metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: tinyllama/tinyllama-1.1b-chat-v1.0
datasets:
- generator
model-index:
- name: tinyllama_instruct
results: []
tinyllama_instruct
This model is a fine-tuned version of tinyllama/tinyllama-1.1b-chat-v1.0 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.2777
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5934 | 0.0281 | 30 | 1.3952 |
| 1.4781 | 0.0561 | 60 | 1.2923 |
| 1.3692 | 0.0842 | 90 | 1.2777 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1