 0.021139730102448635,
+      "grad_norm": 0.9660176038742065,
+      "learning_rate": 2.005128205128205e-05,
+      "loss": 0.618731164932251,
+      "step": 3610
+    },
+    {
+      "epoch": 0.021198288911596693,
+      "grad_norm": 0.8069267868995667,
+      "learning_rate": 1.9538461538461537e-05,
+      "loss": 0.5255807399749756,
+      "step": 3620
+    },
+    {
+      "epoch": 0.02125684772074475,
+      "grad_norm": 0.9080344438552856,
+      "learning_rate": 1.9025641025641027e-05,
+      "loss": 0.46593737602233887,
+      "step": 3630
+    },
+    {
+      "epoch": 0.02131540652989281,
+      "grad_norm": 1.0831979513168335,
+      "learning_rate": 1.8512820512820514e-05,
+      "loss": 0.5550206184387207,
+      "step": 3640
+    },
+    {
+      "epoch": 0.021373965339040867,
+      "grad_norm": 0.86371910572052,
+      "learning_rate": 1.8e-05,
+      "loss": 0.5238677978515625,
+      "step": 3650
+    },
+    {
+      "epoch": 0.02143252414818892,
+      "grad_norm": 0.9403280019760132,
+      "learning_rate": 1.748717948717949e-05,
+      "loss": 0.5675028800964356,
+      "step": 3660
+    },
+    {
+      "epoch": 0.02149108295733698,
+      "grad_norm": 1.034886360168457,
+      "learning_rate": 1.6974358974358977e-05,
+      "loss": 0.4517046928405762,
+      "step": 3670
+    },
+    {
+      "epoch": 0.021549641766485036,
+      "grad_norm": 0.8609821200370789,
+      "learning_rate": 1.646153846153846e-05,
+      "loss": 0.5229743003845215,
+      "step": 3680
+    },
+    {
+      "epoch": 0.021608200575633094,
+      "grad_norm": 0.9956978559494019,
+      "learning_rate": 1.594871794871795e-05,
+      "loss": 0.544053030014038,
+      "step": 3690
+    },
+    {
+      "epoch": 0.021666759384781152,
+      "grad_norm": 0.7684548497200012,
+      "learning_rate": 1.5435897435897436e-05,
+      "loss": 0.4915327548980713,
+      "step": 3700
+    },
+    {
+      "epoch": 0.02172531819392921,
+      "grad_norm": 0.9081255197525024,
+      "learning_rate": 1.4923076923076923e-05,
+      "loss": 0.6240507125854492,
+      "step": 3710
+    },
+    {
+      "epoch": 0.021783877003077264,
+      "grad_norm": 0.9593307375907898,
+      "learning_rate": 1.4410256410256411e-05,
+      "loss": 0.5579314231872559,
+      "step": 3720
+    },
+    {
+      "epoch": 0.021842435812225322,
+      "grad_norm": 0.7121111154556274,
+      "learning_rate": 1.3897435897435898e-05,
+      "loss": 0.5342877388000489,
+      "step": 3730
+    },
+    {
+      "epoch": 0.02190099462137338,
+      "grad_norm": 0.6428033113479614,
+      "learning_rate": 1.3384615384615384e-05,
+      "loss": 0.5590609550476074,
+      "step": 3740
+    },
+    {
+      "epoch": 0.021959553430521438,
+      "grad_norm": 0.7580998539924622,
+      "learning_rate": 1.2871794871794873e-05,
+      "loss": 0.5434789657592773,
+      "step": 3750
+    },
+    {
+      "epoch": 0.022018112239669495,
+      "grad_norm": 0.7449846267700195,
+      "learning_rate": 1.2358974358974359e-05,
+      "loss": 0.6341854572296143,
+      "step": 3760
+    },
+    {
+      "epoch": 0.02207667104881755,
+      "grad_norm": 0.8563600778579712,
+      "learning_rate": 1.1846153846153847e-05,
+      "loss": 0.5225186347961426,
+      "step": 3770
+    },
+    {
+      "epoch": 0.022135229857965608,
+      "grad_norm": 0.77638179063797,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 0.5983168125152588,
+      "step": 3780
+    },
+    {
+      "epoch": 0.022193788667113665,
+      "grad_norm": 0.9314567446708679,
+      "learning_rate": 1.082051282051282e-05,
+      "loss": 0.5252968311309815,
+      "step": 3790
+    },
+    {
+      "epoch": 0.022252347476261723,
+      "grad_norm": 0.7917819619178772,
+      "learning_rate": 1.0307692307692309e-05,
+      "loss": 0.5200023651123047,
+      "step": 3800
+    },
+    {
+      "epoch": 0.02231090628540978,
+      "grad_norm": 0.8292711973190308,
+      "learning_rate": 9.794871794871795e-06,
+      "loss": 0.6304655075073242,
+      "step": 3810
+    },
+    {
+      "epoch": 0.022369465094557835,
+      "grad_norm": 0.9499213099479675,
+      "learning_rate": 9.282051282051282e-06,
+      "loss": 0.5582314491271972,
+      "step": 3820
+    },
+    {
+      "epoch": 0.022428023903705893,
+      "grad_norm": 0.8777642250061035,
+      "learning_rate": 8.76923076923077e-06,
+      "loss": 0.5100115776062012,
+      "step": 3830
+    },
+    {
+      "epoch": 0.02248658271285395,
+      "grad_norm": 1.1725077629089355,
+      "learning_rate": 8.256410256410258e-06,
+      "loss": 0.45162396430969237,
+      "step": 3840
+    },
+    {
+      "epoch": 0.02254514152200201,
+      "grad_norm": 0.7961176037788391,
+      "learning_rate": 7.743589743589743e-06,
+      "loss": 0.6337620735168457,
+      "step": 3850
+    },
+    {
+      "epoch": 0.022603700331150067,
+      "grad_norm": 0.6456913948059082,
+      "learning_rate": 7.230769230769231e-06,
+      "loss": 0.5502284049987793,
+      "step": 3860
+    },
+    {
+      "epoch": 0.022662259140298124,
+      "grad_norm": 1.164849042892456,
+      "learning_rate": 6.7179487179487185e-06,
+      "loss": 0.5302950859069824,
+      "step": 3870
+    },
+    {
+      "epoch": 0.02272081794944618,
+      "grad_norm": 0.6571502089500427,
+      "learning_rate": 6.205128205128206e-06,
+      "loss": 0.5240830898284912,
+      "step": 3880
+    },
+    {
+      "epoch": 0.022779376758594237,
+      "grad_norm": 0.9722093939781189,
+      "learning_rate": 5.692307692307692e-06,
+      "loss": 0.4951435089111328,
+      "step": 3890
+    },
+    {
+      "epoch": 0.022837935567742294,
+      "grad_norm": 0.9843414425849915,
+      "learning_rate": 5.17948717948718e-06,
+      "loss": 0.5722742557525635,
+      "step": 3900
+    },
+    {
+      "epoch": 0.022896494376890352,
+      "grad_norm": 0.6342486143112183,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.4842282772064209,
+      "step": 3910
+    },
+    {
+      "epoch": 0.02295505318603841,
+      "grad_norm": 0.6415958404541016,
+      "learning_rate": 4.153846153846154e-06,
+      "loss": 0.47517008781433107,
+      "step": 3920
+    },
+    {
+      "epoch": 0.023013611995186464,
+      "grad_norm": 1.1181350946426392,
+      "learning_rate": 3.641025641025641e-06,
+      "loss": 0.5694285869598389,
+      "step": 3930
+    },
+    {
+      "epoch": 0.023072170804334522,
+      "grad_norm": 0.9920271635055542,
+      "learning_rate": 3.1282051282051284e-06,
+      "loss": 0.5452847480773926,
+      "step": 3940
+    },
+    {
+      "epoch": 0.02313072961348258,
+      "grad_norm": 0.9259868860244751,
+      "learning_rate": 2.6153846153846154e-06,
+      "loss": 0.46974477767944334,
+      "step": 3950
+    },
+    {
+      "epoch": 0.023189288422630638,
+      "grad_norm": 0.9503214955329895,
+      "learning_rate": 2.1025641025641028e-06,
+      "loss": 0.5481606006622315,
+      "step": 3960
+    },
+    {
+      "epoch": 0.023247847231778695,
+      "grad_norm": 0.6119986772537231,
+      "learning_rate": 1.58974358974359e-06,
+      "loss": 0.5004695892333985,
+      "step": 3970
+    },
+    {
+      "epoch": 0.023306406040926753,
+      "grad_norm": 1.1628342866897583,
+      "learning_rate": 1.0769230769230769e-06,
+      "loss": 0.5574374675750733,
+      "step": 3980
+    },
+    {
+      "epoch": 0.023364964850074808,
+      "grad_norm": 1.1909202337265015,
+      "learning_rate": 5.641025641025642e-07,
+      "loss": 0.5625033855438233,
+      "step": 3990
+    },
+    {
+      "epoch": 0.023423523659222865,
+      "grad_norm": 0.8099654316902161,
+      "learning_rate": 5.1282051282051286e-08,
+      "loss": 0.5457859516143799,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.098826736098355e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

adapter/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b31c165767a8418547683b7b0bb98466ae2cea43d76fd57aefee2b75c80453
+size 5713