metadata
license: mit
base_model: microsoft/phi-2
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: laft_lug_phi
results: []
laft_lug_phi
This model is a fine-tuned version of microsoft/phi-2 on the mozilla-foundation/common_voice_11_0 lg dataset. It achieves the following results on the evaluation set:
- Loss: 2.6248
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 2000
- num_epochs: 6.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4008 | 1.0 | 1549 | 2.4035 |
| 2.214 | 2.0 | 3098 | 2.2156 |
| 2.0438 | 3.0 | 4647 | 2.1054 |
| 1.5148 | 4.0 | 6196 | 2.0929 |
| 1.1932 | 5.0 | 7745 | 2.3810 |
| 0.5055 | 6.0 | 9294 | 2.6248 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1