metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
- generator
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: humor_classification_mistral
results: []
humor_classification_mistral
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.5774
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.353 | 0.1923 | 10 | 1.1693 |
| 1.1391 | 0.3846 | 20 | 1.0883 |
| 1.0853 | 0.5769 | 30 | 1.0559 |
| 1.0487 | 0.7692 | 40 | 1.0024 |
| 0.8044 | 0.9615 | 50 | 0.6411 |
| 0.639 | 1.1538 | 60 | 0.6102 |
| 0.5972 | 1.3462 | 70 | 0.5955 |
| 0.584 | 1.5385 | 80 | 0.5854 |
| 0.5802 | 1.7308 | 90 | 0.5794 |
| 0.573 | 1.9231 | 100 | 0.5774 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1