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-dataset-frequency-human-pairwise-mse-cycle1
results: []
SChem5Labels-mistralai-Mistral-7B-v0.1-intra-dataset-frequency-human-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: 0.4274
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 |
|---|---|---|---|
| 1.0662 | 0.02 | 69 | 1.0445 |
| 0.8086 | 1.02 | 138 | 0.7814 |
| 0.5488 | 2.02 | 207 | 0.5977 |
| 0.4417 | 3.02 | 276 | 0.4975 |
| 0.3974 | 4.02 | 345 | 0.4499 |
| 0.3802 | 5.02 | 414 | 0.4198 |
| 0.3573 | 6.02 | 483 | 0.3998 |
| 0.3355 | 7.02 | 552 | 0.3874 |
| 0.3116 | 8.02 | 621 | 0.3949 |
| 0.3116 | 9.02 | 690 | 0.3912 |
| 0.2769 | 10.02 | 759 | 0.4027 |
| 0.2649 | 11.02 | 828 | 0.4274 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0