out
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: 1.4144
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: 6e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 300
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.6699 | 0.02 | 20 | 1.5921 |
1.3657 | 0.04 | 40 | 1.5729 |
1.5918 | 0.07 | 60 | 1.5610 |
1.6343 | 0.09 | 80 | 1.5550 |
1.5015 | 0.11 | 100 | 1.5456 |
1.5233 | 0.13 | 120 | 1.5392 |
1.5025 | 0.15 | 140 | 1.5314 |
1.6424 | 0.18 | 160 | 1.5275 |
1.6267 | 0.2 | 180 | 1.5219 |
1.4698 | 0.22 | 200 | 1.5174 |
1.4297 | 0.24 | 220 | 1.5131 |
1.4826 | 0.26 | 240 | 1.5065 |
1.3671 | 0.29 | 260 | 1.4998 |
1.3661 | 0.31 | 280 | 1.4971 |
1.3012 | 0.33 | 300 | 1.4908 |
1.7249 | 0.35 | 320 | 1.4869 |
1.1596 | 0.37 | 340 | 1.4837 |
1.3188 | 0.4 | 360 | 1.4806 |
1.5087 | 0.42 | 380 | 1.4785 |
1.6028 | 0.44 | 400 | 1.4739 |
1.4167 | 0.46 | 420 | 1.4715 |
1.4823 | 0.48 | 440 | 1.4666 |
1.5418 | 0.51 | 460 | 1.4637 |
1.6369 | 0.53 | 480 | 1.4619 |
1.5098 | 0.55 | 500 | 1.4604 |
1.5404 | 0.57 | 520 | 1.4586 |
1.4594 | 0.6 | 540 | 1.4539 |
1.6358 | 0.62 | 560 | 1.4516 |
1.5025 | 0.64 | 580 | 1.4481 |
1.5119 | 0.66 | 600 | 1.4455 |
1.4617 | 0.68 | 620 | 1.4444 |
1.5281 | 0.71 | 640 | 1.4422 |
1.3506 | 0.73 | 660 | 1.4400 |
1.4467 | 0.75 | 680 | 1.4379 |
1.3382 | 0.77 | 700 | 1.4393 |
1.4894 | 0.79 | 720 | 1.4361 |
1.496 | 0.82 | 740 | 1.4329 |
1.516 | 0.84 | 760 | 1.4314 |
1.4118 | 0.86 | 780 | 1.4303 |
1.5408 | 0.88 | 800 | 1.4259 |
1.5307 | 0.9 | 820 | 1.4254 |
1.5376 | 0.93 | 840 | 1.4227 |
1.4129 | 0.95 | 860 | 1.4190 |
1.7808 | 0.97 | 880 | 1.4154 |
1.3279 | 0.99 | 900 | 1.4144 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.