metadata
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
model-index:
- name: V0404MP4
results: []
V0404MP4
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1140
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 20
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.1408 | 0.09 | 10 | 2.5415 |
| 5.4886 | 0.18 | 20 | 2.4963 |
| 4.5457 | 0.27 | 30 | 2.4110 |
| 4.1074 | 0.36 | 40 | 2.3242 |
| 3.5825 | 0.45 | 50 | 2.2528 |
| 3.1612 | 0.54 | 60 | 2.2006 |
| 2.8782 | 0.63 | 70 | 2.1606 |
| 2.5962 | 0.73 | 80 | 2.1360 |
| 2.7051 | 0.82 | 90 | 2.1230 |
| 2.5853 | 0.91 | 100 | 2.1162 |
| 2.6212 | 1.0 | 110 | 2.1140 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1