SChem5Labels-google-t5-v1_1-large-inter_model-dataset-frequency-model_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: 0.8911

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
19.7803	1.0	25	23.9207
18.7939	2.0	50	19.6774
17.9347	3.0	75	14.1935
14.9562	4.0	100	11.5018
12.9185	5.0	125	9.7946
11.0104	6.0	150	9.0519
10.1946	7.0	175	8.9336
8.6775	8.0	200	8.6692
8.2895	9.0	225	8.4222
8.067	10.0	250	8.2689
7.7922	11.0	275	8.1862
7.702	12.0	300	8.0916
7.5801	13.0	325	7.9765
7.4381	14.0	350	7.7605
7.4223	15.0	375	7.4846
7.0379	16.0	400	7.3010
6.9279	17.0	425	7.1606
6.7912	18.0	450	7.0390
6.7047	19.0	475	6.9686
6.5986	20.0	500	6.9092
6.5577	21.0	525	6.8427
6.4589	22.0	550	6.7866
6.3207	23.0	575	6.7021
1.1695	24.0	600	0.7696
0.7697	25.0	625	0.6522
0.6978	26.0	650	0.6488
0.6832	27.0	675	0.6470
0.7033	28.0	700	0.6322
0.692	29.0	725	0.6369
0.6703	30.0	750	0.6372
0.6781	31.0	775	0.6364
0.677	32.0	800	0.6252
0.6632	33.0	825	0.6301
0.6684	34.0	850	0.6254
0.6823	35.0	875	0.6312
0.6665	36.0	900	0.6328
0.6583	37.0	925	0.6256

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1