scripts-two-coref-mem-base

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

• Loss: 0.0012

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.0035	1.0	1807	0.0028
0.0029	2.0	3614	0.0025
0.0025	3.0	5421	0.0023
0.0021	4.0	7228	0.0021
0.0017	5.0	9035	0.0020
0.0015	6.0	10842	0.0017
0.0014	7.0	12649	0.0017
0.0015	8.0	14456	0.0016
0.0013	9.0	16263	0.0014
0.0013	10.0	18070	0.0014
0.0013	11.0	19877	0.0013
0.0014	12.0	21684	0.0013
0.0013	13.0	23491	0.0012
0.0013	14.0	25298	0.0012
0.0014	15.0	27105	0.0012

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.17.0
• Tokenizers 0.19.1