metadata
base_model: meta-llama/Meta-Llama-3-8B
library_name: peft
license: llama3
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: MedLLAMA
results: []
MedLLAMA
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8819
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1988 | 0.6000 | 2435 | 0.9183 |
| 0.7397 | 1.2001 | 4870 | 0.9037 |
| 0.646 | 1.8001 | 7305 | 0.8777 |
| 0.8205 | 2.4002 | 9740 | 0.8819 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.19.1
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- _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: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
Framework versions
- PEFT 0.6.2