1e-5_bnoniid_layer1
This model is a fine-tuned version of /data/public_models/Meta-Llama-3-8B on the vicgalle/alpaca-gpt4 default dataset. It achieves the following results on the evaluation set:
- Loss: 1.0550
- Accuracy: 0.7204
- Bleu: 0.0
- Rougel: 0.5717
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: 8.78925141040004e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
Framework versions
- Transformers 4.46.2
- Pytorch 2.4.1+cu121
- Datasets 2.19.0
- Tokenizers 0.20.3
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for yyyjwang/1e-5_bnoniid_layer1
Base model
meta-llama/Meta-Llama-3-8BDataset used to train yyyjwang/1e-5_bnoniid_layer1
Evaluation results
- Accuracy on vicgalle/alpaca-gpt4 defaultself-reported0.720
- Bleu on vicgalle/alpaca-gpt4 defaultself-reported0.000