metadata
base_model: meta-llama/Meta-Llama-3-8B
datasets:
- generator
library_name: peft
license: llama3
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: RoBERTa_Llama3_dependent_V2
results: []
RoBERTa_Llama3_dependent_V2
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.3585
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9882 | 42 | 1.4093 |
| No log | 2.0 | 85 | 1.3646 |
| No log | 2.9882 | 127 | 1.3536 |
| No log | 4.0 | 170 | 1.3487 |
| No log | 4.9882 | 212 | 1.3485 |
| No log | 6.0 | 255 | 1.3498 |
| No log | 6.9882 | 297 | 1.3531 |
| No log | 8.0 | 340 | 1.3552 |
| No log | 8.9882 | 382 | 1.3572 |
| No log | 9.8824 | 420 | 1.3585 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1