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-inter-frequency-model-cross-ent
results: []
SChem5Labels-mistralai-Mistral-7B-v0.1-inter-frequency-model-cross-ent
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: 0.4869
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 |
|---|---|---|---|
| 1.0106 | 0.02 | 69 | 0.9779 |
| 0.7159 | 1.02 | 138 | 0.6948 |
| 0.501 | 2.02 | 207 | 0.5356 |
| 0.4159 | 3.02 | 276 | 0.4473 |
| 0.3818 | 4.02 | 345 | 0.4104 |
| 0.359 | 5.02 | 414 | 0.4004 |
| 0.3514 | 6.02 | 483 | 0.3858 |
| 0.3326 | 7.02 | 552 | 0.3819 |
| 0.3099 | 8.02 | 621 | 0.3810 |
| 0.2878 | 9.02 | 690 | 0.4035 |
| 0.2635 | 10.02 | 759 | 0.4181 |
| 0.2274 | 11.02 | 828 | 0.4483 |
| 0.1877 | 12.02 | 897 | 0.4869 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0