metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: tiiuae/falcon-7b-instruct
model-index:
- name: alpaca-code-java
results: []
alpaca-code-java
This model is a fine-tuned version of tiiuae/falcon-7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0793
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: 2e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1092 | 0.8451 | 30 | 1.1258 |
| 1.0983 | 1.6901 | 60 | 1.0906 |
| 1.0562 | 2.5352 | 90 | 1.0793 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1