metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: ibm-granite/granite-8b-code-instruct
datasets:
- generator
model-index:
- name: granite-8b-code-instruct-spider
results: []
granite-8b-code-instruct-spider
This model is a fine-tuned version of ibm-granite/granite-8b-code-instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.8823
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: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1877 | 0.1 | 100 | 0.6620 |
| 0.0784 | 0.2 | 200 | 0.6879 |
| 0.0552 | 0.3 | 300 | 0.7506 |
| 0.0607 | 0.4 | 400 | 0.8319 |
| 0.049 | 0.51 | 500 | 0.8430 |
| 0.0485 | 0.61 | 600 | 0.8774 |
| 0.0448 | 0.71 | 700 | 0.8839 |
| 0.0478 | 0.81 | 800 | 0.8807 |
| 0.0472 | 0.91 | 900 | 0.8823 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2