metadata
license: apache-2.0
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
tags:
- generated_from_trainer
model-index:
- name: mixtral_54B_instruct_8k
results: []
mixtral_54B_instruct_8k
This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7899
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: 5e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5125 | 1.0 | 32 | 1.4529 |
| 0.9656 | 2.0 | 64 | 0.9357 |
| 0.7992 | 3.0 | 96 | 0.8070 |
| 0.7865 | 4.0 | 128 | 0.7899 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0