metadata
library_name: peft
license: apache-2.0
base_model: llamafactory/tiny-random-Llama-3
tags:
- axolotl
- generated_from_trainer
model-index:
- name: b6517a65-a5a0-464c-904c-fda8d07f87b2
results: []
b6517a65-a5a0-464c-904c-fda8d07f87b2
This model is a fine-tuned version of llamafactory/tiny-random-Llama-3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 11.7310
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: 0.000201
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0012 | 1 | 11.7627 |
| 11.7386 | 0.0583 | 50 | 11.7464 |
| 11.7345 | 0.1166 | 100 | 11.7421 |
| 11.7294 | 0.1749 | 150 | 11.7398 |
| 11.7288 | 0.2332 | 200 | 11.7372 |
| 11.7259 | 0.2915 | 250 | 11.7359 |
| 11.7248 | 0.3499 | 300 | 11.7337 |
| 11.7234 | 0.4082 | 350 | 11.7331 |
| 11.7217 | 0.4665 | 400 | 11.7315 |
| 11.7236 | 0.5248 | 450 | 11.7313 |
| 11.7218 | 0.5831 | 500 | 11.7310 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1