Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+checkpoint-413/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+model_name: deepseek-simple-bot
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for deepseek-simple-bot
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.26.0
+- Transformers: 4.57.3
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d032b8add463bc6b3db221921a224cfa497ac4de1df952366516d285765f361
+size 8746152

chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

checkpoint-413/README.md

@@ -0,0 +1,209 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-413/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-413/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2896f71733b1a6821cf90bf8dcb8f25ce9fe59103710866f4466cb25fd6d739e
+size 8746152

checkpoint-413/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

checkpoint-413/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c318d0a34b9e22c2de6e6daf22975e1eb742bee55608d6d75a93f2f96714da
+size 9115403

checkpoint-413/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48362cf15000339828db080555a204cbfaf6a0fabe8e330927da061389077258
+size 14645

checkpoint-413/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6b2d367bf362397b5ac18e74d9c7fe58dd77d17958d0cfade2278391a5a19c
+size 1465

checkpoint-413/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-413/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

checkpoint-413/tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-413/trainer_state.json

@@ -0,0 +1,854 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 59.0,
+  "eval_steps": 500,
+  "global_step": 413,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.792788255214691,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 3.796875,
+      "learning_rate": 8e-05,
+      "loss": 11.6274,
+      "mean_token_accuracy": 0.06541444137692451,
+      "num_tokens": 476.0,
+      "step": 5
+    },
+    {
+      "entropy": 3.021514046192169,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 6.0625,
+      "learning_rate": 0.00018,
+      "loss": 11.1858,
+      "mean_token_accuracy": 0.05801193509250879,
+      "num_tokens": 932.0,
+      "step": 10
+    },
+    {
+      "entropy": 3.211867570877075,
+      "epoch": 2.142857142857143,
+      "grad_norm": 6.8125,
+      "learning_rate": 0.0001999530335191093,
+      "loss": 8.534,
+      "mean_token_accuracy": 0.2204773288220167,
+      "num_tokens": 1402.0,
+      "step": 15
+    },
+    {
+      "entropy": 3.1594600677490234,
+      "epoch": 2.857142857142857,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019976230779866525,
+      "loss": 6.8815,
+      "mean_token_accuracy": 0.4090729311108589,
+      "num_tokens": 1876.0,
+      "step": 20
+    },
+    {
+      "entropy": 3.0886474013328553,
+      "epoch": 3.571428571428571,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.000199425167134466,
+      "loss": 6.1235,
+      "mean_token_accuracy": 0.4721266597509384,
+      "num_tokens": 2340.0,
+      "step": 25
+    },
+    {
+      "entropy": 3.463414764404297,
+      "epoch": 4.285714285714286,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.00019894210632692745,
+      "loss": 5.7784,
+      "mean_token_accuracy": 0.510290502011776,
+      "num_tokens": 2801.0,
+      "step": 30
+    },
+    {
+      "entropy": 3.8815927505493164,
+      "epoch": 5.0,
+      "grad_norm": 3.0,
+      "learning_rate": 0.00019831383433439797,
+      "loss": 5.38,
+      "mean_token_accuracy": 0.5277783393859863,
+      "num_tokens": 3265.0,
+      "step": 35
+    },
+    {
+      "entropy": 4.158239090442658,
+      "epoch": 5.714285714285714,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00019754127323266428,
+      "loss": 5.1591,
+      "mean_token_accuracy": 0.5269556432962418,
+      "num_tokens": 3740.0,
+      "step": 40
+    },
+    {
+      "entropy": 4.185952496528626,
+      "epoch": 6.428571428571429,
+      "grad_norm": 3.625,
+      "learning_rate": 0.00019662555686167808,
+      "loss": 5.0174,
+      "mean_token_accuracy": 0.5208964943885803,
+      "num_tokens": 4202.0,
+      "step": 45
+    },
+    {
+      "entropy": 4.530175316333771,
+      "epoch": 7.142857142857143,
+      "grad_norm": 19.375,
+      "learning_rate": 0.00019556802916148962,
+      "loss": 4.6408,
+      "mean_token_accuracy": 0.5506966844201088,
+      "num_tokens": 4672.0,
+      "step": 50
+    },
+    {
+      "entropy": 4.300695955753326,
+      "epoch": 7.857142857142857,
+      "grad_norm": 11.8125,
+      "learning_rate": 0.00019437024219983028,
+      "loss": 4.6472,
+      "mean_token_accuracy": 0.5373089402914047,
+      "num_tokens": 5137.0,
+      "step": 55
+    },
+    {
+      "entropy": 3.987451708316803,
+      "epoch": 8.571428571428571,
+      "grad_norm": 61.25,
+      "learning_rate": 0.00019303395389423918,
+      "loss": 4.3489,
+      "mean_token_accuracy": 0.5535169959068298,
+      "num_tokens": 5610.0,
+      "step": 60
+    },
+    {
+      "entropy": 4.105983006954193,
+      "epoch": 9.285714285714286,
+      "grad_norm": 13.4375,
+      "learning_rate": 0.00019156112543207673,
+      "loss": 4.5453,
+      "mean_token_accuracy": 0.5401277467608452,
+      "num_tokens": 6061.0,
+      "step": 65
+    },
+    {
+      "entropy": 3.8240280985832213,
+      "epoch": 10.0,
+      "grad_norm": 30.0,
+      "learning_rate": 0.0001899539183922119,
+      "loss": 4.2579,
+      "mean_token_accuracy": 0.5578698441386223,
+      "num_tokens": 6530.0,
+      "step": 70
+    },
+    {
+      "entropy": 4.034175276756287,
+      "epoch": 10.714285714285714,
+      "grad_norm": 23.125,
+      "learning_rate": 0.00018821469157260685,
+      "loss": 4.2314,
+      "mean_token_accuracy": 0.5486329942941666,
+      "num_tokens": 6995.0,
+      "step": 75
+    },
+    {
+      "entropy": 3.841754984855652,
+      "epoch": 11.428571428571429,
+      "grad_norm": 14.875,
+      "learning_rate": 0.00018634599752845592,
+      "loss": 3.8716,
+      "mean_token_accuracy": 0.5841306641697883,
+      "num_tokens": 7471.0,
+      "step": 80
+    },
+    {
+      "entropy": 3.5902714014053343,
+      "epoch": 12.142857142857142,
+      "grad_norm": 32.25,
+      "learning_rate": 0.00018435057882595882,
+      "loss": 3.9024,
+      "mean_token_accuracy": 0.5768814936280251,
+      "num_tokens": 7933.0,
+      "step": 85
+    },
+    {
+      "entropy": 3.4303754687309267,
+      "epoch": 12.857142857142858,
+      "grad_norm": 4.90625,
+      "learning_rate": 0.0001822313640172265,
+      "loss": 3.9375,
+      "mean_token_accuracy": 0.5777893230319023,
+      "num_tokens": 8405.0,
+      "step": 90
+    },
+    {
+      "entropy": 3.499199378490448,
+      "epoch": 13.571428571428571,
+      "grad_norm": 5.90625,
+      "learning_rate": 0.00017999146334222695,
+      "loss": 3.828,
+      "mean_token_accuracy": 0.5822847858071327,
+      "num_tokens": 8868.0,
+      "step": 95
+    },
+    {
+      "entropy": 3.481586956977844,
+      "epoch": 14.285714285714286,
+      "grad_norm": 11.0,
+      "learning_rate": 0.00017763416416407952,
+      "loss": 3.8184,
+      "mean_token_accuracy": 0.5630636841058732,
+      "num_tokens": 9332.0,
+      "step": 100
+    },
+    {
+      "entropy": 3.500191032886505,
+      "epoch": 15.0,
+      "grad_norm": 9.5625,
+      "learning_rate": 0.00017516292614439585,
+      "loss": 3.7067,
+      "mean_token_accuracy": 0.5884620487689972,
+      "num_tokens": 9795.0,
+      "step": 105
+    },
+    {
+      "entropy": 3.3229552149772643,
+      "epoch": 15.714285714285714,
+      "grad_norm": 16.75,
+      "learning_rate": 0.0001725813761657495,
+      "loss": 3.6108,
+      "mean_token_accuracy": 0.5895725131034851,
+      "num_tokens": 10276.0,
+      "step": 110
+    },
+    {
+      "entropy": 3.4739368081092836,
+      "epoch": 16.428571428571427,
+      "grad_norm": 1.8203125,
+      "learning_rate": 0.00016989330300872576,
+      "loss": 3.7059,
+      "mean_token_accuracy": 0.5850941985845566,
+      "num_tokens": 10729.0,
+      "step": 115
+    },
+    {
+      "entropy": 3.3542731404304504,
+      "epoch": 17.142857142857142,
+      "grad_norm": 6.25,
+      "learning_rate": 0.0001671026517913634,
+      "loss": 3.5096,
+      "mean_token_accuracy": 0.5724321246147156,
+      "num_tokens": 11190.0,
+      "step": 120
+    },
+    {
+      "entropy": 3.404970145225525,
+      "epoch": 17.857142857142858,
+      "grad_norm": 7.875,
+      "learning_rate": 0.00016421351817915024,
+      "loss": 3.4129,
+      "mean_token_accuracy": 0.5794804036617279,
+      "num_tokens": 11671.0,
+      "step": 125
+    },
+    {
+      "entropy": 3.306301200389862,
+      "epoch": 18.571428571428573,
+      "grad_norm": 5.0625,
+      "learning_rate": 0.00016123014237406913,
+      "loss": 3.4746,
+      "mean_token_accuracy": 0.5921303346753121,
+      "num_tokens": 12129.0,
+      "step": 130
+    },
+    {
+      "entropy": 3.2350066781044005,
+      "epoch": 19.285714285714285,
+      "grad_norm": 11.5625,
+      "learning_rate": 0.00015815690289151658,
+      "loss": 3.4275,
+      "mean_token_accuracy": 0.5821803495287895,
+      "num_tokens": 12590.0,
+      "step": 135
+    },
+    {
+      "entropy": 3.1699514985084534,
+      "epoch": 20.0,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00015499831013422803,
+      "loss": 3.3178,
+      "mean_token_accuracy": 0.5850699409842491,
+      "num_tokens": 13060.0,
+      "step": 140
+    },
+    {
+      "entropy": 3.258501207828522,
+      "epoch": 20.714285714285715,
+      "grad_norm": 5.1875,
+      "learning_rate": 0.00015175899977263964,
+      "loss": 3.3249,
+      "mean_token_accuracy": 0.5848709657788277,
+      "num_tokens": 13539.0,
+      "step": 145
+    },
+    {
+      "entropy": 3.08921275138855,
+      "epoch": 21.428571428571427,
+      "grad_norm": 13.0,
+      "learning_rate": 0.0001484437259414027,
+      "loss": 3.3491,
+      "mean_token_accuracy": 0.5895937442779541,
+      "num_tokens": 14000.0,
+      "step": 150
+    },
+    {
+      "entropy": 3.2806772351264955,
+      "epoch": 22.142857142857142,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00014505735426203543,
+      "loss": 3.3437,
+      "mean_token_accuracy": 0.5769101306796074,
+      "num_tokens": 14462.0,
+      "step": 155
+    },
+    {
+      "entropy": 3.1934503316879272,
+      "epoch": 22.857142857142858,
+      "grad_norm": 1.9765625,
+      "learning_rate": 0.00014160485470195245,
+      "loss": 3.3165,
+      "mean_token_accuracy": 0.5840009838342667,
+      "num_tokens": 14934.0,
+      "step": 160
+    },
+    {
+      "entropy": 3.2089458227157595,
+      "epoch": 23.571428571428573,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00013809129428035227,
+      "loss": 3.2531,
+      "mean_token_accuracy": 0.5786520332098007,
+      "num_tokens": 15403.0,
+      "step": 165
+    },
+    {
+      "entropy": 3.1576090097427367,
+      "epoch": 24.285714285714285,
+      "grad_norm": 6.09375,
+      "learning_rate": 0.00013452182963166794,
+      "loss": 3.3004,
+      "mean_token_accuracy": 0.6059059157967568,
+      "num_tokens": 15862.0,
+      "step": 170
+    },
+    {
+      "entropy": 3.2066342711448668,
+      "epoch": 25.0,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.2804,
+      "mean_token_accuracy": 0.5795390039682389,
+      "num_tokens": 16325.0,
+      "step": 175
+    },
+    {
+      "entropy": 3.362099051475525,
+      "epoch": 25.714285714285715,
+      "grad_norm": 17.25,
+      "learning_rate": 0.00012723621673810275,
+      "loss": 3.2069,
+      "mean_token_accuracy": 0.5881811708211899,
+      "num_tokens": 16799.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.6156115889549256,
+      "epoch": 26.428571428571427,
+      "grad_norm": 27.625,
+      "learning_rate": 0.0001235307611348174,
+      "loss": 2.8529,
+      "mean_token_accuracy": 0.5825759828090668,
+      "num_tokens": 17267.0,
+      "step": 185
+    },
+    {
+      "entropy": 2.415853571891785,
+      "epoch": 27.142857142857142,
+      "grad_norm": 14.375,
+      "learning_rate": 0.00011979077089471287,
+      "loss": 2.7167,
+      "mean_token_accuracy": 0.582954004406929,
+      "num_tokens": 17731.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.675187420845032,
+      "epoch": 27.857142857142858,
+      "grad_norm": 3.96875,
+      "learning_rate": 0.0001160217349692051,
+      "loss": 2.5242,
+      "mean_token_accuracy": 0.5845647603273392,
+      "num_tokens": 18207.0,
+      "step": 195
+    },
+    {
+      "entropy": 2.1901154220104218,
+      "epoch": 28.571428571428573,
+      "grad_norm": 3.78125,
+      "learning_rate": 0.00011222918493825876,
+      "loss": 2.4576,
+      "mean_token_accuracy": 0.6518612474203109,
+      "num_tokens": 18665.0,
+      "step": 200
+    },
+    {
+      "entropy": 2.5898417711257933,
+      "epoch": 29.285714285714285,
+      "grad_norm": 3.703125,
+      "learning_rate": 0.00010841868689203071,
+      "loss": 2.4075,
+      "mean_token_accuracy": 0.6468133866786957,
+      "num_tokens": 19120.0,
+      "step": 205
+    },
+    {
+      "entropy": 2.553648865222931,
+      "epoch": 30.0,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.00010459583326186533,
+      "loss": 2.2898,
+      "mean_token_accuracy": 0.6661897540092468,
+      "num_tokens": 19590.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.7572616219520567,
+      "epoch": 30.714285714285715,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00010076623461263018,
+      "loss": 2.2313,
+      "mean_token_accuracy": 0.661624762415886,
+      "num_tokens": 20072.0,
+      "step": 215
+    },
+    {
+      "entropy": 2.5715539693832397,
+      "epoch": 31.428571428571427,
+      "grad_norm": 3.65625,
+      "learning_rate": 9.693551140843847e-05,
+      "loss": 2.2627,
+      "mean_token_accuracy": 0.6698364645242691,
+      "num_tokens": 20533.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.8709237337112428,
+      "epoch": 32.142857142857146,
+      "grad_norm": 2.625,
+      "learning_rate": 9.310928576384293e-05,
+      "loss": 2.2747,
+      "mean_token_accuracy": 0.6794737994670867,
+      "num_tokens": 20992.0,
+      "step": 225
+    },
+    {
+      "entropy": 2.866812515258789,
+      "epoch": 32.857142857142854,
+      "grad_norm": 2.9375,
+      "learning_rate": 8.929317319260726e-05,
+      "loss": 2.2043,
+      "mean_token_accuracy": 0.6827087312936783,
+      "num_tokens": 21468.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.8384140014648436,
+      "epoch": 33.57142857142857,
+      "grad_norm": 1.7578125,
+      "learning_rate": 8.549277436616551e-05,
+      "loss": 2.1872,
+      "mean_token_accuracy": 0.6919413447380066,
+      "num_tokens": 21935.0,
+      "step": 235
+    },
+    {
+      "entropy": 2.808937168121338,
+      "epoch": 34.285714285714285,
+      "grad_norm": 2.015625,
+      "learning_rate": 8.171366689386432e-05,
+      "loss": 2.1838,
+      "mean_token_accuracy": 0.6732392847537995,
+      "num_tokens": 22397.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.814043712615967,
+      "epoch": 35.0,
+      "grad_norm": 3.03125,
+      "learning_rate": 7.796139713705213e-05,
+      "loss": 2.2053,
+      "mean_token_accuracy": 0.6772474765777587,
+      "num_tokens": 22855.0,
+      "step": 245
+    },
+    {
+      "entropy": 2.8783643364906313,
+      "epoch": 35.714285714285715,
+      "grad_norm": 2.59375,
+      "learning_rate": 7.424147206902891e-05,
+      "loss": 2.1232,
+      "mean_token_accuracy": 0.6868797898292541,
+      "num_tokens": 23333.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.97629771232605,
+      "epoch": 36.42857142857143,
+      "grad_norm": 2.9375,
+      "learning_rate": 7.055935119280369e-05,
+      "loss": 2.1552,
+      "mean_token_accuracy": 0.6787474125623703,
+      "num_tokens": 23798.0,
+      "step": 255
+    },
+    {
+      "entropy": 2.854850912094116,
+      "epoch": 37.142857142857146,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.692043852852079e-05,
+      "loss": 2.1633,
+      "mean_token_accuracy": 0.6688450396060943,
+      "num_tokens": 24253.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.8933450102806093,
+      "epoch": 37.857142857142854,
+      "grad_norm": 2.296875,
+      "learning_rate": 6.333007468231521e-05,
+      "loss": 2.1136,
+      "mean_token_accuracy": 0.6864002913236618,
+      "num_tokens": 24731.0,
+      "step": 265
+    },
+    {
+      "entropy": 2.996083164215088,
+      "epoch": 38.57142857142857,
+      "grad_norm": 2.890625,
+      "learning_rate": 5.9793529008236625e-05,
+      "loss": 2.1131,
+      "mean_token_accuracy": 0.6867775231599808,
+      "num_tokens": 25197.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.940924847126007,
+      "epoch": 39.285714285714285,
+      "grad_norm": 1.9765625,
+      "learning_rate": 5.63159918747457e-05,
+      "loss": 2.1133,
+      "mean_token_accuracy": 0.6733382165431976,
+      "num_tokens": 25659.0,
+      "step": 275
+    },
+    {
+      "entropy": 2.88932341337204,
+      "epoch": 40.0,
+      "grad_norm": 2.515625,
+      "learning_rate": 5.29025670471325e-05,
+      "loss": 2.1294,
+      "mean_token_accuracy": 0.6762734591960907,
+      "num_tokens": 26120.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.940540242195129,
+      "epoch": 40.714285714285715,
+      "grad_norm": 2.265625,
+      "learning_rate": 4.955826419703735e-05,
+      "loss": 2.1154,
+      "mean_token_accuracy": 0.6798080980777741,
+      "num_tokens": 26593.0,
+      "step": 285
+    },
+    {
+      "entropy": 2.8611413836479187,
+      "epoch": 41.42857142857143,
+      "grad_norm": 2.296875,
+      "learning_rate": 4.628799155006669e-05,
+      "loss": 2.1303,
+      "mean_token_accuracy": 0.6833127319812775,
+      "num_tokens": 27051.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.788492774963379,
+      "epoch": 42.142857142857146,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.30965486822953e-05,
+      "loss": 2.0905,
+      "mean_token_accuracy": 0.6859421670436859,
+      "num_tokens": 27519.0,
+      "step": 295
+    },
+    {
+      "entropy": 2.825607216358185,
+      "epoch": 42.857142857142854,
+      "grad_norm": 2.90625,
+      "learning_rate": 3.9988619476226355e-05,
+      "loss": 2.1233,
+      "mean_token_accuracy": 0.6781422436237335,
+      "num_tokens": 27992.0,
+      "step": 300
+    },
+    {
+      "entropy": 2.8424060583114623,
+      "epoch": 43.57142857142857,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.69687652465482e-05,
+      "loss": 2.1294,
+      "mean_token_accuracy": 0.6826364696025848,
+      "num_tokens": 28450.0,
+      "step": 305
+    },
+    {
+      "entropy": 2.943496787548065,
+      "epoch": 44.285714285714285,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.4041418045775895e-05,
+      "loss": 2.0765,
+      "mean_token_accuracy": 0.6848883599042892,
+      "num_tokens": 28917.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.9284329414367676,
+      "epoch": 45.0,
+      "grad_norm": 3.484375,
+      "learning_rate": 3.121087415960304e-05,
+      "loss": 2.0799,
+      "mean_token_accuracy": 0.6815178602933883,
+      "num_tokens": 29385.0,
+      "step": 315
+    },
+    {
+      "entropy": 2.9191814422607423,
+      "epoch": 45.714285714285715,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.848128780150995e-05,
+      "loss": 2.0739,
+      "mean_token_accuracy": 0.6732985526323318,
+      "num_tokens": 29864.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.8771293640136717,
+      "epoch": 46.42857142857143,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.5856665015882685e-05,
+      "loss": 2.1473,
+      "mean_token_accuracy": 0.6779996395111084,
+      "num_tokens": 30316.0,
+      "step": 325
+    },
+    {
+      "entropy": 2.8732030630111693,
+      "epoch": 47.142857142857146,
+      "grad_norm": 3.09375,
+      "learning_rate": 2.334085779859041e-05,
+      "loss": 2.0682,
+      "mean_token_accuracy": 0.6850162357091903,
+      "num_tokens": 30786.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.854801392555237,
+      "epoch": 47.857142857142854,
+      "grad_norm": 2.390625,
+      "learning_rate": 2.0937558443650206e-05,
+      "loss": 2.0922,
+      "mean_token_accuracy": 0.6852636992931366,
+      "num_tokens": 31262.0,
+      "step": 335
+    },
+    {
+      "entropy": 2.86720290184021,
+      "epoch": 48.57142857142857,
+      "grad_norm": 2.375,
+      "learning_rate": 1.8650294124276556e-05,
+      "loss": 2.0703,
+      "mean_token_accuracy": 0.6739754348993301,
+      "num_tokens": 31730.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.895400083065033,
+      "epoch": 49.285714285714285,
+      "grad_norm": 2.125,
+      "learning_rate": 1.6482421716268215e-05,
+      "loss": 2.1473,
+      "mean_token_accuracy": 0.6959782302379608,
+      "num_tokens": 32181.0,
+      "step": 345
+    },
+    {
+      "entropy": 2.848699188232422,
+      "epoch": 50.0,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4437122871329955e-05,
+      "loss": 2.0674,
+      "mean_token_accuracy": 0.6875059276819229,
+      "num_tokens": 32650.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.8375518679618836,
+      "epoch": 50.714285714285715,
+      "grad_norm": 2.875,
+      "learning_rate": 1.2517399347560167e-05,
+      "loss": 2.0397,
+      "mean_token_accuracy": 0.6838070601224899,
+      "num_tokens": 33136.0,
+      "step": 355
+    },
+    {
+      "entropy": 2.9130619883537294,
+      "epoch": 51.42857142857143,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.0726068603956741e-05,
+      "loss": 2.1365,
+      "mean_token_accuracy": 0.6878471314907074,
+      "num_tokens": 33592.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.8615196347236633,
+      "epoch": 52.142857142857146,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.065759665407515e-06,
+      "loss": 2.0888,
+      "mean_token_accuracy": 0.6820801556110382,
+      "num_tokens": 34055.0,
+      "step": 365
+    },
+    {
+      "entropy": 2.919237267971039,
+      "epoch": 52.857142857142854,
+      "grad_norm": 2.234375,
+      "learning_rate": 7.538909264233751e-06,
+      "loss": 2.1245,
+      "mean_token_accuracy": 0.6777568966150284,
+      "num_tokens": 34522.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.8638850450515747,
+      "epoch": 53.57142857142857,
+      "grad_norm": 2.078125,
+      "learning_rate": 6.147758263949321e-06,
+      "loss": 2.0537,
+      "mean_token_accuracy": 0.6949527800083161,
+      "num_tokens": 34993.0,
+      "step": 375
+    },
+    {
+      "entropy": 2.867327034473419,
+      "epoch": 54.285714285714285,
+      "grad_norm": 1.9453125,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.0949,
+      "mean_token_accuracy": 0.6912687718868256,
+      "num_tokens": 35455.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.901234805583954,
+      "epoch": 55.0,
+      "grad_norm": 3.34375,
+      "learning_rate": 3.7805191357015657e-06,
+      "loss": 2.0993,
+      "mean_token_accuracy": 0.6810127884149552,
+      "num_tokens": 35915.0,
+      "step": 385
+    },
+    {
+      "entropy": 2.8476656675338745,
+      "epoch": 55.714285714285715,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.8079052575973765e-06,
+      "loss": 2.0817,
+      "mean_token_accuracy": 0.6901296317577362,
+      "num_tokens": 36393.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.946032130718231,
+      "epoch": 56.42857142857143,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.9779341811600794e-06,
+      "loss": 2.1254,
+      "mean_token_accuracy": 0.6843662798404694,
+      "num_tokens": 36849.0,
+      "step": 395
+    },
+    {
+      "entropy": 2.875570738315582,
+      "epoch": 57.142857142857146,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.2918240033960027e-06,
+      "loss": 2.0784,
+      "mean_token_accuracy": 0.6810542076826096,
+      "num_tokens": 37315.0,
+      "step": 400
+    },
+    {
+      "entropy": 2.842552292346954,
+      "epoch": 57.857142857142854,
+      "grad_norm": 2.296875,
+      "learning_rate": 7.505816856045012e-07,
+      "loss": 2.0681,
+      "mean_token_accuracy": 0.6921821653842926,
+      "num_tokens": 37794.0,
+      "step": 405
+    },
+    {
+      "entropy": 2.9718944311141966,
+      "epoch": 58.57142857142857,
+      "grad_norm": 2.390625,
+      "learning_rate": 3.5500157552337264e-07,
+      "loss": 2.1589,
+      "mean_token_accuracy": 0.6764526933431625,
+      "num_tokens": 38242.0,
+      "step": 410
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 60,
+  "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": 382135491499008.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-413/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b256380a2efd5dd6123f384ec228c1e2bd5abaee7aa77748dcaf9a93e538be
+size 6225

checkpoint-420/README.md

@@ -0,0 +1,209 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-420/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-420/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d032b8add463bc6b3db221921a224cfa497ac4de1df952366516d285765f361
+size 8746152

checkpoint-420/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

checkpoint-420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a863f8a1c1fb441a40f82e7985dc879ca24e1a9d02fd67813b9698d27edced4a
+size 9115403

checkpoint-420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd3dd848f872409d83f09d6966c53404e71ec3c09bca4b74174b3ec10ff3539
+size 14645

checkpoint-420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfca6679d6aae159a03c33c09391721a5d407754ba9bcc324c9a9bf875f750c8
+size 1465

checkpoint-420/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-420/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

checkpoint-420/tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-420/trainer_state.json

@@ -0,0 +1,874 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 60.0,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.792788255214691,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 3.796875,
+      "learning_rate": 8e-05,
+      "loss": 11.6274,
+      "mean_token_accuracy": 0.06541444137692451,
+      "num_tokens": 476.0,
+      "step": 5
+    },
+    {
+      "entropy": 3.021514046192169,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 6.0625,
+      "learning_rate": 0.00018,
+      "loss": 11.1858,
+      "mean_token_accuracy": 0.05801193509250879,
+      "num_tokens": 932.0,
+      "step": 10
+    },
+    {
+      "entropy": 3.211867570877075,
+      "epoch": 2.142857142857143,
+      "grad_norm": 6.8125,
+      "learning_rate": 0.0001999530335191093,
+      "loss": 8.534,
+      "mean_token_accuracy": 0.2204773288220167,
+      "num_tokens": 1402.0,
+      "step": 15
+    },
+    {
+      "entropy": 3.1594600677490234,
+      "epoch": 2.857142857142857,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019976230779866525,
+      "loss": 6.8815,
+      "mean_token_accuracy": 0.4090729311108589,
+      "num_tokens": 1876.0,
+      "step": 20
+    },
+    {
+      "entropy": 3.0886474013328553,
+      "epoch": 3.571428571428571,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.000199425167134466,
+      "loss": 6.1235,
+      "mean_token_accuracy": 0.4721266597509384,
+      "num_tokens": 2340.0,
+      "step": 25
+    },
+    {
+      "entropy": 3.463414764404297,
+      "epoch": 4.285714285714286,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.00019894210632692745,
+      "loss": 5.7784,
+      "mean_token_accuracy": 0.510290502011776,
+      "num_tokens": 2801.0,
+      "step": 30
+    },
+    {
+      "entropy": 3.8815927505493164,
+      "epoch": 5.0,
+      "grad_norm": 3.0,
+      "learning_rate": 0.00019831383433439797,
+      "loss": 5.38,
+      "mean_token_accuracy": 0.5277783393859863,
+      "num_tokens": 3265.0,
+      "step": 35
+    },
+    {
+      "entropy": 4.158239090442658,
+      "epoch": 5.714285714285714,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00019754127323266428,
+      "loss": 5.1591,
+      "mean_token_accuracy": 0.5269556432962418,
+      "num_tokens": 3740.0,
+      "step": 40
+    },
+    {
+      "entropy": 4.185952496528626,
+      "epoch": 6.428571428571429,
+      "grad_norm": 3.625,
+      "learning_rate": 0.00019662555686167808,
+      "loss": 5.0174,
+      "mean_token_accuracy": 0.5208964943885803,
+      "num_tokens": 4202.0,
+      "step": 45
+    },
+    {
+      "entropy": 4.530175316333771,
+      "epoch": 7.142857142857143,
+      "grad_norm": 19.375,
+      "learning_rate": 0.00019556802916148962,
+      "loss": 4.6408,
+      "mean_token_accuracy": 0.5506966844201088,
+      "num_tokens": 4672.0,
+      "step": 50
+    },
+    {
+      "entropy": 4.300695955753326,
+      "epoch": 7.857142857142857,
+      "grad_norm": 11.8125,
+      "learning_rate": 0.00019437024219983028,
+      "loss": 4.6472,
+      "mean_token_accuracy": 0.5373089402914047,
+      "num_tokens": 5137.0,
+      "step": 55
+    },
+    {
+      "entropy": 3.987451708316803,
+      "epoch": 8.571428571428571,
+      "grad_norm": 61.25,
+      "learning_rate": 0.00019303395389423918,
+      "loss": 4.3489,
+      "mean_token_accuracy": 0.5535169959068298,
+      "num_tokens": 5610.0,
+      "step": 60
+    },
+    {
+      "entropy": 4.105983006954193,
+      "epoch": 9.285714285714286,
+      "grad_norm": 13.4375,
+      "learning_rate": 0.00019156112543207673,
+      "loss": 4.5453,
+      "mean_token_accuracy": 0.5401277467608452,
+      "num_tokens": 6061.0,
+      "step": 65
+    },
+    {
+      "entropy": 3.8240280985832213,
+      "epoch": 10.0,
+      "grad_norm": 30.0,
+      "learning_rate": 0.0001899539183922119,
+      "loss": 4.2579,
+      "mean_token_accuracy": 0.5578698441386223,
+      "num_tokens": 6530.0,
+      "step": 70
+    },
+    {
+      "entropy": 4.034175276756287,
+      "epoch": 10.714285714285714,
+      "grad_norm": 23.125,
+      "learning_rate": 0.00018821469157260685,
+      "loss": 4.2314,
+      "mean_token_accuracy": 0.5486329942941666,
+      "num_tokens": 6995.0,
+      "step": 75
+    },
+    {
+      "entropy": 3.841754984855652,
+      "epoch": 11.428571428571429,
+      "grad_norm": 14.875,
+      "learning_rate": 0.00018634599752845592,
+      "loss": 3.8716,
+      "mean_token_accuracy": 0.5841306641697883,
+      "num_tokens": 7471.0,
+      "step": 80
+    },
+    {
+      "entropy": 3.5902714014053343,
+      "epoch": 12.142857142857142,
+      "grad_norm": 32.25,
+      "learning_rate": 0.00018435057882595882,
+      "loss": 3.9024,
+      "mean_token_accuracy": 0.5768814936280251,
+      "num_tokens": 7933.0,
+      "step": 85
+    },
+    {
+      "entropy": 3.4303754687309267,
+      "epoch": 12.857142857142858,
+      "grad_norm": 4.90625,
+      "learning_rate": 0.0001822313640172265,
+      "loss": 3.9375,
+      "mean_token_accuracy": 0.5777893230319023,
+      "num_tokens": 8405.0,
+      "step": 90
+    },
+    {
+      "entropy": 3.499199378490448,
+      "epoch": 13.571428571428571,
+      "grad_norm": 5.90625,
+      "learning_rate": 0.00017999146334222695,
+      "loss": 3.828,
+      "mean_token_accuracy": 0.5822847858071327,
+      "num_tokens": 8868.0,
+      "step": 95
+    },
+    {
+      "entropy": 3.481586956977844,
+      "epoch": 14.285714285714286,
+      "grad_norm": 11.0,
+      "learning_rate": 0.00017763416416407952,
+      "loss": 3.8184,
+      "mean_token_accuracy": 0.5630636841058732,
+      "num_tokens": 9332.0,
+      "step": 100
+    },
+    {
+      "entropy": 3.500191032886505,
+      "epoch": 15.0,
+      "grad_norm": 9.5625,
+      "learning_rate": 0.00017516292614439585,
+      "loss": 3.7067,
+      "mean_token_accuracy": 0.5884620487689972,
+      "num_tokens": 9795.0,
+      "step": 105
+    },
+    {
+      "entropy": 3.3229552149772643,
+      "epoch": 15.714285714285714,
+      "grad_norm": 16.75,
+      "learning_rate": 0.0001725813761657495,
+      "loss": 3.6108,
+      "mean_token_accuracy": 0.5895725131034851,
+      "num_tokens": 10276.0,
+      "step": 110
+    },
+    {
+      "entropy": 3.4739368081092836,
+      "epoch": 16.428571428571427,
+      "grad_norm": 1.8203125,
+      "learning_rate": 0.00016989330300872576,
+      "loss": 3.7059,
+      "mean_token_accuracy": 0.5850941985845566,
+      "num_tokens": 10729.0,
+      "step": 115
+    },
+    {
+      "entropy": 3.3542731404304504,
+      "epoch": 17.142857142857142,
+      "grad_norm": 6.25,
+      "learning_rate": 0.0001671026517913634,
+      "loss": 3.5096,
+      "mean_token_accuracy": 0.5724321246147156,
+      "num_tokens": 11190.0,
+      "step": 120
+    },
+    {
+      "entropy": 3.404970145225525,
+      "epoch": 17.857142857142858,
+      "grad_norm": 7.875,
+      "learning_rate": 0.00016421351817915024,
+      "loss": 3.4129,
+      "mean_token_accuracy": 0.5794804036617279,
+      "num_tokens": 11671.0,
+      "step": 125
+    },
+    {
+      "entropy": 3.306301200389862,
+      "epoch": 18.571428571428573,
+      "grad_norm": 5.0625,
+      "learning_rate": 0.00016123014237406913,
+      "loss": 3.4746,
+      "mean_token_accuracy": 0.5921303346753121,
+      "num_tokens": 12129.0,
+      "step": 130
+    },
+    {
+      "entropy": 3.2350066781044005,
+      "epoch": 19.285714285714285,
+      "grad_norm": 11.5625,
+      "learning_rate": 0.00015815690289151658,
+      "loss": 3.4275,
+      "mean_token_accuracy": 0.5821803495287895,
+      "num_tokens": 12590.0,
+      "step": 135
+    },
+    {
+      "entropy": 3.1699514985084534,
+      "epoch": 20.0,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00015499831013422803,
+      "loss": 3.3178,
+      "mean_token_accuracy": 0.5850699409842491,
+      "num_tokens": 13060.0,
+      "step": 140
+    },
+    {
+      "entropy": 3.258501207828522,
+      "epoch": 20.714285714285715,
+      "grad_norm": 5.1875,
+      "learning_rate": 0.00015175899977263964,
+      "loss": 3.3249,
+      "mean_token_accuracy": 0.5848709657788277,
+      "num_tokens": 13539.0,
+      "step": 145
+    },
+    {
+      "entropy": 3.08921275138855,
+      "epoch": 21.428571428571427,
+      "grad_norm": 13.0,
+      "learning_rate": 0.0001484437259414027,
+      "loss": 3.3491,
+      "mean_token_accuracy": 0.5895937442779541,
+      "num_tokens": 14000.0,
+      "step": 150
+    },
+    {
+      "entropy": 3.2806772351264955,
+      "epoch": 22.142857142857142,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00014505735426203543,
+      "loss": 3.3437,
+      "mean_token_accuracy": 0.5769101306796074,
+      "num_tokens": 14462.0,
+      "step": 155
+    },
+    {
+      "entropy": 3.1934503316879272,
+      "epoch": 22.857142857142858,
+      "grad_norm": 1.9765625,
+      "learning_rate": 0.00014160485470195245,
+      "loss": 3.3165,
+      "mean_token_accuracy": 0.5840009838342667,
+      "num_tokens": 14934.0,
+      "step": 160
+    },
+    {
+      "entropy": 3.2089458227157595,
+      "epoch": 23.571428571428573,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00013809129428035227,
+      "loss": 3.2531,
+      "mean_token_accuracy": 0.5786520332098007,
+      "num_tokens": 15403.0,
+      "step": 165
+    },
+    {
+      "entropy": 3.1576090097427367,
+      "epoch": 24.285714285714285,
+      "grad_norm": 6.09375,
+      "learning_rate": 0.00013452182963166794,
+      "loss": 3.3004,
+      "mean_token_accuracy": 0.6059059157967568,
+      "num_tokens": 15862.0,
+      "step": 170
+    },
+    {
+      "entropy": 3.2066342711448668,
+      "epoch": 25.0,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.2804,
+      "mean_token_accuracy": 0.5795390039682389,
+      "num_tokens": 16325.0,
+      "step": 175
+    },
+    {
+      "entropy": 3.362099051475525,
+      "epoch": 25.714285714285715,
+      "grad_norm": 17.25,
+      "learning_rate": 0.00012723621673810275,
+      "loss": 3.2069,
+      "mean_token_accuracy": 0.5881811708211899,
+      "num_tokens": 16799.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.6156115889549256,
+      "epoch": 26.428571428571427,
+      "grad_norm": 27.625,
+      "learning_rate": 0.0001235307611348174,
+      "loss": 2.8529,
+      "mean_token_accuracy": 0.5825759828090668,
+      "num_tokens": 17267.0,
+      "step": 185
+    },
+    {
+      "entropy": 2.415853571891785,
+      "epoch": 27.142857142857142,
+      "grad_norm": 14.375,
+      "learning_rate": 0.00011979077089471287,
+      "loss": 2.7167,
+      "mean_token_accuracy": 0.582954004406929,
+      "num_tokens": 17731.0,
+      "step": 190
+    },
+    {
+      "entropy": 2.675187420845032,
+      "epoch": 27.857142857142858,
+      "grad_norm": 3.96875,
+      "learning_rate": 0.0001160217349692051,
+      "loss": 2.5242,
+      "mean_token_accuracy": 0.5845647603273392,
+      "num_tokens": 18207.0,
+      "step": 195
+    },
+    {
+      "entropy": 2.1901154220104218,
+      "epoch": 28.571428571428573,
+      "grad_norm": 3.78125,
+      "learning_rate": 0.00011222918493825876,
+      "loss": 2.4576,
+      "mean_token_accuracy": 0.6518612474203109,
+      "num_tokens": 18665.0,
+      "step": 200
+    },
+    {
+      "entropy": 2.5898417711257933,
+      "epoch": 29.285714285714285,
+      "grad_norm": 3.703125,
+      "learning_rate": 0.00010841868689203071,
+      "loss": 2.4075,
+      "mean_token_accuracy": 0.6468133866786957,
+      "num_tokens": 19120.0,
+      "step": 205
+    },
+    {
+      "entropy": 2.553648865222931,
+      "epoch": 30.0,
+      "grad_norm": 4.5625,
+      "learning_rate": 0.00010459583326186533,
+      "loss": 2.2898,
+      "mean_token_accuracy": 0.6661897540092468,
+      "num_tokens": 19590.0,
+      "step": 210
+    },
+    {
+      "entropy": 2.7572616219520567,
+      "epoch": 30.714285714285715,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00010076623461263018,
+      "loss": 2.2313,
+      "mean_token_accuracy": 0.661624762415886,
+      "num_tokens": 20072.0,
+      "step": 215
+    },
+    {
+      "entropy": 2.5715539693832397,
+      "epoch": 31.428571428571427,
+      "grad_norm": 3.65625,
+      "learning_rate": 9.693551140843847e-05,
+      "loss": 2.2627,
+      "mean_token_accuracy": 0.6698364645242691,
+      "num_tokens": 20533.0,
+      "step": 220
+    },
+    {
+      "entropy": 2.8709237337112428,
+      "epoch": 32.142857142857146,
+      "grad_norm": 2.625,
+      "learning_rate": 9.310928576384293e-05,
+      "loss": 2.2747,
+      "mean_token_accuracy": 0.6794737994670867,
+      "num_tokens": 20992.0,
+      "step": 225
+    },
+    {
+      "entropy": 2.866812515258789,
+      "epoch": 32.857142857142854,
+      "grad_norm": 2.9375,
+      "learning_rate": 8.929317319260726e-05,
+      "loss": 2.2043,
+      "mean_token_accuracy": 0.6827087312936783,
+      "num_tokens": 21468.0,
+      "step": 230
+    },
+    {
+      "entropy": 2.8384140014648436,
+      "epoch": 33.57142857142857,
+      "grad_norm": 1.7578125,
+      "learning_rate": 8.549277436616551e-05,
+      "loss": 2.1872,
+      "mean_token_accuracy": 0.6919413447380066,
+      "num_tokens": 21935.0,
+      "step": 235
+    },
+    {
+      "entropy": 2.808937168121338,
+      "epoch": 34.285714285714285,
+      "grad_norm": 2.015625,
+      "learning_rate": 8.171366689386432e-05,
+      "loss": 2.1838,
+      "mean_token_accuracy": 0.6732392847537995,
+      "num_tokens": 22397.0,
+      "step": 240
+    },
+    {
+      "entropy": 2.814043712615967,
+      "epoch": 35.0,
+      "grad_norm": 3.03125,
+      "learning_rate": 7.796139713705213e-05,
+      "loss": 2.2053,
+      "mean_token_accuracy": 0.6772474765777587,
+      "num_tokens": 22855.0,
+      "step": 245
+    },
+    {
+      "entropy": 2.8783643364906313,
+      "epoch": 35.714285714285715,
+      "grad_norm": 2.59375,
+      "learning_rate": 7.424147206902891e-05,
+      "loss": 2.1232,
+      "mean_token_accuracy": 0.6868797898292541,
+      "num_tokens": 23333.0,
+      "step": 250
+    },
+    {
+      "entropy": 2.97629771232605,
+      "epoch": 36.42857142857143,
+      "grad_norm": 2.9375,
+      "learning_rate": 7.055935119280369e-05,
+      "loss": 2.1552,
+      "mean_token_accuracy": 0.6787474125623703,
+      "num_tokens": 23798.0,
+      "step": 255
+    },
+    {
+      "entropy": 2.854850912094116,
+      "epoch": 37.142857142857146,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.692043852852079e-05,
+      "loss": 2.1633,
+      "mean_token_accuracy": 0.6688450396060943,
+      "num_tokens": 24253.0,
+      "step": 260
+    },
+    {
+      "entropy": 2.8933450102806093,
+      "epoch": 37.857142857142854,
+      "grad_norm": 2.296875,
+      "learning_rate": 6.333007468231521e-05,
+      "loss": 2.1136,
+      "mean_token_accuracy": 0.6864002913236618,
+      "num_tokens": 24731.0,
+      "step": 265
+    },
+    {
+      "entropy": 2.996083164215088,
+      "epoch": 38.57142857142857,
+      "grad_norm": 2.890625,
+      "learning_rate": 5.9793529008236625e-05,
+      "loss": 2.1131,
+      "mean_token_accuracy": 0.6867775231599808,
+      "num_tokens": 25197.0,
+      "step": 270
+    },
+    {
+      "entropy": 2.940924847126007,
+      "epoch": 39.285714285714285,
+      "grad_norm": 1.9765625,
+      "learning_rate": 5.63159918747457e-05,
+      "loss": 2.1133,
+      "mean_token_accuracy": 0.6733382165431976,
+      "num_tokens": 25659.0,
+      "step": 275
+    },
+    {
+      "entropy": 2.88932341337204,
+      "epoch": 40.0,
+      "grad_norm": 2.515625,
+      "learning_rate": 5.29025670471325e-05,
+      "loss": 2.1294,
+      "mean_token_accuracy": 0.6762734591960907,
+      "num_tokens": 26120.0,
+      "step": 280
+    },
+    {
+      "entropy": 2.940540242195129,
+      "epoch": 40.714285714285715,
+      "grad_norm": 2.265625,
+      "learning_rate": 4.955826419703735e-05,
+      "loss": 2.1154,
+      "mean_token_accuracy": 0.6798080980777741,
+      "num_tokens": 26593.0,
+      "step": 285
+    },
+    {
+      "entropy": 2.8611413836479187,
+      "epoch": 41.42857142857143,
+      "grad_norm": 2.296875,
+      "learning_rate": 4.628799155006669e-05,
+      "loss": 2.1303,
+      "mean_token_accuracy": 0.6833127319812775,
+      "num_tokens": 27051.0,
+      "step": 290
+    },
+    {
+      "entropy": 2.788492774963379,
+      "epoch": 42.142857142857146,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.30965486822953e-05,
+      "loss": 2.0905,
+      "mean_token_accuracy": 0.6859421670436859,
+      "num_tokens": 27519.0,
+      "step": 295
+    },
+    {
+      "entropy": 2.825607216358185,
+      "epoch": 42.857142857142854,
+      "grad_norm": 2.90625,
+      "learning_rate": 3.9988619476226355e-05,
+      "loss": 2.1233,
+      "mean_token_accuracy": 0.6781422436237335,
+      "num_tokens": 27992.0,
+      "step": 300
+    },
+    {
+      "entropy": 2.8424060583114623,
+      "epoch": 43.57142857142857,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.69687652465482e-05,
+      "loss": 2.1294,
+      "mean_token_accuracy": 0.6826364696025848,
+      "num_tokens": 28450.0,
+      "step": 305
+    },
+    {
+      "entropy": 2.943496787548065,
+      "epoch": 44.285714285714285,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.4041418045775895e-05,
+      "loss": 2.0765,
+      "mean_token_accuracy": 0.6848883599042892,
+      "num_tokens": 28917.0,
+      "step": 310
+    },
+    {
+      "entropy": 2.9284329414367676,
+      "epoch": 45.0,
+      "grad_norm": 3.484375,
+      "learning_rate": 3.121087415960304e-05,
+      "loss": 2.0799,
+      "mean_token_accuracy": 0.6815178602933883,
+      "num_tokens": 29385.0,
+      "step": 315
+    },
+    {
+      "entropy": 2.9191814422607423,
+      "epoch": 45.714285714285715,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.848128780150995e-05,
+      "loss": 2.0739,
+      "mean_token_accuracy": 0.6732985526323318,
+      "num_tokens": 29864.0,
+      "step": 320
+    },
+    {
+      "entropy": 2.8771293640136717,
+      "epoch": 46.42857142857143,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.5856665015882685e-05,
+      "loss": 2.1473,
+      "mean_token_accuracy": 0.6779996395111084,
+      "num_tokens": 30316.0,
+      "step": 325
+    },
+    {
+      "entropy": 2.8732030630111693,
+      "epoch": 47.142857142857146,
+      "grad_norm": 3.09375,
+      "learning_rate": 2.334085779859041e-05,
+      "loss": 2.0682,
+      "mean_token_accuracy": 0.6850162357091903,
+      "num_tokens": 30786.0,
+      "step": 330
+    },
+    {
+      "entropy": 2.854801392555237,
+      "epoch": 47.857142857142854,
+      "grad_norm": 2.390625,
+      "learning_rate": 2.0937558443650206e-05,
+      "loss": 2.0922,
+      "mean_token_accuracy": 0.6852636992931366,
+      "num_tokens": 31262.0,
+      "step": 335
+    },
+    {
+      "entropy": 2.86720290184021,
+      "epoch": 48.57142857142857,
+      "grad_norm": 2.375,
+      "learning_rate": 1.8650294124276556e-05,
+      "loss": 2.0703,
+      "mean_token_accuracy": 0.6739754348993301,
+      "num_tokens": 31730.0,
+      "step": 340
+    },
+    {
+      "entropy": 2.895400083065033,
+      "epoch": 49.285714285714285,
+      "grad_norm": 2.125,
+      "learning_rate": 1.6482421716268215e-05,
+      "loss": 2.1473,
+      "mean_token_accuracy": 0.6959782302379608,
+      "num_tokens": 32181.0,
+      "step": 345
+    },
+    {
+      "entropy": 2.848699188232422,
+      "epoch": 50.0,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.4437122871329955e-05,
+      "loss": 2.0674,
+      "mean_token_accuracy": 0.6875059276819229,
+      "num_tokens": 32650.0,
+      "step": 350
+    },
+    {
+      "entropy": 2.8375518679618836,
+      "epoch": 50.714285714285715,
+      "grad_norm": 2.875,
+      "learning_rate": 1.2517399347560167e-05,
+      "loss": 2.0397,
+      "mean_token_accuracy": 0.6838070601224899,
+      "num_tokens": 33136.0,
+      "step": 355
+    },
+    {
+      "entropy": 2.9130619883537294,
+      "epoch": 51.42857142857143,
+      "grad_norm": 3.015625,
+      "learning_rate": 1.0726068603956741e-05,
+      "loss": 2.1365,
+      "mean_token_accuracy": 0.6878471314907074,
+      "num_tokens": 33592.0,
+      "step": 360
+    },
+    {
+      "entropy": 2.8615196347236633,
+      "epoch": 52.142857142857146,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.065759665407515e-06,
+      "loss": 2.0888,
+      "mean_token_accuracy": 0.6820801556110382,
+      "num_tokens": 34055.0,
+      "step": 365
+    },
+    {
+      "entropy": 2.919237267971039,
+      "epoch": 52.857142857142854,
+      "grad_norm": 2.234375,
+      "learning_rate": 7.538909264233751e-06,
+      "loss": 2.1245,
+      "mean_token_accuracy": 0.6777568966150284,
+      "num_tokens": 34522.0,
+      "step": 370
+    },
+    {
+      "entropy": 2.8638850450515747,
+      "epoch": 53.57142857142857,
+      "grad_norm": 2.078125,
+      "learning_rate": 6.147758263949321e-06,
+      "loss": 2.0537,
+      "mean_token_accuracy": 0.6949527800083161,
+      "num_tokens": 34993.0,
+      "step": 375
+    },
+    {
+      "entropy": 2.867327034473419,
+      "epoch": 54.285714285714285,
+      "grad_norm": 1.9453125,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.0949,
+      "mean_token_accuracy": 0.6912687718868256,
+      "num_tokens": 35455.0,
+      "step": 380
+    },
+    {
+      "entropy": 2.901234805583954,
+      "epoch": 55.0,
+      "grad_norm": 3.34375,
+      "learning_rate": 3.7805191357015657e-06,
+      "loss": 2.0993,
+      "mean_token_accuracy": 0.6810127884149552,
+      "num_tokens": 35915.0,
+      "step": 385
+    },
+    {
+      "entropy": 2.8476656675338745,
+      "epoch": 55.714285714285715,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.8079052575973765e-06,
+      "loss": 2.0817,
+      "mean_token_accuracy": 0.6901296317577362,
+      "num_tokens": 36393.0,
+      "step": 390
+    },
+    {
+      "entropy": 2.946032130718231,
+      "epoch": 56.42857142857143,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.9779341811600794e-06,
+      "loss": 2.1254,
+      "mean_token_accuracy": 0.6843662798404694,
+      "num_tokens": 36849.0,
+      "step": 395
+    },
+    {
+      "entropy": 2.875570738315582,
+      "epoch": 57.142857142857146,
+      "grad_norm": 2.984375,
+      "learning_rate": 1.2918240033960027e-06,
+      "loss": 2.0784,
+      "mean_token_accuracy": 0.6810542076826096,
+      "num_tokens": 37315.0,
+      "step": 400
+    },
+    {
+      "entropy": 2.842552292346954,
+      "epoch": 57.857142857142854,
+      "grad_norm": 2.296875,
+      "learning_rate": 7.505816856045012e-07,
+      "loss": 2.0681,
+      "mean_token_accuracy": 0.6921821653842926,
+      "num_tokens": 37794.0,
+      "step": 405
+    },
+    {
+      "entropy": 2.9718944311141966,
+      "epoch": 58.57142857142857,
+      "grad_norm": 2.390625,
+      "learning_rate": 3.5500157552337264e-07,
+      "loss": 2.1589,
+      "mean_token_accuracy": 0.6764526933431625,
+      "num_tokens": 38242.0,
+      "step": 410
+    },
+    {
+      "entropy": 2.825828289985657,
+      "epoch": 59.285714285714285,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.0566424151401411e-07,
+      "loss": 2.0296,
+      "mean_token_accuracy": 0.699629956483841,
+      "num_tokens": 38719.0,
+      "step": 415
+    },
+    {
+      "entropy": 2.88580926656723,
+      "epoch": 60.0,
+      "grad_norm": 2.65625,
+      "learning_rate": 2.935620497301894e-09,
+      "loss": 2.0999,
+      "mean_token_accuracy": 0.6771395444869995,
+      "num_tokens": 39180.0,
+      "step": 420
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 60,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 388609530476544.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b256380a2efd5dd6123f384ec228c1e2bd5abaee7aa77748dcaf9a93e538be
+size 6225

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}