metadata
base_model: microsoft/Phi-3.5-mini-instruct
library_name: peft
license: mit
metrics:
- rouge
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: grounded-ai-rag-3
results: []
grounded-ai-rag-3
This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4248
- Rouge1: 1.0
- Rouge2: 0.0
- Rougel: 1.0
- Rougelsum: 1.0
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-05
- 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: cosine
- lr_scheduler_warmup_steps: 15
- training_steps: 150
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.0354 | 5.0 | 5 | 1.7161 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.9393 | 10.0 | 10 | 1.5598 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.8098 | 15.0 | 15 | 1.3913 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.6939 | 20.0 | 20 | 1.2470 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.5662 | 25.0 | 25 | 1.0859 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.4027 | 30.0 | 30 | 0.9390 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.2595 | 35.0 | 35 | 0.8088 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.159 | 40.0 | 40 | 0.8187 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.1225 | 45.0 | 45 | 0.9043 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.0808 | 50.0 | 50 | 0.9985 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.0334 | 55.0 | 55 | 1.1227 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.0121 | 60.0 | 60 | 1.2501 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.0052 | 65.0 | 65 | 1.3779 | 1.0 | 0.0 | 1.0 | 1.0 |
| 0.0043 | 70.0 | 70 | 1.4248 | 1.0 | 0.0 | 1.0 | 1.0 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1