<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
phi-1_5-finetuned-model-classification
This model is a fine-tuned version of microsoft/phi-1_5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.4343
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: 0.0004
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6171 | 4.0 | 250 | 2.7650 |
| 2.3312 | 8.0 | 500 | 2.7894 |
| 1.9386 | 12.0 | 750 | 2.9510 |
| 1.4978 | 16.0 | 1000 | 3.2375 |
| 1.0947 | 20.0 | 1250 | 3.7212 |
| 0.8685 | 24.0 | 1500 | 4.1141 |
| 0.7308 | 28.0 | 1750 | 4.3801 |
| 0.6995 | 32.0 | 2000 | 4.4343 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
