metadata
license: apache-2.0
base_model: tiiuae/falcon-7b
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- GAIR/lima
model-index:
- name: test
results: []
test
This model is a fine-tuned version of tiiuae/falcon-7b on the GAIR/lima dataset. It achieves the following results on the evaluation set:
- Loss: 2.4176
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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0635 | 0.91 | 5 | 1.9126 |
| 1.9282 | 2.0 | 11 | 1.8814 |
| 1.7541 | 2.91 | 16 | 2.2656 |
| 1.5669 | 4.0 | 22 | 2.2188 |
| 1.3975 | 4.91 | 27 | 2.2543 |
| 1.2431 | 6.0 | 33 | 2.3338 |
| 1.1081 | 6.91 | 38 | 2.3438 |
| 1.0212 | 8.0 | 44 | 2.4276 |
| 0.9554 | 8.91 | 49 | 2.4176 |
| 0.9463 | 9.09 | 50 | 2.4176 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2