llama-sentiment-classifier-classic-fine-tuning

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4995

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.551	0.3915	500	1.6018
1.6264	0.7831	1000	1.5546
1.5287	1.1746	1500	1.5336
1.4458	1.5662	2000	1.5179
1.4449	1.9577	2500	1.5072
1.4057	2.3493	3000	1.5033
1.5532	2.7408	3500	1.4967
1.474	3.1323	4000	1.4997
1.3809	3.5239	4500	1.4990
1.3981	3.9154	5000	1.4937
1.311	4.3070	5500	1.4971
1.2245	4.6985	6000	1.4995

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1