roberta-cbl-Reflections-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current

This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6912
• Accuracy: 0.8883
• Precision: 0.0
• Recall: 0.0
• F1: 0.0

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: 0.0009958025071527669
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.7589	1.0	243	0.8676	0.1117	0.1117	1.0	0.2009
0.7949	2.0	486	0.9892	0.1117	0.1117	1.0	0.2009
0.7443	3.0	729	0.6907	0.8883	0.0	0.0	0.0
0.765	4.0	972	0.7383	0.1117	0.1117	1.0	0.2009
0.7549	5.0	1215	0.6875	0.8883	0.0	0.0	0.0
0.7383	6.0	1458	0.6875	0.8883	0.0	0.0	0.0
0.748	7.0	1701	0.6875	0.8883	0.0	0.0	0.0
0.7502	8.0	1944	0.7498	0.1117	0.1117	1.0	0.2009
0.7406	9.0	2187	0.6895	0.8883	0.0	0.0	0.0
0.725	10.0	2430	0.6979	0.1117	0.1117	1.0	0.2009
0.7159	11.0	2673	0.7053	0.1117	0.1117	1.0	0.2009
0.7222	12.0	2916	0.6876	0.8883	0.0	0.0	0.0
0.7139	13.0	3159	0.7088	0.1117	0.1117	1.0	0.2009
0.7053	14.0	3402	0.6971	0.1117	0.1117	1.0	0.2009
0.7206	15.0	3645	0.6880	0.8883	0.0	0.0	0.0
0.7108	16.0	3888	0.6886	0.8883	0.0	0.0	0.0
0.7075	17.0	4131	0.6954	0.8883	0.0	0.0	0.0
0.7035	18.0	4374	0.6885	0.8883	0.0	0.0	0.0
0.696	19.0	4617	0.6909	0.8883	0.0	0.0	0.0
0.6996	20.0	4860	0.6912	0.8883	0.0	0.0	0.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 2.21.0
• Tokenizers 0.21.0