text_entailment_anli

This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4436
• Accuracy: 0.8373

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: 90
• eval_batch_size: 90
• seed: 42
• optimizer: Use OptimizerNames.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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8984	0.1589	200	0.7369	0.6892
0.6427	0.3177	400	0.5919	0.7621
0.5597	0.4766	600	0.5397	0.7810
0.5361	0.6354	800	0.5033	0.7983
0.5291	0.7943	1000	0.5028	0.7982
0.5042	0.9531	1200	0.4763	0.8158
0.4036	1.1120	1400	0.4849	0.8184
0.4082	1.2708	1600	0.4690	0.8253
0.4241	1.4297	1800	0.4604	0.8282
0.3989	1.5886	2000	0.4544	0.8300
0.3932	1.7474	2200	0.4628	0.8267
0.3881	1.9063	2400	0.4436	0.8373
0.3366	2.0651	2600	0.4664	0.8346
0.3091	2.2240	2800	0.4624	0.8377
0.3125	2.3828	3000	0.4536	0.8437

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0