---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-0.5B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: a7f83208-aa47-4ecd-80e6-f21bda70bb90
results: []
---
[
](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: Qwen/Qwen2.5-0.5B
batch_size: 8
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- data_files:
- 44664facd5408a4c_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/44664facd5408a4c_train_data.json
type:
field_input: choices
field_instruction: full_prompt
field_output: example
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
evals_per_epoch: 1
flash_attention: true
gpu_memory_limit: 80GiB
gradient_checkpointing: true
group_by_length: true
hub_model_id: willtensora/a7f83208-aa47-4ecd-80e6-f21bda70bb90
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lora_alpha: 256
lora_dropout: 0.1
lora_r: 128
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 1
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: false
saves_per_epoch: 2
sequence_len: 2048
tokenizer_type: Qwen2TokenizerFast
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05
xformers_attention: true
```
# a7f83208-aa47-4ecd-80e6-f21bda70bb90
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0000
## 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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 8
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 24
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 0.025 | 1 | 0.9385 |
| 0.0292 | 1.0 | 40 | 0.0043 |
| 0.0148 | 2.0 | 80 | 0.0332 |
| 0.1015 | 3.0 | 120 | 0.0044 |
| 0.0002 | 4.0 | 160 | 0.0001 |
| 0.0 | 5.0 | 200 | 0.0000 |
| 0.0 | 6.0 | 240 | 0.0000 |
| 0.0 | 7.0 | 280 | 0.0000 |
| 0.0 | 8.0 | 320 | 0.0000 |
| 0.0 | 9.0 | 360 | 0.0000 |
| 0.0 | 10.0 | 400 | 0.0000 |
| 0.0 | 11.0 | 440 | 0.0000 |
| 0.0 | 12.0 | 480 | 0.0000 |
| 0.0 | 13.0 | 520 | 0.0000 |
| 0.0 | 14.0 | 560 | 0.0000 |
| 0.0 | 15.0 | 600 | 0.0000 |
| 0.0 | 16.0 | 640 | 0.0000 |
| 0.0 | 17.0 | 680 | 0.0000 |
| 0.0 | 18.0 | 720 | 0.0000 |
| 0.0 | 19.0 | 760 | 0.0000 |
| 0.0 | 20.0 | 800 | 0.0000 |
| 0.0 | 21.0 | 840 | 0.0000 |
| 0.0 | 22.0 | 880 | 0.0000 |
| 0.0 | 23.0 | 920 | 0.0000 |
| 0.0 | 24.0 | 960 | 0.0000 |
| 0.0 | 25.0 | 1000 | 0.0000 |
| 0.0 | 26.0 | 1040 | 0.0000 |
| 0.0 | 27.0 | 1080 | 0.0000 |
| 0.0 | 28.0 | 1120 | 0.0000 |
| 0.0 | 29.0 | 1160 | 0.0000 |
| 0.0 | 30.0 | 1200 | 0.0000 |
| 0.0 | 31.0 | 1240 | 0.0000 |
| 0.0 | 32.0 | 1280 | 0.0000 |
| 0.0 | 33.0 | 1320 | 0.0000 |
| 0.0 | 34.0 | 1360 | 0.0000 |
| 0.0 | 35.0 | 1400 | 0.0000 |
| 0.0 | 36.0 | 1440 | 0.0000 |
| 0.0 | 37.0 | 1480 | 0.0000 |
| 0.0 | 38.0 | 1520 | 0.0000 |
| 0.0 | 39.0 | 1560 | 0.0000 |
| 0.0 | 40.0 | 1600 | 0.0000 |
| 0.0 | 41.0 | 1640 | 0.0000 |
| 0.0 | 42.0 | 1680 | 0.0000 |
| 0.0 | 43.0 | 1720 | 0.0000 |
| 0.0 | 44.0 | 1760 | 0.0000 |
| 0.0 | 45.0 | 1800 | 0.0000 |
| 0.0 | 46.0 | 1840 | 0.0000 |
| 0.0 | 47.0 | 1880 | 0.0000 |
| 0.0 | 48.0 | 1920 | 0.0000 |
| 0.0 | 49.0 | 1960 | 0.0000 |
| 0.0 | 50.0 | 2000 | 0.0000 |
| 0.0 | 51.0 | 2040 | 0.0000 |
| 0.0 | 52.0 | 2080 | 0.0000 |
| 0.0 | 53.0 | 2120 | 0.0000 |
| 0.0 | 54.0 | 2160 | 0.0000 |
| 0.0 | 55.0 | 2200 | 0.0000 |
| 0.0 | 56.0 | 2240 | 0.0000 |
| 0.0 | 57.0 | 2280 | 0.0000 |
| 0.0 | 58.0 | 2320 | 0.0000 |
| 0.0 | 59.0 | 2360 | 0.0000 |
| 0.0 | 60.0 | 2400 | 0.0000 |
| 0.0 | 61.0 | 2440 | 0.0000 |
| 0.0 | 62.0 | 2480 | 0.0000 |
| 0.0 | 63.0 | 2520 | 0.0000 |
| 0.0 | 64.0 | 2560 | 0.0000 |
| 0.0 | 65.0 | 2600 | 0.0000 |
| 0.0 | 66.0 | 2640 | 0.0000 |
| 0.0 | 67.0 | 2680 | 0.0000 |
| 0.0 | 68.0 | 2720 | 0.0000 |
| 0.0 | 69.0 | 2760 | 0.0000 |
| 0.0 | 70.0 | 2800 | 0.0000 |
| 0.0 | 71.0 | 2840 | 0.0000 |
| 0.0 | 72.0 | 2880 | 0.0000 |
| 0.0 | 73.0 | 2920 | 0.0000 |
| 0.0 | 74.0 | 2960 | 0.0000 |
| 0.0 | 75.0 | 3000 | 0.0000 |
| 0.0 | 76.0 | 3040 | 0.0000 |
| 0.0 | 77.0 | 3080 | 0.0000 |
| 0.0 | 78.0 | 3120 | 0.0000 |
| 0.0 | 79.0 | 3160 | 0.0000 |
| 0.0 | 80.0 | 3200 | 0.0000 |
| 0.0 | 81.0 | 3240 | 0.0000 |
| 0.0 | 82.0 | 3280 | 0.0000 |
| 0.0 | 83.0 | 3320 | 0.0000 |
| 0.0 | 84.0 | 3360 | 0.0000 |
| 0.0 | 85.0 | 3400 | 0.0000 |
| 0.0 | 86.0 | 3440 | 0.0000 |
| 0.0 | 87.0 | 3480 | 0.0000 |
| 0.0 | 88.0 | 3520 | 0.0000 |
| 0.0 | 89.0 | 3560 | 0.0000 |
| 0.0 | 90.0 | 3600 | 0.0000 |
| 0.0 | 91.0 | 3640 | 0.0000 |
| 0.0 | 92.0 | 3680 | 0.0000 |
| 0.0 | 93.0 | 3720 | 0.0000 |
| 0.0 | 94.0 | 3760 | 0.0000 |
| 0.0 | 95.0 | 3800 | 0.0000 |
| 0.0 | 96.0 | 3840 | 0.0000 |
| 0.0 | 97.0 | 3880 | 0.0000 |
| 0.0 | 98.0 | 3920 | 0.0000 |
| 0.0 | 99.0 | 3960 | 0.0000 |
| 0.0 | 100.0 | 4000 | 0.0000 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1