metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: mistral_texmin
results: []
mistral_texmin
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0292
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6494 | 0.62 | 20 | 0.4569 |
| 0.3477 | 1.25 | 40 | 0.1761 |
| 0.1239 | 1.88 | 60 | 0.0429 |
| 0.0443 | 2.5 | 80 | 0.0345 |
| 0.034 | 3.12 | 100 | 0.0292 |
Framework versions
- PEFT 0.7.0
- Transformers 4.36.0
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0