metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: microsoft/Phi-3-mini-4k-instruct
datasets:
- generator
model-index:
- name: cls_sentiment_phi3_v1
results: []
cls_sentiment_phi3_v1
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.7122
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9066 | 0.2083 | 50 | 0.9011 |
0.854 | 0.4167 | 100 | 0.8419 |
0.787 | 0.625 | 150 | 0.8062 |
0.7476 | 0.8333 | 200 | 0.7764 |
0.7141 | 1.0417 | 250 | 0.7636 |
0.6989 | 1.25 | 300 | 0.7528 |
0.6482 | 1.4583 | 350 | 0.7397 |
0.6537 | 1.6667 | 400 | 0.7207 |
0.6526 | 1.875 | 450 | 0.7122 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1