metadata
license: apache-2.0
base_model: amazon/MistralLite
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of amazon/MistralLite on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5882
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7183 | 0.12 | 300 | 2.9336 |
| 2.2065 | 0.23 | 600 | 2.2421 |
| 2.037 | 0.35 | 900 | 2.9672 |
| 1.7939 | 0.46 | 1200 | 1.0765 |
| 1.5232 | 0.58 | 1500 | 1.8086 |
| 1.6083 | 0.7 | 1800 | 1.5882 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.15.0