---
library_name: peft
base_model: Qwen/Qwen3-8B
tags:
- axolotl
- base_model:adapter:Qwen/Qwen3-8B
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: out/qwen3-8b-persistent-navigation-20260525_121743
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.13.2`
```yaml
adapter: lora
base_model: Qwen/Qwen3-8B
bf16: true
bnb_4bit_compute_dtype: bfloat16
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: true
dataset_prepared_path: out/prepared_dataset_persistent
  message_field_content: content
  message_field_role: role
  path: /e/project1/reformo/salgarkar1/agents_learn/pythonformer-workshop/paired/train/out/paired_data/persistent/navigation/traces.jsonl
  roles_to_train:
  - assistant
  type: chat_template
eval_steps: 5
flash_attention: true
gradient_accumulation_steps: 16
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
learning_rate: 0.0001
load_in_4bit: true
load_in_8bit: false
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_r: 64
lora_target_linear: false
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
lr_scheduler: cosine
micro_batch_size: 1
model_type: AutoModelForCausalLM
num_epochs: 3.0
optimizer: adamw_torch
output_dir: out/qwen3-8b-persistent-navigation-20260525_121743
pad_to_sequence_len: true
sample_packing: false
save_strategy: epoch
save_total_limit: 3
seed: 3407
sequence_len: 16384
strict: false
tf32: true
tokenizer_type: AutoTokenizer
trust_remote_code: true
val_set_size: 0.04
wandb_log_model: null
wandb_project: pythonformer
wandb_watch: null
warmup_ratio: 0.03
weight_decay: 0.01

```

</details><br>

# out/qwen3-8b-persistent-navigation-20260525_121743

This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/project1/reformo/salgarkar1/agents_learn/pythonformer-workshop/paired/train/out/paired_data/persistent/navigation/traces.jsonl dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2875
- Ppl: 1.3331
- Memory/max Active (gib): 54.54
- Memory/max Allocated (gib): 54.54
- Memory/device Reserved (gib): 66.97

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 3407
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 2
- training_steps: 45

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Ppl    | Active (gib) | Allocated (gib) | Reserved (gib) |
|:-------------:|:------:|:----:|:---------------:|:------:|:------------:|:---------------:|:--------------:|
| No log        | 0      | 0    | 0.9681          | 2.6330 | 53.19        | 53.19           | 56.52          |
| 0.6197        | 0.3333 | 5    | 0.5761          | 1.7792 | 54.54        | 54.54           | 66.97          |
| 0.4796        | 0.6667 | 10   | 0.4404          | 1.5533 | 54.54        | 54.54           | 66.97          |
| 0.4179        | 1.0    | 15   | 0.3768          | 1.4576 | 54.54        | 54.54           | 66.97          |
| 0.3473        | 1.3333 | 20   | 0.3375          | 1.4014 | 54.54        | 54.54           | 66.97          |
| 0.3125        | 1.6667 | 25   | 0.3142          | 1.3692 | 54.54        | 54.54           | 66.97          |
| 0.3015        | 2.0    | 30   | 0.2998          | 1.3496 | 54.54        | 54.54           | 66.97          |
| 0.3033        | 2.3333 | 35   | 0.2914          | 1.3383 | 54.54        | 54.54           | 66.97          |
| 0.2925        | 2.6667 | 40   | 0.2881          | 1.3339 | 54.54        | 54.54           | 66.97          |
| 0.2815        | 3.0    | 45   | 0.2875          | 1.3331 | 54.54        | 54.54           | 66.97          |


### Framework versions

- PEFT 0.18.1
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2