metadata
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2406
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2518 | 0.0530 | 100 | 1.3453 |
| 1.3137 | 0.1059 | 200 | 1.2820 |
| 1.2681 | 0.1589 | 300 | 1.2684 |
| 1.2611 | 0.2118 | 400 | 1.2625 |
| 1.2599 | 0.2648 | 500 | 1.2587 |
| 1.2709 | 0.3177 | 600 | 1.2561 |
| 1.2607 | 0.3707 | 700 | 1.2537 |
| 1.2502 | 0.4236 | 800 | 1.2515 |
| 1.2475 | 0.4766 | 900 | 1.2494 |
| 1.2479 | 0.5295 | 1000 | 1.2476 |
| 1.2535 | 0.5825 | 1100 | 1.2469 |
| 1.2546 | 0.6354 | 1200 | 1.2455 |
| 1.2498 | 0.6884 | 1300 | 1.2440 |
| 1.2445 | 0.7413 | 1400 | 1.2433 |
| 1.247 | 0.7943 | 1500 | 1.2423 |
| 1.2438 | 0.8472 | 1600 | 1.2418 |
| 1.2434 | 0.9002 | 1700 | 1.2413 |
| 1.2425 | 0.9531 | 1800 | 1.2406 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1