Upload LoRA model

.gitattributes

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

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-11B-Vision-Instruct
+library_name: peft
+---
+
+# 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 0.15.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-11B-Vision-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|fc1|fc2|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|fc1|fc2|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d15022c1cf2b2982ec60146c7b2f6e2bd896199e5559f1d8c627df6ebe958e
+size 537553128

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- for content in message['content'] %}\n        {%- if content['type'] == 'image' %}\n            {%- set image_ns.has_images = true %}\n        {%- endif %}\n    {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n    {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n    {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n    {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c51aa6d76c9951af91fb1b4f48116330550bc6d94c977347431f464659a3535
+size 274115796

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "MllamaImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_image_tiles": 4,
+  "processor_class": "MllamaProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 560,
+    "width": 560
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138de50ad6b3b921a022dee7f6e2b3b8fb8a85b405698282930e0365039524ee
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195417c027687310dbf52a7a6255af2c7103e9ece2b5a6d66e10b186c9a4b183
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9816d43bd5347d64bccc66b7710947fb18e9818cc660215b1462061d4a44e449
+size 17210088

tokenizer_config.json

@@ -0,0 +1,2075 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|step_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- for content in message['content'] %}\n        {%- if content['type'] == 'image' %}\n            {%- set image_ns.has_images = true %}\n        {%- endif %}\n    {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n    {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n    {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n    {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "processor_class": "MllamaProcessor",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3544 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1637506304069518,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023276564379097644,
+      "grad_norm": 0.27823981642723083,
+      "learning_rate": 0.0001998253681820828,
+      "loss": 0.7939,
+      "step": 20
+    },
+    {
+      "epoch": 0.004655312875819529,
+      "grad_norm": 0.1868295669555664,
+      "learning_rate": 0.00019959252575819315,
+      "loss": 0.5151,
+      "step": 40
+    },
+    {
+      "epoch": 0.006982969313729294,
+      "grad_norm": 0.1747283935546875,
+      "learning_rate": 0.00019935968333430353,
+      "loss": 0.5012,
+      "step": 60
+    },
+    {
+      "epoch": 0.009310625751639058,
+      "grad_norm": 0.25282350182533264,
+      "learning_rate": 0.00019912684091041388,
+      "loss": 0.4886,
+      "step": 80
+    },
+    {
+      "epoch": 0.011638282189548823,
+      "grad_norm": 0.2447253316640854,
+      "learning_rate": 0.00019889399848652426,
+      "loss": 0.496,
+      "step": 100
+    },
+    {
+      "epoch": 0.013965938627458587,
+      "grad_norm": 0.16302281618118286,
+      "learning_rate": 0.00019866115606263462,
+      "loss": 0.486,
+      "step": 120
+    },
+    {
+      "epoch": 0.01629359506536835,
+      "grad_norm": 0.35491931438446045,
+      "learning_rate": 0.000198428313638745,
+      "loss": 0.4679,
+      "step": 140
+    },
+    {
+      "epoch": 0.018621251503278115,
+      "grad_norm": 0.17740242183208466,
+      "learning_rate": 0.00019819547121485535,
+      "loss": 0.4611,
+      "step": 160
+    },
+    {
+      "epoch": 0.02094890794118788,
+      "grad_norm": 0.17487157881259918,
+      "learning_rate": 0.00019796262879096573,
+      "loss": 0.4438,
+      "step": 180
+    },
+    {
+      "epoch": 0.023276564379097645,
+      "grad_norm": 0.1718546748161316,
+      "learning_rate": 0.0001977297863670761,
+      "loss": 0.4547,
+      "step": 200
+    },
+    {
+      "epoch": 0.02560422081700741,
+      "grad_norm": 0.18816465139389038,
+      "learning_rate": 0.00019749694394318644,
+      "loss": 0.4634,
+      "step": 220
+    },
+    {
+      "epoch": 0.027931877254917175,
+      "grad_norm": 0.21253204345703125,
+      "learning_rate": 0.00019726410151929682,
+      "loss": 0.4552,
+      "step": 240
+    },
+    {
+      "epoch": 0.03025953369282694,
+      "grad_norm": 0.14169463515281677,
+      "learning_rate": 0.00019703125909540718,
+      "loss": 0.4392,
+      "step": 260
+    },
+    {
+      "epoch": 0.0325871901307367,
+      "grad_norm": 0.2283576875925064,
+      "learning_rate": 0.00019679841667151756,
+      "loss": 0.4438,
+      "step": 280
+    },
+    {
+      "epoch": 0.03491484656864647,
+      "grad_norm": 0.2746244966983795,
+      "learning_rate": 0.00019656557424762794,
+      "loss": 0.4496,
+      "step": 300
+    },
+    {
+      "epoch": 0.03724250300655623,
+      "grad_norm": 18.962121963500977,
+      "learning_rate": 0.0001963327318237383,
+      "loss": 0.4681,
+      "step": 320
+    },
+    {
+      "epoch": 0.039570159444466,
+      "grad_norm": 0.2113800346851349,
+      "learning_rate": 0.00019609988939984867,
+      "loss": 0.4549,
+      "step": 340
+    },
+    {
+      "epoch": 0.04189781588237576,
+      "grad_norm": 0.19274094700813293,
+      "learning_rate": 0.00019586704697595903,
+      "loss": 0.423,
+      "step": 360
+    },
+    {
+      "epoch": 0.04422547232028553,
+      "grad_norm": 0.20447246730327606,
+      "learning_rate": 0.0001956342045520694,
+      "loss": 0.4267,
+      "step": 380
+    },
+    {
+      "epoch": 0.04655312875819529,
+      "grad_norm": 0.19354546070098877,
+      "learning_rate": 0.00019540136212817976,
+      "loss": 0.4407,
+      "step": 400
+    },
+    {
+      "epoch": 0.04888078519610505,
+      "grad_norm": 0.17711375653743744,
+      "learning_rate": 0.00019516851970429014,
+      "loss": 0.4435,
+      "step": 420
+    },
+    {
+      "epoch": 0.05120844163401482,
+      "grad_norm": 0.16099664568901062,
+      "learning_rate": 0.0001949356772804005,
+      "loss": 0.4404,
+      "step": 440
+    },
+    {
+      "epoch": 0.05353609807192458,
+      "grad_norm": 0.2000165581703186,
+      "learning_rate": 0.00019470283485651088,
+      "loss": 0.4294,
+      "step": 460
+    },
+    {
+      "epoch": 0.05586375450983435,
+      "grad_norm": 0.16999505460262299,
+      "learning_rate": 0.00019446999243262123,
+      "loss": 0.4434,
+      "step": 480
+    },
+    {
+      "epoch": 0.05819141094774411,
+      "grad_norm": 0.15882228314876556,
+      "learning_rate": 0.00019423715000873158,
+      "loss": 0.4314,
+      "step": 500
+    },
+    {
+      "epoch": 0.06051906738565388,
+      "grad_norm": 0.26531532406806946,
+      "learning_rate": 0.00019400430758484196,
+      "loss": 0.4251,
+      "step": 520
+    },
+    {
+      "epoch": 0.06284672382356364,
+      "grad_norm": 0.31235167384147644,
+      "learning_rate": 0.00019377146516095232,
+      "loss": 0.4437,
+      "step": 540
+    },
+    {
+      "epoch": 0.0651743802614734,
+      "grad_norm": 0.22516918182373047,
+      "learning_rate": 0.0001935386227370627,
+      "loss": 0.4348,
+      "step": 560
+    },
+    {
+      "epoch": 0.06750203669938318,
+      "grad_norm": 0.25530752539634705,
+      "learning_rate": 0.00019330578031317308,
+      "loss": 0.4315,
+      "step": 580
+    },
+    {
+      "epoch": 0.06982969313729294,
+      "grad_norm": 0.15258176624774933,
+      "learning_rate": 0.00019307293788928343,
+      "loss": 0.4086,
+      "step": 600
+    },
+    {
+      "epoch": 0.0721573495752027,
+      "grad_norm": 0.3304138481616974,
+      "learning_rate": 0.0001928400954653938,
+      "loss": 0.4016,
+      "step": 620
+    },
+    {
+      "epoch": 0.07448500601311246,
+      "grad_norm": 0.24660417437553406,
+      "learning_rate": 0.00019260725304150417,
+      "loss": 0.436,
+      "step": 640
+    },
+    {
+      "epoch": 0.07681266245102222,
+      "grad_norm": 0.14858856797218323,
+      "learning_rate": 0.00019237441061761455,
+      "loss": 0.4119,
+      "step": 660
+    },
+    {
+      "epoch": 0.079140318888932,
+      "grad_norm": 0.2687036693096161,
+      "learning_rate": 0.0001921415681937249,
+      "loss": 0.415,
+      "step": 680
+    },
+    {
+      "epoch": 0.08146797532684176,
+      "grad_norm": 5081.99462890625,
+      "learning_rate": 0.00019190872576983528,
+      "loss": 0.422,
+      "step": 700
+    },
+    {
+      "epoch": 0.08379563176475152,
+      "grad_norm": 0.17293968796730042,
+      "learning_rate": 0.00019167588334594564,
+      "loss": 0.4175,
+      "step": 720
+    },
+    {
+      "epoch": 0.08612328820266128,
+      "grad_norm": 0.1896151751279831,
+      "learning_rate": 0.00019144304092205602,
+      "loss": 0.3949,
+      "step": 740
+    },
+    {
+      "epoch": 0.08845094464057106,
+      "grad_norm": 0.16419611871242523,
+      "learning_rate": 0.00019121019849816637,
+      "loss": 0.4072,
+      "step": 760
+    },
+    {
+      "epoch": 0.09077860107848082,
+      "grad_norm": 0.16328750550746918,
+      "learning_rate": 0.00019097735607427672,
+      "loss": 0.417,
+      "step": 780
+    },
+    {
+      "epoch": 0.09310625751639058,
+      "grad_norm": 0.22866682708263397,
+      "learning_rate": 0.0001907445136503871,
+      "loss": 0.4161,
+      "step": 800
+    },
+    {
+      "epoch": 0.09543391395430034,
+      "grad_norm": 0.23260928690433502,
+      "learning_rate": 0.00019051167122649746,
+      "loss": 0.4223,
+      "step": 820
+    },
+    {
+      "epoch": 0.0977615703922101,
+      "grad_norm": 0.22623369097709656,
+      "learning_rate": 0.00019027882880260784,
+      "loss": 0.4163,
+      "step": 840
+    },
+    {
+      "epoch": 0.10008922683011988,
+      "grad_norm": 0.191610649228096,
+      "learning_rate": 0.00019004598637871822,
+      "loss": 0.4042,
+      "step": 860
+    },
+    {
+      "epoch": 0.10241688326802964,
+      "grad_norm": 0.18824578821659088,
+      "learning_rate": 0.00018981314395482857,
+      "loss": 0.4195,
+      "step": 880
+    },
+    {
+      "epoch": 0.1047445397059394,
+      "grad_norm": 0.27082520723342896,
+      "learning_rate": 0.00018958030153093895,
+      "loss": 0.429,
+      "step": 900
+    },
+    {
+      "epoch": 0.10707219614384916,
+      "grad_norm": 0.19178633391857147,
+      "learning_rate": 0.0001893474591070493,
+      "loss": 0.4015,
+      "step": 920
+    },
+    {
+      "epoch": 0.10939985258175894,
+      "grad_norm": 0.2990035116672516,
+      "learning_rate": 0.0001891146166831597,
+      "loss": 0.4093,
+      "step": 940
+    },
+    {
+      "epoch": 0.1117275090196687,
+      "grad_norm": 0.15209130942821503,
+      "learning_rate": 0.00018888177425927004,
+      "loss": 0.4074,
+      "step": 960
+    },
+    {
+      "epoch": 0.11405516545757846,
+      "grad_norm": 0.6236697435379028,
+      "learning_rate": 0.00018864893183538042,
+      "loss": 0.4216,
+      "step": 980
+    },
+    {
+      "epoch": 0.11638282189548822,
+      "eval_loss": 0.3763071894645691,
+      "eval_runtime": 24.8295,
+      "eval_samples_per_second": 0.805,
+      "eval_steps_per_second": 0.805,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11871047833339798,
+      "grad_norm": 0.22461196780204773,
+      "learning_rate": 0.00018818324698760116,
+      "loss": 0.4211,
+      "step": 1020
+    },
+    {
+      "epoch": 0.12103813477130776,
+      "grad_norm": 0.16002358496189117,
+      "learning_rate": 0.0001879504045637115,
+      "loss": 0.4158,
+      "step": 1040
+    },
+    {
+      "epoch": 0.12336579120921752,
+      "grad_norm": 243.7849884033203,
+      "learning_rate": 0.00018771756213982187,
+      "loss": 0.4027,
+      "step": 1060
+    },
+    {
+      "epoch": 0.12569344764712728,
+      "grad_norm": 0.28064680099487305,
+      "learning_rate": 0.00018748471971593225,
+      "loss": 0.4145,
+      "step": 1080
+    },
+    {
+      "epoch": 0.12802110408503706,
+      "grad_norm": 0.20418238639831543,
+      "learning_rate": 0.0001872518772920426,
+      "loss": 0.4073,
+      "step": 1100
+    },
+    {
+      "epoch": 0.1303487605229468,
+      "grad_norm": 0.26232343912124634,
+      "learning_rate": 0.00018701903486815298,
+      "loss": 0.4065,
+      "step": 1120
+    },
+    {
+      "epoch": 0.13267641696085658,
+      "grad_norm": 0.3850109279155731,
+      "learning_rate": 0.00018678619244426336,
+      "loss": 0.4166,
+      "step": 1140
+    },
+    {
+      "epoch": 0.13500407339876636,
+      "grad_norm": 0.22884441912174225,
+      "learning_rate": 0.00018655335002037374,
+      "loss": 0.4029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.1373317298366761,
+      "grad_norm": 0.24277088046073914,
+      "learning_rate": 0.0001863205075964841,
+      "loss": 0.3963,
+      "step": 1180
+    },
+    {
+      "epoch": 0.13965938627458588,
+      "grad_norm": 0.13874240219593048,
+      "learning_rate": 0.00018608766517259445,
+      "loss": 0.3981,
+      "step": 1200
+    },
+    {
+      "epoch": 0.14198704271249563,
+      "grad_norm": 0.26910531520843506,
+      "learning_rate": 0.00018585482274870483,
+      "loss": 0.3998,
+      "step": 1220
+    },
+    {
+      "epoch": 0.1443146991504054,
+      "grad_norm": 0.32635343074798584,
+      "learning_rate": 0.00018562198032481518,
+      "loss": 0.4044,
+      "step": 1240
+    },
+    {
+      "epoch": 0.14664235558831518,
+      "grad_norm": 0.16277135908603668,
+      "learning_rate": 0.00018538913790092557,
+      "loss": 0.3985,
+      "step": 1260
+    },
+    {
+      "epoch": 0.14897001202622492,
+      "grad_norm": 0.18236328661441803,
+      "learning_rate": 0.00018515629547703592,
+      "loss": 0.3974,
+      "step": 1280
+    },
+    {
+      "epoch": 0.1512976684641347,
+      "grad_norm": 7.105894565582275,
+      "learning_rate": 0.0001849234530531463,
+      "loss": 0.3834,
+      "step": 1300
+    },
+    {
+      "epoch": 0.15362532490204445,
+      "grad_norm": 0.502718448638916,
+      "learning_rate": 0.00018469061062925665,
+      "loss": 0.3955,
+      "step": 1320
+    },
+    {
+      "epoch": 0.15595298133995422,
+      "grad_norm": 0.16201145946979523,
+      "learning_rate": 0.000184457768205367,
+      "loss": 0.4094,
+      "step": 1340
+    },
+    {
+      "epoch": 0.158280637777864,
+      "grad_norm": 0.2192452996969223,
+      "learning_rate": 0.0001842249257814774,
+      "loss": 0.4178,
+      "step": 1360
+    },
+    {
+      "epoch": 0.16060829421577374,
+      "grad_norm": 0.17844466865062714,
+      "learning_rate": 0.00018399208335758774,
+      "loss": 0.3994,
+      "step": 1380
+    },
+    {
+      "epoch": 0.16293595065368352,
+      "grad_norm": 0.25548145174980164,
+      "learning_rate": 0.00018375924093369812,
+      "loss": 0.4008,
+      "step": 1400
+    },
+    {
+      "epoch": 0.16526360709159327,
+      "grad_norm": 0.18552140891551971,
+      "learning_rate": 0.0001835263985098085,
+      "loss": 0.405,
+      "step": 1420
+    },
+    {
+      "epoch": 0.16759126352950304,
+      "grad_norm": 0.18394050002098083,
+      "learning_rate": 0.00018329355608591888,
+      "loss": 0.403,
+      "step": 1440
+    },
+    {
+      "epoch": 0.16991891996741282,
+      "grad_norm": 0.18141116201877594,
+      "learning_rate": 0.00018306071366202924,
+      "loss": 0.3917,
+      "step": 1460
+    },
+    {
+      "epoch": 0.17224657640532257,
+      "grad_norm": 0.2414783388376236,
+      "learning_rate": 0.0001828278712381396,
+      "loss": 0.3898,
+      "step": 1480
+    },
+    {
+      "epoch": 0.17457423284323234,
+      "grad_norm": 0.18284501135349274,
+      "learning_rate": 0.00018259502881424997,
+      "loss": 0.4019,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17690188928114212,
+      "grad_norm": 0.18713632225990295,
+      "learning_rate": 0.00018236218639036033,
+      "loss": 0.4008,
+      "step": 1520
+    },
+    {
+      "epoch": 0.17922954571905186,
+      "grad_norm": 0.15932808816432953,
+      "learning_rate": 0.0001821293439664707,
+      "loss": 0.4021,
+      "step": 1540
+    },
+    {
+      "epoch": 0.18155720215696164,
+      "grad_norm": 0.23227080702781677,
+      "learning_rate": 0.00018189650154258106,
+      "loss": 0.4137,
+      "step": 1560
+    },
+    {
+      "epoch": 0.1838848585948714,
+      "grad_norm": 0.48624494671821594,
+      "learning_rate": 0.00018166365911869144,
+      "loss": 0.3949,
+      "step": 1580
+    },
+    {
+      "epoch": 0.18621251503278116,
+      "grad_norm": 0.20129570364952087,
+      "learning_rate": 0.0001814308166948018,
+      "loss": 0.4021,
+      "step": 1600
+    },
+    {
+      "epoch": 0.18854017147069094,
+      "grad_norm": 0.23552119731903076,
+      "learning_rate": 0.00018119797427091218,
+      "loss": 0.4085,
+      "step": 1620
+    },
+    {
+      "epoch": 0.19086782790860068,
+      "grad_norm": 0.1774003803730011,
+      "learning_rate": 0.00018096513184702253,
+      "loss": 0.3931,
+      "step": 1640
+    },
+    {
+      "epoch": 0.19319548434651046,
+      "grad_norm": 0.17817728221416473,
+      "learning_rate": 0.00018073228942313288,
+      "loss": 0.3796,
+      "step": 1660
+    },
+    {
+      "epoch": 0.1955231407844202,
+      "grad_norm": 0.1823066771030426,
+      "learning_rate": 0.00018049944699924326,
+      "loss": 0.3811,
+      "step": 1680
+    },
+    {
+      "epoch": 0.19785079722232998,
+      "grad_norm": 0.23608751595020294,
+      "learning_rate": 0.00018026660457535365,
+      "loss": 0.3887,
+      "step": 1700
+    },
+    {
+      "epoch": 0.20017845366023976,
+      "grad_norm": 0.2972647249698639,
+      "learning_rate": 0.00018003376215146403,
+      "loss": 0.3747,
+      "step": 1720
+    },
+    {
+      "epoch": 0.2025061100981495,
+      "grad_norm": 132.2842254638672,
+      "learning_rate": 0.00017980091972757438,
+      "loss": 0.4069,
+      "step": 1740
+    },
+    {
+      "epoch": 0.20483376653605928,
+      "grad_norm": 0.16777588427066803,
+      "learning_rate": 0.00017956807730368473,
+      "loss": 0.3905,
+      "step": 1760
+    },
+    {
+      "epoch": 0.20716142297396906,
+      "grad_norm": 0.19773095846176147,
+      "learning_rate": 0.00017933523487979511,
+      "loss": 0.3849,
+      "step": 1780
+    },
+    {
+      "epoch": 0.2094890794118788,
+      "grad_norm": 0.20314164459705353,
+      "learning_rate": 0.00017910239245590547,
+      "loss": 0.385,
+      "step": 1800
+    },
+    {
+      "epoch": 0.21181673584978858,
+      "grad_norm": 0.5555147528648376,
+      "learning_rate": 0.00017886955003201585,
+      "loss": 0.3957,
+      "step": 1820
+    },
+    {
+      "epoch": 0.21414439228769833,
+      "grad_norm": 0.26315221190452576,
+      "learning_rate": 0.0001786367076081262,
+      "loss": 0.3938,
+      "step": 1840
+    },
+    {
+      "epoch": 0.2164720487256081,
+      "grad_norm": 0.25817161798477173,
+      "learning_rate": 0.00017840386518423658,
+      "loss": 0.3796,
+      "step": 1860
+    },
+    {
+      "epoch": 0.21879970516351788,
+      "grad_norm": 0.19764716923236847,
+      "learning_rate": 0.00017817102276034694,
+      "loss": 0.3838,
+      "step": 1880
+    },
+    {
+      "epoch": 0.22112736160142762,
+      "grad_norm": 0.18681293725967407,
+      "learning_rate": 0.00017793818033645732,
+      "loss": 0.3857,
+      "step": 1900
+    },
+    {
+      "epoch": 0.2234550180393374,
+      "grad_norm": 0.15669210255146027,
+      "learning_rate": 0.00017770533791256767,
+      "loss": 0.3747,
+      "step": 1920
+    },
+    {
+      "epoch": 0.22578267447724715,
+      "grad_norm": 0.23186907172203064,
+      "learning_rate": 0.00017747249548867803,
+      "loss": 0.3861,
+      "step": 1940
+    },
+    {
+      "epoch": 0.22811033091515692,
+      "grad_norm": 0.1924745738506317,
+      "learning_rate": 0.0001772396530647884,
+      "loss": 0.3744,
+      "step": 1960
+    },
+    {
+      "epoch": 0.2304379873530667,
+      "grad_norm": 0.22534002363681793,
+      "learning_rate": 0.0001770068106408988,
+      "loss": 0.4079,
+      "step": 1980
+    },
+    {
+      "epoch": 0.23276564379097645,
+      "eval_loss": 0.34105929732322693,
+      "eval_runtime": 20.5754,
+      "eval_samples_per_second": 0.972,
+      "eval_steps_per_second": 0.972,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23509330022888622,
+      "grad_norm": 0.3466629087924957,
+      "learning_rate": 0.00017654112579311952,
+      "loss": 0.3872,
+      "step": 2020
+    },
+    {
+      "epoch": 0.23742095666679597,
+      "grad_norm": 0.18336734175682068,
+      "learning_rate": 0.00017630828336922988,
+      "loss": 0.3819,
+      "step": 2040
+    },
+    {
+      "epoch": 0.23974861310470574,
+      "grad_norm": 0.28359469771385193,
+      "learning_rate": 0.00017607544094534026,
+      "loss": 0.3897,
+      "step": 2060
+    },
+    {
+      "epoch": 0.24207626954261552,
+      "grad_norm": 0.23424173891544342,
+      "learning_rate": 0.0001758425985214506,
+      "loss": 0.4037,
+      "step": 2080
+    },
+    {
+      "epoch": 0.24440392598052527,
+      "grad_norm": 0.1805504858493805,
+      "learning_rate": 0.000175609756097561,
+      "loss": 0.3925,
+      "step": 2100
+    },
+    {
+      "epoch": 0.24673158241843504,
+      "grad_norm": 0.19148534536361694,
+      "learning_rate": 0.00017537691367367134,
+      "loss": 0.3913,
+      "step": 2120
+    },
+    {
+      "epoch": 0.24905923885634482,
+      "grad_norm": 0.2876415252685547,
+      "learning_rate": 0.00017514407124978173,
+      "loss": 0.3949,
+      "step": 2140
+    },
+    {
+      "epoch": 0.25138689529425456,
+      "grad_norm": 0.19835978746414185,
+      "learning_rate": 0.00017491122882589208,
+      "loss": 0.3796,
+      "step": 2160
+    },
+    {
+      "epoch": 0.25371455173216434,
+      "grad_norm": 0.18503338098526,
+      "learning_rate": 0.00017467838640200246,
+      "loss": 0.3976,
+      "step": 2180
+    },
+    {
+      "epoch": 0.2560422081700741,
+      "grad_norm": 0.2951093018054962,
+      "learning_rate": 0.0001744455439781128,
+      "loss": 0.3939,
+      "step": 2200
+    },
+    {
+      "epoch": 0.25836986460798383,
+      "grad_norm": 0.19800181686878204,
+      "learning_rate": 0.00017421270155422317,
+      "loss": 0.3762,
+      "step": 2220
+    },
+    {
+      "epoch": 0.2606975210458936,
+      "grad_norm": 0.180307537317276,
+      "learning_rate": 0.00017397985913033355,
+      "loss": 0.367,
+      "step": 2240
+    },
+    {
+      "epoch": 0.2630251774838034,
+      "grad_norm": 0.3579519987106323,
+      "learning_rate": 0.00017374701670644393,
+      "loss": 0.3852,
+      "step": 2260
+    },
+    {
+      "epoch": 0.26535283392171316,
+      "grad_norm": 0.20861206948757172,
+      "learning_rate": 0.0001735141742825543,
+      "loss": 0.377,
+      "step": 2280
+    },
+    {
+      "epoch": 0.26768049035962294,
+      "grad_norm": 0.1822461485862732,
+      "learning_rate": 0.00017328133185866466,
+      "loss": 0.3964,
+      "step": 2300
+    },
+    {
+      "epoch": 0.2700081467975327,
+      "grad_norm": 0.23378489911556244,
+      "learning_rate": 0.00017304848943477502,
+      "loss": 0.3879,
+      "step": 2320
+    },
+    {
+      "epoch": 0.27233580323544243,
+      "grad_norm": 18.86492919921875,
+      "learning_rate": 0.0001728156470108854,
+      "loss": 0.3704,
+      "step": 2340
+    },
+    {
+      "epoch": 0.2746634596733522,
+      "grad_norm": 0.4792926609516144,
+      "learning_rate": 0.00017258280458699575,
+      "loss": 0.395,
+      "step": 2360
+    },
+    {
+      "epoch": 0.276991116111262,
+      "grad_norm": 0.3864307403564453,
+      "learning_rate": 0.00017234996216310613,
+      "loss": 0.372,
+      "step": 2380
+    },
+    {
+      "epoch": 0.27931877254917176,
+      "grad_norm": 0.3222472071647644,
+      "learning_rate": 0.00017211711973921649,
+      "loss": 0.3809,
+      "step": 2400
+    },
+    {
+      "epoch": 0.28164642898708153,
+      "grad_norm": 0.3821967542171478,
+      "learning_rate": 0.00017188427731532687,
+      "loss": 0.3755,
+      "step": 2420
+    },
+    {
+      "epoch": 0.28397408542499125,
+      "grad_norm": 0.2431473731994629,
+      "learning_rate": 0.00017165143489143722,
+      "loss": 0.3796,
+      "step": 2440
+    },
+    {
+      "epoch": 0.286301741862901,
+      "grad_norm": 0.21729710698127747,
+      "learning_rate": 0.0001714185924675476,
+      "loss": 0.383,
+      "step": 2460
+    },
+    {
+      "epoch": 0.2886293983008108,
+      "grad_norm": 0.2408316433429718,
+      "learning_rate": 0.00017118575004365796,
+      "loss": 0.3658,
+      "step": 2480
+    },
+    {
+      "epoch": 0.2909570547387206,
+      "grad_norm": 0.155660018324852,
+      "learning_rate": 0.0001709529076197683,
+      "loss": 0.3767,
+      "step": 2500
+    },
+    {
+      "epoch": 0.29328471117663035,
+      "grad_norm": 0.40486574172973633,
+      "learning_rate": 0.0001707200651958787,
+      "loss": 0.3777,
+      "step": 2520
+    },
+    {
+      "epoch": 0.2956123676145401,
+      "grad_norm": 0.19449765980243683,
+      "learning_rate": 0.00017048722277198907,
+      "loss": 0.381,
+      "step": 2540
+    },
+    {
+      "epoch": 0.29794002405244985,
+      "grad_norm": 0.19322779774665833,
+      "learning_rate": 0.00017025438034809945,
+      "loss": 0.3677,
+      "step": 2560
+    },
+    {
+      "epoch": 0.3002676804903596,
+      "grad_norm": 0.16566042602062225,
+      "learning_rate": 0.0001700215379242098,
+      "loss": 0.3707,
+      "step": 2580
+    },
+    {
+      "epoch": 0.3025953369282694,
+      "grad_norm": 0.28576773405075073,
+      "learning_rate": 0.00016978869550032016,
+      "loss": 0.3734,
+      "step": 2600
+    },
+    {
+      "epoch": 0.3049229933661792,
+      "grad_norm": 0.1702573150396347,
+      "learning_rate": 0.00016955585307643054,
+      "loss": 0.3766,
+      "step": 2620
+    },
+    {
+      "epoch": 0.3072506498040889,
+      "grad_norm": 0.23310710489749908,
+      "learning_rate": 0.0001693230106525409,
+      "loss": 0.3531,
+      "step": 2640
+    },
+    {
+      "epoch": 0.30957830624199867,
+      "grad_norm": 0.25369375944137573,
+      "learning_rate": 0.00016909016822865127,
+      "loss": 0.3507,
+      "step": 2660
+    },
+    {
+      "epoch": 0.31190596267990844,
+      "grad_norm": 0.17957869172096252,
+      "learning_rate": 0.00016885732580476163,
+      "loss": 0.373,
+      "step": 2680
+    },
+    {
+      "epoch": 0.3142336191178182,
+      "grad_norm": 0.2045636624097824,
+      "learning_rate": 0.000168624483380872,
+      "loss": 0.3749,
+      "step": 2700
+    },
+    {
+      "epoch": 0.316561275555728,
+      "grad_norm": 0.19951078295707703,
+      "learning_rate": 0.00016839164095698236,
+      "loss": 0.3731,
+      "step": 2720
+    },
+    {
+      "epoch": 0.3188889319936377,
+      "grad_norm": 0.18379923701286316,
+      "learning_rate": 0.00016815879853309274,
+      "loss": 0.3691,
+      "step": 2740
+    },
+    {
+      "epoch": 0.3212165884315475,
+      "grad_norm": 0.23755669593811035,
+      "learning_rate": 0.0001679259561092031,
+      "loss": 0.3842,
+      "step": 2760
+    },
+    {
+      "epoch": 0.32354424486945726,
+      "grad_norm": 0.2947305142879486,
+      "learning_rate": 0.00016769311368531345,
+      "loss": 0.3715,
+      "step": 2780
+    },
+    {
+      "epoch": 0.32587190130736704,
+      "grad_norm": 0.25311100482940674,
+      "learning_rate": 0.00016746027126142383,
+      "loss": 0.3467,
+      "step": 2800
+    },
+    {
+      "epoch": 0.3281995577452768,
+      "grad_norm": 0.1826748102903366,
+      "learning_rate": 0.0001672274288375342,
+      "loss": 0.3824,
+      "step": 2820
+    },
+    {
+      "epoch": 0.33052721418318654,
+      "grad_norm": 0.21817153692245483,
+      "learning_rate": 0.0001669945864136446,
+      "loss": 0.3814,
+      "step": 2840
+    },
+    {
+      "epoch": 0.3328548706210963,
+      "grad_norm": 0.26214322447776794,
+      "learning_rate": 0.00016676174398975495,
+      "loss": 0.3569,
+      "step": 2860
+    },
+    {
+      "epoch": 0.3351825270590061,
+      "grad_norm": 0.14921711385250092,
+      "learning_rate": 0.00016652890156586533,
+      "loss": 0.3532,
+      "step": 2880
+    },
+    {
+      "epoch": 0.33751018349691586,
+      "grad_norm": 0.19131538271903992,
+      "learning_rate": 0.00016629605914197568,
+      "loss": 0.3835,
+      "step": 2900
+    },
+    {
+      "epoch": 0.33983783993482564,
+      "grad_norm": 0.25280335545539856,
+      "learning_rate": 0.00016606321671808603,
+      "loss": 0.3519,
+      "step": 2920
+    },
+    {
+      "epoch": 0.3421654963727354,
+      "grad_norm": 0.23450925946235657,
+      "learning_rate": 0.00016583037429419642,
+      "loss": 0.3629,
+      "step": 2940
+    },
+    {
+      "epoch": 0.34449315281064513,
+      "grad_norm": 0.16666562855243683,
+      "learning_rate": 0.00016559753187030677,
+      "loss": 0.3726,
+      "step": 2960
+    },
+    {
+      "epoch": 0.3468208092485549,
+      "grad_norm": 0.1999836266040802,
+      "learning_rate": 0.00016536468944641715,
+      "loss": 0.3672,
+      "step": 2980
+    },
+    {
+      "epoch": 0.3491484656864647,
+      "eval_loss": 0.33955806493759155,
+      "eval_runtime": 20.488,
+      "eval_samples_per_second": 0.976,
+      "eval_steps_per_second": 0.976,
+      "step": 3000
+    },
+    {
+      "epoch": 0.35147612212437446,
+      "grad_norm": 0.258916437625885,
+      "learning_rate": 0.00016489900459863788,
+      "loss": 0.361,
+      "step": 3020
+    },
+    {
+      "epoch": 0.35380377856228423,
+      "grad_norm": 0.3194919228553772,
+      "learning_rate": 0.00016466616217474824,
+      "loss": 0.3776,
+      "step": 3040
+    },
+    {
+      "epoch": 0.35613143500019395,
+      "grad_norm": 0.2585081458091736,
+      "learning_rate": 0.0001644333197508586,
+      "loss": 0.3673,
+      "step": 3060
+    },
+    {
+      "epoch": 0.3584590914381037,
+      "grad_norm": 0.19240811467170715,
+      "learning_rate": 0.00016420047732696897,
+      "loss": 0.3681,
+      "step": 3080
+    },
+    {
+      "epoch": 0.3607867478760135,
+      "grad_norm": 0.19897238910198212,
+      "learning_rate": 0.00016396763490307935,
+      "loss": 0.372,
+      "step": 3100
+    },
+    {
+      "epoch": 0.3631144043139233,
+      "grad_norm": 0.47343334555625916,
+      "learning_rate": 0.00016373479247918973,
+      "loss": 0.3608,
+      "step": 3120
+    },
+    {
+      "epoch": 0.36544206075183305,
+      "grad_norm": 0.19204185903072357,
+      "learning_rate": 0.0001635019500553001,
+      "loss": 0.3697,
+      "step": 3140
+    },
+    {
+      "epoch": 0.3677697171897428,
+      "grad_norm": 0.23948988318443298,
+      "learning_rate": 0.00016326910763141047,
+      "loss": 0.3606,
+      "step": 3160
+    },
+    {
+      "epoch": 0.37009737362765255,
+      "grad_norm": 0.18690457940101624,
+      "learning_rate": 0.00016303626520752082,
+      "loss": 0.3662,
+      "step": 3180
+    },
+    {
+      "epoch": 0.3724250300655623,
+      "grad_norm": 0.2347842901945114,
+      "learning_rate": 0.00016280342278363118,
+      "loss": 0.3687,
+      "step": 3200
+    },
+    {
+      "epoch": 0.3747526865034721,
+      "grad_norm": 0.35743722319602966,
+      "learning_rate": 0.00016257058035974156,
+      "loss": 0.3704,
+      "step": 3220
+    },
+    {
+      "epoch": 0.3770803429413819,
+      "grad_norm": 0.21768271923065186,
+      "learning_rate": 0.0001623377379358519,
+      "loss": 0.3583,
+      "step": 3240
+    },
+    {
+      "epoch": 0.3794079993792916,
+      "grad_norm": 0.1767244189977646,
+      "learning_rate": 0.0001621048955119623,
+      "loss": 0.3677,
+      "step": 3260
+    },
+    {
+      "epoch": 0.38173565581720137,
+      "grad_norm": 0.17066846787929535,
+      "learning_rate": 0.00016187205308807265,
+      "loss": 0.379,
+      "step": 3280
+    },
+    {
+      "epoch": 0.38406331225511114,
+      "grad_norm": 0.1612280160188675,
+      "learning_rate": 0.00016163921066418303,
+      "loss": 0.37,
+      "step": 3300
+    },
+    {
+      "epoch": 0.3863909686930209,
+      "grad_norm": 0.24048790335655212,
+      "learning_rate": 0.00016140636824029338,
+      "loss": 0.381,
+      "step": 3320
+    },
+    {
+      "epoch": 0.3887186251309307,
+      "grad_norm": 0.24847067892551422,
+      "learning_rate": 0.00016117352581640376,
+      "loss": 0.3638,
+      "step": 3340
+    },
+    {
+      "epoch": 0.3910462815688404,
+      "grad_norm": 0.17553377151489258,
+      "learning_rate": 0.00016094068339251411,
+      "loss": 0.3736,
+      "step": 3360
+    },
+    {
+      "epoch": 0.3933739380067502,
+      "grad_norm": 0.1982511729001999,
+      "learning_rate": 0.0001607078409686245,
+      "loss": 0.3554,
+      "step": 3380
+    },
+    {
+      "epoch": 0.39570159444465997,
+      "grad_norm": 0.24017345905303955,
+      "learning_rate": 0.00016047499854473488,
+      "loss": 0.3615,
+      "step": 3400
+    },
+    {
+      "epoch": 0.39802925088256974,
+      "grad_norm": 0.38525983691215515,
+      "learning_rate": 0.00016024215612084523,
+      "loss": 0.3731,
+      "step": 3420
+    },
+    {
+      "epoch": 0.4003569073204795,
+      "grad_norm": 0.2311367243528366,
+      "learning_rate": 0.0001600093136969556,
+      "loss": 0.353,
+      "step": 3440
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.3101646304130554,
+      "learning_rate": 0.00015977647127306596,
+      "loss": 0.385,
+      "step": 3460
+    },
+    {
+      "epoch": 0.405012220196299,
+      "grad_norm": 0.3255872130393982,
+      "learning_rate": 0.00015954362884917632,
+      "loss": 0.3523,
+      "step": 3480
+    },
+    {
+      "epoch": 0.4073398766342088,
+      "grad_norm": 0.43426716327667236,
+      "learning_rate": 0.0001593107864252867,
+      "loss": 0.3604,
+      "step": 3500
+    },
+    {
+      "epoch": 0.40966753307211856,
+      "grad_norm": 0.2444802075624466,
+      "learning_rate": 0.00015907794400139705,
+      "loss": 0.362,
+      "step": 3520
+    },
+    {
+      "epoch": 0.41199518951002834,
+      "grad_norm": 0.2865477204322815,
+      "learning_rate": 0.00015884510157750743,
+      "loss": 0.3601,
+      "step": 3540
+    },
+    {
+      "epoch": 0.4143228459479381,
+      "grad_norm": 0.22279277443885803,
+      "learning_rate": 0.0001586122591536178,
+      "loss": 0.3668,
+      "step": 3560
+    },
+    {
+      "epoch": 0.41665050238584783,
+      "grad_norm": 1.8566228151321411,
+      "learning_rate": 0.00015837941672972817,
+      "loss": 0.3566,
+      "step": 3580
+    },
+    {
+      "epoch": 0.4189781588237576,
+      "grad_norm": 0.5629792809486389,
+      "learning_rate": 0.00015814657430583852,
+      "loss": 0.3715,
+      "step": 3600
+    },
+    {
+      "epoch": 0.4213058152616674,
+      "grad_norm": 0.22610370814800262,
+      "learning_rate": 0.0001579137318819489,
+      "loss": 0.3692,
+      "step": 3620
+    },
+    {
+      "epoch": 0.42363347169957716,
+      "grad_norm": 0.19026003777980804,
+      "learning_rate": 0.00015768088945805926,
+      "loss": 0.3581,
+      "step": 3640
+    },
+    {
+      "epoch": 0.42596112813748693,
+      "grad_norm": 0.178512305021286,
+      "learning_rate": 0.00015744804703416964,
+      "loss": 0.3612,
+      "step": 3660
+    },
+    {
+      "epoch": 0.42828878457539665,
+      "grad_norm": 0.38026803731918335,
+      "learning_rate": 0.00015721520461028002,
+      "loss": 0.3543,
+      "step": 3680
+    },
+    {
+      "epoch": 0.43061644101330643,
+      "grad_norm": 0.6063324809074402,
+      "learning_rate": 0.00015698236218639037,
+      "loss": 0.3766,
+      "step": 3700
+    },
+    {
+      "epoch": 0.4329440974512162,
+      "grad_norm": 0.8279145956039429,
+      "learning_rate": 0.00015674951976250075,
+      "loss": 0.3676,
+      "step": 3720
+    },
+    {
+      "epoch": 0.435271753889126,
+      "grad_norm": 0.2203836590051651,
+      "learning_rate": 0.0001565166773386111,
+      "loss": 0.3654,
+      "step": 3740
+    },
+    {
+      "epoch": 0.43759941032703575,
+      "grad_norm": 0.19508014619350433,
+      "learning_rate": 0.00015628383491472146,
+      "loss": 0.3644,
+      "step": 3760
+    },
+    {
+      "epoch": 0.4399270667649455,
+      "grad_norm": 0.22672756016254425,
+      "learning_rate": 0.00015605099249083184,
+      "loss": 0.3675,
+      "step": 3780
+    },
+    {
+      "epoch": 0.44225472320285525,
+      "grad_norm": 0.24534592032432556,
+      "learning_rate": 0.0001558181500669422,
+      "loss": 0.3494,
+      "step": 3800
+    },
+    {
+      "epoch": 0.444582379640765,
+      "grad_norm": 0.29605987668037415,
+      "learning_rate": 0.00015558530764305258,
+      "loss": 0.3647,
+      "step": 3820
+    },
+    {
+      "epoch": 0.4469100360786748,
+      "grad_norm": 0.19488602876663208,
+      "learning_rate": 0.00015535246521916293,
+      "loss": 0.3364,
+      "step": 3840
+    },
+    {
+      "epoch": 0.4492376925165846,
+      "grad_norm": 0.25351813435554504,
+      "learning_rate": 0.0001551196227952733,
+      "loss": 0.3662,
+      "step": 3860
+    },
+    {
+      "epoch": 0.4515653489544943,
+      "grad_norm": 0.17733800411224365,
+      "learning_rate": 0.00015488678037138366,
+      "loss": 0.3484,
+      "step": 3880
+    },
+    {
+      "epoch": 0.45389300539240407,
+      "grad_norm": 0.16233082115650177,
+      "learning_rate": 0.00015465393794749404,
+      "loss": 0.3565,
+      "step": 3900
+    },
+    {
+      "epoch": 0.45622066183031385,
+      "grad_norm": 0.18378767371177673,
+      "learning_rate": 0.0001544210955236044,
+      "loss": 0.3563,
+      "step": 3920
+    },
+    {
+      "epoch": 0.4585483182682236,
+      "grad_norm": 0.18663223087787628,
+      "learning_rate": 0.00015418825309971478,
+      "loss": 0.3476,
+      "step": 3940
+    },
+    {
+      "epoch": 0.4608759747061334,
+      "grad_norm": 0.23771430552005768,
+      "learning_rate": 0.00015395541067582516,
+      "loss": 0.3474,
+      "step": 3960
+    },
+    {
+      "epoch": 0.4632036311440431,
+      "grad_norm": 0.18909785151481628,
+      "learning_rate": 0.0001537225682519355,
+      "loss": 0.3653,
+      "step": 3980
+    },
+    {
+      "epoch": 0.4655312875819529,
+      "eval_loss": 0.31149590015411377,
+      "eval_runtime": 20.5163,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 4000
+    },
+    {
+      "epoch": 0.46785894401986267,
+      "grad_norm": 0.19774921238422394,
+      "learning_rate": 0.00015325688340415625,
+      "loss": 0.3529,
+      "step": 4020
+    },
+    {
+      "epoch": 0.47018660045777244,
+      "grad_norm": 0.24778500199317932,
+      "learning_rate": 0.0001530240409802666,
+      "loss": 0.359,
+      "step": 4040
+    },
+    {
+      "epoch": 0.4725142568956822,
+      "grad_norm": 0.24743713438510895,
+      "learning_rate": 0.00015279119855637698,
+      "loss": 0.343,
+      "step": 4060
+    },
+    {
+      "epoch": 0.47484191333359194,
+      "grad_norm": 0.34825143218040466,
+      "learning_rate": 0.00015255835613248734,
+      "loss": 0.3503,
+      "step": 4080
+    },
+    {
+      "epoch": 0.4771695697715017,
+      "grad_norm": 0.24310366809368134,
+      "learning_rate": 0.00015232551370859772,
+      "loss": 0.355,
+      "step": 4100
+    },
+    {
+      "epoch": 0.4794972262094115,
+      "grad_norm": 0.24217070639133453,
+      "learning_rate": 0.00015209267128470807,
+      "loss": 0.3536,
+      "step": 4120
+    },
+    {
+      "epoch": 0.48182488264732126,
+      "grad_norm": 0.25677749514579773,
+      "learning_rate": 0.00015185982886081845,
+      "loss": 0.3457,
+      "step": 4140
+    },
+    {
+      "epoch": 0.48415253908523104,
+      "grad_norm": 0.2656559944152832,
+      "learning_rate": 0.0001516269864369288,
+      "loss": 0.3523,
+      "step": 4160
+    },
+    {
+      "epoch": 0.48648019552314076,
+      "grad_norm": 0.42824068665504456,
+      "learning_rate": 0.00015139414401303919,
+      "loss": 0.351,
+      "step": 4180
+    },
+    {
+      "epoch": 0.48880785196105053,
+      "grad_norm": 0.20235295593738556,
+      "learning_rate": 0.00015116130158914954,
+      "loss": 0.3555,
+      "step": 4200
+    },
+    {
+      "epoch": 0.4911355083989603,
+      "grad_norm": 0.37820956110954285,
+      "learning_rate": 0.00015092845916525992,
+      "loss": 0.3631,
+      "step": 4220
+    },
+    {
+      "epoch": 0.4934631648368701,
+      "grad_norm": 0.26479631662368774,
+      "learning_rate": 0.0001506956167413703,
+      "loss": 0.3618,
+      "step": 4240
+    },
+    {
+      "epoch": 0.49579082127477986,
+      "grad_norm": 0.2804780602455139,
+      "learning_rate": 0.00015046277431748066,
+      "loss": 0.3627,
+      "step": 4260
+    },
+    {
+      "epoch": 0.49811847771268963,
+      "grad_norm": 0.2443319857120514,
+      "learning_rate": 0.00015022993189359104,
+      "loss": 0.357,
+      "step": 4280
+    },
+    {
+      "epoch": 0.5004461341505994,
+      "grad_norm": 0.24147436022758484,
+      "learning_rate": 0.0001499970894697014,
+      "loss": 0.3597,
+      "step": 4300
+    },
+    {
+      "epoch": 0.5027737905885091,
+      "grad_norm": 0.22768740355968475,
+      "learning_rate": 0.00014976424704581174,
+      "loss": 0.3473,
+      "step": 4320
+    },
+    {
+      "epoch": 0.5051014470264189,
+      "grad_norm": 0.2021336555480957,
+      "learning_rate": 0.00014953140462192212,
+      "loss": 0.3452,
+      "step": 4340
+    },
+    {
+      "epoch": 0.5074291034643287,
+      "grad_norm": 0.29667967557907104,
+      "learning_rate": 0.00014929856219803248,
+      "loss": 0.3618,
+      "step": 4360
+    },
+    {
+      "epoch": 0.5097567599022385,
+      "grad_norm": 0.6347065567970276,
+      "learning_rate": 0.00014906571977414286,
+      "loss": 0.3553,
+      "step": 4380
+    },
+    {
+      "epoch": 0.5120844163401482,
+      "grad_norm": 0.24045443534851074,
+      "learning_rate": 0.0001488328773502532,
+      "loss": 0.3485,
+      "step": 4400
+    },
+    {
+      "epoch": 0.514412072778058,
+      "grad_norm": 0.18905188143253326,
+      "learning_rate": 0.0001486000349263636,
+      "loss": 0.3503,
+      "step": 4420
+    },
+    {
+      "epoch": 0.5167397292159677,
+      "grad_norm": 0.22376835346221924,
+      "learning_rate": 0.00014836719250247395,
+      "loss": 0.3625,
+      "step": 4440
+    },
+    {
+      "epoch": 0.5190673856538774,
+      "grad_norm": 0.1905108392238617,
+      "learning_rate": 0.00014813435007858433,
+      "loss": 0.3627,
+      "step": 4460
+    },
+    {
+      "epoch": 0.5213950420917872,
+      "grad_norm": 0.16056381165981293,
+      "learning_rate": 0.00014790150765469468,
+      "loss": 0.3539,
+      "step": 4480
+    },
+    {
+      "epoch": 0.523722698529697,
+      "grad_norm": 0.3105067312717438,
+      "learning_rate": 0.00014766866523080506,
+      "loss": 0.3487,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5260503549676068,
+      "grad_norm": 0.17728884518146515,
+      "learning_rate": 0.00014743582280691544,
+      "loss": 0.352,
+      "step": 4520
+    },
+    {
+      "epoch": 0.5283780114055165,
+      "grad_norm": 0.324103981256485,
+      "learning_rate": 0.0001472029803830258,
+      "loss": 0.3554,
+      "step": 4540
+    },
+    {
+      "epoch": 0.5307056678434263,
+      "grad_norm": 0.22545209527015686,
+      "learning_rate": 0.00014697013795913618,
+      "loss": 0.3518,
+      "step": 4560
+    },
+    {
+      "epoch": 0.5330333242813361,
+      "grad_norm": 0.21231485903263092,
+      "learning_rate": 0.00014673729553524653,
+      "loss": 0.3602,
+      "step": 4580
+    },
+    {
+      "epoch": 0.5353609807192459,
+      "grad_norm": 0.20037336647510529,
+      "learning_rate": 0.00014650445311135689,
+      "loss": 0.3424,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5376886371571556,
+      "grad_norm": 0.236566424369812,
+      "learning_rate": 0.00014627161068746727,
+      "loss": 0.3384,
+      "step": 4620
+    },
+    {
+      "epoch": 0.5400162935950654,
+      "grad_norm": 0.20465651154518127,
+      "learning_rate": 0.00014603876826357762,
+      "loss": 0.3413,
+      "step": 4640
+    },
+    {
+      "epoch": 0.5423439500329751,
+      "grad_norm": 0.2966756522655487,
+      "learning_rate": 0.000145805925839688,
+      "loss": 0.3484,
+      "step": 4660
+    },
+    {
+      "epoch": 0.5446716064708849,
+      "grad_norm": 0.24104952812194824,
+      "learning_rate": 0.00014557308341579835,
+      "loss": 0.3451,
+      "step": 4680
+    },
+    {
+      "epoch": 0.5469992629087946,
+      "grad_norm": 0.17582967877388,
+      "learning_rate": 0.00014534024099190873,
+      "loss": 0.3463,
+      "step": 4700
+    },
+    {
+      "epoch": 0.5493269193467044,
+      "grad_norm": 0.20060794055461884,
+      "learning_rate": 0.0001451073985680191,
+      "loss": 0.3493,
+      "step": 4720
+    },
+    {
+      "epoch": 0.5516545757846142,
+      "grad_norm": 0.18853868544101715,
+      "learning_rate": 0.00014487455614412947,
+      "loss": 0.3554,
+      "step": 4740
+    },
+    {
+      "epoch": 0.553982232222524,
+      "grad_norm": 123.7918701171875,
+      "learning_rate": 0.00014464171372023982,
+      "loss": 0.3565,
+      "step": 4760
+    },
+    {
+      "epoch": 0.5563098886604337,
+      "grad_norm": 0.20567387342453003,
+      "learning_rate": 0.0001444088712963502,
+      "loss": 0.3554,
+      "step": 4780
+    },
+    {
+      "epoch": 0.5586375450983435,
+      "grad_norm": 0.18615809082984924,
+      "learning_rate": 0.00014417602887246058,
+      "loss": 0.3432,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5609652015362533,
+      "grad_norm": 0.1741110235452652,
+      "learning_rate": 0.00014394318644857094,
+      "loss": 0.3452,
+      "step": 4820
+    },
+    {
+      "epoch": 0.5632928579741631,
+      "grad_norm": 0.2044975459575653,
+      "learning_rate": 0.00014371034402468132,
+      "loss": 0.3527,
+      "step": 4840
+    },
+    {
+      "epoch": 0.5656205144120727,
+      "grad_norm": 0.20385336875915527,
+      "learning_rate": 0.00014347750160079167,
+      "loss": 0.3502,
+      "step": 4860
+    },
+    {
+      "epoch": 0.5679481708499825,
+      "grad_norm": 0.39861437678337097,
+      "learning_rate": 0.00014324465917690205,
+      "loss": 0.3552,
+      "step": 4880
+    },
+    {
+      "epoch": 0.5702758272878923,
+      "grad_norm": 0.3018192648887634,
+      "learning_rate": 0.0001430118167530124,
+      "loss": 0.3474,
+      "step": 4900
+    },
+    {
+      "epoch": 0.572603483725802,
+      "grad_norm": 0.3321334421634674,
+      "learning_rate": 0.00014277897432912276,
+      "loss": 0.3696,
+      "step": 4920
+    },
+    {
+      "epoch": 0.5749311401637118,
+      "grad_norm": 0.28781139850616455,
+      "learning_rate": 0.00014254613190523314,
+      "loss": 0.3615,
+      "step": 4940
+    },
+    {
+      "epoch": 0.5772587966016216,
+      "grad_norm": 0.30906185507774353,
+      "learning_rate": 0.0001423132894813435,
+      "loss": 0.3475,
+      "step": 4960
+    },
+    {
+      "epoch": 0.5795864530395314,
+      "grad_norm": 0.35933470726013184,
+      "learning_rate": 0.00014208044705745388,
+      "loss": 0.3476,
+      "step": 4980
+    },
+    {
+      "epoch": 0.5819141094774412,
+      "eval_loss": 0.3145809769630432,
+      "eval_runtime": 20.5668,
+      "eval_samples_per_second": 0.972,
+      "eval_steps_per_second": 0.972,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5842417659153509,
+      "grad_norm": 0.292654812335968,
+      "learning_rate": 0.0001416147622096746,
+      "loss": 0.348,
+      "step": 5020
+    },
+    {
+      "epoch": 0.5865694223532607,
+      "grad_norm": 0.2097272276878357,
+      "learning_rate": 0.00014138191978578496,
+      "loss": 0.354,
+      "step": 5040
+    },
+    {
+      "epoch": 0.5888970787911704,
+      "grad_norm": 0.35698607563972473,
+      "learning_rate": 0.00014114907736189535,
+      "loss": 0.354,
+      "step": 5060
+    },
+    {
+      "epoch": 0.5912247352290801,
+      "grad_norm": 0.2368643432855606,
+      "learning_rate": 0.00014091623493800573,
+      "loss": 0.3533,
+      "step": 5080
+    },
+    {
+      "epoch": 0.5935523916669899,
+      "grad_norm": 0.3160126209259033,
+      "learning_rate": 0.00014068339251411608,
+      "loss": 0.349,
+      "step": 5100
+    },
+    {
+      "epoch": 0.5958800481048997,
+      "grad_norm": 0.3857573866844177,
+      "learning_rate": 0.00014045055009022646,
+      "loss": 0.3434,
+      "step": 5120
+    },
+    {
+      "epoch": 0.5982077045428095,
+      "grad_norm": 0.18679650127887726,
+      "learning_rate": 0.00014021770766633681,
+      "loss": 0.351,
+      "step": 5140
+    },
+    {
+      "epoch": 0.6005353609807192,
+      "grad_norm": 0.29045769572257996,
+      "learning_rate": 0.0001399848652424472,
+      "loss": 0.3388,
+      "step": 5160
+    },
+    {
+      "epoch": 0.602863017418629,
+      "grad_norm": 0.22361379861831665,
+      "learning_rate": 0.00013975202281855755,
+      "loss": 0.348,
+      "step": 5180
+    },
+    {
+      "epoch": 0.6051906738565388,
+      "grad_norm": 0.24997544288635254,
+      "learning_rate": 0.0001395191803946679,
+      "loss": 0.355,
+      "step": 5200
+    },
+    {
+      "epoch": 0.6075183302944486,
+      "grad_norm": 0.2645764946937561,
+      "learning_rate": 0.00013928633797077828,
+      "loss": 0.342,
+      "step": 5220
+    },
+    {
+      "epoch": 0.6098459867323583,
+      "grad_norm": 0.31037524342536926,
+      "learning_rate": 0.00013905349554688864,
+      "loss": 0.3531,
+      "step": 5240
+    },
+    {
+      "epoch": 0.6121736431702681,
+      "grad_norm": 0.2432362288236618,
+      "learning_rate": 0.00013882065312299902,
+      "loss": 0.3446,
+      "step": 5260
+    },
+    {
+      "epoch": 0.6145012996081778,
+      "grad_norm": 0.4462791681289673,
+      "learning_rate": 0.00013858781069910937,
+      "loss": 0.3348,
+      "step": 5280
+    },
+    {
+      "epoch": 0.6168289560460876,
+      "grad_norm": 0.2270222008228302,
+      "learning_rate": 0.00013835496827521975,
+      "loss": 0.3526,
+      "step": 5300
+    },
+    {
+      "epoch": 0.6191566124839973,
+      "grad_norm": 0.6763991117477417,
+      "learning_rate": 0.0001381221258513301,
+      "loss": 0.3397,
+      "step": 5320
+    },
+    {
+      "epoch": 0.6214842689219071,
+      "grad_norm": 0.29420357942581177,
+      "learning_rate": 0.0001378892834274405,
+      "loss": 0.3537,
+      "step": 5340
+    },
+    {
+      "epoch": 0.6238119253598169,
+      "grad_norm": 0.2442043572664261,
+      "learning_rate": 0.00013765644100355087,
+      "loss": 0.3519,
+      "step": 5360
+    },
+    {
+      "epoch": 0.6261395817977267,
+      "grad_norm": 0.18237663805484772,
+      "learning_rate": 0.00013742359857966122,
+      "loss": 0.3497,
+      "step": 5380
+    },
+    {
+      "epoch": 0.6284672382356364,
+      "grad_norm": 209.17459106445312,
+      "learning_rate": 0.0001371907561557716,
+      "loss": 0.3462,
+      "step": 5400
+    },
+    {
+      "epoch": 0.6307948946735462,
+      "grad_norm": 0.26512980461120605,
+      "learning_rate": 0.00013695791373188196,
+      "loss": 0.3557,
+      "step": 5420
+    },
+    {
+      "epoch": 0.633122551111456,
+      "grad_norm": 7.529220104217529,
+      "learning_rate": 0.00013672507130799234,
+      "loss": 0.3504,
+      "step": 5440
+    },
+    {
+      "epoch": 0.6354502075493658,
+      "grad_norm": 0.3562451899051666,
+      "learning_rate": 0.0001364922288841027,
+      "loss": 0.3468,
+      "step": 5460
+    },
+    {
+      "epoch": 0.6377778639872754,
+      "grad_norm": 0.3037929832935333,
+      "learning_rate": 0.00013625938646021304,
+      "loss": 0.3285,
+      "step": 5480
+    },
+    {
+      "epoch": 0.6401055204251852,
+      "grad_norm": 0.19235365092754364,
+      "learning_rate": 0.00013602654403632343,
+      "loss": 0.3316,
+      "step": 5500
+    },
+    {
+      "epoch": 0.642433176863095,
+      "grad_norm": 0.3225952982902527,
+      "learning_rate": 0.00013579370161243378,
+      "loss": 0.3626,
+      "step": 5520
+    },
+    {
+      "epoch": 0.6447608333010048,
+      "grad_norm": 0.21773532032966614,
+      "learning_rate": 0.00013556085918854416,
+      "loss": 0.3396,
+      "step": 5540
+    },
+    {
+      "epoch": 0.6470884897389145,
+      "grad_norm": 0.37126588821411133,
+      "learning_rate": 0.00013532801676465451,
+      "loss": 0.345,
+      "step": 5560
+    },
+    {
+      "epoch": 0.6494161461768243,
+      "grad_norm": 0.20414815843105316,
+      "learning_rate": 0.0001350951743407649,
+      "loss": 0.3497,
+      "step": 5580
+    },
+    {
+      "epoch": 0.6517438026147341,
+      "grad_norm": 0.2483614981174469,
+      "learning_rate": 0.00013486233191687525,
+      "loss": 0.3459,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6540714590526439,
+      "grad_norm": 0.26560285687446594,
+      "learning_rate": 0.00013462948949298563,
+      "loss": 0.3492,
+      "step": 5620
+    },
+    {
+      "epoch": 0.6563991154905536,
+      "grad_norm": 0.2463219314813614,
+      "learning_rate": 0.000134396647069096,
+      "loss": 0.3329,
+      "step": 5640
+    },
+    {
+      "epoch": 0.6587267719284634,
+      "grad_norm": 0.2952941656112671,
+      "learning_rate": 0.00013416380464520636,
+      "loss": 0.3525,
+      "step": 5660
+    },
+    {
+      "epoch": 0.6610544283663731,
+      "grad_norm": 0.290284126996994,
+      "learning_rate": 0.00013393096222131674,
+      "loss": 0.3574,
+      "step": 5680
+    },
+    {
+      "epoch": 0.6633820848042828,
+      "grad_norm": 0.26414546370506287,
+      "learning_rate": 0.0001336981197974271,
+      "loss": 0.3438,
+      "step": 5700
+    },
+    {
+      "epoch": 0.6657097412421926,
+      "grad_norm": 0.19366157054901123,
+      "learning_rate": 0.00013346527737353748,
+      "loss": 0.3552,
+      "step": 5720
+    },
+    {
+      "epoch": 0.6680373976801024,
+      "grad_norm": 0.17558442056179047,
+      "learning_rate": 0.00013323243494964783,
+      "loss": 0.3456,
+      "step": 5740
+    },
+    {
+      "epoch": 0.6703650541180122,
+      "grad_norm": 0.2544914782047272,
+      "learning_rate": 0.00013299959252575819,
+      "loss": 0.3375,
+      "step": 5760
+    },
+    {
+      "epoch": 0.672692710555922,
+      "grad_norm": 0.23441466689109802,
+      "learning_rate": 0.00013276675010186857,
+      "loss": 0.3455,
+      "step": 5780
+    },
+    {
+      "epoch": 0.6750203669938317,
+      "grad_norm": 2.0445973873138428,
+      "learning_rate": 0.00013253390767797892,
+      "loss": 0.3345,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6773480234317415,
+      "grad_norm": 0.24779553711414337,
+      "learning_rate": 0.0001323010652540893,
+      "loss": 0.3397,
+      "step": 5820
+    },
+    {
+      "epoch": 0.6796756798696513,
+      "grad_norm": 0.21170444786548615,
+      "learning_rate": 0.00013206822283019966,
+      "loss": 0.3363,
+      "step": 5840
+    },
+    {
+      "epoch": 0.682003336307561,
+      "grad_norm": 0.30850765109062195,
+      "learning_rate": 0.00013183538040631004,
+      "loss": 0.3506,
+      "step": 5860
+    },
+    {
+      "epoch": 0.6843309927454708,
+      "grad_norm": 0.21219059824943542,
+      "learning_rate": 0.0001316025379824204,
+      "loss": 0.3419,
+      "step": 5880
+    },
+    {
+      "epoch": 0.6866586491833805,
+      "grad_norm": 0.197677344083786,
+      "learning_rate": 0.00013136969555853077,
+      "loss": 0.3421,
+      "step": 5900
+    },
+    {
+      "epoch": 0.6889863056212903,
+      "grad_norm": 0.32310721278190613,
+      "learning_rate": 0.00013113685313464115,
+      "loss": 0.3446,
+      "step": 5920
+    },
+    {
+      "epoch": 0.6913139620592,
+      "grad_norm": 0.31309011578559875,
+      "learning_rate": 0.0001309040107107515,
+      "loss": 0.3412,
+      "step": 5940
+    },
+    {
+      "epoch": 0.6936416184971098,
+      "grad_norm": 0.24054917693138123,
+      "learning_rate": 0.00013067116828686189,
+      "loss": 0.3571,
+      "step": 5960
+    },
+    {
+      "epoch": 0.6959692749350196,
+      "grad_norm": 0.22533154487609863,
+      "learning_rate": 0.00013043832586297224,
+      "loss": 0.3414,
+      "step": 5980
+    },
+    {
+      "epoch": 0.6982969313729294,
+      "eval_loss": 0.31252363324165344,
+      "eval_runtime": 20.5182,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7006245878108391,
+      "grad_norm": 0.23956398665905,
+      "learning_rate": 0.00012997264101519297,
+      "loss": 0.3434,
+      "step": 6020
+    },
+    {
+      "epoch": 0.7029522442487489,
+      "grad_norm": 0.23302090167999268,
+      "learning_rate": 0.00012973979859130333,
+      "loss": 0.3396,
+      "step": 6040
+    },
+    {
+      "epoch": 0.7052799006866587,
+      "grad_norm": 0.24427565932273865,
+      "learning_rate": 0.0001295069561674137,
+      "loss": 0.3399,
+      "step": 6060
+    },
+    {
+      "epoch": 0.7076075571245685,
+      "grad_norm": 0.2539879381656647,
+      "learning_rate": 0.00012927411374352406,
+      "loss": 0.3407,
+      "step": 6080
+    },
+    {
+      "epoch": 0.7099352135624781,
+      "grad_norm": 0.34259453415870667,
+      "learning_rate": 0.00012904127131963444,
+      "loss": 0.3476,
+      "step": 6100
+    },
+    {
+      "epoch": 0.7122628700003879,
+      "grad_norm": 0.7580363750457764,
+      "learning_rate": 0.0001288084288957448,
+      "loss": 0.3333,
+      "step": 6120
+    },
+    {
+      "epoch": 0.7145905264382977,
+      "grad_norm": 0.2014712542295456,
+      "learning_rate": 0.00012857558647185518,
+      "loss": 0.3318,
+      "step": 6140
+    },
+    {
+      "epoch": 0.7169181828762075,
+      "grad_norm": 0.19354534149169922,
+      "learning_rate": 0.00012834274404796553,
+      "loss": 0.3468,
+      "step": 6160
+    },
+    {
+      "epoch": 0.7192458393141172,
+      "grad_norm": 0.2484605461359024,
+      "learning_rate": 0.0001281099016240759,
+      "loss": 0.3374,
+      "step": 6180
+    },
+    {
+      "epoch": 0.721573495752027,
+      "grad_norm": 0.18194323778152466,
+      "learning_rate": 0.0001278770592001863,
+      "loss": 0.3476,
+      "step": 6200
+    },
+    {
+      "epoch": 0.7239011521899368,
+      "grad_norm": 0.3695623278617859,
+      "learning_rate": 0.00012764421677629665,
+      "loss": 0.3388,
+      "step": 6220
+    },
+    {
+      "epoch": 0.7262288086278466,
+      "grad_norm": 0.18656660616397858,
+      "learning_rate": 0.00012741137435240703,
+      "loss": 0.3432,
+      "step": 6240
+    },
+    {
+      "epoch": 0.7285564650657563,
+      "grad_norm": 0.2397935390472412,
+      "learning_rate": 0.00012717853192851738,
+      "loss": 0.3353,
+      "step": 6260
+    },
+    {
+      "epoch": 0.7308841215036661,
+      "grad_norm": 0.23836293816566467,
+      "learning_rate": 0.00012694568950462776,
+      "loss": 0.3356,
+      "step": 6280
+    },
+    {
+      "epoch": 0.7332117779415758,
+      "grad_norm": 0.26712825894355774,
+      "learning_rate": 0.00012671284708073812,
+      "loss": 0.3343,
+      "step": 6300
+    },
+    {
+      "epoch": 0.7355394343794855,
+      "grad_norm": 0.637722373008728,
+      "learning_rate": 0.00012648000465684847,
+      "loss": 0.3394,
+      "step": 6320
+    },
+    {
+      "epoch": 0.7378670908173953,
+      "grad_norm": 0.2768455445766449,
+      "learning_rate": 0.00012624716223295885,
+      "loss": 0.3431,
+      "step": 6340
+    },
+    {
+      "epoch": 0.7401947472553051,
+      "grad_norm": 0.3580669164657593,
+      "learning_rate": 0.0001260143198090692,
+      "loss": 0.3397,
+      "step": 6360
+    },
+    {
+      "epoch": 0.7425224036932149,
+      "grad_norm": 0.2058987021446228,
+      "learning_rate": 0.00012578147738517959,
+      "loss": 0.3253,
+      "step": 6380
+    },
+    {
+      "epoch": 0.7448500601311246,
+      "grad_norm": 0.29821643233299255,
+      "learning_rate": 0.00012554863496128994,
+      "loss": 0.3528,
+      "step": 6400
+    },
+    {
+      "epoch": 0.7471777165690344,
+      "grad_norm": 0.22168321907520294,
+      "learning_rate": 0.00012531579253740032,
+      "loss": 0.3463,
+      "step": 6420
+    },
+    {
+      "epoch": 0.7495053730069442,
+      "grad_norm": 0.20312601327896118,
+      "learning_rate": 0.00012508295011351067,
+      "loss": 0.3351,
+      "step": 6440
+    },
+    {
+      "epoch": 0.751833029444854,
+      "grad_norm": 0.19957271218299866,
+      "learning_rate": 0.00012485010768962105,
+      "loss": 0.3423,
+      "step": 6460
+    },
+    {
+      "epoch": 0.7541606858827637,
+      "grad_norm": 0.25446709990501404,
+      "learning_rate": 0.00012461726526573143,
+      "loss": 0.3264,
+      "step": 6480
+    },
+    {
+      "epoch": 0.7564883423206735,
+      "grad_norm": 0.21114079654216766,
+      "learning_rate": 0.0001243844228418418,
+      "loss": 0.3284,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7588159987585832,
+      "grad_norm": 4.584723472595215,
+      "learning_rate": 0.00012415158041795217,
+      "loss": 0.3206,
+      "step": 6520
+    },
+    {
+      "epoch": 0.761143655196493,
+      "grad_norm": 0.22033460438251495,
+      "learning_rate": 0.00012391873799406252,
+      "loss": 0.3483,
+      "step": 6540
+    },
+    {
+      "epoch": 0.7634713116344027,
+      "grad_norm": 0.2275933176279068,
+      "learning_rate": 0.0001236858955701729,
+      "loss": 0.3335,
+      "step": 6560
+    },
+    {
+      "epoch": 0.7657989680723125,
+      "grad_norm": 0.26012253761291504,
+      "learning_rate": 0.00012345305314628326,
+      "loss": 0.325,
+      "step": 6580
+    },
+    {
+      "epoch": 0.7681266245102223,
+      "grad_norm": 0.23552890121936798,
+      "learning_rate": 0.00012322021072239364,
+      "loss": 0.3266,
+      "step": 6600
+    },
+    {
+      "epoch": 0.7704542809481321,
+      "grad_norm": 0.21740244328975677,
+      "learning_rate": 0.000122987368298504,
+      "loss": 0.3355,
+      "step": 6620
+    },
+    {
+      "epoch": 0.7727819373860418,
+      "grad_norm": 0.3150811791419983,
+      "learning_rate": 0.00012275452587461435,
+      "loss": 0.3417,
+      "step": 6640
+    },
+    {
+      "epoch": 0.7751095938239516,
+      "grad_norm": 0.26851484179496765,
+      "learning_rate": 0.00012252168345072473,
+      "loss": 0.3466,
+      "step": 6660
+    },
+    {
+      "epoch": 0.7774372502618614,
+      "grad_norm": 0.6656216979026794,
+      "learning_rate": 0.00012228884102683508,
+      "loss": 0.352,
+      "step": 6680
+    },
+    {
+      "epoch": 0.7797649066997712,
+      "grad_norm": 0.17582151293754578,
+      "learning_rate": 0.00012205599860294545,
+      "loss": 0.3172,
+      "step": 6700
+    },
+    {
+      "epoch": 0.7820925631376808,
+      "grad_norm": 0.35307776927948,
+      "learning_rate": 0.00012182315617905582,
+      "loss": 0.3279,
+      "step": 6720
+    },
+    {
+      "epoch": 0.7844202195755906,
+      "grad_norm": 0.2920871675014496,
+      "learning_rate": 0.00012159031375516621,
+      "loss": 0.3381,
+      "step": 6740
+    },
+    {
+      "epoch": 0.7867478760135004,
+      "grad_norm": 0.23374487459659576,
+      "learning_rate": 0.00012135747133127658,
+      "loss": 0.3388,
+      "step": 6760
+    },
+    {
+      "epoch": 0.7890755324514102,
+      "grad_norm": 0.20663613080978394,
+      "learning_rate": 0.00012112462890738694,
+      "loss": 0.3445,
+      "step": 6780
+    },
+    {
+      "epoch": 0.7914031888893199,
+      "grad_norm": 0.24840141832828522,
+      "learning_rate": 0.00012089178648349731,
+      "loss": 0.3369,
+      "step": 6800
+    },
+    {
+      "epoch": 0.7937308453272297,
+      "grad_norm": 0.21013478934764862,
+      "learning_rate": 0.00012065894405960766,
+      "loss": 0.3254,
+      "step": 6820
+    },
+    {
+      "epoch": 0.7960585017651395,
+      "grad_norm": 0.3410046696662903,
+      "learning_rate": 0.00012042610163571803,
+      "loss": 0.321,
+      "step": 6840
+    },
+    {
+      "epoch": 0.7983861582030493,
+      "grad_norm": 0.3851812481880188,
+      "learning_rate": 0.0001201932592118284,
+      "loss": 0.3423,
+      "step": 6860
+    },
+    {
+      "epoch": 0.800713814640959,
+      "grad_norm": 0.16629061102867126,
+      "learning_rate": 0.00011996041678793877,
+      "loss": 0.3208,
+      "step": 6880
+    },
+    {
+      "epoch": 0.8030414710788688,
+      "grad_norm": 48.18583297729492,
+      "learning_rate": 0.00011972757436404913,
+      "loss": 0.3353,
+      "step": 6900
+    },
+    {
+      "epoch": 0.8053691275167785,
+      "grad_norm": 0.25795847177505493,
+      "learning_rate": 0.0001194947319401595,
+      "loss": 0.3437,
+      "step": 6920
+    },
+    {
+      "epoch": 0.8076967839546882,
+      "grad_norm": 0.20115159451961517,
+      "learning_rate": 0.00011926188951626987,
+      "loss": 0.3433,
+      "step": 6940
+    },
+    {
+      "epoch": 0.810024440392598,
+      "grad_norm": 0.20792783796787262,
+      "learning_rate": 0.00011902904709238024,
+      "loss": 0.3336,
+      "step": 6960
+    },
+    {
+      "epoch": 0.8123520968305078,
+      "grad_norm": 0.2534950077533722,
+      "learning_rate": 0.00011879620466849059,
+      "loss": 0.3396,
+      "step": 6980
+    },
+    {
+      "epoch": 0.8146797532684176,
+      "eval_loss": 0.3010511100292206,
+      "eval_runtime": 20.5045,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8170074097063273,
+      "grad_norm": 0.23660871386528015,
+      "learning_rate": 0.00011833051982071135,
+      "loss": 0.3328,
+      "step": 7020
+    },
+    {
+      "epoch": 0.8193350661442371,
+      "grad_norm": 0.23649924993515015,
+      "learning_rate": 0.00011809767739682172,
+      "loss": 0.3492,
+      "step": 7040
+    },
+    {
+      "epoch": 0.8216627225821469,
+      "grad_norm": 0.24621158838272095,
+      "learning_rate": 0.00011786483497293209,
+      "loss": 0.3253,
+      "step": 7060
+    },
+    {
+      "epoch": 0.8239903790200567,
+      "grad_norm": 0.18772444128990173,
+      "learning_rate": 0.00011763199254904245,
+      "loss": 0.3384,
+      "step": 7080
+    },
+    {
+      "epoch": 0.8263180354579664,
+      "grad_norm": 0.2801457941532135,
+      "learning_rate": 0.0001173991501251528,
+      "loss": 0.3312,
+      "step": 7100
+    },
+    {
+      "epoch": 0.8286456918958762,
+      "grad_norm": 0.21918728947639465,
+      "learning_rate": 0.00011716630770126317,
+      "loss": 0.3245,
+      "step": 7120
+    },
+    {
+      "epoch": 0.8309733483337859,
+      "grad_norm": 0.1776329129934311,
+      "learning_rate": 0.00011693346527737354,
+      "loss": 0.3315,
+      "step": 7140
+    },
+    {
+      "epoch": 0.8333010047716957,
+      "grad_norm": 12.983736038208008,
+      "learning_rate": 0.00011670062285348391,
+      "loss": 0.3362,
+      "step": 7160
+    },
+    {
+      "epoch": 0.8356286612096054,
+      "grad_norm": 0.21647751331329346,
+      "learning_rate": 0.00011646778042959428,
+      "loss": 0.3291,
+      "step": 7180
+    },
+    {
+      "epoch": 0.8379563176475152,
+      "grad_norm": 0.3001130223274231,
+      "learning_rate": 0.00011623493800570464,
+      "loss": 0.3393,
+      "step": 7200
+    },
+    {
+      "epoch": 0.840283974085425,
+      "grad_norm": 0.39479219913482666,
+      "learning_rate": 0.00011600209558181501,
+      "loss": 0.3438,
+      "step": 7220
+    },
+    {
+      "epoch": 0.8426116305233348,
+      "grad_norm": 0.234198197722435,
+      "learning_rate": 0.00011576925315792538,
+      "loss": 0.3409,
+      "step": 7240
+    },
+    {
+      "epoch": 0.8449392869612445,
+      "grad_norm": 0.2157607227563858,
+      "learning_rate": 0.00011553641073403574,
+      "loss": 0.3338,
+      "step": 7260
+    },
+    {
+      "epoch": 0.8472669433991543,
+      "grad_norm": 0.2433777153491974,
+      "learning_rate": 0.0001153035683101461,
+      "loss": 0.3348,
+      "step": 7280
+    },
+    {
+      "epoch": 0.8495945998370641,
+      "grad_norm": 0.47679832577705383,
+      "learning_rate": 0.00011507072588625649,
+      "loss": 0.3353,
+      "step": 7300
+    },
+    {
+      "epoch": 0.8519222562749739,
+      "grad_norm": 0.2851008176803589,
+      "learning_rate": 0.00011483788346236686,
+      "loss": 0.3292,
+      "step": 7320
+    },
+    {
+      "epoch": 0.8542499127128835,
+      "grad_norm": 0.19934503734111786,
+      "learning_rate": 0.00011460504103847723,
+      "loss": 0.3205,
+      "step": 7340
+    },
+    {
+      "epoch": 0.8565775691507933,
+      "grad_norm": 0.2159925103187561,
+      "learning_rate": 0.0001143721986145876,
+      "loss": 0.3337,
+      "step": 7360
+    },
+    {
+      "epoch": 0.8589052255887031,
+      "grad_norm": 0.29275134205818176,
+      "learning_rate": 0.00011413935619069795,
+      "loss": 0.3331,
+      "step": 7380
+    },
+    {
+      "epoch": 0.8612328820266129,
+      "grad_norm": 0.20441026985645294,
+      "learning_rate": 0.00011390651376680832,
+      "loss": 0.3305,
+      "step": 7400
+    },
+    {
+      "epoch": 0.8635605384645226,
+      "grad_norm": 0.21615193784236908,
+      "learning_rate": 0.00011367367134291868,
+      "loss": 0.3288,
+      "step": 7420
+    },
+    {
+      "epoch": 0.8658881949024324,
+      "grad_norm": 0.21526269614696503,
+      "learning_rate": 0.00011344082891902905,
+      "loss": 0.3358,
+      "step": 7440
+    },
+    {
+      "epoch": 0.8682158513403422,
+      "grad_norm": 0.265211820602417,
+      "learning_rate": 0.00011320798649513942,
+      "loss": 0.3264,
+      "step": 7460
+    },
+    {
+      "epoch": 0.870543507778252,
+      "grad_norm": 0.22178636491298676,
+      "learning_rate": 0.00011297514407124978,
+      "loss": 0.3207,
+      "step": 7480
+    },
+    {
+      "epoch": 0.8728711642161617,
+      "grad_norm": 0.21639615297317505,
+      "learning_rate": 0.00011274230164736015,
+      "loss": 0.3315,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8751988206540715,
+      "grad_norm": 57.44207763671875,
+      "learning_rate": 0.00011250945922347052,
+      "loss": 0.3198,
+      "step": 7520
+    },
+    {
+      "epoch": 0.8775264770919812,
+      "grad_norm": 0.4084792137145996,
+      "learning_rate": 0.00011227661679958089,
+      "loss": 0.347,
+      "step": 7540
+    },
+    {
+      "epoch": 0.879854133529891,
+      "grad_norm": 0.2810383439064026,
+      "learning_rate": 0.00011204377437569124,
+      "loss": 0.32,
+      "step": 7560
+    },
+    {
+      "epoch": 0.8821817899678007,
+      "grad_norm": 0.27973487973213196,
+      "learning_rate": 0.00011181093195180163,
+      "loss": 0.3356,
+      "step": 7580
+    },
+    {
+      "epoch": 0.8845094464057105,
+      "grad_norm": 0.2550235390663147,
+      "learning_rate": 0.000111578089527912,
+      "loss": 0.3309,
+      "step": 7600
+    },
+    {
+      "epoch": 0.8868371028436203,
+      "grad_norm": 0.20432604849338531,
+      "learning_rate": 0.00011134524710402237,
+      "loss": 0.3369,
+      "step": 7620
+    },
+    {
+      "epoch": 0.88916475928153,
+      "grad_norm": 0.30316558480262756,
+      "learning_rate": 0.00011111240468013274,
+      "loss": 0.3395,
+      "step": 7640
+    },
+    {
+      "epoch": 0.8914924157194398,
+      "grad_norm": 0.2645493149757385,
+      "learning_rate": 0.0001108795622562431,
+      "loss": 0.3467,
+      "step": 7660
+    },
+    {
+      "epoch": 0.8938200721573496,
+      "grad_norm": 0.19967636466026306,
+      "learning_rate": 0.00011064671983235346,
+      "loss": 0.3371,
+      "step": 7680
+    },
+    {
+      "epoch": 0.8961477285952594,
+      "grad_norm": 0.2843848466873169,
+      "learning_rate": 0.00011041387740846382,
+      "loss": 0.3326,
+      "step": 7700
+    },
+    {
+      "epoch": 0.8984753850331691,
+      "grad_norm": 0.2311348170042038,
+      "learning_rate": 0.00011018103498457419,
+      "loss": 0.3244,
+      "step": 7720
+    },
+    {
+      "epoch": 0.9008030414710788,
+      "grad_norm": 0.2645195722579956,
+      "learning_rate": 0.00010994819256068456,
+      "loss": 0.3258,
+      "step": 7740
+    },
+    {
+      "epoch": 0.9031306979089886,
+      "grad_norm": 0.2115214765071869,
+      "learning_rate": 0.00010971535013679493,
+      "loss": 0.3229,
+      "step": 7760
+    },
+    {
+      "epoch": 0.9054583543468984,
+      "grad_norm": 0.29056933522224426,
+      "learning_rate": 0.0001094825077129053,
+      "loss": 0.3223,
+      "step": 7780
+    },
+    {
+      "epoch": 0.9077860107848081,
+      "grad_norm": 0.5415270328521729,
+      "learning_rate": 0.00010924966528901566,
+      "loss": 0.3249,
+      "step": 7800
+    },
+    {
+      "epoch": 0.9101136672227179,
+      "grad_norm": 0.2580903172492981,
+      "learning_rate": 0.00010901682286512603,
+      "loss": 0.3139,
+      "step": 7820
+    },
+    {
+      "epoch": 0.9124413236606277,
+      "grad_norm": 0.26741182804107666,
+      "learning_rate": 0.00010878398044123638,
+      "loss": 0.3373,
+      "step": 7840
+    },
+    {
+      "epoch": 0.9147689800985375,
+      "grad_norm": 0.2504960894584656,
+      "learning_rate": 0.00010855113801734678,
+      "loss": 0.3283,
+      "step": 7860
+    },
+    {
+      "epoch": 0.9170966365364472,
+      "grad_norm": 0.21173089742660522,
+      "learning_rate": 0.00010831829559345714,
+      "loss": 0.3216,
+      "step": 7880
+    },
+    {
+      "epoch": 0.919424292974357,
+      "grad_norm": 0.29330143332481384,
+      "learning_rate": 0.00010808545316956751,
+      "loss": 0.3402,
+      "step": 7900
+    },
+    {
+      "epoch": 0.9217519494122668,
+      "grad_norm": 0.26648497581481934,
+      "learning_rate": 0.00010785261074567788,
+      "loss": 0.3368,
+      "step": 7920
+    },
+    {
+      "epoch": 0.9240796058501766,
+      "grad_norm": 0.18227796256542206,
+      "learning_rate": 0.00010761976832178825,
+      "loss": 0.3185,
+      "step": 7940
+    },
+    {
+      "epoch": 0.9264072622880862,
+      "grad_norm": 0.42053866386413574,
+      "learning_rate": 0.0001073869258978986,
+      "loss": 0.3346,
+      "step": 7960
+    },
+    {
+      "epoch": 0.928734918725996,
+      "grad_norm": 0.26630160212516785,
+      "learning_rate": 0.00010715408347400897,
+      "loss": 0.3224,
+      "step": 7980
+    },
+    {
+      "epoch": 0.9310625751639058,
+      "eval_loss": 0.3001655638217926,
+      "eval_runtime": 20.5025,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9333902316018156,
+      "grad_norm": 0.24935676157474518,
+      "learning_rate": 0.0001066883986262297,
+      "loss": 0.3254,
+      "step": 8020
+    },
+    {
+      "epoch": 0.9357178880397253,
+      "grad_norm": 0.2132023274898529,
+      "learning_rate": 0.00010645555620234007,
+      "loss": 0.3299,
+      "step": 8040
+    },
+    {
+      "epoch": 0.9380455444776351,
+      "grad_norm": 0.4576941430568695,
+      "learning_rate": 0.00010622271377845044,
+      "loss": 0.328,
+      "step": 8060
+    },
+    {
+      "epoch": 0.9403732009155449,
+      "grad_norm": 0.18452784419059753,
+      "learning_rate": 0.0001059898713545608,
+      "loss": 0.334,
+      "step": 8080
+    },
+    {
+      "epoch": 0.9427008573534547,
+      "grad_norm": 0.2533165216445923,
+      "learning_rate": 0.00010575702893067117,
+      "loss": 0.3357,
+      "step": 8100
+    },
+    {
+      "epoch": 0.9450285137913644,
+      "grad_norm": 0.26251518726348877,
+      "learning_rate": 0.00010552418650678154,
+      "loss": 0.3206,
+      "step": 8120
+    },
+    {
+      "epoch": 0.9473561702292742,
+      "grad_norm": 0.21704651415348053,
+      "learning_rate": 0.00010529134408289192,
+      "loss": 0.329,
+      "step": 8140
+    },
+    {
+      "epoch": 0.9496838266671839,
+      "grad_norm": 0.16483543813228607,
+      "learning_rate": 0.00010505850165900229,
+      "loss": 0.325,
+      "step": 8160
+    },
+    {
+      "epoch": 0.9520114831050936,
+      "grad_norm": 0.5089607238769531,
+      "learning_rate": 0.00010482565923511265,
+      "loss": 0.326,
+      "step": 8180
+    },
+    {
+      "epoch": 0.9543391395430034,
+      "grad_norm": 0.275442898273468,
+      "learning_rate": 0.00010459281681122302,
+      "loss": 0.3363,
+      "step": 8200
+    },
+    {
+      "epoch": 0.9566667959809132,
+      "grad_norm": 0.2757873237133026,
+      "learning_rate": 0.00010435997438733339,
+      "loss": 0.3253,
+      "step": 8220
+    },
+    {
+      "epoch": 0.958994452418823,
+      "grad_norm": 0.2259269803762436,
+      "learning_rate": 0.00010412713196344374,
+      "loss": 0.3381,
+      "step": 8240
+    },
+    {
+      "epoch": 0.9613221088567327,
+      "grad_norm": 0.22286689281463623,
+      "learning_rate": 0.00010389428953955411,
+      "loss": 0.3287,
+      "step": 8260
+    },
+    {
+      "epoch": 0.9636497652946425,
+      "grad_norm": 0.35119926929473877,
+      "learning_rate": 0.00010366144711566448,
+      "loss": 0.3326,
+      "step": 8280
+    },
+    {
+      "epoch": 0.9659774217325523,
+      "grad_norm": 0.20044976472854614,
+      "learning_rate": 0.00010342860469177484,
+      "loss": 0.3169,
+      "step": 8300
+    },
+    {
+      "epoch": 0.9683050781704621,
+      "grad_norm": 0.4732118844985962,
+      "learning_rate": 0.00010319576226788521,
+      "loss": 0.3153,
+      "step": 8320
+    },
+    {
+      "epoch": 0.9706327346083718,
+      "grad_norm": 0.4038439393043518,
+      "learning_rate": 0.00010296291984399558,
+      "loss": 0.3145,
+      "step": 8340
+    },
+    {
+      "epoch": 0.9729603910462815,
+      "grad_norm": 0.21932996809482574,
+      "learning_rate": 0.00010273007742010594,
+      "loss": 0.3301,
+      "step": 8360
+    },
+    {
+      "epoch": 0.9752880474841913,
+      "grad_norm": 0.3449685573577881,
+      "learning_rate": 0.00010249723499621631,
+      "loss": 0.3282,
+      "step": 8380
+    },
+    {
+      "epoch": 0.9776157039221011,
+      "grad_norm": 0.2299947589635849,
+      "learning_rate": 0.00010226439257232668,
+      "loss": 0.3299,
+      "step": 8400
+    },
+    {
+      "epoch": 0.9799433603600108,
+      "grad_norm": 0.2672164738178253,
+      "learning_rate": 0.00010203155014843706,
+      "loss": 0.3126,
+      "step": 8420
+    },
+    {
+      "epoch": 0.9822710167979206,
+      "grad_norm": 0.2478913813829422,
+      "learning_rate": 0.00010179870772454743,
+      "loss": 0.33,
+      "step": 8440
+    },
+    {
+      "epoch": 0.9845986732358304,
+      "grad_norm": 0.23997768759727478,
+      "learning_rate": 0.0001015658653006578,
+      "loss": 0.3257,
+      "step": 8460
+    },
+    {
+      "epoch": 0.9869263296737402,
+      "grad_norm": 0.23790204524993896,
+      "learning_rate": 0.00010133302287676816,
+      "loss": 0.3232,
+      "step": 8480
+    },
+    {
+      "epoch": 0.9892539861116499,
+      "grad_norm": 0.23755834996700287,
+      "learning_rate": 0.00010110018045287853,
+      "loss": 0.325,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9915816425495597,
+      "grad_norm": 0.24350681900978088,
+      "learning_rate": 0.0001008673380289889,
+      "loss": 0.334,
+      "step": 8520
+    },
+    {
+      "epoch": 0.9939092989874695,
+      "grad_norm": 0.2278716266155243,
+      "learning_rate": 0.00010063449560509925,
+      "loss": 0.3244,
+      "step": 8540
+    },
+    {
+      "epoch": 0.9962369554253793,
+      "grad_norm": 0.604132354259491,
+      "learning_rate": 0.00010040165318120962,
+      "loss": 0.3182,
+      "step": 8560
+    },
+    {
+      "epoch": 0.9985646118632889,
+      "grad_norm": 0.3018403649330139,
+      "learning_rate": 0.00010016881075731998,
+      "loss": 0.3373,
+      "step": 8580
+    },
+    {
+      "epoch": 1.0008146797532684,
+      "grad_norm": 0.244240865111351,
+      "learning_rate": 9.993596833343035e-05,
+      "loss": 0.3122,
+      "step": 8600
+    },
+    {
+      "epoch": 1.0031423361911782,
+      "grad_norm": 0.3051922023296356,
+      "learning_rate": 9.970312590954072e-05,
+      "loss": 0.3205,
+      "step": 8620
+    },
+    {
+      "epoch": 1.005469992629088,
+      "grad_norm": 0.24074581265449524,
+      "learning_rate": 9.94702834856511e-05,
+      "loss": 0.3126,
+      "step": 8640
+    },
+    {
+      "epoch": 1.0077976490669978,
+      "grad_norm": 0.36978912353515625,
+      "learning_rate": 9.923744106176147e-05,
+      "loss": 0.31,
+      "step": 8660
+    },
+    {
+      "epoch": 1.0101253055049075,
+      "grad_norm": 0.1907973736524582,
+      "learning_rate": 9.900459863787182e-05,
+      "loss": 0.3082,
+      "step": 8680
+    },
+    {
+      "epoch": 1.0124529619428173,
+      "grad_norm": 0.2336815595626831,
+      "learning_rate": 9.877175621398219e-05,
+      "loss": 0.3029,
+      "step": 8700
+    },
+    {
+      "epoch": 1.014780618380727,
+      "grad_norm": 0.23371773958206177,
+      "learning_rate": 9.853891379009255e-05,
+      "loss": 0.3122,
+      "step": 8720
+    },
+    {
+      "epoch": 1.0171082748186369,
+      "grad_norm": 0.2922288179397583,
+      "learning_rate": 9.830607136620292e-05,
+      "loss": 0.3139,
+      "step": 8740
+    },
+    {
+      "epoch": 1.0194359312565466,
+      "grad_norm": 0.38291946053504944,
+      "learning_rate": 9.807322894231329e-05,
+      "loss": 0.3144,
+      "step": 8760
+    },
+    {
+      "epoch": 1.0217635876944562,
+      "grad_norm": 0.2271076887845993,
+      "learning_rate": 9.784038651842367e-05,
+      "loss": 0.31,
+      "step": 8780
+    },
+    {
+      "epoch": 1.024091244132366,
+      "grad_norm": 0.3076484501361847,
+      "learning_rate": 9.760754409453404e-05,
+      "loss": 0.3136,
+      "step": 8800
+    },
+    {
+      "epoch": 1.0264189005702757,
+      "grad_norm": 0.1866464465856552,
+      "learning_rate": 9.737470167064439e-05,
+      "loss": 0.3054,
+      "step": 8820
+    },
+    {
+      "epoch": 1.0287465570081855,
+      "grad_norm": 0.24267898499965668,
+      "learning_rate": 9.714185924675476e-05,
+      "loss": 0.3174,
+      "step": 8840
+    },
+    {
+      "epoch": 1.0310742134460953,
+      "grad_norm": 0.2136778086423874,
+      "learning_rate": 9.690901682286513e-05,
+      "loss": 0.3271,
+      "step": 8860
+    },
+    {
+      "epoch": 1.033401869884005,
+      "grad_norm": 0.2531084418296814,
+      "learning_rate": 9.667617439897549e-05,
+      "loss": 0.307,
+      "step": 8880
+    },
+    {
+      "epoch": 1.0357295263219148,
+      "grad_norm": 0.3214069604873657,
+      "learning_rate": 9.644333197508586e-05,
+      "loss": 0.3105,
+      "step": 8900
+    },
+    {
+      "epoch": 1.0380571827598246,
+      "grad_norm": 0.41361871361732483,
+      "learning_rate": 9.621048955119624e-05,
+      "loss": 0.3096,
+      "step": 8920
+    },
+    {
+      "epoch": 1.0403848391977344,
+      "grad_norm": 0.24096006155014038,
+      "learning_rate": 9.597764712730661e-05,
+      "loss": 0.3212,
+      "step": 8940
+    },
+    {
+      "epoch": 1.0427124956356442,
+      "grad_norm": 0.2052450031042099,
+      "learning_rate": 9.574480470341696e-05,
+      "loss": 0.3038,
+      "step": 8960
+    },
+    {
+      "epoch": 1.045040152073554,
+      "grad_norm": 0.23341313004493713,
+      "learning_rate": 9.551196227952733e-05,
+      "loss": 0.3195,
+      "step": 8980
+    },
+    {
+      "epoch": 1.0473678085114637,
+      "eval_loss": 0.3088056743144989,
+      "eval_runtime": 20.5127,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 9000
+    },
+    {
+      "epoch": 1.0496954649493735,
+      "grad_norm": 0.2070196568965912,
+      "learning_rate": 9.504627743174806e-05,
+      "loss": 0.3198,
+      "step": 9020
+    },
+    {
+      "epoch": 1.0520231213872833,
+      "grad_norm": 0.23446215689182281,
+      "learning_rate": 9.481343500785843e-05,
+      "loss": 0.3155,
+      "step": 9040
+    },
+    {
+      "epoch": 1.054350777825193,
+      "grad_norm": 0.2329404056072235,
+      "learning_rate": 9.458059258396881e-05,
+      "loss": 0.2999,
+      "step": 9060
+    },
+    {
+      "epoch": 1.0566784342631028,
+      "grad_norm": 0.1957203894853592,
+      "learning_rate": 9.434775016007918e-05,
+      "loss": 0.3021,
+      "step": 9080
+    },
+    {
+      "epoch": 1.0590060907010126,
+      "grad_norm": 0.21453732252120972,
+      "learning_rate": 9.411490773618953e-05,
+      "loss": 0.2958,
+      "step": 9100
+    },
+    {
+      "epoch": 1.0613337471389224,
+      "grad_norm": 0.2094150334596634,
+      "learning_rate": 9.38820653122999e-05,
+      "loss": 0.3106,
+      "step": 9120
+    },
+    {
+      "epoch": 1.0636614035768321,
+      "grad_norm": 0.2443944662809372,
+      "learning_rate": 9.364922288841027e-05,
+      "loss": 0.3017,
+      "step": 9140
+    },
+    {
+      "epoch": 1.065989060014742,
+      "grad_norm": 0.21869835257530212,
+      "learning_rate": 9.341638046452063e-05,
+      "loss": 0.315,
+      "step": 9160
+    },
+    {
+      "epoch": 1.0683167164526517,
+      "grad_norm": 0.28906378149986267,
+      "learning_rate": 9.3183538040631e-05,
+      "loss": 0.3132,
+      "step": 9180
+    },
+    {
+      "epoch": 1.0706443728905612,
+      "grad_norm": 0.4606005549430847,
+      "learning_rate": 9.295069561674138e-05,
+      "loss": 0.3223,
+      "step": 9200
+    },
+    {
+      "epoch": 1.072972029328471,
+      "grad_norm": 0.25607815384864807,
+      "learning_rate": 9.271785319285175e-05,
+      "loss": 0.3163,
+      "step": 9220
+    },
+    {
+      "epoch": 1.0752996857663808,
+      "grad_norm": 0.5417608618736267,
+      "learning_rate": 9.24850107689621e-05,
+      "loss": 0.2977,
+      "step": 9240
+    },
+    {
+      "epoch": 1.0776273422042906,
+      "grad_norm": 0.31004786491394043,
+      "learning_rate": 9.225216834507247e-05,
+      "loss": 0.3255,
+      "step": 9260
+    },
+    {
+      "epoch": 1.0799549986422003,
+      "grad_norm": 0.35875990986824036,
+      "learning_rate": 9.201932592118284e-05,
+      "loss": 0.3164,
+      "step": 9280
+    },
+    {
+      "epoch": 1.0822826550801101,
+      "grad_norm": 0.3279019892215729,
+      "learning_rate": 9.17864834972932e-05,
+      "loss": 0.3109,
+      "step": 9300
+    },
+    {
+      "epoch": 1.08461031151802,
+      "grad_norm": 0.2438986450433731,
+      "learning_rate": 9.155364107340357e-05,
+      "loss": 0.3235,
+      "step": 9320
+    },
+    {
+      "epoch": 1.0869379679559297,
+      "grad_norm": 0.3360047936439514,
+      "learning_rate": 9.132079864951395e-05,
+      "loss": 0.3009,
+      "step": 9340
+    },
+    {
+      "epoch": 1.0892656243938394,
+      "grad_norm": 0.3423820436000824,
+      "learning_rate": 9.108795622562432e-05,
+      "loss": 0.3145,
+      "step": 9360
+    },
+    {
+      "epoch": 1.0915932808317492,
+      "grad_norm": 0.25532302260398865,
+      "learning_rate": 9.085511380173469e-05,
+      "loss": 0.3166,
+      "step": 9380
+    },
+    {
+      "epoch": 1.093920937269659,
+      "grad_norm": 152.79296875,
+      "learning_rate": 9.062227137784504e-05,
+      "loss": 0.3109,
+      "step": 9400
+    },
+    {
+      "epoch": 1.0962485937075688,
+      "grad_norm": 0.5132696628570557,
+      "learning_rate": 9.038942895395541e-05,
+      "loss": 0.3393,
+      "step": 9420
+    },
+    {
+      "epoch": 1.0985762501454786,
+      "grad_norm": 0.24221967160701752,
+      "learning_rate": 9.015658653006578e-05,
+      "loss": 0.3154,
+      "step": 9440
+    },
+    {
+      "epoch": 1.1009039065833883,
+      "grad_norm": 0.20894664525985718,
+      "learning_rate": 8.992374410617614e-05,
+      "loss": 0.3077,
+      "step": 9460
+    },
+    {
+      "epoch": 1.103231563021298,
+      "grad_norm": 0.24484246969223022,
+      "learning_rate": 8.969090168228652e-05,
+      "loss": 0.3153,
+      "step": 9480
+    },
+    {
+      "epoch": 1.1055592194592079,
+      "grad_norm": 0.2670360505580902,
+      "learning_rate": 8.945805925839689e-05,
+      "loss": 0.3253,
+      "step": 9500
+    },
+    {
+      "epoch": 1.1078868758971177,
+      "grad_norm": 0.264602392911911,
+      "learning_rate": 8.922521683450726e-05,
+      "loss": 0.3048,
+      "step": 9520
+    },
+    {
+      "epoch": 1.1102145323350274,
+      "grad_norm": 0.23756831884384155,
+      "learning_rate": 8.899237441061761e-05,
+      "loss": 0.3043,
+      "step": 9540
+    },
+    {
+      "epoch": 1.1125421887729372,
+      "grad_norm": 0.2739344537258148,
+      "learning_rate": 8.875953198672798e-05,
+      "loss": 0.3073,
+      "step": 9560
+    },
+    {
+      "epoch": 1.114869845210847,
+      "grad_norm": 0.3609209954738617,
+      "learning_rate": 8.852668956283835e-05,
+      "loss": 0.32,
+      "step": 9580
+    },
+    {
+      "epoch": 1.1171975016487568,
+      "grad_norm": 0.2006099820137024,
+      "learning_rate": 8.829384713894871e-05,
+      "loss": 0.2964,
+      "step": 9600
+    },
+    {
+      "epoch": 1.1195251580866663,
+      "grad_norm": 0.24351206421852112,
+      "learning_rate": 8.80610047150591e-05,
+      "loss": 0.3114,
+      "step": 9620
+    },
+    {
+      "epoch": 1.121852814524576,
+      "grad_norm": 0.25505977869033813,
+      "learning_rate": 8.782816229116946e-05,
+      "loss": 0.2941,
+      "step": 9640
+    },
+    {
+      "epoch": 1.1241804709624859,
+      "grad_norm": 0.22329363226890564,
+      "learning_rate": 8.759531986727983e-05,
+      "loss": 0.3017,
+      "step": 9660
+    },
+    {
+      "epoch": 1.1265081274003956,
+      "grad_norm": 0.25461211800575256,
+      "learning_rate": 8.736247744339018e-05,
+      "loss": 0.2949,
+      "step": 9680
+    },
+    {
+      "epoch": 1.1288357838383054,
+      "grad_norm": 0.39750778675079346,
+      "learning_rate": 8.712963501950055e-05,
+      "loss": 0.3241,
+      "step": 9700
+    },
+    {
+      "epoch": 1.1311634402762152,
+      "grad_norm": 0.26190921664237976,
+      "learning_rate": 8.689679259561092e-05,
+      "loss": 0.3067,
+      "step": 9720
+    },
+    {
+      "epoch": 1.133491096714125,
+      "grad_norm": 0.2876713275909424,
+      "learning_rate": 8.666395017172129e-05,
+      "loss": 0.3282,
+      "step": 9740
+    },
+    {
+      "epoch": 1.1358187531520347,
+      "grad_norm": 0.1941649168729782,
+      "learning_rate": 8.643110774783167e-05,
+      "loss": 0.3008,
+      "step": 9760
+    },
+    {
+      "epoch": 1.1381464095899445,
+      "grad_norm": 0.2520879805088043,
+      "learning_rate": 8.619826532394203e-05,
+      "loss": 0.3115,
+      "step": 9780
+    },
+    {
+      "epoch": 1.1404740660278543,
+      "grad_norm": 0.3471347391605377,
+      "learning_rate": 8.59654229000524e-05,
+      "loss": 0.3178,
+      "step": 9800
+    },
+    {
+      "epoch": 1.142801722465764,
+      "grad_norm": 0.18873412907123566,
+      "learning_rate": 8.573258047616275e-05,
+      "loss": 0.3177,
+      "step": 9820
+    },
+    {
+      "epoch": 1.1451293789036738,
+      "grad_norm": 0.22296294569969177,
+      "learning_rate": 8.549973805227312e-05,
+      "loss": 0.3001,
+      "step": 9840
+    },
+    {
+      "epoch": 1.1474570353415836,
+      "grad_norm": 0.3296689987182617,
+      "learning_rate": 8.526689562838349e-05,
+      "loss": 0.3073,
+      "step": 9860
+    },
+    {
+      "epoch": 1.1497846917794934,
+      "grad_norm": 0.2323330193758011,
+      "learning_rate": 8.503405320449386e-05,
+      "loss": 0.3241,
+      "step": 9880
+    },
+    {
+      "epoch": 1.1521123482174032,
+      "grad_norm": 0.28804194927215576,
+      "learning_rate": 8.480121078060424e-05,
+      "loss": 0.3161,
+      "step": 9900
+    },
+    {
+      "epoch": 1.154440004655313,
+      "grad_norm": 0.4116811454296112,
+      "learning_rate": 8.45683683567146e-05,
+      "loss": 0.3099,
+      "step": 9920
+    },
+    {
+      "epoch": 1.1567676610932227,
+      "grad_norm": 0.21347229182720184,
+      "learning_rate": 8.433552593282497e-05,
+      "loss": 0.3189,
+      "step": 9940
+    },
+    {
+      "epoch": 1.1590953175311325,
+      "grad_norm": 0.27963757514953613,
+      "learning_rate": 8.410268350893533e-05,
+      "loss": 0.329,
+      "step": 9960
+    },
+    {
+      "epoch": 1.1614229739690423,
+      "grad_norm": 0.2386089563369751,
+      "learning_rate": 8.386984108504569e-05,
+      "loss": 0.3009,
+      "step": 9980
+    },
+    {
+      "epoch": 1.1637506304069518,
+      "eval_loss": 0.29284584522247314,
+      "eval_runtime": 20.5117,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.975,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 17184,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.1094053958164905e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7159d8f91fe644de34c5ef49b0f5bfcccad58ed0f6cdc6aa9990bd2a25a78220
+size 5688