metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral_Sparse_refined_web_relu_2024-03-10
results: []
Mistral_Sparse_refined_web_relu_2024-03-10
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: 2.5409
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: 1
- seed: 0
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 600
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.7862 | 0.0 | 25 | 8.7098 |
| 8.1838 | 0.01 | 50 | 8.1781 |
| 7.7537 | 0.01 | 75 | 7.8068 |
| 7.5371 | 0.02 | 100 | 7.6076 |
| 7.2146 | 0.02 | 125 | 7.1801 |
| 4.832 | 0.02 | 150 | 4.7717 |
| 3.7768 | 0.03 | 175 | 3.8167 |
| 3.2705 | 0.03 | 200 | 3.4268 |
| 3.0907 | 0.04 | 225 | 3.2364 |
| 2.9979 | 0.04 | 250 | 3.1210 |
| 2.8613 | 0.04 | 275 | 3.0444 |
| 2.8331 | 0.05 | 300 | 2.9912 |
| 2.7972 | 0.05 | 325 | 2.9533 |
| 2.6097 | 0.06 | 350 | 2.9186 |
| 2.7506 | 0.06 | 375 | 2.8954 |
| 2.7809 | 0.06 | 400 | 2.8744 |
| 2.7346 | 0.07 | 425 | 2.8555 |
| 2.6997 | 0.07 | 450 | 2.8420 |
| 2.5839 | 0.08 | 475 | 2.8263 |
| 2.6435 | 0.08 | 500 | 2.8170 |
| 2.7207 | 0.08 | 525 | 2.8085 |
| 2.6248 | 0.09 | 550 | 2.7985 |
| 2.7277 | 0.09 | 575 | 2.7876 |
| 2.5448 | 0.1 | 600 | 2.7807 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0