logs
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7854
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: 8
- 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: cosine
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9083 | 0.16 | 100 | 0.9578 |
0.7997 | 0.32 | 200 | 0.9078 |
0.7535 | 0.48 | 300 | 0.8746 |
0.7232 | 0.64 | 400 | 0.8580 |
0.6994 | 0.8 | 500 | 0.8348 |
0.6882 | 0.96 | 600 | 0.8228 |
0.6433 | 1.12 | 700 | 0.8008 |
0.5995 | 1.28 | 800 | 0.7912 |
0.5908 | 1.44 | 900 | 0.7864 |
0.5902 | 1.6 | 1000 | 0.7836 |
0.5671 | 1.76 | 1100 | 0.7850 |
0.5749 | 1.92 | 1200 | 0.7854 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 2
Model tree for nhatminh/TinyLLama-Chat-CoT
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Adapter
this model