metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.6
model-index:
- name: shawgpt-ft
results: []
shawgpt-ft
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v0.6 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0521
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.6937 | 0.92 | 3 | 3.2909 |
| 3.6497 | 1.85 | 6 | 3.2640 |
| 3.6197 | 2.77 | 9 | 3.2310 |
| 2.6805 | 4.0 | 13 | 3.1818 |
| 3.5328 | 4.92 | 16 | 3.1453 |
| 3.48 | 5.85 | 19 | 3.1126 |
| 3.4458 | 6.77 | 22 | 3.0858 |
| 2.547 | 8.0 | 26 | 3.0614 |
| 3.3807 | 8.92 | 29 | 3.0531 |
| 2.2947 | 9.23 | 30 | 3.0521 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2