metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- generated_from_trainer
model-index:
- name: mistral-viggo-finetune
results: []
mistral-viggo-finetune
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4072
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4563 | 0.01 | 50 | 0.7277 |
| 0.5873 | 0.01 | 100 | 0.5276 |
| 0.4951 | 0.02 | 150 | 0.4817 |
| 0.4645 | 0.02 | 200 | 0.4664 |
| 0.4682 | 0.03 | 250 | 0.4541 |
| 0.4569 | 0.03 | 300 | 0.4447 |
| 0.4428 | 0.04 | 350 | 0.4362 |
| 0.4184 | 0.04 | 400 | 0.4326 |
| 0.4174 | 0.05 | 450 | 0.4280 |
| 0.4122 | 0.05 | 500 | 0.4242 |
| 0.4176 | 0.06 | 550 | 0.4228 |
| 0.4105 | 0.06 | 600 | 0.4175 |
| 0.4103 | 0.07 | 650 | 0.4154 |
| 0.4113 | 0.07 | 700 | 0.4133 |
| 0.3979 | 0.08 | 750 | 0.4118 |
| 0.3895 | 0.08 | 800 | 0.4109 |
| 0.4088 | 0.09 | 850 | 0.4092 |
| 0.399 | 0.09 | 900 | 0.4082 |
| 0.4001 | 0.1 | 950 | 0.4075 |
| 0.4067 | 0.1 | 1000 | 0.4072 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1