meow
This model is a fine-tuned version of upstage/SOLAR-10.7B-Instruct-v1.0 on HuggingFaceH4/no_robots dataset. It achieves the following results on the evaluation set:
- Loss: 2.3831
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 128
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3864 | 0.11 | 2 | 2.3831 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0
Training procedure
Framework versions
- PEFT 0.6.1
- Downloads last month
- 0
Model tree for LoneStriker/meow-8.0bpw-h8-exl2
Base model
upstage/SOLAR-10.7B-v1.0
Finetuned
upstage/SOLAR-10.7B-Instruct-v1.0