metadata
base_model: microsoft/Phi-3.5-mini-instruct
datasets:
- generator
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Phi-3.5-MultiCap-tool-embedding-past
results: []
Phi-3.5-MultiCap-tool-embedding-past
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.7561
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1082 | 0.1524 | 50 | 1.1135 |
| 0.9647 | 0.3048 | 100 | 1.0051 |
| 0.9516 | 0.4571 | 150 | 0.9498 |
| 0.8882 | 0.6095 | 200 | 0.9027 |
| 0.9183 | 0.7619 | 250 | 0.8649 |
| 0.7923 | 0.9143 | 300 | 0.8355 |
| 0.8078 | 1.0667 | 350 | 0.8137 |
| 0.7677 | 1.2190 | 400 | 0.7969 |
| 0.765 | 1.3714 | 450 | 0.7822 |
| 0.812 | 1.5238 | 500 | 0.7720 |
| 0.7376 | 1.6762 | 550 | 0.7638 |
| 0.7617 | 1.8286 | 600 | 0.7586 |
| 0.7299 | 1.9810 | 650 | 0.7561 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1