metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Phi-3.5-MultiCap-tool-new
results: []
Phi-3.5-MultiCap-tool-new
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4307
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 |
|---|---|---|---|
| 0.6201 | 0.2256 | 50 | 0.6052 |
| 0.4722 | 0.4512 | 100 | 0.4734 |
| 0.4609 | 0.6768 | 150 | 0.4540 |
| 0.4803 | 0.9024 | 200 | 0.4442 |
| 0.4207 | 1.1280 | 250 | 0.4381 |
| 0.4162 | 1.3536 | 300 | 0.4343 |
| 0.3933 | 1.5792 | 350 | 0.4320 |
| 0.4517 | 1.8049 | 400 | 0.4307 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 3.0.0
- Tokenizers 0.19.1