ZeroShot-3.3.3-Mistral-7b-Multilanguage-1-epoch-3.2.0
/
.ipynb_checkpoints
/README_old-checkpoint.md
metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: ZeroShot-3.3.3-Mistral-7b-Multilanguage-1-epoch-3.2.0
results: []
ZeroShot-3.3.3-Mistral-7b-Multilanguage-1-epoch-3.2.0
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4078
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 201
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5561 | 0.1 | 20 | 0.8398 |
| 0.594 | 0.2 | 40 | 0.5099 |
| 0.4849 | 0.3 | 60 | 0.4661 |
| 0.4516 | 0.4 | 80 | 0.4328 |
| 0.4237 | 0.5 | 100 | 0.4192 |
| 0.4235 | 0.59 | 120 | 0.4142 |
| 0.4128 | 0.69 | 140 | 0.4110 |
| 0.4152 | 0.79 | 160 | 0.4090 |
| 0.4092 | 0.89 | 180 | 0.4080 |
| 0.41 | 0.99 | 200 | 0.4078 |
Framework versions
- PEFT 0.8.2
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.1