relu_mistral_7b_refined_web_relu_2024-04-14
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6436
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 0
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 600
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
8.7888 | 0.0 | 25 | 8.6564 |
8.1778 | 0.01 | 50 | 8.0973 |
7.7512 | 0.01 | 75 | 7.7433 |
7.5335 | 0.02 | 100 | 7.5552 |
7.1808 | 0.02 | 125 | 7.0788 |
4.7889 | 0.02 | 150 | 4.6519 |
3.7653 | 0.03 | 175 | 3.6891 |
3.265 | 0.03 | 200 | 3.2900 |
3.0933 | 0.04 | 225 | 3.1086 |
2.9959 | 0.04 | 250 | 2.9870 |
2.8586 | 0.04 | 275 | 2.9095 |
2.8306 | 0.05 | 300 | 2.8576 |
2.7949 | 0.05 | 325 | 2.8202 |
2.6088 | 0.06 | 350 | 2.7864 |
2.7494 | 0.06 | 375 | 2.7613 |
2.7798 | 0.06 | 400 | 2.7390 |
2.733 | 0.07 | 425 | 2.7212 |
2.6986 | 0.07 | 450 | 2.7077 |
2.5827 | 0.08 | 475 | 2.6930 |
2.6429 | 0.08 | 500 | 2.6816 |
2.72 | 0.08 | 525 | 2.6721 |
2.6241 | 0.09 | 550 | 2.6629 |
2.7274 | 0.09 | 575 | 2.6540 |
2.5444 | 0.1 | 600 | 2.6489 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 11
Inference API (serverless) does not yet support model repos that contain custom code.
Model tree for thrunlab/relu_mistral_7b_refined_web_relu_2024-04-14
Base model
mistralai/Mistral-7B-v0.1