|
--- |
|
license: llama3 |
|
base_model: meta-llama/Meta-Llama-3-8B-Instruct |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: MSc_llama3_finetuned_model_secondData |
|
results: [] |
|
library_name: peft |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# MSc_llama3_finetuned_model_secondData |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7658 |
|
|
|
## 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 |
|
- load_in_4bit: True |
|
- load_in_8bit: False |
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- training_steps: 250 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.7986 | 1.36 | 10 | 3.3486 | |
|
| 2.781 | 2.71 | 20 | 1.9851 | |
|
| 1.6096 | 4.07 | 30 | 1.3075 | |
|
| 1.2107 | 5.42 | 40 | 1.1210 | |
|
| 1.0597 | 6.78 | 50 | 1.0222 | |
|
| 0.9672 | 8.14 | 60 | 0.9562 | |
|
| 0.8924 | 9.49 | 70 | 0.9131 | |
|
| 0.8189 | 10.85 | 80 | 0.8582 | |
|
| 0.7393 | 12.2 | 90 | 0.7907 | |
|
| 0.6355 | 13.56 | 100 | 0.7136 | |
|
| 0.5683 | 14.92 | 110 | 0.7013 | |
|
| 0.533 | 16.27 | 120 | 0.7011 | |
|
| 0.5155 | 17.63 | 130 | 0.7049 | |
|
| 0.4965 | 18.98 | 140 | 0.7194 | |
|
| 0.4826 | 20.34 | 150 | 0.7222 | |
|
| 0.4617 | 21.69 | 160 | 0.7294 | |
|
| 0.453 | 23.05 | 170 | 0.7347 | |
|
| 0.439 | 24.41 | 180 | 0.7418 | |
|
| 0.4333 | 25.76 | 190 | 0.7473 | |
|
| 0.4261 | 27.12 | 200 | 0.7600 | |
|
| 0.4238 | 28.47 | 210 | 0.7580 | |
|
| 0.4163 | 29.83 | 220 | 0.7646 | |
|
| 0.4158 | 31.19 | 230 | 0.7659 | |
|
| 0.4137 | 32.54 | 240 | 0.7662 | |
|
| 0.4131 | 33.9 | 250 | 0.7658 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.4.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.15.2 |
|
|