metadata
library_name: peft
license: apache-2.0
base_model: EleutherAI/pythia-410m-deduped
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 462b79a5-6086-4314-b090-029009c90b2d
results: []
462b79a5-6086-4314-b090-029009c90b2d
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: 0.8018
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: 0.000202
- train_batch_size: 4
- eval_batch_size: 4
- seed: 20
- 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 | 4.2533 |
| 3.1402 | 0.0239 | 50 | 1.5783 |
| 2.985 | 0.0478 | 100 | 1.1787 |
| 2.6554 | 0.0717 | 150 | 1.1248 |
| 3.5819 | 0.0956 | 200 | 1.1990 |
| 2.4072 | 0.1194 | 250 | 1.1132 |
| 2.1323 | 0.1433 | 300 | 0.9466 |
| 2.3506 | 0.1672 | 350 | 0.8946 |
| 2.0516 | 0.1911 | 400 | 0.8264 |
| 1.9909 | 0.2150 | 450 | 0.8030 |
| 2.0245 | 0.2389 | 500 | 0.8018 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1