sanchit-gandhi/Mistral-7B-v0.1-6-layer
This model is a fine-tuned version of sanchit-gandhi/Mistral-7B-v0.1-6-layer on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 2.1183
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 512
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8342 | 1.0 | 273 | 4.7379 |
| 3.3301 | 2.0 | 546 | 3.2846 |
| 2.4158 | 3.0 | 819 | 2.4134 |
| 2.1322 | 4.0 | 1092 | 2.1637 |
| 2.0369 | 5.0 | 1365 | 2.1183 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.0
- Downloads last month
- 9