metadata
license: llama2
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Llama-2-7b-hf
model-index:
- name: llama_domar_finetune_e1
results: []
llama_domar_finetune_e1
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5880
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5895 | 0.2 | 50 | 0.6149 |
| 0.5736 | 0.4 | 100 | 0.6047 |
| 0.566 | 0.6 | 150 | 0.6001 |
| 0.5885 | 0.79 | 200 | 0.5974 |
| 0.5662 | 0.99 | 250 | 0.5966 |
| 0.515 | 1.19 | 300 | 0.5953 |
| 0.5473 | 1.39 | 350 | 0.5945 |
| 0.5126 | 1.59 | 400 | 0.5926 |
| 0.5027 | 1.79 | 450 | 0.5920 |
| 0.555 | 1.99 | 500 | 0.5902 |
| 0.4932 | 2.19 | 550 | 0.5912 |
| 0.5849 | 2.38 | 600 | 0.5899 |
| 0.544 | 2.58 | 650 | 0.5897 |
| 0.5308 | 2.78 | 700 | 0.5887 |
| 0.4975 | 2.98 | 750 | 0.5886 |
| 0.5555 | 3.18 | 800 | 0.5881 |
| 0.4924 | 3.38 | 850 | 0.5885 |
| 0.5424 | 3.58 | 900 | 0.5886 |
| 0.5217 | 3.78 | 950 | 0.5881 |
| 0.5179 | 3.97 | 1000 | 0.5881 |
| 0.5296 | 4.17 | 1050 | 0.5881 |
| 0.489 | 4.37 | 1100 | 0.5880 |
| 0.5308 | 4.57 | 1150 | 0.5880 |
| 0.4585 | 4.77 | 1200 | 0.5881 |
| 0.595 | 4.97 | 1250 | 0.5880 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2