metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: ckpts/llama2-7b-viettel_v3_2epoch
results: []
ckpts/llama2-7b-viettel_v3_2epoch
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4619
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- total_eval_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5149 | 0.25 | 200 | 0.5149 |
| 0.4977 | 0.51 | 400 | 0.4941 |
| 0.4727 | 0.76 | 600 | 0.4824 |
| 0.4375 | 1.02 | 800 | 0.4730 |
| 0.4455 | 1.27 | 1000 | 0.4682 |
| 0.4539 | 1.53 | 1200 | 0.4638 |
| 0.4411 | 1.78 | 1400 | 0.4619 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.14.0