litbank-coref-mem-base

This model is a fine-tuned version of eddieman78/onto-coref-mem-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0220

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	339	0.0255
0.0407	2.0	678	0.0221
0.0279	3.0	1017	0.0206
0.0279	4.0	1356	0.0197
0.0232	5.0	1695	0.0191
0.0212	6.0	2034	0.0189
0.0212	7.0	2373	0.0184
0.0193	8.0	2712	0.0184
0.0176	9.0	3051	0.0181
0.0176	10.0	3390	0.0187
0.0164	11.0	3729	0.0182
0.0155	12.0	4068	0.0183
0.0155	13.0	4407	0.0182
0.0143	14.0	4746	0.0185
0.0134	15.0	5085	0.0184
0.0134	16.0	5424	0.0187
0.0127	17.0	5763	0.0188
0.0121	18.0	6102	0.0186
0.0121	19.0	6441	0.0188
0.0118	20.0	6780	0.0192
0.0111	21.0	7119	0.0192
0.0111	22.0	7458	0.0191
0.0108	23.0	7797	0.0197
0.01	24.0	8136	0.0199
0.01	25.0	8475	0.0202
0.0098	26.0	8814	0.0200
0.0093	27.0	9153	0.0198
0.0093	28.0	9492	0.0200
0.0093	29.0	9831	0.0208
0.0089	30.0	10170	0.0203
0.0087	31.0	10509	0.0214
0.0087	32.0	10848	0.0203
0.0087	33.0	11187	0.0208
0.008	34.0	11526	0.0213
0.008	35.0	11865	0.0212
0.0079	36.0	12204	0.0215
0.0079	37.0	12543	0.0216
0.0079	38.0	12882	0.0217
0.0077	39.0	13221	0.0217
0.0075	40.0	13560	0.0219
0.0075	41.0	13899	0.0221
0.0074	42.0	14238	0.0218
0.0072	43.0	14577	0.0220
0.0072	44.0	14916	0.0220
0.0071	45.0	15255	0.0220
0.0072	46.0	15594	0.0220
0.0072	47.0	15933	0.0220
0.0071	48.0	16272	0.0220
0.0072	49.0	16611	0.0220
0.0072	50.0	16950	0.0220

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.17.0
• Tokenizers 0.15.2