metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: neural-matia-ft
results: []
neural-matia-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8946
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.4598 | 0.93 | 7 | 3.2557 |
2.9593 | 2.0 | 15 | 3.1634 |
3.2911 | 2.93 | 22 | 3.0877 |
2.8107 | 4.0 | 30 | 3.0155 |
3.1487 | 4.93 | 37 | 2.9706 |
2.7215 | 6.0 | 45 | 2.9352 |
3.0814 | 6.93 | 52 | 2.9147 |
2.6827 | 8.0 | 60 | 2.9008 |
3.0544 | 8.93 | 67 | 2.8953 |
2.3489 | 9.33 | 70 | 2.8946 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2