metadata
license: mit
base_model: microsoft/Phi-3-mini-128k-instruct
tags:
- generated_from_trainer
model-index:
- name: CodePhi-3-mini-128k-instruct-APPS1.4k
results: []
CodePhi-3-mini-128k-instruct-APPS1.4k
This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6034
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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- 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: 1400
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5991 | 0.1429 | 200 | 0.6309 |
| 0.579 | 0.2857 | 400 | 0.6142 |
| 0.5665 | 0.4286 | 600 | 0.6070 |
| 0.545 | 0.5714 | 800 | 0.6044 |
| 0.5199 | 0.7143 | 1000 | 0.6035 |
| 0.5763 | 0.8571 | 1200 | 0.6035 |
| 0.5594 | 1.0 | 1400 | 0.6034 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1