metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: teknium/OpenHermes-2.5-Mistral-7B
model-index:
- name: results
results: []
results
This model is a fine-tuned version of teknium/OpenHermes-2.5-Mistral-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4192
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3147 | 0.17 | 25 | 1.1471 |
| 0.6178 | 0.34 | 50 | 0.5957 |
| 0.4326 | 0.51 | 75 | 0.4810 |
| 0.3723 | 0.67 | 100 | 0.4367 |
| 0.348 | 0.84 | 125 | 0.4192 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
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
Framework versions
- PEFT 0.6.2