metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: mistral_sparse_80__graceful_reg_50_pt_2000
results: []
mistral_sparse_80__graceful_reg_50_pt_2000
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8040
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 16
- seed: 0
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- total_eval_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3491 | 0.12 | 50 | 1.1168 |
| 0.861 | 1.2 | 500 | 0.8770 |
| 0.7974 | 2.4 | 1000 | 0.8263 |
| 0.8279 | 3.6 | 1500 | 0.8116 |
| 0.7578 | 4.8 | 2000 | 0.8040 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0