metadata
base_model: unsloth/tinyllama-chat-bnb-4bit
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- unsloth
- generated_from_trainer
model-index:
- name: outputs_tinyllama
results: []
outputs_tinyllama
This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0807
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: 8
- eval_batch_size: 16
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6584 | 0.9912 | 28 | 1.4045 |
| 1.4446 | 1.9823 | 56 | 1.1826 |
| 1.1341 | 2.9735 | 84 | 1.0892 |
| 1.1061 | 3.5398 | 100 | 1.0807 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1