layai/syn-dataaug-youtube-context

context

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.7005
• Accuracy: 0.4548

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: 40
• eval_batch_size: 40
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 160
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7716	0.6479	500	3.7005	0.4548
0.3675	1.2958	1000	3.8487	0.4565
0.2102	1.9436	1500	3.9705	0.4568
0.1164	2.5915	2000	4.1546	0.4570

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1