Add files using upload-large-folder tool

.gitattributes

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

README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/Qwen3-14B-Base
+library_name: peft
+model_name: qwentaur-14b-bf16
+tags:
+- base_model:adapter:unsloth/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for qwentaur-14b-bf16
+
+This model is a fine-tuned version of [unsloth/Qwen3-14B-Base](https://huggingface.co/unsloth/Qwen3-14B-Base).
+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
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nick-sh-oh/qwentaur/runs/591cqre5) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.24.0
+- Transformers: 4.57.6
+- Pytorch: 2.10.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## 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 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-14B-Base",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1000/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-14B-Base",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08df59f7677b62b4cdc4110950296b7fb586ce6f1f5ddf394a2fe68db8b7ebb0
+size 256976504

checkpoint-1000/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "!",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,750 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5325168075617387,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005325168075617386,
+      "grad_norm": 0.22119790315628052,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5996,
+      "step": 10
+    },
+    {
+      "epoch": 0.010650336151234773,
+      "grad_norm": 0.16633106768131256,
+      "learning_rate": 9.5e-06,
+      "loss": 0.6377,
+      "step": 20
+    },
+    {
+      "epoch": 0.01597550422685216,
+      "grad_norm": 0.15750865638256073,
+      "learning_rate": 1.45e-05,
+      "loss": 0.5448,
+      "step": 30
+    },
+    {
+      "epoch": 0.021300672302469546,
+      "grad_norm": 0.1806253343820572,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.5772,
+      "step": 40
+    },
+    {
+      "epoch": 0.026625840378086935,
+      "grad_norm": 0.18283385038375854,
+      "learning_rate": 2.45e-05,
+      "loss": 0.5577,
+      "step": 50
+    },
+    {
+      "epoch": 0.03195100845370432,
+      "grad_norm": 0.2903732359409332,
+      "learning_rate": 2.95e-05,
+      "loss": 0.5611,
+      "step": 60
+    },
+    {
+      "epoch": 0.037276176529321706,
+      "grad_norm": 0.21062836050987244,
+      "learning_rate": 3.45e-05,
+      "loss": 0.472,
+      "step": 70
+    },
+    {
+      "epoch": 0.04260134460493909,
+      "grad_norm": 0.2517930269241333,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.5674,
+      "step": 80
+    },
+    {
+      "epoch": 0.04792651268055648,
+      "grad_norm": 0.25084561109542847,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.4704,
+      "step": 90
+    },
+    {
+      "epoch": 0.05325168075617387,
+      "grad_norm": 0.22995634377002716,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5068,
+      "step": 100
+    },
+    {
+      "epoch": 0.058576848831791255,
+      "grad_norm": 0.3184715509414673,
+      "learning_rate": 4.9746906636670424e-05,
+      "loss": 0.4727,
+      "step": 110
+    },
+    {
+      "epoch": 0.06390201690740864,
+      "grad_norm": 0.21488015353679657,
+      "learning_rate": 4.9465691788526435e-05,
+      "loss": 0.4914,
+      "step": 120
+    },
+    {
+      "epoch": 0.06922718498302603,
+      "grad_norm": 0.4201931953430176,
+      "learning_rate": 4.9184476940382454e-05,
+      "loss": 0.4662,
+      "step": 130
+    },
+    {
+      "epoch": 0.07455235305864341,
+      "grad_norm": 0.24147631227970123,
+      "learning_rate": 4.890326209223847e-05,
+      "loss": 0.5425,
+      "step": 140
+    },
+    {
+      "epoch": 0.0798775211342608,
+      "grad_norm": 0.32419461011886597,
+      "learning_rate": 4.862204724409449e-05,
+      "loss": 0.5136,
+      "step": 150
+    },
+    {
+      "epoch": 0.08520268920987818,
+      "grad_norm": 0.20325051248073578,
+      "learning_rate": 4.834083239595051e-05,
+      "loss": 0.4848,
+      "step": 160
+    },
+    {
+      "epoch": 0.09052785728549557,
+      "grad_norm": 0.26200124621391296,
+      "learning_rate": 4.805961754780653e-05,
+      "loss": 0.4795,
+      "step": 170
+    },
+    {
+      "epoch": 0.09585302536111295,
+      "grad_norm": 0.2597779929637909,
+      "learning_rate": 4.7778402699662545e-05,
+      "loss": 0.4701,
+      "step": 180
+    },
+    {
+      "epoch": 0.10117819343673035,
+      "grad_norm": 0.2209395468235016,
+      "learning_rate": 4.749718785151856e-05,
+      "loss": 0.4643,
+      "step": 190
+    },
+    {
+      "epoch": 0.10650336151234774,
+      "grad_norm": 0.18556272983551025,
+      "learning_rate": 4.721597300337458e-05,
+      "loss": 0.4392,
+      "step": 200
+    },
+    {
+      "epoch": 0.11182852958796512,
+      "grad_norm": 0.2606329917907715,
+      "learning_rate": 4.6934758155230594e-05,
+      "loss": 0.5305,
+      "step": 210
+    },
+    {
+      "epoch": 0.11715369766358251,
+      "grad_norm": 0.32324516773223877,
+      "learning_rate": 4.665354330708662e-05,
+      "loss": 0.4361,
+      "step": 220
+    },
+    {
+      "epoch": 0.12247886573919989,
+      "grad_norm": 0.773040235042572,
+      "learning_rate": 4.637232845894263e-05,
+      "loss": 0.4514,
+      "step": 230
+    },
+    {
+      "epoch": 0.12780403381481728,
+      "grad_norm": 0.19772544503211975,
+      "learning_rate": 4.6091113610798655e-05,
+      "loss": 0.5154,
+      "step": 240
+    },
+    {
+      "epoch": 0.13312920189043467,
+      "grad_norm": 0.21351611614227295,
+      "learning_rate": 4.580989876265467e-05,
+      "loss": 0.442,
+      "step": 250
+    },
+    {
+      "epoch": 0.13845436996605207,
+      "grad_norm": 0.6194823980331421,
+      "learning_rate": 4.552868391451069e-05,
+      "loss": 0.4623,
+      "step": 260
+    },
+    {
+      "epoch": 0.14377953804166943,
+      "grad_norm": 0.2469085454940796,
+      "learning_rate": 4.5247469066366704e-05,
+      "loss": 0.5265,
+      "step": 270
+    },
+    {
+      "epoch": 0.14910470611728682,
+      "grad_norm": 0.183319553732872,
+      "learning_rate": 4.496625421822272e-05,
+      "loss": 0.4498,
+      "step": 280
+    },
+    {
+      "epoch": 0.15442987419290422,
+      "grad_norm": 0.20639532804489136,
+      "learning_rate": 4.468503937007874e-05,
+      "loss": 0.443,
+      "step": 290
+    },
+    {
+      "epoch": 0.1597550422685216,
+      "grad_norm": 0.3168950378894806,
+      "learning_rate": 4.440382452193476e-05,
+      "loss": 0.5142,
+      "step": 300
+    },
+    {
+      "epoch": 0.165080210344139,
+      "grad_norm": 0.42236635088920593,
+      "learning_rate": 4.412260967379078e-05,
+      "loss": 0.4964,
+      "step": 310
+    },
+    {
+      "epoch": 0.17040537841975636,
+      "grad_norm": 0.3603885769844055,
+      "learning_rate": 4.3841394825646795e-05,
+      "loss": 0.4694,
+      "step": 320
+    },
+    {
+      "epoch": 0.17573054649537376,
+      "grad_norm": 0.5331389904022217,
+      "learning_rate": 4.3560179977502814e-05,
+      "loss": 0.5557,
+      "step": 330
+    },
+    {
+      "epoch": 0.18105571457099115,
+      "grad_norm": 0.2247193604707718,
+      "learning_rate": 4.327896512935883e-05,
+      "loss": 0.485,
+      "step": 340
+    },
+    {
+      "epoch": 0.18638088264660854,
+      "grad_norm": 0.20757395029067993,
+      "learning_rate": 4.299775028121485e-05,
+      "loss": 0.4534,
+      "step": 350
+    },
+    {
+      "epoch": 0.1917060507222259,
+      "grad_norm": 0.3965719938278198,
+      "learning_rate": 4.271653543307087e-05,
+      "loss": 0.4526,
+      "step": 360
+    },
+    {
+      "epoch": 0.1970312187978433,
+      "grad_norm": 0.3099954426288605,
+      "learning_rate": 4.243532058492689e-05,
+      "loss": 0.5196,
+      "step": 370
+    },
+    {
+      "epoch": 0.2023563868734607,
+      "grad_norm": 0.32076820731163025,
+      "learning_rate": 4.2154105736782906e-05,
+      "loss": 0.3987,
+      "step": 380
+    },
+    {
+      "epoch": 0.20768155494907808,
+      "grad_norm": 0.19246822595596313,
+      "learning_rate": 4.1872890888638924e-05,
+      "loss": 0.3958,
+      "step": 390
+    },
+    {
+      "epoch": 0.21300672302469548,
+      "grad_norm": 0.2495279759168625,
+      "learning_rate": 4.159167604049494e-05,
+      "loss": 0.4522,
+      "step": 400
+    },
+    {
+      "epoch": 0.21833189110031284,
+      "grad_norm": 0.3605816662311554,
+      "learning_rate": 4.131046119235096e-05,
+      "loss": 0.5324,
+      "step": 410
+    },
+    {
+      "epoch": 0.22365705917593023,
+      "grad_norm": 0.55950927734375,
+      "learning_rate": 4.102924634420698e-05,
+      "loss": 0.4587,
+      "step": 420
+    },
+    {
+      "epoch": 0.22898222725154763,
+      "grad_norm": 0.21795208752155304,
+      "learning_rate": 4.074803149606299e-05,
+      "loss": 0.4327,
+      "step": 430
+    },
+    {
+      "epoch": 0.23430739532716502,
+      "grad_norm": 0.33580827713012695,
+      "learning_rate": 4.0466816647919016e-05,
+      "loss": 0.4362,
+      "step": 440
+    },
+    {
+      "epoch": 0.2396325634027824,
+      "grad_norm": 0.26251840591430664,
+      "learning_rate": 4.018560179977503e-05,
+      "loss": 0.4533,
+      "step": 450
+    },
+    {
+      "epoch": 0.24495773147839978,
+      "grad_norm": 0.29128602147102356,
+      "learning_rate": 3.9904386951631046e-05,
+      "loss": 0.4854,
+      "step": 460
+    },
+    {
+      "epoch": 0.25028289955401717,
+      "grad_norm": 0.18392464518547058,
+      "learning_rate": 3.9623172103487064e-05,
+      "loss": 0.4367,
+      "step": 470
+    },
+    {
+      "epoch": 0.25560806762963456,
+      "grad_norm": 0.16602832078933716,
+      "learning_rate": 3.934195725534308e-05,
+      "loss": 0.4285,
+      "step": 480
+    },
+    {
+      "epoch": 0.26093323570525195,
+      "grad_norm": 0.19768096506595612,
+      "learning_rate": 3.90607424071991e-05,
+      "loss": 0.4703,
+      "step": 490
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "grad_norm": 0.34657010436058044,
+      "learning_rate": 3.877952755905512e-05,
+      "loss": 0.4661,
+      "step": 500
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "eval_loss": 0.5697944760322571,
+      "eval_runtime": 5453.8439,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 1.203,
+      "step": 500
+    },
+    {
+      "epoch": 0.27158357185648674,
+      "grad_norm": 0.31953340768814087,
+      "learning_rate": 3.849831271091114e-05,
+      "loss": 0.4225,
+      "step": 510
+    },
+    {
+      "epoch": 0.27690873993210413,
+      "grad_norm": 0.3757156729698181,
+      "learning_rate": 3.8217097862767156e-05,
+      "loss": 0.4425,
+      "step": 520
+    },
+    {
+      "epoch": 0.28223390800772147,
+      "grad_norm": 0.3416071832180023,
+      "learning_rate": 3.7935883014623174e-05,
+      "loss": 0.5368,
+      "step": 530
+    },
+    {
+      "epoch": 0.28755907608333886,
+      "grad_norm": 0.37404417991638184,
+      "learning_rate": 3.765466816647919e-05,
+      "loss": 0.5324,
+      "step": 540
+    },
+    {
+      "epoch": 0.29288424415895625,
+      "grad_norm": 0.4058983027935028,
+      "learning_rate": 3.737345331833521e-05,
+      "loss": 0.4785,
+      "step": 550
+    },
+    {
+      "epoch": 0.29820941223457365,
+      "grad_norm": 1.0426571369171143,
+      "learning_rate": 3.709223847019123e-05,
+      "loss": 0.4853,
+      "step": 560
+    },
+    {
+      "epoch": 0.30353458031019104,
+      "grad_norm": 0.24327947199344635,
+      "learning_rate": 3.681102362204725e-05,
+      "loss": 0.3702,
+      "step": 570
+    },
+    {
+      "epoch": 0.30885974838580843,
+      "grad_norm": 0.45736777782440186,
+      "learning_rate": 3.652980877390326e-05,
+      "loss": 0.416,
+      "step": 580
+    },
+    {
+      "epoch": 0.3141849164614258,
+      "grad_norm": 0.35099077224731445,
+      "learning_rate": 3.6248593925759284e-05,
+      "loss": 0.4667,
+      "step": 590
+    },
+    {
+      "epoch": 0.3195100845370432,
+      "grad_norm": 0.2792291045188904,
+      "learning_rate": 3.5967379077615296e-05,
+      "loss": 0.4689,
+      "step": 600
+    },
+    {
+      "epoch": 0.3248352526126606,
+      "grad_norm": 0.38183653354644775,
+      "learning_rate": 3.568616422947132e-05,
+      "loss": 0.352,
+      "step": 610
+    },
+    {
+      "epoch": 0.330160420688278,
+      "grad_norm": 0.23597702383995056,
+      "learning_rate": 3.540494938132733e-05,
+      "loss": 0.4939,
+      "step": 620
+    },
+    {
+      "epoch": 0.33548558876389534,
+      "grad_norm": 0.2534731924533844,
+      "learning_rate": 3.512373453318336e-05,
+      "loss": 0.4943,
+      "step": 630
+    },
+    {
+      "epoch": 0.34081075683951273,
+      "grad_norm": 0.5729730725288391,
+      "learning_rate": 3.484251968503937e-05,
+      "loss": 0.4278,
+      "step": 640
+    },
+    {
+      "epoch": 0.3461359249151301,
+      "grad_norm": 0.2920810580253601,
+      "learning_rate": 3.4561304836895394e-05,
+      "loss": 0.4518,
+      "step": 650
+    },
+    {
+      "epoch": 0.3514610929907475,
+      "grad_norm": 0.5853344202041626,
+      "learning_rate": 3.4280089988751406e-05,
+      "loss": 0.4772,
+      "step": 660
+    },
+    {
+      "epoch": 0.3567862610663649,
+      "grad_norm": 0.3440340757369995,
+      "learning_rate": 3.399887514060743e-05,
+      "loss": 0.5105,
+      "step": 670
+    },
+    {
+      "epoch": 0.3621114291419823,
+      "grad_norm": 0.17302438616752625,
+      "learning_rate": 3.371766029246344e-05,
+      "loss": 0.3868,
+      "step": 680
+    },
+    {
+      "epoch": 0.3674365972175997,
+      "grad_norm": 0.21418416500091553,
+      "learning_rate": 3.343644544431946e-05,
+      "loss": 0.4887,
+      "step": 690
+    },
+    {
+      "epoch": 0.3727617652932171,
+      "grad_norm": 0.21750663220882416,
+      "learning_rate": 3.315523059617548e-05,
+      "loss": 0.454,
+      "step": 700
+    },
+    {
+      "epoch": 0.3780869333688345,
+      "grad_norm": 0.2412487417459488,
+      "learning_rate": 3.28740157480315e-05,
+      "loss": 0.4225,
+      "step": 710
+    },
+    {
+      "epoch": 0.3834121014444518,
+      "grad_norm": 0.21244391798973083,
+      "learning_rate": 3.2592800899887516e-05,
+      "loss": 0.4257,
+      "step": 720
+    },
+    {
+      "epoch": 0.3887372695200692,
+      "grad_norm": 0.21693073213100433,
+      "learning_rate": 3.2311586051743534e-05,
+      "loss": 0.3583,
+      "step": 730
+    },
+    {
+      "epoch": 0.3940624375956866,
+      "grad_norm": 0.21653209626674652,
+      "learning_rate": 3.203037120359955e-05,
+      "loss": 0.4635,
+      "step": 740
+    },
+    {
+      "epoch": 0.399387605671304,
+      "grad_norm": 0.2929733693599701,
+      "learning_rate": 3.1749156355455564e-05,
+      "loss": 0.4788,
+      "step": 750
+    },
+    {
+      "epoch": 0.4047127737469214,
+      "grad_norm": 0.34718650579452515,
+      "learning_rate": 3.146794150731159e-05,
+      "loss": 0.4767,
+      "step": 760
+    },
+    {
+      "epoch": 0.4100379418225388,
+      "grad_norm": 0.2642233371734619,
+      "learning_rate": 3.11867266591676e-05,
+      "loss": 0.5099,
+      "step": 770
+    },
+    {
+      "epoch": 0.41536310989815617,
+      "grad_norm": 0.2616298794746399,
+      "learning_rate": 3.0905511811023626e-05,
+      "loss": 0.4999,
+      "step": 780
+    },
+    {
+      "epoch": 0.42068827797377356,
+      "grad_norm": 0.34992748498916626,
+      "learning_rate": 3.062429696287964e-05,
+      "loss": 0.4332,
+      "step": 790
+    },
+    {
+      "epoch": 0.42601344604939095,
+      "grad_norm": 0.2279980331659317,
+      "learning_rate": 3.034308211473566e-05,
+      "loss": 0.3728,
+      "step": 800
+    },
+    {
+      "epoch": 0.43133861412500835,
+      "grad_norm": 0.22256392240524292,
+      "learning_rate": 3.0061867266591674e-05,
+      "loss": 0.3916,
+      "step": 810
+    },
+    {
+      "epoch": 0.4366637822006257,
+      "grad_norm": 0.41548892855644226,
+      "learning_rate": 2.9780652418447696e-05,
+      "loss": 0.3982,
+      "step": 820
+    },
+    {
+      "epoch": 0.4419889502762431,
+      "grad_norm": 0.2539462447166443,
+      "learning_rate": 2.949943757030371e-05,
+      "loss": 0.4004,
+      "step": 830
+    },
+    {
+      "epoch": 0.44731411835186047,
+      "grad_norm": 0.4111381471157074,
+      "learning_rate": 2.9218222722159733e-05,
+      "loss": 0.5092,
+      "step": 840
+    },
+    {
+      "epoch": 0.45263928642747786,
+      "grad_norm": 0.38108745217323303,
+      "learning_rate": 2.8937007874015748e-05,
+      "loss": 0.4486,
+      "step": 850
+    },
+    {
+      "epoch": 0.45796445450309525,
+      "grad_norm": 0.48172271251678467,
+      "learning_rate": 2.865579302587177e-05,
+      "loss": 0.3567,
+      "step": 860
+    },
+    {
+      "epoch": 0.46328962257871265,
+      "grad_norm": 0.41752544045448303,
+      "learning_rate": 2.8374578177727784e-05,
+      "loss": 0.4139,
+      "step": 870
+    },
+    {
+      "epoch": 0.46861479065433004,
+      "grad_norm": 0.5029560327529907,
+      "learning_rate": 2.8093363329583806e-05,
+      "loss": 0.4041,
+      "step": 880
+    },
+    {
+      "epoch": 0.47393995872994743,
+      "grad_norm": 0.2200966477394104,
+      "learning_rate": 2.781214848143982e-05,
+      "loss": 0.4504,
+      "step": 890
+    },
+    {
+      "epoch": 0.4792651268055648,
+      "grad_norm": 0.29369235038757324,
+      "learning_rate": 2.7530933633295843e-05,
+      "loss": 0.4431,
+      "step": 900
+    },
+    {
+      "epoch": 0.48459029488118216,
+      "grad_norm": 0.25833240151405334,
+      "learning_rate": 2.7249718785151858e-05,
+      "loss": 0.4545,
+      "step": 910
+    },
+    {
+      "epoch": 0.48991546295679955,
+      "grad_norm": 0.26288172602653503,
+      "learning_rate": 2.6968503937007876e-05,
+      "loss": 0.3826,
+      "step": 920
+    },
+    {
+      "epoch": 0.49524063103241694,
+      "grad_norm": 0.25969257950782776,
+      "learning_rate": 2.668728908886389e-05,
+      "loss": 0.4591,
+      "step": 930
+    },
+    {
+      "epoch": 0.5005657991080343,
+      "grad_norm": 0.18059171736240387,
+      "learning_rate": 2.6406074240719913e-05,
+      "loss": 0.3603,
+      "step": 940
+    },
+    {
+      "epoch": 0.5058909671836518,
+      "grad_norm": 0.2396785318851471,
+      "learning_rate": 2.6124859392575928e-05,
+      "loss": 0.4397,
+      "step": 950
+    },
+    {
+      "epoch": 0.5112161352592691,
+      "grad_norm": 0.22924205660820007,
+      "learning_rate": 2.584364454443195e-05,
+      "loss": 0.4193,
+      "step": 960
+    },
+    {
+      "epoch": 0.5165413033348865,
+      "grad_norm": 0.21614229679107666,
+      "learning_rate": 2.5562429696287964e-05,
+      "loss": 0.3669,
+      "step": 970
+    },
+    {
+      "epoch": 0.5218664714105039,
+      "grad_norm": 0.21129848062992096,
+      "learning_rate": 2.5281214848143986e-05,
+      "loss": 0.3862,
+      "step": 980
+    },
+    {
+      "epoch": 0.5271916394861212,
+      "grad_norm": 0.24497318267822266,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3859,
+      "step": 990
+    },
+    {
+      "epoch": 0.5325168075617387,
+      "grad_norm": 0.46682098507881165,
+      "learning_rate": 2.471878515185602e-05,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5325168075617387,
+      "eval_loss": 0.5570288300514221,
+      "eval_runtime": 5584.3711,
+      "eval_samples_per_second": 1.175,
+      "eval_steps_per_second": 1.175,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1878,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1632463843388273e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-14B-Base",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c814083d7da833c1fcfed7c5e62565eb97dabd6f6768263c0ae5bfbed67ec5a6
+size 256976504

checkpoint-1500/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d569a9c96ff4e89d32dfe8ca0b97952cc2edcd76f89c14caa7e57238c4b46c8a
+size 14645

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "!",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1108 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.798775211342608,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005325168075617386,
+      "grad_norm": 0.22119790315628052,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5996,
+      "step": 10
+    },
+    {
+      "epoch": 0.010650336151234773,
+      "grad_norm": 0.16633106768131256,
+      "learning_rate": 9.5e-06,
+      "loss": 0.6377,
+      "step": 20
+    },
+    {
+      "epoch": 0.01597550422685216,
+      "grad_norm": 0.15750865638256073,
+      "learning_rate": 1.45e-05,
+      "loss": 0.5448,
+      "step": 30
+    },
+    {
+      "epoch": 0.021300672302469546,
+      "grad_norm": 0.1806253343820572,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.5772,
+      "step": 40
+    },
+    {
+      "epoch": 0.026625840378086935,
+      "grad_norm": 0.18283385038375854,
+      "learning_rate": 2.45e-05,
+      "loss": 0.5577,
+      "step": 50
+    },
+    {
+      "epoch": 0.03195100845370432,
+      "grad_norm": 0.2903732359409332,
+      "learning_rate": 2.95e-05,
+      "loss": 0.5611,
+      "step": 60
+    },
+    {
+      "epoch": 0.037276176529321706,
+      "grad_norm": 0.21062836050987244,
+      "learning_rate": 3.45e-05,
+      "loss": 0.472,
+      "step": 70
+    },
+    {
+      "epoch": 0.04260134460493909,
+      "grad_norm": 0.2517930269241333,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.5674,
+      "step": 80
+    },
+    {
+      "epoch": 0.04792651268055648,
+      "grad_norm": 0.25084561109542847,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.4704,
+      "step": 90
+    },
+    {
+      "epoch": 0.05325168075617387,
+      "grad_norm": 0.22995634377002716,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5068,
+      "step": 100
+    },
+    {
+      "epoch": 0.058576848831791255,
+      "grad_norm": 0.3184715509414673,
+      "learning_rate": 4.9746906636670424e-05,
+      "loss": 0.4727,
+      "step": 110
+    },
+    {
+      "epoch": 0.06390201690740864,
+      "grad_norm": 0.21488015353679657,
+      "learning_rate": 4.9465691788526435e-05,
+      "loss": 0.4914,
+      "step": 120
+    },
+    {
+      "epoch": 0.06922718498302603,
+      "grad_norm": 0.4201931953430176,
+      "learning_rate": 4.9184476940382454e-05,
+      "loss": 0.4662,
+      "step": 130
+    },
+    {
+      "epoch": 0.07455235305864341,
+      "grad_norm": 0.24147631227970123,
+      "learning_rate": 4.890326209223847e-05,
+      "loss": 0.5425,
+      "step": 140
+    },
+    {
+      "epoch": 0.0798775211342608,
+      "grad_norm": 0.32419461011886597,
+      "learning_rate": 4.862204724409449e-05,
+      "loss": 0.5136,
+      "step": 150
+    },
+    {
+      "epoch": 0.08520268920987818,
+      "grad_norm": 0.20325051248073578,
+      "learning_rate": 4.834083239595051e-05,
+      "loss": 0.4848,
+      "step": 160
+    },
+    {
+      "epoch": 0.09052785728549557,
+      "grad_norm": 0.26200124621391296,
+      "learning_rate": 4.805961754780653e-05,
+      "loss": 0.4795,
+      "step": 170
+    },
+    {
+      "epoch": 0.09585302536111295,
+      "grad_norm": 0.2597779929637909,
+      "learning_rate": 4.7778402699662545e-05,
+      "loss": 0.4701,
+      "step": 180
+    },
+    {
+      "epoch": 0.10117819343673035,
+      "grad_norm": 0.2209395468235016,
+      "learning_rate": 4.749718785151856e-05,
+      "loss": 0.4643,
+      "step": 190
+    },
+    {
+      "epoch": 0.10650336151234774,
+      "grad_norm": 0.18556272983551025,
+      "learning_rate": 4.721597300337458e-05,
+      "loss": 0.4392,
+      "step": 200
+    },
+    {
+      "epoch": 0.11182852958796512,
+      "grad_norm": 0.2606329917907715,
+      "learning_rate": 4.6934758155230594e-05,
+      "loss": 0.5305,
+      "step": 210
+    },
+    {
+      "epoch": 0.11715369766358251,
+      "grad_norm": 0.32324516773223877,
+      "learning_rate": 4.665354330708662e-05,
+      "loss": 0.4361,
+      "step": 220
+    },
+    {
+      "epoch": 0.12247886573919989,
+      "grad_norm": 0.773040235042572,
+      "learning_rate": 4.637232845894263e-05,
+      "loss": 0.4514,
+      "step": 230
+    },
+    {
+      "epoch": 0.12780403381481728,
+      "grad_norm": 0.19772544503211975,
+      "learning_rate": 4.6091113610798655e-05,
+      "loss": 0.5154,
+      "step": 240
+    },
+    {
+      "epoch": 0.13312920189043467,
+      "grad_norm": 0.21351611614227295,
+      "learning_rate": 4.580989876265467e-05,
+      "loss": 0.442,
+      "step": 250
+    },
+    {
+      "epoch": 0.13845436996605207,
+      "grad_norm": 0.6194823980331421,
+      "learning_rate": 4.552868391451069e-05,
+      "loss": 0.4623,
+      "step": 260
+    },
+    {
+      "epoch": 0.14377953804166943,
+      "grad_norm": 0.2469085454940796,
+      "learning_rate": 4.5247469066366704e-05,
+      "loss": 0.5265,
+      "step": 270
+    },
+    {
+      "epoch": 0.14910470611728682,
+      "grad_norm": 0.183319553732872,
+      "learning_rate": 4.496625421822272e-05,
+      "loss": 0.4498,
+      "step": 280
+    },
+    {
+      "epoch": 0.15442987419290422,
+      "grad_norm": 0.20639532804489136,
+      "learning_rate": 4.468503937007874e-05,
+      "loss": 0.443,
+      "step": 290
+    },
+    {
+      "epoch": 0.1597550422685216,
+      "grad_norm": 0.3168950378894806,
+      "learning_rate": 4.440382452193476e-05,
+      "loss": 0.5142,
+      "step": 300
+    },
+    {
+      "epoch": 0.165080210344139,
+      "grad_norm": 0.42236635088920593,
+      "learning_rate": 4.412260967379078e-05,
+      "loss": 0.4964,
+      "step": 310
+    },
+    {
+      "epoch": 0.17040537841975636,
+      "grad_norm": 0.3603885769844055,
+      "learning_rate": 4.3841394825646795e-05,
+      "loss": 0.4694,
+      "step": 320
+    },
+    {
+      "epoch": 0.17573054649537376,
+      "grad_norm": 0.5331389904022217,
+      "learning_rate": 4.3560179977502814e-05,
+      "loss": 0.5557,
+      "step": 330
+    },
+    {
+      "epoch": 0.18105571457099115,
+      "grad_norm": 0.2247193604707718,
+      "learning_rate": 4.327896512935883e-05,
+      "loss": 0.485,
+      "step": 340
+    },
+    {
+      "epoch": 0.18638088264660854,
+      "grad_norm": 0.20757395029067993,
+      "learning_rate": 4.299775028121485e-05,
+      "loss": 0.4534,
+      "step": 350
+    },
+    {
+      "epoch": 0.1917060507222259,
+      "grad_norm": 0.3965719938278198,
+      "learning_rate": 4.271653543307087e-05,
+      "loss": 0.4526,
+      "step": 360
+    },
+    {
+      "epoch": 0.1970312187978433,
+      "grad_norm": 0.3099954426288605,
+      "learning_rate": 4.243532058492689e-05,
+      "loss": 0.5196,
+      "step": 370
+    },
+    {
+      "epoch": 0.2023563868734607,
+      "grad_norm": 0.32076820731163025,
+      "learning_rate": 4.2154105736782906e-05,
+      "loss": 0.3987,
+      "step": 380
+    },
+    {
+      "epoch": 0.20768155494907808,
+      "grad_norm": 0.19246822595596313,
+      "learning_rate": 4.1872890888638924e-05,
+      "loss": 0.3958,
+      "step": 390
+    },
+    {
+      "epoch": 0.21300672302469548,
+      "grad_norm": 0.2495279759168625,
+      "learning_rate": 4.159167604049494e-05,
+      "loss": 0.4522,
+      "step": 400
+    },
+    {
+      "epoch": 0.21833189110031284,
+      "grad_norm": 0.3605816662311554,
+      "learning_rate": 4.131046119235096e-05,
+      "loss": 0.5324,
+      "step": 410
+    },
+    {
+      "epoch": 0.22365705917593023,
+      "grad_norm": 0.55950927734375,
+      "learning_rate": 4.102924634420698e-05,
+      "loss": 0.4587,
+      "step": 420
+    },
+    {
+      "epoch": 0.22898222725154763,
+      "grad_norm": 0.21795208752155304,
+      "learning_rate": 4.074803149606299e-05,
+      "loss": 0.4327,
+      "step": 430
+    },
+    {
+      "epoch": 0.23430739532716502,
+      "grad_norm": 0.33580827713012695,
+      "learning_rate": 4.0466816647919016e-05,
+      "loss": 0.4362,
+      "step": 440
+    },
+    {
+      "epoch": 0.2396325634027824,
+      "grad_norm": 0.26251840591430664,
+      "learning_rate": 4.018560179977503e-05,
+      "loss": 0.4533,
+      "step": 450
+    },
+    {
+      "epoch": 0.24495773147839978,
+      "grad_norm": 0.29128602147102356,
+      "learning_rate": 3.9904386951631046e-05,
+      "loss": 0.4854,
+      "step": 460
+    },
+    {
+      "epoch": 0.25028289955401717,
+      "grad_norm": 0.18392464518547058,
+      "learning_rate": 3.9623172103487064e-05,
+      "loss": 0.4367,
+      "step": 470
+    },
+    {
+      "epoch": 0.25560806762963456,
+      "grad_norm": 0.16602832078933716,
+      "learning_rate": 3.934195725534308e-05,
+      "loss": 0.4285,
+      "step": 480
+    },
+    {
+      "epoch": 0.26093323570525195,
+      "grad_norm": 0.19768096506595612,
+      "learning_rate": 3.90607424071991e-05,
+      "loss": 0.4703,
+      "step": 490
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "grad_norm": 0.34657010436058044,
+      "learning_rate": 3.877952755905512e-05,
+      "loss": 0.4661,
+      "step": 500
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "eval_loss": 0.5697944760322571,
+      "eval_runtime": 5453.8439,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 1.203,
+      "step": 500
+    },
+    {
+      "epoch": 0.27158357185648674,
+      "grad_norm": 0.31953340768814087,
+      "learning_rate": 3.849831271091114e-05,
+      "loss": 0.4225,
+      "step": 510
+    },
+    {
+      "epoch": 0.27690873993210413,
+      "grad_norm": 0.3757156729698181,
+      "learning_rate": 3.8217097862767156e-05,
+      "loss": 0.4425,
+      "step": 520
+    },
+    {
+      "epoch": 0.28223390800772147,
+      "grad_norm": 0.3416071832180023,
+      "learning_rate": 3.7935883014623174e-05,
+      "loss": 0.5368,
+      "step": 530
+    },
+    {
+      "epoch": 0.28755907608333886,
+      "grad_norm": 0.37404417991638184,
+      "learning_rate": 3.765466816647919e-05,
+      "loss": 0.5324,
+      "step": 540
+    },
+    {
+      "epoch": 0.29288424415895625,
+      "grad_norm": 0.4058983027935028,
+      "learning_rate": 3.737345331833521e-05,
+      "loss": 0.4785,
+      "step": 550
+    },
+    {
+      "epoch": 0.29820941223457365,
+      "grad_norm": 1.0426571369171143,
+      "learning_rate": 3.709223847019123e-05,
+      "loss": 0.4853,
+      "step": 560
+    },
+    {
+      "epoch": 0.30353458031019104,
+      "grad_norm": 0.24327947199344635,
+      "learning_rate": 3.681102362204725e-05,
+      "loss": 0.3702,
+      "step": 570
+    },
+    {
+      "epoch": 0.30885974838580843,
+      "grad_norm": 0.45736777782440186,
+      "learning_rate": 3.652980877390326e-05,
+      "loss": 0.416,
+      "step": 580
+    },
+    {
+      "epoch": 0.3141849164614258,
+      "grad_norm": 0.35099077224731445,
+      "learning_rate": 3.6248593925759284e-05,
+      "loss": 0.4667,
+      "step": 590
+    },
+    {
+      "epoch": 0.3195100845370432,
+      "grad_norm": 0.2792291045188904,
+      "learning_rate": 3.5967379077615296e-05,
+      "loss": 0.4689,
+      "step": 600
+    },
+    {
+      "epoch": 0.3248352526126606,
+      "grad_norm": 0.38183653354644775,
+      "learning_rate": 3.568616422947132e-05,
+      "loss": 0.352,
+      "step": 610
+    },
+    {
+      "epoch": 0.330160420688278,
+      "grad_norm": 0.23597702383995056,
+      "learning_rate": 3.540494938132733e-05,
+      "loss": 0.4939,
+      "step": 620
+    },
+    {
+      "epoch": 0.33548558876389534,
+      "grad_norm": 0.2534731924533844,
+      "learning_rate": 3.512373453318336e-05,
+      "loss": 0.4943,
+      "step": 630
+    },
+    {
+      "epoch": 0.34081075683951273,
+      "grad_norm": 0.5729730725288391,
+      "learning_rate": 3.484251968503937e-05,
+      "loss": 0.4278,
+      "step": 640
+    },
+    {
+      "epoch": 0.3461359249151301,
+      "grad_norm": 0.2920810580253601,
+      "learning_rate": 3.4561304836895394e-05,
+      "loss": 0.4518,
+      "step": 650
+    },
+    {
+      "epoch": 0.3514610929907475,
+      "grad_norm": 0.5853344202041626,
+      "learning_rate": 3.4280089988751406e-05,
+      "loss": 0.4772,
+      "step": 660
+    },
+    {
+      "epoch": 0.3567862610663649,
+      "grad_norm": 0.3440340757369995,
+      "learning_rate": 3.399887514060743e-05,
+      "loss": 0.5105,
+      "step": 670
+    },
+    {
+      "epoch": 0.3621114291419823,
+      "grad_norm": 0.17302438616752625,
+      "learning_rate": 3.371766029246344e-05,
+      "loss": 0.3868,
+      "step": 680
+    },
+    {
+      "epoch": 0.3674365972175997,
+      "grad_norm": 0.21418416500091553,
+      "learning_rate": 3.343644544431946e-05,
+      "loss": 0.4887,
+      "step": 690
+    },
+    {
+      "epoch": 0.3727617652932171,
+      "grad_norm": 0.21750663220882416,
+      "learning_rate": 3.315523059617548e-05,
+      "loss": 0.454,
+      "step": 700
+    },
+    {
+      "epoch": 0.3780869333688345,
+      "grad_norm": 0.2412487417459488,
+      "learning_rate": 3.28740157480315e-05,
+      "loss": 0.4225,
+      "step": 710
+    },
+    {
+      "epoch": 0.3834121014444518,
+      "grad_norm": 0.21244391798973083,
+      "learning_rate": 3.2592800899887516e-05,
+      "loss": 0.4257,
+      "step": 720
+    },
+    {
+      "epoch": 0.3887372695200692,
+      "grad_norm": 0.21693073213100433,
+      "learning_rate": 3.2311586051743534e-05,
+      "loss": 0.3583,
+      "step": 730
+    },
+    {
+      "epoch": 0.3940624375956866,
+      "grad_norm": 0.21653209626674652,
+      "learning_rate": 3.203037120359955e-05,
+      "loss": 0.4635,
+      "step": 740
+    },
+    {
+      "epoch": 0.399387605671304,
+      "grad_norm": 0.2929733693599701,
+      "learning_rate": 3.1749156355455564e-05,
+      "loss": 0.4788,
+      "step": 750
+    },
+    {
+      "epoch": 0.4047127737469214,
+      "grad_norm": 0.34718650579452515,
+      "learning_rate": 3.146794150731159e-05,
+      "loss": 0.4767,
+      "step": 760
+    },
+    {
+      "epoch": 0.4100379418225388,
+      "grad_norm": 0.2642233371734619,
+      "learning_rate": 3.11867266591676e-05,
+      "loss": 0.5099,
+      "step": 770
+    },
+    {
+      "epoch": 0.41536310989815617,
+      "grad_norm": 0.2616298794746399,
+      "learning_rate": 3.0905511811023626e-05,
+      "loss": 0.4999,
+      "step": 780
+    },
+    {
+      "epoch": 0.42068827797377356,
+      "grad_norm": 0.34992748498916626,
+      "learning_rate": 3.062429696287964e-05,
+      "loss": 0.4332,
+      "step": 790
+    },
+    {
+      "epoch": 0.42601344604939095,
+      "grad_norm": 0.2279980331659317,
+      "learning_rate": 3.034308211473566e-05,
+      "loss": 0.3728,
+      "step": 800
+    },
+    {
+      "epoch": 0.43133861412500835,
+      "grad_norm": 0.22256392240524292,
+      "learning_rate": 3.0061867266591674e-05,
+      "loss": 0.3916,
+      "step": 810
+    },
+    {
+      "epoch": 0.4366637822006257,
+      "grad_norm": 0.41548892855644226,
+      "learning_rate": 2.9780652418447696e-05,
+      "loss": 0.3982,
+      "step": 820
+    },
+    {
+      "epoch": 0.4419889502762431,
+      "grad_norm": 0.2539462447166443,
+      "learning_rate": 2.949943757030371e-05,
+      "loss": 0.4004,
+      "step": 830
+    },
+    {
+      "epoch": 0.44731411835186047,
+      "grad_norm": 0.4111381471157074,
+      "learning_rate": 2.9218222722159733e-05,
+      "loss": 0.5092,
+      "step": 840
+    },
+    {
+      "epoch": 0.45263928642747786,
+      "grad_norm": 0.38108745217323303,
+      "learning_rate": 2.8937007874015748e-05,
+      "loss": 0.4486,
+      "step": 850
+    },
+    {
+      "epoch": 0.45796445450309525,
+      "grad_norm": 0.48172271251678467,
+      "learning_rate": 2.865579302587177e-05,
+      "loss": 0.3567,
+      "step": 860
+    },
+    {
+      "epoch": 0.46328962257871265,
+      "grad_norm": 0.41752544045448303,
+      "learning_rate": 2.8374578177727784e-05,
+      "loss": 0.4139,
+      "step": 870
+    },
+    {
+      "epoch": 0.46861479065433004,
+      "grad_norm": 0.5029560327529907,
+      "learning_rate": 2.8093363329583806e-05,
+      "loss": 0.4041,
+      "step": 880
+    },
+    {
+      "epoch": 0.47393995872994743,
+      "grad_norm": 0.2200966477394104,
+      "learning_rate": 2.781214848143982e-05,
+      "loss": 0.4504,
+      "step": 890
+    },
+    {
+      "epoch": 0.4792651268055648,
+      "grad_norm": 0.29369235038757324,
+      "learning_rate": 2.7530933633295843e-05,
+      "loss": 0.4431,
+      "step": 900
+    },
+    {
+      "epoch": 0.48459029488118216,
+      "grad_norm": 0.25833240151405334,
+      "learning_rate": 2.7249718785151858e-05,
+      "loss": 0.4545,
+      "step": 910
+    },
+    {
+      "epoch": 0.48991546295679955,
+      "grad_norm": 0.26288172602653503,
+      "learning_rate": 2.6968503937007876e-05,
+      "loss": 0.3826,
+      "step": 920
+    },
+    {
+      "epoch": 0.49524063103241694,
+      "grad_norm": 0.25969257950782776,
+      "learning_rate": 2.668728908886389e-05,
+      "loss": 0.4591,
+      "step": 930
+    },
+    {
+      "epoch": 0.5005657991080343,
+      "grad_norm": 0.18059171736240387,
+      "learning_rate": 2.6406074240719913e-05,
+      "loss": 0.3603,
+      "step": 940
+    },
+    {
+      "epoch": 0.5058909671836518,
+      "grad_norm": 0.2396785318851471,
+      "learning_rate": 2.6124859392575928e-05,
+      "loss": 0.4397,
+      "step": 950
+    },
+    {
+      "epoch": 0.5112161352592691,
+      "grad_norm": 0.22924205660820007,
+      "learning_rate": 2.584364454443195e-05,
+      "loss": 0.4193,
+      "step": 960
+    },
+    {
+      "epoch": 0.5165413033348865,
+      "grad_norm": 0.21614229679107666,
+      "learning_rate": 2.5562429696287964e-05,
+      "loss": 0.3669,
+      "step": 970
+    },
+    {
+      "epoch": 0.5218664714105039,
+      "grad_norm": 0.21129848062992096,
+      "learning_rate": 2.5281214848143986e-05,
+      "loss": 0.3862,
+      "step": 980
+    },
+    {
+      "epoch": 0.5271916394861212,
+      "grad_norm": 0.24497318267822266,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3859,
+      "step": 990
+    },
+    {
+      "epoch": 0.5325168075617387,
+      "grad_norm": 0.46682098507881165,
+      "learning_rate": 2.471878515185602e-05,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5325168075617387,
+      "eval_loss": 0.5570288300514221,
+      "eval_runtime": 5584.3711,
+      "eval_samples_per_second": 1.175,
+      "eval_steps_per_second": 1.175,
+      "step": 1000
+    },
+    {
+      "epoch": 0.537841975637356,
+      "grad_norm": 0.3136838972568512,
+      "learning_rate": 2.4437570303712038e-05,
+      "loss": 0.3728,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5431671437129735,
+      "grad_norm": 0.27630332112312317,
+      "learning_rate": 2.4156355455568056e-05,
+      "loss": 0.3588,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5484923117885908,
+      "grad_norm": 0.18581336736679077,
+      "learning_rate": 2.3875140607424075e-05,
+      "loss": 0.3999,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5538174798642083,
+      "grad_norm": 0.7955025434494019,
+      "learning_rate": 2.3593925759280093e-05,
+      "loss": 0.405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5591426479398256,
+      "grad_norm": 0.2039509415626526,
+      "learning_rate": 2.331271091113611e-05,
+      "loss": 0.4214,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5644678160154429,
+      "grad_norm": 0.28698962926864624,
+      "learning_rate": 2.3031496062992126e-05,
+      "loss": 0.3916,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5697929840910604,
+      "grad_norm": 0.5037312507629395,
+      "learning_rate": 2.2750281214848145e-05,
+      "loss": 0.4866,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5751181521666777,
+      "grad_norm": 0.32183122634887695,
+      "learning_rate": 2.2469066366704163e-05,
+      "loss": 0.4274,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5804433202422952,
+      "grad_norm": 0.228108212351799,
+      "learning_rate": 2.218785151856018e-05,
+      "loss": 0.4369,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5857684883179125,
+      "grad_norm": 0.420781672000885,
+      "learning_rate": 2.19066366704162e-05,
+      "loss": 0.3923,
+      "step": 1100
+    },
+    {
+      "epoch": 0.59109365639353,
+      "grad_norm": 0.241056889295578,
+      "learning_rate": 2.1625421822272218e-05,
+      "loss": 0.4149,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5964188244691473,
+      "grad_norm": 0.1952434480190277,
+      "learning_rate": 2.1344206974128236e-05,
+      "loss": 0.386,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6017439925447647,
+      "grad_norm": 0.24534425139427185,
+      "learning_rate": 2.106299212598425e-05,
+      "loss": 0.4176,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6070691606203821,
+      "grad_norm": 0.2993834912776947,
+      "learning_rate": 2.078177727784027e-05,
+      "loss": 0.4151,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6123943286959994,
+      "grad_norm": 0.30427229404449463,
+      "learning_rate": 2.0500562429696288e-05,
+      "loss": 0.4105,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6177194967716169,
+      "grad_norm": 0.2612472176551819,
+      "learning_rate": 2.0219347581552306e-05,
+      "loss": 0.3928,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6230446648472342,
+      "grad_norm": 0.3657764494419098,
+      "learning_rate": 1.9938132733408325e-05,
+      "loss": 0.4531,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6283698329228516,
+      "grad_norm": 0.3054160475730896,
+      "learning_rate": 1.9656917885264343e-05,
+      "loss": 0.4729,
+      "step": 1180
+    },
+    {
+      "epoch": 0.633695000998469,
+      "grad_norm": 0.33150824904441833,
+      "learning_rate": 1.937570303712036e-05,
+      "loss": 0.4367,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6390201690740864,
+      "grad_norm": 0.3431392014026642,
+      "learning_rate": 1.909448818897638e-05,
+      "loss": 0.4147,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6443453371497038,
+      "grad_norm": 0.22645828127861023,
+      "learning_rate": 1.8813273340832395e-05,
+      "loss": 0.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6496705052253212,
+      "grad_norm": 0.2550465166568756,
+      "learning_rate": 1.8532058492688413e-05,
+      "loss": 0.5022,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6549956733009386,
+      "grad_norm": 0.225558802485466,
+      "learning_rate": 1.825084364454443e-05,
+      "loss": 0.3702,
+      "step": 1230
+    },
+    {
+      "epoch": 0.660320841376556,
+      "grad_norm": 0.2979082465171814,
+      "learning_rate": 1.796962879640045e-05,
+      "loss": 0.4897,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6656460094521733,
+      "grad_norm": 0.21975426375865936,
+      "learning_rate": 1.7688413948256468e-05,
+      "loss": 0.4337,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6709711775277907,
+      "grad_norm": 0.28157928586006165,
+      "learning_rate": 1.7407199100112486e-05,
+      "loss": 0.4995,
+      "step": 1260
+    },
+    {
+      "epoch": 0.6762963456034081,
+      "grad_norm": 0.2661578953266144,
+      "learning_rate": 1.7125984251968505e-05,
+      "loss": 0.4386,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6816215136790255,
+      "grad_norm": 0.15529419481754303,
+      "learning_rate": 1.6844769403824523e-05,
+      "loss": 0.4123,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6869466817546429,
+      "grad_norm": 0.23675470054149628,
+      "learning_rate": 1.656355455568054e-05,
+      "loss": 0.4087,
+      "step": 1290
+    },
+    {
+      "epoch": 0.6922718498302602,
+      "grad_norm": 0.15718118846416473,
+      "learning_rate": 1.628233970753656e-05,
+      "loss": 0.4166,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6975970179058777,
+      "grad_norm": 0.13441318273544312,
+      "learning_rate": 1.6001124859392578e-05,
+      "loss": 0.4284,
+      "step": 1310
+    },
+    {
+      "epoch": 0.702922185981495,
+      "grad_norm": 0.20030011236667633,
+      "learning_rate": 1.5719910011248597e-05,
+      "loss": 0.3879,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7082473540571125,
+      "grad_norm": 0.19878657162189484,
+      "learning_rate": 1.5438695163104615e-05,
+      "loss": 0.4291,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7135725221327298,
+      "grad_norm": 0.21621963381767273,
+      "learning_rate": 1.5157480314960632e-05,
+      "loss": 0.3967,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7188976902083472,
+      "grad_norm": 0.1658986657857895,
+      "learning_rate": 1.487626546681665e-05,
+      "loss": 0.482,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7242228582839646,
+      "grad_norm": 0.26133596897125244,
+      "learning_rate": 1.4595050618672668e-05,
+      "loss": 0.4453,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7295480263595819,
+      "grad_norm": 0.3131881058216095,
+      "learning_rate": 1.4313835770528685e-05,
+      "loss": 0.4097,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7348731944351994,
+      "grad_norm": 0.2788180708885193,
+      "learning_rate": 1.4032620922384703e-05,
+      "loss": 0.3803,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7401983625108167,
+      "grad_norm": 0.46388930082321167,
+      "learning_rate": 1.3751406074240722e-05,
+      "loss": 0.4903,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7455235305864342,
+      "grad_norm": 0.2546781301498413,
+      "learning_rate": 1.3470191226096737e-05,
+      "loss": 0.4182,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7508486986620515,
+      "grad_norm": 0.26159873604774475,
+      "learning_rate": 1.3188976377952755e-05,
+      "loss": 0.4529,
+      "step": 1410
+    },
+    {
+      "epoch": 0.756173866737669,
+      "grad_norm": 0.1894073188304901,
+      "learning_rate": 1.2907761529808773e-05,
+      "loss": 0.4192,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7614990348132863,
+      "grad_norm": 0.19885149598121643,
+      "learning_rate": 1.2626546681664792e-05,
+      "loss": 0.4264,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7668242028889036,
+      "grad_norm": 0.2684880793094635,
+      "learning_rate": 1.2345331833520812e-05,
+      "loss": 0.3945,
+      "step": 1440
+    },
+    {
+      "epoch": 0.7721493709645211,
+      "grad_norm": 0.26786723732948303,
+      "learning_rate": 1.2064116985376828e-05,
+      "loss": 0.4476,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7774745390401384,
+      "grad_norm": 0.19035054743289948,
+      "learning_rate": 1.1782902137232847e-05,
+      "loss": 0.3809,
+      "step": 1460
+    },
+    {
+      "epoch": 0.7827997071157559,
+      "grad_norm": 0.386610746383667,
+      "learning_rate": 1.1501687289088863e-05,
+      "loss": 0.4071,
+      "step": 1470
+    },
+    {
+      "epoch": 0.7881248751913732,
+      "grad_norm": 0.45737364888191223,
+      "learning_rate": 1.1220472440944882e-05,
+      "loss": 0.3513,
+      "step": 1480
+    },
+    {
+      "epoch": 0.7934500432669906,
+      "grad_norm": 0.27761179208755493,
+      "learning_rate": 1.09392575928009e-05,
+      "loss": 0.4155,
+      "step": 1490
+    },
+    {
+      "epoch": 0.798775211342608,
+      "grad_norm": 0.310969740152359,
+      "learning_rate": 1.0658042744656918e-05,
+      "loss": 0.4197,
+      "step": 1500
+    },
+    {
+      "epoch": 0.798775211342608,
+      "eval_loss": 0.5527679920196533,
+      "eval_runtime": 5246.1058,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 1.251,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1878,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7483018665412106e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1878/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-1878/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-14B-Base",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-1878/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8c3591f82ab5173a51d2f6a398706846a6333c618ce2510cbe68ab965a33f2
+size 256976504

checkpoint-1878/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1878/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d569a9c96ff4e89d32dfe8ca0b97952cc2edcd76f89c14caa7e57238c4b46c8a
+size 14645

checkpoint-1878/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b78f02229a7a970ad15e0a0f9e7360e1420a71062ba7b837ac4f9cad1c67b9
+size 1465

checkpoint-1878/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

checkpoint-1878/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "!",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1878/trainer_state.json

@@ -0,0 +1,1367 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1878,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005325168075617386,
+      "grad_norm": 0.22119790315628052,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5996,
+      "step": 10
+    },
+    {
+      "epoch": 0.010650336151234773,
+      "grad_norm": 0.16633106768131256,
+      "learning_rate": 9.5e-06,
+      "loss": 0.6377,
+      "step": 20
+    },
+    {
+      "epoch": 0.01597550422685216,
+      "grad_norm": 0.15750865638256073,
+      "learning_rate": 1.45e-05,
+      "loss": 0.5448,
+      "step": 30
+    },
+    {
+      "epoch": 0.021300672302469546,
+      "grad_norm": 0.1806253343820572,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.5772,
+      "step": 40
+    },
+    {
+      "epoch": 0.026625840378086935,
+      "grad_norm": 0.18283385038375854,
+      "learning_rate": 2.45e-05,
+      "loss": 0.5577,
+      "step": 50
+    },
+    {
+      "epoch": 0.03195100845370432,
+      "grad_norm": 0.2903732359409332,
+      "learning_rate": 2.95e-05,
+      "loss": 0.5611,
+      "step": 60
+    },
+    {
+      "epoch": 0.037276176529321706,
+      "grad_norm": 0.21062836050987244,
+      "learning_rate": 3.45e-05,
+      "loss": 0.472,
+      "step": 70
+    },
+    {
+      "epoch": 0.04260134460493909,
+      "grad_norm": 0.2517930269241333,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.5674,
+      "step": 80
+    },
+    {
+      "epoch": 0.04792651268055648,
+      "grad_norm": 0.25084561109542847,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.4704,
+      "step": 90
+    },
+    {
+      "epoch": 0.05325168075617387,
+      "grad_norm": 0.22995634377002716,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5068,
+      "step": 100
+    },
+    {
+      "epoch": 0.058576848831791255,
+      "grad_norm": 0.3184715509414673,
+      "learning_rate": 4.9746906636670424e-05,
+      "loss": 0.4727,
+      "step": 110
+    },
+    {
+      "epoch": 0.06390201690740864,
+      "grad_norm": 0.21488015353679657,
+      "learning_rate": 4.9465691788526435e-05,
+      "loss": 0.4914,
+      "step": 120
+    },
+    {
+      "epoch": 0.06922718498302603,
+      "grad_norm": 0.4201931953430176,
+      "learning_rate": 4.9184476940382454e-05,
+      "loss": 0.4662,
+      "step": 130
+    },
+    {
+      "epoch": 0.07455235305864341,
+      "grad_norm": 0.24147631227970123,
+      "learning_rate": 4.890326209223847e-05,
+      "loss": 0.5425,
+      "step": 140
+    },
+    {
+      "epoch": 0.0798775211342608,
+      "grad_norm": 0.32419461011886597,
+      "learning_rate": 4.862204724409449e-05,
+      "loss": 0.5136,
+      "step": 150
+    },
+    {
+      "epoch": 0.08520268920987818,
+      "grad_norm": 0.20325051248073578,
+      "learning_rate": 4.834083239595051e-05,
+      "loss": 0.4848,
+      "step": 160
+    },
+    {
+      "epoch": 0.09052785728549557,
+      "grad_norm": 0.26200124621391296,
+      "learning_rate": 4.805961754780653e-05,
+      "loss": 0.4795,
+      "step": 170
+    },
+    {
+      "epoch": 0.09585302536111295,
+      "grad_norm": 0.2597779929637909,
+      "learning_rate": 4.7778402699662545e-05,
+      "loss": 0.4701,
+      "step": 180
+    },
+    {
+      "epoch": 0.10117819343673035,
+      "grad_norm": 0.2209395468235016,
+      "learning_rate": 4.749718785151856e-05,
+      "loss": 0.4643,
+      "step": 190
+    },
+    {
+      "epoch": 0.10650336151234774,
+      "grad_norm": 0.18556272983551025,
+      "learning_rate": 4.721597300337458e-05,
+      "loss": 0.4392,
+      "step": 200
+    },
+    {
+      "epoch": 0.11182852958796512,
+      "grad_norm": 0.2606329917907715,
+      "learning_rate": 4.6934758155230594e-05,
+      "loss": 0.5305,
+      "step": 210
+    },
+    {
+      "epoch": 0.11715369766358251,
+      "grad_norm": 0.32324516773223877,
+      "learning_rate": 4.665354330708662e-05,
+      "loss": 0.4361,
+      "step": 220
+    },
+    {
+      "epoch": 0.12247886573919989,
+      "grad_norm": 0.773040235042572,
+      "learning_rate": 4.637232845894263e-05,
+      "loss": 0.4514,
+      "step": 230
+    },
+    {
+      "epoch": 0.12780403381481728,
+      "grad_norm": 0.19772544503211975,
+      "learning_rate": 4.6091113610798655e-05,
+      "loss": 0.5154,
+      "step": 240
+    },
+    {
+      "epoch": 0.13312920189043467,
+      "grad_norm": 0.21351611614227295,
+      "learning_rate": 4.580989876265467e-05,
+      "loss": 0.442,
+      "step": 250
+    },
+    {
+      "epoch": 0.13845436996605207,
+      "grad_norm": 0.6194823980331421,
+      "learning_rate": 4.552868391451069e-05,
+      "loss": 0.4623,
+      "step": 260
+    },
+    {
+      "epoch": 0.14377953804166943,
+      "grad_norm": 0.2469085454940796,
+      "learning_rate": 4.5247469066366704e-05,
+      "loss": 0.5265,
+      "step": 270
+    },
+    {
+      "epoch": 0.14910470611728682,
+      "grad_norm": 0.183319553732872,
+      "learning_rate": 4.496625421822272e-05,
+      "loss": 0.4498,
+      "step": 280
+    },
+    {
+      "epoch": 0.15442987419290422,
+      "grad_norm": 0.20639532804489136,
+      "learning_rate": 4.468503937007874e-05,
+      "loss": 0.443,
+      "step": 290
+    },
+    {
+      "epoch": 0.1597550422685216,
+      "grad_norm": 0.3168950378894806,
+      "learning_rate": 4.440382452193476e-05,
+      "loss": 0.5142,
+      "step": 300
+    },
+    {
+      "epoch": 0.165080210344139,
+      "grad_norm": 0.42236635088920593,
+      "learning_rate": 4.412260967379078e-05,
+      "loss": 0.4964,
+      "step": 310
+    },
+    {
+      "epoch": 0.17040537841975636,
+      "grad_norm": 0.3603885769844055,
+      "learning_rate": 4.3841394825646795e-05,
+      "loss": 0.4694,
+      "step": 320
+    },
+    {
+      "epoch": 0.17573054649537376,
+      "grad_norm": 0.5331389904022217,
+      "learning_rate": 4.3560179977502814e-05,
+      "loss": 0.5557,
+      "step": 330
+    },
+    {
+      "epoch": 0.18105571457099115,
+      "grad_norm": 0.2247193604707718,
+      "learning_rate": 4.327896512935883e-05,
+      "loss": 0.485,
+      "step": 340
+    },
+    {
+      "epoch": 0.18638088264660854,
+      "grad_norm": 0.20757395029067993,
+      "learning_rate": 4.299775028121485e-05,
+      "loss": 0.4534,
+      "step": 350
+    },
+    {
+      "epoch": 0.1917060507222259,
+      "grad_norm": 0.3965719938278198,
+      "learning_rate": 4.271653543307087e-05,
+      "loss": 0.4526,
+      "step": 360
+    },
+    {
+      "epoch": 0.1970312187978433,
+      "grad_norm": 0.3099954426288605,
+      "learning_rate": 4.243532058492689e-05,
+      "loss": 0.5196,
+      "step": 370
+    },
+    {
+      "epoch": 0.2023563868734607,
+      "grad_norm": 0.32076820731163025,
+      "learning_rate": 4.2154105736782906e-05,
+      "loss": 0.3987,
+      "step": 380
+    },
+    {
+      "epoch": 0.20768155494907808,
+      "grad_norm": 0.19246822595596313,
+      "learning_rate": 4.1872890888638924e-05,
+      "loss": 0.3958,
+      "step": 390
+    },
+    {
+      "epoch": 0.21300672302469548,
+      "grad_norm": 0.2495279759168625,
+      "learning_rate": 4.159167604049494e-05,
+      "loss": 0.4522,
+      "step": 400
+    },
+    {
+      "epoch": 0.21833189110031284,
+      "grad_norm": 0.3605816662311554,
+      "learning_rate": 4.131046119235096e-05,
+      "loss": 0.5324,
+      "step": 410
+    },
+    {
+      "epoch": 0.22365705917593023,
+      "grad_norm": 0.55950927734375,
+      "learning_rate": 4.102924634420698e-05,
+      "loss": 0.4587,
+      "step": 420
+    },
+    {
+      "epoch": 0.22898222725154763,
+      "grad_norm": 0.21795208752155304,
+      "learning_rate": 4.074803149606299e-05,
+      "loss": 0.4327,
+      "step": 430
+    },
+    {
+      "epoch": 0.23430739532716502,
+      "grad_norm": 0.33580827713012695,
+      "learning_rate": 4.0466816647919016e-05,
+      "loss": 0.4362,
+      "step": 440
+    },
+    {
+      "epoch": 0.2396325634027824,
+      "grad_norm": 0.26251840591430664,
+      "learning_rate": 4.018560179977503e-05,
+      "loss": 0.4533,
+      "step": 450
+    },
+    {
+      "epoch": 0.24495773147839978,
+      "grad_norm": 0.29128602147102356,
+      "learning_rate": 3.9904386951631046e-05,
+      "loss": 0.4854,
+      "step": 460
+    },
+    {
+      "epoch": 0.25028289955401717,
+      "grad_norm": 0.18392464518547058,
+      "learning_rate": 3.9623172103487064e-05,
+      "loss": 0.4367,
+      "step": 470
+    },
+    {
+      "epoch": 0.25560806762963456,
+      "grad_norm": 0.16602832078933716,
+      "learning_rate": 3.934195725534308e-05,
+      "loss": 0.4285,
+      "step": 480
+    },
+    {
+      "epoch": 0.26093323570525195,
+      "grad_norm": 0.19768096506595612,
+      "learning_rate": 3.90607424071991e-05,
+      "loss": 0.4703,
+      "step": 490
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "grad_norm": 0.34657010436058044,
+      "learning_rate": 3.877952755905512e-05,
+      "loss": 0.4661,
+      "step": 500
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "eval_loss": 0.5697944760322571,
+      "eval_runtime": 5453.8439,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 1.203,
+      "step": 500
+    },
+    {
+      "epoch": 0.27158357185648674,
+      "grad_norm": 0.31953340768814087,
+      "learning_rate": 3.849831271091114e-05,
+      "loss": 0.4225,
+      "step": 510
+    },
+    {
+      "epoch": 0.27690873993210413,
+      "grad_norm": 0.3757156729698181,
+      "learning_rate": 3.8217097862767156e-05,
+      "loss": 0.4425,
+      "step": 520
+    },
+    {
+      "epoch": 0.28223390800772147,
+      "grad_norm": 0.3416071832180023,
+      "learning_rate": 3.7935883014623174e-05,
+      "loss": 0.5368,
+      "step": 530
+    },
+    {
+      "epoch": 0.28755907608333886,
+      "grad_norm": 0.37404417991638184,
+      "learning_rate": 3.765466816647919e-05,
+      "loss": 0.5324,
+      "step": 540
+    },
+    {
+      "epoch": 0.29288424415895625,
+      "grad_norm": 0.4058983027935028,
+      "learning_rate": 3.737345331833521e-05,
+      "loss": 0.4785,
+      "step": 550
+    },
+    {
+      "epoch": 0.29820941223457365,
+      "grad_norm": 1.0426571369171143,
+      "learning_rate": 3.709223847019123e-05,
+      "loss": 0.4853,
+      "step": 560
+    },
+    {
+      "epoch": 0.30353458031019104,
+      "grad_norm": 0.24327947199344635,
+      "learning_rate": 3.681102362204725e-05,
+      "loss": 0.3702,
+      "step": 570
+    },
+    {
+      "epoch": 0.30885974838580843,
+      "grad_norm": 0.45736777782440186,
+      "learning_rate": 3.652980877390326e-05,
+      "loss": 0.416,
+      "step": 580
+    },
+    {
+      "epoch": 0.3141849164614258,
+      "grad_norm": 0.35099077224731445,
+      "learning_rate": 3.6248593925759284e-05,
+      "loss": 0.4667,
+      "step": 590
+    },
+    {
+      "epoch": 0.3195100845370432,
+      "grad_norm": 0.2792291045188904,
+      "learning_rate": 3.5967379077615296e-05,
+      "loss": 0.4689,
+      "step": 600
+    },
+    {
+      "epoch": 0.3248352526126606,
+      "grad_norm": 0.38183653354644775,
+      "learning_rate": 3.568616422947132e-05,
+      "loss": 0.352,
+      "step": 610
+    },
+    {
+      "epoch": 0.330160420688278,
+      "grad_norm": 0.23597702383995056,
+      "learning_rate": 3.540494938132733e-05,
+      "loss": 0.4939,
+      "step": 620
+    },
+    {
+      "epoch": 0.33548558876389534,
+      "grad_norm": 0.2534731924533844,
+      "learning_rate": 3.512373453318336e-05,
+      "loss": 0.4943,
+      "step": 630
+    },
+    {
+      "epoch": 0.34081075683951273,
+      "grad_norm": 0.5729730725288391,
+      "learning_rate": 3.484251968503937e-05,
+      "loss": 0.4278,
+      "step": 640
+    },
+    {
+      "epoch": 0.3461359249151301,
+      "grad_norm": 0.2920810580253601,
+      "learning_rate": 3.4561304836895394e-05,
+      "loss": 0.4518,
+      "step": 650
+    },
+    {
+      "epoch": 0.3514610929907475,
+      "grad_norm": 0.5853344202041626,
+      "learning_rate": 3.4280089988751406e-05,
+      "loss": 0.4772,
+      "step": 660
+    },
+    {
+      "epoch": 0.3567862610663649,
+      "grad_norm": 0.3440340757369995,
+      "learning_rate": 3.399887514060743e-05,
+      "loss": 0.5105,
+      "step": 670
+    },
+    {
+      "epoch": 0.3621114291419823,
+      "grad_norm": 0.17302438616752625,
+      "learning_rate": 3.371766029246344e-05,
+      "loss": 0.3868,
+      "step": 680
+    },
+    {
+      "epoch": 0.3674365972175997,
+      "grad_norm": 0.21418416500091553,
+      "learning_rate": 3.343644544431946e-05,
+      "loss": 0.4887,
+      "step": 690
+    },
+    {
+      "epoch": 0.3727617652932171,
+      "grad_norm": 0.21750663220882416,
+      "learning_rate": 3.315523059617548e-05,
+      "loss": 0.454,
+      "step": 700
+    },
+    {
+      "epoch": 0.3780869333688345,
+      "grad_norm": 0.2412487417459488,
+      "learning_rate": 3.28740157480315e-05,
+      "loss": 0.4225,
+      "step": 710
+    },
+    {
+      "epoch": 0.3834121014444518,
+      "grad_norm": 0.21244391798973083,
+      "learning_rate": 3.2592800899887516e-05,
+      "loss": 0.4257,
+      "step": 720
+    },
+    {
+      "epoch": 0.3887372695200692,
+      "grad_norm": 0.21693073213100433,
+      "learning_rate": 3.2311586051743534e-05,
+      "loss": 0.3583,
+      "step": 730
+    },
+    {
+      "epoch": 0.3940624375956866,
+      "grad_norm": 0.21653209626674652,
+      "learning_rate": 3.203037120359955e-05,
+      "loss": 0.4635,
+      "step": 740
+    },
+    {
+      "epoch": 0.399387605671304,
+      "grad_norm": 0.2929733693599701,
+      "learning_rate": 3.1749156355455564e-05,
+      "loss": 0.4788,
+      "step": 750
+    },
+    {
+      "epoch": 0.4047127737469214,
+      "grad_norm": 0.34718650579452515,
+      "learning_rate": 3.146794150731159e-05,
+      "loss": 0.4767,
+      "step": 760
+    },
+    {
+      "epoch": 0.4100379418225388,
+      "grad_norm": 0.2642233371734619,
+      "learning_rate": 3.11867266591676e-05,
+      "loss": 0.5099,
+      "step": 770
+    },
+    {
+      "epoch": 0.41536310989815617,
+      "grad_norm": 0.2616298794746399,
+      "learning_rate": 3.0905511811023626e-05,
+      "loss": 0.4999,
+      "step": 780
+    },
+    {
+      "epoch": 0.42068827797377356,
+      "grad_norm": 0.34992748498916626,
+      "learning_rate": 3.062429696287964e-05,
+      "loss": 0.4332,
+      "step": 790
+    },
+    {
+      "epoch": 0.42601344604939095,
+      "grad_norm": 0.2279980331659317,
+      "learning_rate": 3.034308211473566e-05,
+      "loss": 0.3728,
+      "step": 800
+    },
+    {
+      "epoch": 0.43133861412500835,
+      "grad_norm": 0.22256392240524292,
+      "learning_rate": 3.0061867266591674e-05,
+      "loss": 0.3916,
+      "step": 810
+    },
+    {
+      "epoch": 0.4366637822006257,
+      "grad_norm": 0.41548892855644226,
+      "learning_rate": 2.9780652418447696e-05,
+      "loss": 0.3982,
+      "step": 820
+    },
+    {
+      "epoch": 0.4419889502762431,
+      "grad_norm": 0.2539462447166443,
+      "learning_rate": 2.949943757030371e-05,
+      "loss": 0.4004,
+      "step": 830
+    },
+    {
+      "epoch": 0.44731411835186047,
+      "grad_norm": 0.4111381471157074,
+      "learning_rate": 2.9218222722159733e-05,
+      "loss": 0.5092,
+      "step": 840
+    },
+    {
+      "epoch": 0.45263928642747786,
+      "grad_norm": 0.38108745217323303,
+      "learning_rate": 2.8937007874015748e-05,
+      "loss": 0.4486,
+      "step": 850
+    },
+    {
+      "epoch": 0.45796445450309525,
+      "grad_norm": 0.48172271251678467,
+      "learning_rate": 2.865579302587177e-05,
+      "loss": 0.3567,
+      "step": 860
+    },
+    {
+      "epoch": 0.46328962257871265,
+      "grad_norm": 0.41752544045448303,
+      "learning_rate": 2.8374578177727784e-05,
+      "loss": 0.4139,
+      "step": 870
+    },
+    {
+      "epoch": 0.46861479065433004,
+      "grad_norm": 0.5029560327529907,
+      "learning_rate": 2.8093363329583806e-05,
+      "loss": 0.4041,
+      "step": 880
+    },
+    {
+      "epoch": 0.47393995872994743,
+      "grad_norm": 0.2200966477394104,
+      "learning_rate": 2.781214848143982e-05,
+      "loss": 0.4504,
+      "step": 890
+    },
+    {
+      "epoch": 0.4792651268055648,
+      "grad_norm": 0.29369235038757324,
+      "learning_rate": 2.7530933633295843e-05,
+      "loss": 0.4431,
+      "step": 900
+    },
+    {
+      "epoch": 0.48459029488118216,
+      "grad_norm": 0.25833240151405334,
+      "learning_rate": 2.7249718785151858e-05,
+      "loss": 0.4545,
+      "step": 910
+    },
+    {
+      "epoch": 0.48991546295679955,
+      "grad_norm": 0.26288172602653503,
+      "learning_rate": 2.6968503937007876e-05,
+      "loss": 0.3826,
+      "step": 920
+    },
+    {
+      "epoch": 0.49524063103241694,
+      "grad_norm": 0.25969257950782776,
+      "learning_rate": 2.668728908886389e-05,
+      "loss": 0.4591,
+      "step": 930
+    },
+    {
+      "epoch": 0.5005657991080343,
+      "grad_norm": 0.18059171736240387,
+      "learning_rate": 2.6406074240719913e-05,
+      "loss": 0.3603,
+      "step": 940
+    },
+    {
+      "epoch": 0.5058909671836518,
+      "grad_norm": 0.2396785318851471,
+      "learning_rate": 2.6124859392575928e-05,
+      "loss": 0.4397,
+      "step": 950
+    },
+    {
+      "epoch": 0.5112161352592691,
+      "grad_norm": 0.22924205660820007,
+      "learning_rate": 2.584364454443195e-05,
+      "loss": 0.4193,
+      "step": 960
+    },
+    {
+      "epoch": 0.5165413033348865,
+      "grad_norm": 0.21614229679107666,
+      "learning_rate": 2.5562429696287964e-05,
+      "loss": 0.3669,
+      "step": 970
+    },
+    {
+      "epoch": 0.5218664714105039,
+      "grad_norm": 0.21129848062992096,
+      "learning_rate": 2.5281214848143986e-05,
+      "loss": 0.3862,
+      "step": 980
+    },
+    {
+      "epoch": 0.5271916394861212,
+      "grad_norm": 0.24497318267822266,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3859,
+      "step": 990
+    },
+    {
+      "epoch": 0.5325168075617387,
+      "grad_norm": 0.46682098507881165,
+      "learning_rate": 2.471878515185602e-05,
+      "loss": 0.4416,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5325168075617387,
+      "eval_loss": 0.5570288300514221,
+      "eval_runtime": 5584.3711,
+      "eval_samples_per_second": 1.175,
+      "eval_steps_per_second": 1.175,
+      "step": 1000
+    },
+    {
+      "epoch": 0.537841975637356,
+      "grad_norm": 0.3136838972568512,
+      "learning_rate": 2.4437570303712038e-05,
+      "loss": 0.3728,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5431671437129735,
+      "grad_norm": 0.27630332112312317,
+      "learning_rate": 2.4156355455568056e-05,
+      "loss": 0.3588,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5484923117885908,
+      "grad_norm": 0.18581336736679077,
+      "learning_rate": 2.3875140607424075e-05,
+      "loss": 0.3999,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5538174798642083,
+      "grad_norm": 0.7955025434494019,
+      "learning_rate": 2.3593925759280093e-05,
+      "loss": 0.405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5591426479398256,
+      "grad_norm": 0.2039509415626526,
+      "learning_rate": 2.331271091113611e-05,
+      "loss": 0.4214,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5644678160154429,
+      "grad_norm": 0.28698962926864624,
+      "learning_rate": 2.3031496062992126e-05,
+      "loss": 0.3916,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5697929840910604,
+      "grad_norm": 0.5037312507629395,
+      "learning_rate": 2.2750281214848145e-05,
+      "loss": 0.4866,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5751181521666777,
+      "grad_norm": 0.32183122634887695,
+      "learning_rate": 2.2469066366704163e-05,
+      "loss": 0.4274,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5804433202422952,
+      "grad_norm": 0.228108212351799,
+      "learning_rate": 2.218785151856018e-05,
+      "loss": 0.4369,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5857684883179125,
+      "grad_norm": 0.420781672000885,
+      "learning_rate": 2.19066366704162e-05,
+      "loss": 0.3923,
+      "step": 1100
+    },
+    {
+      "epoch": 0.59109365639353,
+      "grad_norm": 0.241056889295578,
+      "learning_rate": 2.1625421822272218e-05,
+      "loss": 0.4149,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5964188244691473,
+      "grad_norm": 0.1952434480190277,
+      "learning_rate": 2.1344206974128236e-05,
+      "loss": 0.386,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6017439925447647,
+      "grad_norm": 0.24534425139427185,
+      "learning_rate": 2.106299212598425e-05,
+      "loss": 0.4176,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6070691606203821,
+      "grad_norm": 0.2993834912776947,
+      "learning_rate": 2.078177727784027e-05,
+      "loss": 0.4151,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6123943286959994,
+      "grad_norm": 0.30427229404449463,
+      "learning_rate": 2.0500562429696288e-05,
+      "loss": 0.4105,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6177194967716169,
+      "grad_norm": 0.2612472176551819,
+      "learning_rate": 2.0219347581552306e-05,
+      "loss": 0.3928,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6230446648472342,
+      "grad_norm": 0.3657764494419098,
+      "learning_rate": 1.9938132733408325e-05,
+      "loss": 0.4531,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6283698329228516,
+      "grad_norm": 0.3054160475730896,
+      "learning_rate": 1.9656917885264343e-05,
+      "loss": 0.4729,
+      "step": 1180
+    },
+    {
+      "epoch": 0.633695000998469,
+      "grad_norm": 0.33150824904441833,
+      "learning_rate": 1.937570303712036e-05,
+      "loss": 0.4367,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6390201690740864,
+      "grad_norm": 0.3431392014026642,
+      "learning_rate": 1.909448818897638e-05,
+      "loss": 0.4147,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6443453371497038,
+      "grad_norm": 0.22645828127861023,
+      "learning_rate": 1.8813273340832395e-05,
+      "loss": 0.4149,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6496705052253212,
+      "grad_norm": 0.2550465166568756,
+      "learning_rate": 1.8532058492688413e-05,
+      "loss": 0.5022,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6549956733009386,
+      "grad_norm": 0.225558802485466,
+      "learning_rate": 1.825084364454443e-05,
+      "loss": 0.3702,
+      "step": 1230
+    },
+    {
+      "epoch": 0.660320841376556,
+      "grad_norm": 0.2979082465171814,
+      "learning_rate": 1.796962879640045e-05,
+      "loss": 0.4897,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6656460094521733,
+      "grad_norm": 0.21975426375865936,
+      "learning_rate": 1.7688413948256468e-05,
+      "loss": 0.4337,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6709711775277907,
+      "grad_norm": 0.28157928586006165,
+      "learning_rate": 1.7407199100112486e-05,
+      "loss": 0.4995,
+      "step": 1260
+    },
+    {
+      "epoch": 0.6762963456034081,
+      "grad_norm": 0.2661578953266144,
+      "learning_rate": 1.7125984251968505e-05,
+      "loss": 0.4386,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6816215136790255,
+      "grad_norm": 0.15529419481754303,
+      "learning_rate": 1.6844769403824523e-05,
+      "loss": 0.4123,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6869466817546429,
+      "grad_norm": 0.23675470054149628,
+      "learning_rate": 1.656355455568054e-05,
+      "loss": 0.4087,
+      "step": 1290
+    },
+    {
+      "epoch": 0.6922718498302602,
+      "grad_norm": 0.15718118846416473,
+      "learning_rate": 1.628233970753656e-05,
+      "loss": 0.4166,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6975970179058777,
+      "grad_norm": 0.13441318273544312,
+      "learning_rate": 1.6001124859392578e-05,
+      "loss": 0.4284,
+      "step": 1310
+    },
+    {
+      "epoch": 0.702922185981495,
+      "grad_norm": 0.20030011236667633,
+      "learning_rate": 1.5719910011248597e-05,
+      "loss": 0.3879,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7082473540571125,
+      "grad_norm": 0.19878657162189484,
+      "learning_rate": 1.5438695163104615e-05,
+      "loss": 0.4291,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7135725221327298,
+      "grad_norm": 0.21621963381767273,
+      "learning_rate": 1.5157480314960632e-05,
+      "loss": 0.3967,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7188976902083472,
+      "grad_norm": 0.1658986657857895,
+      "learning_rate": 1.487626546681665e-05,
+      "loss": 0.482,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7242228582839646,
+      "grad_norm": 0.26133596897125244,
+      "learning_rate": 1.4595050618672668e-05,
+      "loss": 0.4453,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7295480263595819,
+      "grad_norm": 0.3131881058216095,
+      "learning_rate": 1.4313835770528685e-05,
+      "loss": 0.4097,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7348731944351994,
+      "grad_norm": 0.2788180708885193,
+      "learning_rate": 1.4032620922384703e-05,
+      "loss": 0.3803,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7401983625108167,
+      "grad_norm": 0.46388930082321167,
+      "learning_rate": 1.3751406074240722e-05,
+      "loss": 0.4903,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7455235305864342,
+      "grad_norm": 0.2546781301498413,
+      "learning_rate": 1.3470191226096737e-05,
+      "loss": 0.4182,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7508486986620515,
+      "grad_norm": 0.26159873604774475,
+      "learning_rate": 1.3188976377952755e-05,
+      "loss": 0.4529,
+      "step": 1410
+    },
+    {
+      "epoch": 0.756173866737669,
+      "grad_norm": 0.1894073188304901,
+      "learning_rate": 1.2907761529808773e-05,
+      "loss": 0.4192,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7614990348132863,
+      "grad_norm": 0.19885149598121643,
+      "learning_rate": 1.2626546681664792e-05,
+      "loss": 0.4264,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7668242028889036,
+      "grad_norm": 0.2684880793094635,
+      "learning_rate": 1.2345331833520812e-05,
+      "loss": 0.3945,
+      "step": 1440
+    },
+    {
+      "epoch": 0.7721493709645211,
+      "grad_norm": 0.26786723732948303,
+      "learning_rate": 1.2064116985376828e-05,
+      "loss": 0.4476,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7774745390401384,
+      "grad_norm": 0.19035054743289948,
+      "learning_rate": 1.1782902137232847e-05,
+      "loss": 0.3809,
+      "step": 1460
+    },
+    {
+      "epoch": 0.7827997071157559,
+      "grad_norm": 0.386610746383667,
+      "learning_rate": 1.1501687289088863e-05,
+      "loss": 0.4071,
+      "step": 1470
+    },
+    {
+      "epoch": 0.7881248751913732,
+      "grad_norm": 0.45737364888191223,
+      "learning_rate": 1.1220472440944882e-05,
+      "loss": 0.3513,
+      "step": 1480
+    },
+    {
+      "epoch": 0.7934500432669906,
+      "grad_norm": 0.27761179208755493,
+      "learning_rate": 1.09392575928009e-05,
+      "loss": 0.4155,
+      "step": 1490
+    },
+    {
+      "epoch": 0.798775211342608,
+      "grad_norm": 0.310969740152359,
+      "learning_rate": 1.0658042744656918e-05,
+      "loss": 0.4197,
+      "step": 1500
+    },
+    {
+      "epoch": 0.798775211342608,
+      "eval_loss": 0.5527679920196533,
+      "eval_runtime": 5246.1058,
+      "eval_samples_per_second": 1.251,
+      "eval_steps_per_second": 1.251,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8041003794182254,
+      "grad_norm": 0.19479507207870483,
+      "learning_rate": 1.0376827896512937e-05,
+      "loss": 0.4025,
+      "step": 1510
+    },
+    {
+      "epoch": 0.8094255474938428,
+      "grad_norm": 0.3294892907142639,
+      "learning_rate": 1.0095613048368953e-05,
+      "loss": 0.5292,
+      "step": 1520
+    },
+    {
+      "epoch": 0.8147507155694602,
+      "grad_norm": 0.2421240210533142,
+      "learning_rate": 9.814398200224972e-06,
+      "loss": 0.4052,
+      "step": 1530
+    },
+    {
+      "epoch": 0.8200758836450776,
+      "grad_norm": 0.34715735912323,
+      "learning_rate": 9.53318335208099e-06,
+      "loss": 0.4974,
+      "step": 1540
+    },
+    {
+      "epoch": 0.8254010517206949,
+      "grad_norm": 0.28659817576408386,
+      "learning_rate": 9.251968503937008e-06,
+      "loss": 0.4388,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8307262197963123,
+      "grad_norm": 0.19494527578353882,
+      "learning_rate": 8.970753655793027e-06,
+      "loss": 0.4236,
+      "step": 1560
+    },
+    {
+      "epoch": 0.8360513878719297,
+      "grad_norm": 0.3780122697353363,
+      "learning_rate": 8.689538807649045e-06,
+      "loss": 0.4404,
+      "step": 1570
+    },
+    {
+      "epoch": 0.8413765559475471,
+      "grad_norm": 0.19608207046985626,
+      "learning_rate": 8.408323959505064e-06,
+      "loss": 0.4176,
+      "step": 1580
+    },
+    {
+      "epoch": 0.8467017240231645,
+      "grad_norm": 0.13822776079177856,
+      "learning_rate": 8.12710911136108e-06,
+      "loss": 0.3846,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8520268920987819,
+      "grad_norm": 0.32028502225875854,
+      "learning_rate": 7.845894263217097e-06,
+      "loss": 0.396,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8573520601743992,
+      "grad_norm": 0.2707017660140991,
+      "learning_rate": 7.564679415073116e-06,
+      "loss": 0.4791,
+      "step": 1610
+    },
+    {
+      "epoch": 0.8626772282500167,
+      "grad_norm": 0.20642437040805817,
+      "learning_rate": 7.2834645669291335e-06,
+      "loss": 0.3509,
+      "step": 1620
+    },
+    {
+      "epoch": 0.868002396325634,
+      "grad_norm": 0.1976356953382492,
+      "learning_rate": 7.002249718785152e-06,
+      "loss": 0.3525,
+      "step": 1630
+    },
+    {
+      "epoch": 0.8733275644012514,
+      "grad_norm": 0.23061439394950867,
+      "learning_rate": 6.72103487064117e-06,
+      "loss": 0.4031,
+      "step": 1640
+    },
+    {
+      "epoch": 0.8786527324768688,
+      "grad_norm": 0.34086883068084717,
+      "learning_rate": 6.439820022497188e-06,
+      "loss": 0.4223,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8839779005524862,
+      "grad_norm": 0.5287061333656311,
+      "learning_rate": 6.158605174353206e-06,
+      "loss": 0.4545,
+      "step": 1660
+    },
+    {
+      "epoch": 0.8893030686281036,
+      "grad_norm": 0.31359419226646423,
+      "learning_rate": 5.8773903262092244e-06,
+      "loss": 0.4144,
+      "step": 1670
+    },
+    {
+      "epoch": 0.8946282367037209,
+      "grad_norm": 0.30537229776382446,
+      "learning_rate": 5.596175478065242e-06,
+      "loss": 0.407,
+      "step": 1680
+    },
+    {
+      "epoch": 0.8999534047793384,
+      "grad_norm": 0.18814413249492645,
+      "learning_rate": 5.31496062992126e-06,
+      "loss": 0.3705,
+      "step": 1690
+    },
+    {
+      "epoch": 0.9052785728549557,
+      "grad_norm": 0.3469262719154358,
+      "learning_rate": 5.033745781777278e-06,
+      "loss": 0.3599,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9106037409305732,
+      "grad_norm": 0.19436882436275482,
+      "learning_rate": 4.752530933633296e-06,
+      "loss": 0.4104,
+      "step": 1710
+    },
+    {
+      "epoch": 0.9159289090061905,
+      "grad_norm": 0.31178855895996094,
+      "learning_rate": 4.471316085489314e-06,
+      "loss": 0.4415,
+      "step": 1720
+    },
+    {
+      "epoch": 0.9212540770818078,
+      "grad_norm": 0.21947060525417328,
+      "learning_rate": 4.190101237345332e-06,
+      "loss": 0.4207,
+      "step": 1730
+    },
+    {
+      "epoch": 0.9265792451574253,
+      "grad_norm": 0.31967392563819885,
+      "learning_rate": 3.90888638920135e-06,
+      "loss": 0.4321,
+      "step": 1740
+    },
+    {
+      "epoch": 0.9319044132330426,
+      "grad_norm": 0.2997397780418396,
+      "learning_rate": 3.6276715410573683e-06,
+      "loss": 0.4074,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9372295813086601,
+      "grad_norm": 0.3726807236671448,
+      "learning_rate": 3.346456692913386e-06,
+      "loss": 0.4567,
+      "step": 1760
+    },
+    {
+      "epoch": 0.9425547493842774,
+      "grad_norm": 0.21171921491622925,
+      "learning_rate": 3.065241844769404e-06,
+      "loss": 0.4771,
+      "step": 1770
+    },
+    {
+      "epoch": 0.9478799174598949,
+      "grad_norm": 0.33717474341392517,
+      "learning_rate": 2.784026996625422e-06,
+      "loss": 0.4307,
+      "step": 1780
+    },
+    {
+      "epoch": 0.9532050855355122,
+      "grad_norm": 0.44352519512176514,
+      "learning_rate": 2.50281214848144e-06,
+      "loss": 0.4313,
+      "step": 1790
+    },
+    {
+      "epoch": 0.9585302536111296,
+      "grad_norm": 0.22899667918682098,
+      "learning_rate": 2.221597300337458e-06,
+      "loss": 0.4239,
+      "step": 1800
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.26823002099990845,
+      "learning_rate": 1.940382452193476e-06,
+      "loss": 0.3961,
+      "step": 1810
+    },
+    {
+      "epoch": 0.9691805897623643,
+      "grad_norm": 0.32185128331184387,
+      "learning_rate": 1.6591676040494938e-06,
+      "loss": 0.3969,
+      "step": 1820
+    },
+    {
+      "epoch": 0.9745057578379818,
+      "grad_norm": 0.23674292862415314,
+      "learning_rate": 1.377952755905512e-06,
+      "loss": 0.3565,
+      "step": 1830
+    },
+    {
+      "epoch": 0.9798309259135991,
+      "grad_norm": 0.35923701524734497,
+      "learning_rate": 1.09673790776153e-06,
+      "loss": 0.4661,
+      "step": 1840
+    },
+    {
+      "epoch": 0.9851560939892166,
+      "grad_norm": 0.209647074341774,
+      "learning_rate": 8.155230596175479e-07,
+      "loss": 0.3862,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9904812620648339,
+      "grad_norm": 0.16489411890506744,
+      "learning_rate": 5.343082114735659e-07,
+      "loss": 0.4991,
+      "step": 1860
+    },
+    {
+      "epoch": 0.9958064301404513,
+      "grad_norm": 0.2104809433221817,
+      "learning_rate": 2.530933633295838e-07,
+      "loss": 0.4165,
+      "step": 1870
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1878,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1800742431950127e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1878/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65370271f00c8aaf4e6680dadb84e9a7c9013c61b91548370ec341e27f869117
+size 6353

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-14B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-14B-Base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-14B-Base",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82492c94036b8fd0435fa48e17530c6002c54463b6502f6086688e91057b893f
+size 256976504

checkpoint-500/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109239536768bc3de549d6d27143f712f80c8a3d1a7feb007f1833d3fb5f13c2
+size 131116517

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "!",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.26625840378086935,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005325168075617386,
+      "grad_norm": 0.22119790315628052,
+      "learning_rate": 4.5e-06,
+      "loss": 0.5996,
+      "step": 10
+    },
+    {
+      "epoch": 0.010650336151234773,
+      "grad_norm": 0.16633106768131256,
+      "learning_rate": 9.5e-06,
+      "loss": 0.6377,
+      "step": 20
+    },
+    {
+      "epoch": 0.01597550422685216,
+      "grad_norm": 0.15750865638256073,
+      "learning_rate": 1.45e-05,
+      "loss": 0.5448,
+      "step": 30
+    },
+    {
+      "epoch": 0.021300672302469546,
+      "grad_norm": 0.1806253343820572,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.5772,
+      "step": 40
+    },
+    {
+      "epoch": 0.026625840378086935,
+      "grad_norm": 0.18283385038375854,
+      "learning_rate": 2.45e-05,
+      "loss": 0.5577,
+      "step": 50
+    },
+    {
+      "epoch": 0.03195100845370432,
+      "grad_norm": 0.2903732359409332,
+      "learning_rate": 2.95e-05,
+      "loss": 0.5611,
+      "step": 60
+    },
+    {
+      "epoch": 0.037276176529321706,
+      "grad_norm": 0.21062836050987244,
+      "learning_rate": 3.45e-05,
+      "loss": 0.472,
+      "step": 70
+    },
+    {
+      "epoch": 0.04260134460493909,
+      "grad_norm": 0.2517930269241333,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.5674,
+      "step": 80
+    },
+    {
+      "epoch": 0.04792651268055648,
+      "grad_norm": 0.25084561109542847,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.4704,
+      "step": 90
+    },
+    {
+      "epoch": 0.05325168075617387,
+      "grad_norm": 0.22995634377002716,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.5068,
+      "step": 100
+    },
+    {
+      "epoch": 0.058576848831791255,
+      "grad_norm": 0.3184715509414673,
+      "learning_rate": 4.9746906636670424e-05,
+      "loss": 0.4727,
+      "step": 110
+    },
+    {
+      "epoch": 0.06390201690740864,
+      "grad_norm": 0.21488015353679657,
+      "learning_rate": 4.9465691788526435e-05,
+      "loss": 0.4914,
+      "step": 120
+    },
+    {
+      "epoch": 0.06922718498302603,
+      "grad_norm": 0.4201931953430176,
+      "learning_rate": 4.9184476940382454e-05,
+      "loss": 0.4662,
+      "step": 130
+    },
+    {
+      "epoch": 0.07455235305864341,
+      "grad_norm": 0.24147631227970123,
+      "learning_rate": 4.890326209223847e-05,
+      "loss": 0.5425,
+      "step": 140
+    },
+    {
+      "epoch": 0.0798775211342608,
+      "grad_norm": 0.32419461011886597,
+      "learning_rate": 4.862204724409449e-05,
+      "loss": 0.5136,
+      "step": 150
+    },
+    {
+      "epoch": 0.08520268920987818,
+      "grad_norm": 0.20325051248073578,
+      "learning_rate": 4.834083239595051e-05,
+      "loss": 0.4848,
+      "step": 160
+    },
+    {
+      "epoch": 0.09052785728549557,
+      "grad_norm": 0.26200124621391296,
+      "learning_rate": 4.805961754780653e-05,
+      "loss": 0.4795,
+      "step": 170
+    },
+    {
+      "epoch": 0.09585302536111295,
+      "grad_norm": 0.2597779929637909,
+      "learning_rate": 4.7778402699662545e-05,
+      "loss": 0.4701,
+      "step": 180
+    },
+    {
+      "epoch": 0.10117819343673035,
+      "grad_norm": 0.2209395468235016,
+      "learning_rate": 4.749718785151856e-05,
+      "loss": 0.4643,
+      "step": 190
+    },
+    {
+      "epoch": 0.10650336151234774,
+      "grad_norm": 0.18556272983551025,
+      "learning_rate": 4.721597300337458e-05,
+      "loss": 0.4392,
+      "step": 200
+    },
+    {
+      "epoch": 0.11182852958796512,
+      "grad_norm": 0.2606329917907715,
+      "learning_rate": 4.6934758155230594e-05,
+      "loss": 0.5305,
+      "step": 210
+    },
+    {
+      "epoch": 0.11715369766358251,
+      "grad_norm": 0.32324516773223877,
+      "learning_rate": 4.665354330708662e-05,
+      "loss": 0.4361,
+      "step": 220
+    },
+    {
+      "epoch": 0.12247886573919989,
+      "grad_norm": 0.773040235042572,
+      "learning_rate": 4.637232845894263e-05,
+      "loss": 0.4514,
+      "step": 230
+    },
+    {
+      "epoch": 0.12780403381481728,
+      "grad_norm": 0.19772544503211975,
+      "learning_rate": 4.6091113610798655e-05,
+      "loss": 0.5154,
+      "step": 240
+    },
+    {
+      "epoch": 0.13312920189043467,
+      "grad_norm": 0.21351611614227295,
+      "learning_rate": 4.580989876265467e-05,
+      "loss": 0.442,
+      "step": 250
+    },
+    {
+      "epoch": 0.13845436996605207,
+      "grad_norm": 0.6194823980331421,
+      "learning_rate": 4.552868391451069e-05,
+      "loss": 0.4623,
+      "step": 260
+    },
+    {
+      "epoch": 0.14377953804166943,
+      "grad_norm": 0.2469085454940796,
+      "learning_rate": 4.5247469066366704e-05,
+      "loss": 0.5265,
+      "step": 270
+    },
+    {
+      "epoch": 0.14910470611728682,
+      "grad_norm": 0.183319553732872,
+      "learning_rate": 4.496625421822272e-05,
+      "loss": 0.4498,
+      "step": 280
+    },
+    {
+      "epoch": 0.15442987419290422,
+      "grad_norm": 0.20639532804489136,
+      "learning_rate": 4.468503937007874e-05,
+      "loss": 0.443,
+      "step": 290
+    },
+    {
+      "epoch": 0.1597550422685216,
+      "grad_norm": 0.3168950378894806,
+      "learning_rate": 4.440382452193476e-05,
+      "loss": 0.5142,
+      "step": 300
+    },
+    {
+      "epoch": 0.165080210344139,
+      "grad_norm": 0.42236635088920593,
+      "learning_rate": 4.412260967379078e-05,
+      "loss": 0.4964,
+      "step": 310
+    },
+    {
+      "epoch": 0.17040537841975636,
+      "grad_norm": 0.3603885769844055,
+      "learning_rate": 4.3841394825646795e-05,
+      "loss": 0.4694,
+      "step": 320
+    },
+    {
+      "epoch": 0.17573054649537376,
+      "grad_norm": 0.5331389904022217,
+      "learning_rate": 4.3560179977502814e-05,
+      "loss": 0.5557,
+      "step": 330
+    },
+    {
+      "epoch": 0.18105571457099115,
+      "grad_norm": 0.2247193604707718,
+      "learning_rate": 4.327896512935883e-05,
+      "loss": 0.485,
+      "step": 340
+    },
+    {
+      "epoch": 0.18638088264660854,
+      "grad_norm": 0.20757395029067993,
+      "learning_rate": 4.299775028121485e-05,
+      "loss": 0.4534,
+      "step": 350
+    },
+    {
+      "epoch": 0.1917060507222259,
+      "grad_norm": 0.3965719938278198,
+      "learning_rate": 4.271653543307087e-05,
+      "loss": 0.4526,
+      "step": 360
+    },
+    {
+      "epoch": 0.1970312187978433,
+      "grad_norm": 0.3099954426288605,
+      "learning_rate": 4.243532058492689e-05,
+      "loss": 0.5196,
+      "step": 370
+    },
+    {
+      "epoch": 0.2023563868734607,
+      "grad_norm": 0.32076820731163025,
+      "learning_rate": 4.2154105736782906e-05,
+      "loss": 0.3987,
+      "step": 380
+    },
+    {
+      "epoch": 0.20768155494907808,
+      "grad_norm": 0.19246822595596313,
+      "learning_rate": 4.1872890888638924e-05,
+      "loss": 0.3958,
+      "step": 390
+    },
+    {
+      "epoch": 0.21300672302469548,
+      "grad_norm": 0.2495279759168625,
+      "learning_rate": 4.159167604049494e-05,
+      "loss": 0.4522,
+      "step": 400
+    },
+    {
+      "epoch": 0.21833189110031284,
+      "grad_norm": 0.3605816662311554,
+      "learning_rate": 4.131046119235096e-05,
+      "loss": 0.5324,
+      "step": 410
+    },
+    {
+      "epoch": 0.22365705917593023,
+      "grad_norm": 0.55950927734375,
+      "learning_rate": 4.102924634420698e-05,
+      "loss": 0.4587,
+      "step": 420
+    },
+    {
+      "epoch": 0.22898222725154763,
+      "grad_norm": 0.21795208752155304,
+      "learning_rate": 4.074803149606299e-05,
+      "loss": 0.4327,
+      "step": 430
+    },
+    {
+      "epoch": 0.23430739532716502,
+      "grad_norm": 0.33580827713012695,
+      "learning_rate": 4.0466816647919016e-05,
+      "loss": 0.4362,
+      "step": 440
+    },
+    {
+      "epoch": 0.2396325634027824,
+      "grad_norm": 0.26251840591430664,
+      "learning_rate": 4.018560179977503e-05,
+      "loss": 0.4533,
+      "step": 450
+    },
+    {
+      "epoch": 0.24495773147839978,
+      "grad_norm": 0.29128602147102356,
+      "learning_rate": 3.9904386951631046e-05,
+      "loss": 0.4854,
+      "step": 460
+    },
+    {
+      "epoch": 0.25028289955401717,
+      "grad_norm": 0.18392464518547058,
+      "learning_rate": 3.9623172103487064e-05,
+      "loss": 0.4367,
+      "step": 470
+    },
+    {
+      "epoch": 0.25560806762963456,
+      "grad_norm": 0.16602832078933716,
+      "learning_rate": 3.934195725534308e-05,
+      "loss": 0.4285,
+      "step": 480
+    },
+    {
+      "epoch": 0.26093323570525195,
+      "grad_norm": 0.19768096506595612,
+      "learning_rate": 3.90607424071991e-05,
+      "loss": 0.4703,
+      "step": 490
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "grad_norm": 0.34657010436058044,
+      "learning_rate": 3.877952755905512e-05,
+      "loss": 0.4661,
+      "step": 500
+    },
+    {
+      "epoch": 0.26625840378086935,
+      "eval_loss": 0.5697944760322571,
+      "eval_runtime": 5453.8439,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 1.203,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1878,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.801278592902625e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "!",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65370271f00c8aaf4e6680dadb84e9a7c9013c61b91548370ec341e27f869117
+size 6353