Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-471/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+library_name: peft
+model_name: typescript-slm-7b-reasoning
+tags:
+- typescript
+- code-generation
+- react
+- nextjs
+- angular
+- nodejs
+- lora
+- sft
+- 7b
+- reasoning
+- transformers
+- trl
+license: mit
+pipeline_tag: text-generation
+language:
+- en
+---
+
+# TypeScript SLM 7B - Reasoning Variant
+
+7B TypeScript model with reasoning capabilities for TypeScript code generation, optimized for React, Next.js, Angular, and Node.js.
+
+## Model Details
+
+- **Base Model**: [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
+- **Model Size**: 7B parameters
+- **Training Method**: LoRA (Low-Rank Adaptation)
+- **Context Length**: 2048 tokens
+- **LoRA Rank**: 64
+- **Training Dataset**: 5,000 high-quality TypeScript samples
+
+## Reasoning Capabilities
+This variant includes chain-of-thought reasoning for better code understanding and generation.
+
+## Training Configuration
+
+- Batch Size: 2
+- Gradient Accumulation: 16
+- Effective Batch Size: 32
+- Learning Rate: 0.0001
+- Epochs: 3
+- Hardware: Google Colab A100 40GB
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+base_model = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+model = AutoModelForCausalLM.from_pretrained(
+    base_model,
+    device_map="auto",
+    torch_dtype="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(model, "sylvester-francis/typescript-slm-7b-reasoning")
+
+# Generate code
+prompt = "Write a React component with TypeScript:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Repository
+
+https://github.com/sylvester-francis/slm-typescript-model

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_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:fb28ae9992d2da9853a74b0b2a8b74066f27816d33b0ee83fa09accf7ace9169
+size 645975704

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-471/README.md

@@ -0,0 +1,209 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+- 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-471/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-471/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb28ae9992d2da9853a74b0b2a8b74066f27816d33b0ee83fa09accf7ace9169
+size 645975704

checkpoint-471/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-471/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086a50c3d7c25bef8076faf087a3b5752a7bd3ebb31d1f28ae271f4d31f7d957
+size 1292176635

checkpoint-471/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1f5aa402ed224bd21ac75e3b11f55687ab3108a7f59896ea21ca23e469b699
+size 14645

checkpoint-471/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43ec84ce17ac70535435458670af11900888cd9a53a55de5cc4f7045427326a
+size 1383

checkpoint-471/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e88cdd2b8f02a69e37eb0571770eaefbce9ec77b189187cfdbff43e7aac63
+size 1465

checkpoint-471/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<｜end▁of▁sentence｜>"
+}

checkpoint-471/tokenizer.json

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

checkpoint-471/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": 2048,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-471/trainer_state.json

@@ -0,0 +1,504 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.132301941141486,
+      "epoch": 0.064,
+      "grad_norm": 0.5353747010231018,
+      "learning_rate": 6e-05,
+      "loss": 1.906,
+      "mean_token_accuracy": 0.664031008630991,
+      "num_tokens": 322944.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.6638864956796169,
+      "epoch": 0.128,
+      "grad_norm": 2.618912935256958,
+      "learning_rate": 9.998101535124758e-05,
+      "loss": 1.6494,
+      "mean_token_accuracy": 0.6862719308584928,
+      "num_tokens": 545000.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.6117467258125544,
+      "epoch": 0.192,
+      "grad_norm": 0.3634222745895386,
+      "learning_rate": 9.976760358471686e-05,
+      "loss": 1.621,
+      "mean_token_accuracy": 0.6831253364682197,
+      "num_tokens": 672098.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.638535926118493,
+      "epoch": 0.256,
+      "grad_norm": 0.344290167093277,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 1.6359,
+      "mean_token_accuracy": 0.6802711755037307,
+      "num_tokens": 751980.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.478830385953188,
+      "epoch": 0.32,
+      "grad_norm": 0.2297399342060089,
+      "learning_rate": 9.86345329809282e-05,
+      "loss": 1.4647,
+      "mean_token_accuracy": 0.7069825578480959,
+      "num_tokens": 1072943.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.3794383138418198,
+      "epoch": 0.384,
+      "grad_norm": 0.32549116015434265,
+      "learning_rate": 9.772025009397537e-05,
+      "loss": 1.3838,
+      "mean_token_accuracy": 0.7154554862529039,
+      "num_tokens": 1293367.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.3911591000854968,
+      "epoch": 0.448,
+      "grad_norm": 0.5462145209312439,
+      "learning_rate": 9.657955440256395e-05,
+      "loss": 1.3962,
+      "mean_token_accuracy": 0.7130337696522474,
+      "num_tokens": 1421079.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.3676836647093296,
+      "epoch": 0.512,
+      "grad_norm": 0.49329081177711487,
+      "learning_rate": 9.521785803487889e-05,
+      "loss": 1.3622,
+      "mean_token_accuracy": 0.7188269149512052,
+      "num_tokens": 1528707.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.4105482891201973,
+      "epoch": 0.576,
+      "grad_norm": 0.2888951599597931,
+      "learning_rate": 9.364162167569907e-05,
+      "loss": 1.3927,
+      "mean_token_accuracy": 0.715605778619647,
+      "num_tokens": 1847533.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.305791912227869,
+      "epoch": 0.64,
+      "grad_norm": 0.37133723497390747,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 1.2926,
+      "mean_token_accuracy": 0.7268331546336413,
+      "num_tokens": 2059118.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.3148710001260042,
+      "epoch": 0.704,
+      "grad_norm": 0.5283713340759277,
+      "learning_rate": 8.987642575578545e-05,
+      "loss": 1.3115,
+      "mean_token_accuracy": 0.7234834432601929,
+      "num_tokens": 2178666.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.2872359901666641,
+      "epoch": 0.768,
+      "grad_norm": 0.31060078740119934,
+      "learning_rate": 8.770533048884482e-05,
+      "loss": 1.3189,
+      "mean_token_accuracy": 0.7234059758484364,
+      "num_tokens": 2312681.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.32672161757946,
+      "epoch": 0.832,
+      "grad_norm": 0.35454726219177246,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3119,
+      "mean_token_accuracy": 0.7258770205080509,
+      "num_tokens": 2614727.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.269866293296218,
+      "epoch": 0.896,
+      "grad_norm": 0.4277479648590088,
+      "learning_rate": 8.283760120238672e-05,
+      "loss": 1.2517,
+      "mean_token_accuracy": 0.7334814827889204,
+      "num_tokens": 2803243.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.2557352636009456,
+      "epoch": 0.96,
+      "grad_norm": 0.6087638735771179,
+      "learning_rate": 8.016406254043595e-05,
+      "loss": 1.2487,
+      "mean_token_accuracy": 0.7337574414908886,
+      "num_tokens": 2904223.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.2229601785137847,
+      "epoch": 1.0192,
+      "grad_norm": 0.44533705711364746,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 1.2122,
+      "mean_token_accuracy": 0.7438250542492479,
+      "num_tokens": 3032557.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.2207391697913408,
+      "epoch": 1.0832,
+      "grad_norm": 0.3342125117778778,
+      "learning_rate": 7.440100115804991e-05,
+      "loss": 1.1944,
+      "mean_token_accuracy": 0.7436507247388363,
+      "num_tokens": 3340465.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.152220581099391,
+      "epoch": 1.1472,
+      "grad_norm": 0.4164928197860718,
+      "learning_rate": 7.133882177482019e-05,
+      "loss": 1.1309,
+      "mean_token_accuracy": 0.7519198808819055,
+      "num_tokens": 3536780.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.097483652085066,
+      "epoch": 1.2112,
+      "grad_norm": 0.6432936191558838,
+      "learning_rate": 6.817539852819149e-05,
+      "loss": 1.0807,
+      "mean_token_accuracy": 0.7617782432585954,
+      "num_tokens": 3648002.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.101779579371214,
+      "epoch": 1.2752,
+      "grad_norm": 0.3559873700141907,
+      "learning_rate": 6.492574055008473e-05,
+      "loss": 1.1104,
+      "mean_token_accuracy": 0.7594126090407372,
+      "num_tokens": 3805977.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.2463787905871868,
+      "epoch": 1.3392,
+      "grad_norm": 0.3985288441181183,
+      "learning_rate": 6.16052661204734e-05,
+      "loss": 1.2003,
+      "mean_token_accuracy": 0.7433346386998891,
+      "num_tokens": 4104268.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.0747566115111113,
+      "epoch": 1.4032,
+      "grad_norm": 0.453317254781723,
+      "learning_rate": 5.8229729514036705e-05,
+      "loss": 1.065,
+      "mean_token_accuracy": 0.7647760558873415,
+      "num_tokens": 4287843.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.0693928685039282,
+      "epoch": 1.4672,
+      "grad_norm": 0.7264474034309387,
+      "learning_rate": 5.481514625265709e-05,
+      "loss": 1.0366,
+      "mean_token_accuracy": 0.7683495875447989,
+      "num_tokens": 4385796.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.0543854005634785,
+      "epoch": 1.5312000000000001,
+      "grad_norm": 0.3641473352909088,
+      "learning_rate": 5.1377717118408105e-05,
+      "loss": 1.0748,
+      "mean_token_accuracy": 0.7658001605421305,
+      "num_tokens": 4569560.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.1630858287215233,
+      "epoch": 1.5952,
+      "grad_norm": 0.3796912729740143,
+      "learning_rate": 4.7933751287559335e-05,
+      "loss": 1.1153,
+      "mean_token_accuracy": 0.7540735069662332,
+      "num_tokens": 4862452.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.0660202108323573,
+      "epoch": 1.6592,
+      "grad_norm": 0.4816920757293701,
+      "learning_rate": 4.449958895029604e-05,
+      "loss": 1.0595,
+      "mean_token_accuracy": 0.7640244543552399,
+      "num_tokens": 5039415.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.0577839758247136,
+      "epoch": 1.7231999999999998,
+      "grad_norm": 0.7822772264480591,
+      "learning_rate": 4.109152378329036e-05,
+      "loss": 1.0062,
+      "mean_token_accuracy": 0.776426025852561,
+      "num_tokens": 5131586.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.0857372380793096,
+      "epoch": 1.7872,
+      "grad_norm": 0.3258715271949768,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 1.1158,
+      "mean_token_accuracy": 0.7566418334841728,
+      "num_tokens": 5342733.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.1667305041104554,
+      "epoch": 1.8512,
+      "grad_norm": 0.42681819200515747,
+      "learning_rate": 3.4418163846202944e-05,
+      "loss": 1.1042,
+      "mean_token_accuracy": 0.757396611571312,
+      "num_tokens": 5617863.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.0168558854609728,
+      "epoch": 1.9152,
+      "grad_norm": 0.5727287530899048,
+      "learning_rate": 3.118453140260823e-05,
+      "loss": 1.011,
+      "mean_token_accuracy": 0.7758277267217636,
+      "num_tokens": 5778629.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.0282332608476281,
+      "epoch": 1.9792,
+      "grad_norm": 0.8733853101730347,
+      "learning_rate": 2.804017055763149e-05,
+      "loss": 0.9916,
+      "mean_token_accuracy": 0.779886880889535,
+      "num_tokens": 5856923.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.0680723073514733,
+      "epoch": 2.0384,
+      "grad_norm": 0.3376860022544861,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0635,
+      "mean_token_accuracy": 0.7676570141637648,
+      "num_tokens": 6065114.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.104596570879221,
+      "epoch": 2.1024,
+      "grad_norm": 0.39200761914253235,
+      "learning_rate": 2.207844407871929e-05,
+      "loss": 1.0555,
+      "mean_token_accuracy": 0.766394791379571,
+      "num_tokens": 6346728.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.9890212159603834,
+      "epoch": 2.1664,
+      "grad_norm": 0.5592104196548462,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 0.9469,
+      "mean_token_accuracy": 0.7860675264149904,
+      "num_tokens": 6511390.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.9454210236668587,
+      "epoch": 2.2304,
+      "grad_norm": 0.899586021900177,
+      "learning_rate": 1.6645993887429345e-05,
+      "loss": 0.8828,
+      "mean_token_accuracy": 0.7986020620912313,
+      "num_tokens": 6593692.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.9820889582857489,
+      "epoch": 2.2944,
+      "grad_norm": 0.4264833927154541,
+      "learning_rate": 1.4160874341577446e-05,
+      "loss": 1.0165,
+      "mean_token_accuracy": 0.7796833466738462,
+      "num_tokens": 6832431.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.0525997491553425,
+      "epoch": 2.3584,
+      "grad_norm": 0.44459110498428345,
+      "learning_rate": 1.1845796590009683e-05,
+      "loss": 1.0138,
+      "mean_token_accuracy": 0.7756964165717364,
+      "num_tokens": 7104046.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.035184795409441,
+      "epoch": 2.4224,
+      "grad_norm": 0.6024214029312134,
+      "learning_rate": 9.711744716951093e-06,
+      "loss": 0.9495,
+      "mean_token_accuracy": 0.7859720509499312,
+      "num_tokens": 7263723.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.9147607890889049,
+      "epoch": 2.4864,
+      "grad_norm": 0.9132835865020752,
+      "learning_rate": 7.768843913876756e-06,
+      "loss": 0.8301,
+      "mean_token_accuracy": 0.8119621507823467,
+      "num_tokens": 7338521.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.0235382271930575,
+      "epoch": 2.5504,
+      "grad_norm": 0.44815948605537415,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 1.0674,
+      "mean_token_accuracy": 0.7642808057367801,
+      "num_tokens": 7606163.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.9868468202650547,
+      "epoch": 2.6144,
+      "grad_norm": 0.4431731402873993,
+      "learning_rate": 4.492417883833155e-06,
+      "loss": 0.9819,
+      "mean_token_accuracy": 0.7802640642970801,
+      "num_tokens": 7862086.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.961590089276433,
+      "epoch": 2.6784,
+      "grad_norm": 0.604184627532959,
+      "learning_rate": 3.1744379401472677e-06,
+      "loss": 0.8934,
+      "mean_token_accuracy": 0.7974989850074052,
+      "num_tokens": 8011332.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.9186336389742792,
+      "epoch": 2.7424,
+      "grad_norm": 1.3265639543533325,
+      "learning_rate": 2.0786258770873647e-06,
+      "loss": 0.7948,
+      "mean_token_accuracy": 0.8204942990094424,
+      "num_tokens": 8077794.0,
+      "step": 430
+    },
+    {
+      "entropy": 1.0783039350062609,
+      "epoch": 2.8064,
+      "grad_norm": 0.42422202229499817,
+      "learning_rate": 1.210180868628219e-06,
+      "loss": 1.0754,
+      "mean_token_accuracy": 0.7629928629845381,
+      "num_tokens": 8372249.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.9569812569767236,
+      "epoch": 2.8704,
+      "grad_norm": 0.4604170024394989,
+      "learning_rate": 5.732233263245845e-07,
+      "loss": 0.9381,
+      "mean_token_accuracy": 0.7869165271520615,
+      "num_tokens": 8602659.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.9460787598043681,
+      "epoch": 2.9344,
+      "grad_norm": 0.6459949612617493,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.8793,
+      "mean_token_accuracy": 0.7999289013445378,
+      "num_tokens": 8739138.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.8972176358103752,
+      "epoch": 2.9984,
+      "grad_norm": 1.523201823234558,
+      "learning_rate": 4.746387470044855e-09,
+      "loss": 0.7761,
+      "mean_token_accuracy": 0.8227238561958075,
+      "num_tokens": 8798961.0,
+      "step": 470
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 471,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 3.822788172446208e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-471/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b124ed960a544ac444d3a42df9a57a8587eb07a5b54b6b7ebbf610d163a226
+size 6225

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<｜end▁of▁sentence｜>"
+}

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": 2048,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}