metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: >-
SChem5Labels-mistralai-Mistral-7B-v0.1-intra-frequency-model-pairwise-mse-cycle1
results: []
SChem5Labels-mistralai-Mistral-7B-v0.1-intra-frequency-model-pairwise-mse-cycle1
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4592
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0658 | 0.02 | 69 | 1.0451 |
| 0.8013 | 1.02 | 138 | 0.7708 |
| 0.5397 | 2.02 | 207 | 0.5880 |
| 0.4436 | 3.02 | 276 | 0.4895 |
| 0.3979 | 4.02 | 345 | 0.4425 |
| 0.3844 | 5.02 | 414 | 0.4116 |
| 0.3485 | 6.02 | 483 | 0.4046 |
| 0.3338 | 7.02 | 552 | 0.3989 |
| 0.3093 | 8.02 | 621 | 0.3904 |
| 0.3005 | 9.02 | 690 | 0.4010 |
| 0.271 | 10.02 | 759 | 0.3991 |
| 0.2627 | 11.02 | 828 | 0.4491 |
| 0.2217 | 12.02 | 897 | 0.4592 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0