metadata
library_name: peft
license: mit
base_model: microsoft/phi-1_5
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 305f2bf2-c5bb-4790-87ae-c89a78d932a9
results: []
305f2bf2-c5bb-4790-87ae-c89a78d932a9
This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4900
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: 0.000213
- train_batch_size: 4
- eval_batch_size: 4
- seed: 130
- 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 | 0.0001 | 1 | 1.7984 |
| 1.6398 | 0.0042 | 50 | 1.5793 |
| 1.5217 | 0.0084 | 100 | 1.5389 |
| 1.5051 | 0.0127 | 150 | 1.5195 |
| 1.4835 | 0.0169 | 200 | 1.5095 |
| 1.505 | 0.0211 | 250 | 1.5027 |
| 1.4284 | 0.0253 | 300 | 1.4979 |
| 1.4311 | 0.0296 | 350 | 1.4950 |
| 1.4831 | 0.0338 | 400 | 1.4912 |
| 1.4846 | 0.0380 | 450 | 1.4904 |
| 1.5623 | 0.0422 | 500 | 1.4900 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1