TinyJensen-1.1B
This model is a fine-tuned version of jan-hq/LlamaCorn-1.1B-Chat on the jan-hq/systemchat_binarized and the jan-hq/youtube_transcripts_qa datasets. It achieves the following results on the evaluation set:
- Loss: 0.8390
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: 7e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7614 | 1.0 | 178 | 0.7861 |
| 0.5033 | 2.0 | 356 | 0.7810 |
| 0.3561 | 3.0 | 534 | 0.8390 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0