bart-large-mnli-aitools-11n

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

• Loss: 0.1504
• Accuracy: 0.9631

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	Accuracy
No log	0.05	50	0.5899	0.9171
No log	0.1	100	0.2924	0.9171
No log	0.15	150	0.1300	0.9171
No log	0.21	200	0.3631	0.9447
No log	0.26	250	0.1954	0.9493
No log	0.31	300	0.2654	0.9447
No log	0.36	350	0.3464	0.9401
No log	0.41	400	0.1400	0.9585
No log	0.46	450	0.1686	0.9631
0.311	0.51	500	0.2399	0.9447
0.311	0.56	550	0.2273	0.9585
0.311	0.62	600	0.0956	0.9770
0.311	0.67	650	0.1788	0.9309
0.311	0.72	700	0.1840	0.9447
0.311	0.77	750	0.1828	0.9631
0.311	0.82	800	0.0765	0.9770
0.311	0.87	850	0.1851	0.9585
0.311	0.92	900	0.0854	0.9724
0.311	0.97	950	0.0783	0.9724
0.2123	1.03	1000	0.1504	0.9631
0.2123	1.08	1050	0.2845	0.9585
0.2123	1.13	1100	0.2655	0.9585
0.2123	1.18	1150	0.1718	0.9585

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2