logdataset1000samples3epochs_llama3-1-instruct_8bit

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the svenwey/LogDataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.1207
• Sacrebleu Score: 95.0186
• Logmetric Score: 96.8558

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu Score	Logmetric Score
0.1473	1.0	2035	0.1300	94.6100	96.6295
0.1207	2.0	4070	0.1329	94.9109	96.4886
0.113	3.0	6105	0.1207	95.0186	96.8558

Framework versions

• PEFT 0.12.0
• Transformers 4.45.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1