metadata
library_name: peft
license: apache-2.0
base_model: EleutherAI/pythia-410m-deduped
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3a627ce5-f2f1-4a24-adc3-ed73d41a9ac5
results: []
3a627ce5-f2f1-4a24-adc3-ed73d41a9ac5
This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8325
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: 0.000217
- train_batch_size: 4
- eval_batch_size: 4
- seed: 170
- 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 | 0.0005 | 1 | 4.2542 |
| 2.683 | 0.0239 | 50 | 1.3939 |
| 2.8237 | 0.0478 | 100 | 1.3520 |
| 2.5402 | 0.0717 | 150 | 1.2483 |
| 2.8376 | 0.0956 | 200 | 1.1818 |
| 2.4192 | 0.1194 | 250 | 1.1315 |
| 2.2251 | 0.1433 | 300 | 0.9749 |
| 2.3268 | 0.1672 | 350 | 0.9435 |
| 2.1456 | 0.1911 | 400 | 0.8851 |
| 2.0351 | 0.2150 | 450 | 0.8365 |
| 2.0542 | 0.2389 | 500 | 0.8325 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1