SChem5Labels-google-t5-v1_1-large-intra_model-frequency-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: 1.3184

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
20.7337	1.0	25	23.6105
19.8181	2.0	50	21.7021
18.5121	3.0	75	18.6451
16.2008	4.0	100	12.8515
14.7585	5.0	125	10.1513
11.4985	6.0	150	9.3063
10.0012	7.0	175	9.0999
8.6447	8.0	200	8.8536
8.3766	9.0	225	8.7377
8.1231	10.0	250	8.6065
8.0504	11.0	275	8.4953
8.0051	12.0	300	8.3466
7.7615	13.0	325	8.1101
7.6344	14.0	350	7.8434
7.3869	15.0	375	7.6118
7.3158	16.0	400	7.4364
7.1667	17.0	425	7.3245
6.988	18.0	450	7.2732
7.0234	19.0	475	7.2125
6.9602	20.0	500	7.1699
6.8268	21.0	525	7.1251
6.8999	22.0	550	7.0695
6.3358	23.0	575	0.6967
0.86	24.0	600	0.6708
0.7148	25.0	625	0.6347
0.674	26.0	650	0.6297
0.6683	27.0	675	0.6234
0.6711	28.0	700	0.6214
0.6773	29.0	725	0.6170
0.6596	30.0	750	0.6162
0.6812	31.0	775	0.6207
0.6813	32.0	800	0.6121
0.6655	33.0	825	0.6147
0.653	34.0	850	0.6112
0.651	35.0	875	0.6082
0.6659	36.0	900	0.6075
0.6639	37.0	925	0.6023
0.6529	38.0	950	0.5998
0.6434	39.0	975	0.6023
0.645	40.0	1000	0.5976
0.64	41.0	1025	0.5987
0.6423	42.0	1050	0.5971
0.6439	43.0	1075	0.5940
0.6472	44.0	1100	0.5946
0.6459	45.0	1125	0.5965
0.6229	46.0	1150	0.5940
0.6414	47.0	1175	0.6111
0.6215	48.0	1200	0.5910
0.6375	49.0	1225	0.5928
0.6324	50.0	1250	0.6103
0.6212	51.0	1275	0.6075
0.6406	52.0	1300	0.5869
0.631	53.0	1325	0.5866
0.6227	54.0	1350	0.5833
0.6255	55.0	1375	0.5837
0.633	56.0	1400	0.5833
0.6224	57.0	1425	0.5822
0.628	58.0	1450	0.5858
0.62	59.0	1475	0.5827
0.6211	60.0	1500	0.5834
0.6236	61.0	1525	0.5794
0.6136	62.0	1550	0.5820
0.6132	63.0	1575	0.5800
0.6098	64.0	1600	0.5788
0.6167	65.0	1625	0.5785
0.6271	66.0	1650	0.5794
0.615	67.0	1675	0.5764
0.6143	68.0	1700	0.5789
0.6085	69.0	1725	0.5756
0.611	70.0	1750	0.5740
0.6161	71.0	1775	0.5730
0.5999	72.0	1800	0.5738
0.6194	73.0	1825	0.5753
0.6221	74.0	1850	0.5731
0.6061	75.0	1875	0.5738
0.6038	76.0	1900	0.5745

Framework versions

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