owanr/Sentiment-google-t5-v1_1-large-intra_model-shuffle-model_annots_str

Sentiment-google-t5-v1_1-large-intra_model-shuffle

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: nan

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
26.6182	1.0	44	31.1790
25.1664	2.0	88	25.9630
19.7407	3.0	132	17.5483
17.0241	4.0	176	15.7951
14.1013	5.0	220	13.6385
12.6633	6.0	264	12.1849
11.7434	7.0	308	11.5528
10.4633	8.0	352	10.7603
10.0142	9.0	396	9.7449
9.4309	10.0	440	9.4058
9.4721	11.0	484	9.2254
8.9759	12.0	528	9.0880
8.9786	13.0	572	9.0002
8.8538	14.0	616	8.9090
8.9413	15.0	660	8.8425
8.7639	16.0	704	8.7726
8.7977	17.0	748	8.6950
8.5634	18.0	792	8.6210
8.5154	19.0	836	8.5771
8.3299	20.0	880	8.5047
8.2768	21.0	924	8.4541
8.2174	22.0	968	8.3483
4.2638	23.0	1012	3.7590
3.9317	24.0	1056	3.7476
3.8703	25.0	1100	3.7268
3.8648	26.0	1144	3.7015
3.7132	27.0	1188	3.6620
3.7982	28.0	1232	3.6444
3.7453	29.0	1276	3.6329
3.6892	30.0	1320	3.5919
2.7956	31.0	1364	2.0820
1.2507	32.0	1408	1.0523
1.1008	33.0	1452	1.0461
1.1059	34.0	1496	1.0464
1.1015	35.0	1540	1.0460
1.079	36.0	1584	1.0446
1.0946	37.0	1628	1.0438
1.0985	38.0	1672	1.0461
1.0817	39.0	1716	1.0419
1.0723	40.0	1760	1.0417
1.0867	41.0	1804	1.0411
1.0654	42.0	1848	1.0415
1.0739	43.0	1892	1.0385
1.0643	44.0	1936	1.0395
1.0585	45.0	1980	1.0359
1.0784	46.0	2024	1.0375
1.0831	47.0	2068	1.0349
1.0652	48.0	2112	1.0355
1.0687	49.0	2156	1.0333
1.0717	50.0	2200	1.0350
1.0576	51.0	2244	1.0339
1.0666	52.0	2288	1.0339
1.0648	53.0	2332	1.0334
1.0624	54.0	2376	1.0323
1.0745	55.0	2420	1.0321
1.0542	56.0	2464	1.0339
1.054	57.0	2508	1.0320
1.0866	58.0	2552	1.0294
1.0704	59.0	2596	1.0315
1.0706	60.0	2640	1.0303
1.0464	61.0	2684	1.0312
1.0614	62.0	2728	1.0288
1.0645	63.0	2772	1.0302
1.057	64.0	2816	1.0318
1.0586	65.0	2860	1.0285
1.0724	66.0	2904	1.0300
1.0539	67.0	2948	1.0271
1.0536	68.0	2992	1.0292
1.0595	69.0	3036	1.0271
1.0504	70.0	3080	1.0296
1.0673	71.0	3124	1.0264
1.0548	72.0	3168	1.0277
1.0519	73.0	3212	1.0280
1.0519	74.0	3256	1.0260
1.0497	75.0	3300	1.0286
1.0551	76.0	3344	1.0253
1.0605	77.0	3388	1.0250
1.0495	78.0	3432	1.0250
1.0546	79.0	3476	1.0263
1.0615	80.0	3520	1.0255
1.0603	81.0	3564	1.0238
1.0374	82.0	3608	1.0244
1.0418	83.0	3652	1.0252
1.0603	84.0	3696	1.0241
1.0459	85.0	3740	1.0233
1.0598	86.0	3784	1.0222
1.0589	87.0	3828	1.0232
1.0415	88.0	3872	1.0223
1.0521	89.0	3916	1.0202
1.0443	90.0	3960	1.0198
1.0629	91.0	4004	1.0200
1.0616	92.0	4048	1.0194
1.059	93.0	4092	1.0189
1.036	94.0	4136	1.0226
1.0578	95.0	4180	1.0194
1.0463	96.0	4224	1.0180
1.0586	97.0	4268	1.0169
1.0541	98.0	4312	1.0182
1.052	99.0	4356	1.0154
1.0443	100.0	4400	1.0160
1.0573	101.0	4444	1.0131
1.0423	102.0	4488	1.0151
1.0532	103.0	4532	1.0127
1.0527	104.0	4576	1.0117
1.0387	105.0	4620	1.0120
1.0514	106.0	4664	1.0101
1.0436	107.0	4708	1.0110
1.0377	108.0	4752	1.0099
1.044	109.0	4796	1.0242
1.0399	110.0	4840	1.0139
1.0568	111.0	4884	1.0099
1.079	112.0	4928	1.0127
1.0611	113.0	4972	1.0269
1.0947	114.0	5016	1.0337
1.0635	115.0	5060	1.0312
1.0732	116.0	5104	1.0279

Framework versions

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