owanr/SChem5Labels-google-t5-v1_1-large-intra_model-sorted-model_annots_str2

SChem5Labels-google-t5-v1_1-large-intra_model-sorted-human_annots_str

This model is a fine-tuned version of google/t5-v1_1-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6221

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: 0.0001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss
20.7839	1.0	25	25.3269
20.0699	2.0	50	21.6598
19.1726	3.0	75	21.6652
17.222	4.0	100	15.0207
14.7785	5.0	125	10.0582
12.0504	6.0	150	9.4216
11.1003	7.0	175	9.0795
9.259	8.0	200	8.7145
8.4364	9.0	225	8.5969
8.0676	10.0	250	8.5227
7.975	11.0	275	8.4316
7.9747	12.0	300	8.3585
7.8189	13.0	325	8.2247
7.6989	14.0	350	7.9381
7.3673	15.0	375	7.5837
7.234	16.0	400	7.3654
7.0686	17.0	425	7.2360
6.8718	18.0	450	7.1579
6.8965	19.0	475	7.1054
6.7995	20.0	500	7.0521
6.6533	21.0	525	6.9925
6.5043	22.0	550	6.8905
1.2868	23.0	575	0.6607
0.6465	24.0	600	0.5685
0.6195	25.0	625	0.5598
0.5945	26.0	650	0.5600
0.594	27.0	675	0.5565
0.5851	28.0	700	0.5554
0.5986	29.0	725	0.5510
0.5854	30.0	750	0.5502
0.6018	31.0	775	0.5525
0.5922	32.0	800	0.5482
0.5871	33.0	825	0.5504
0.586	34.0	850	0.5498
0.5847	35.0	875	0.5498
0.5954	36.0	900	0.5502
0.5892	37.0	925	0.5470
0.5853	38.0	950	0.5510
0.5892	39.0	975	0.5483
0.5879	40.0	1000	0.5491
0.5768	41.0	1025	0.5488
0.5886	42.0	1050	0.5530

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.6.1
• Tokenizers 0.14.1