Sentiment-google-t5-v1_1-large-intra_model-dataset-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: 1.0889

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
20.8833	1.0	44	25.4149
17.9582	2.0	88	15.2004
12.4496	3.0	132	11.1146
10.6482	4.0	176	10.7774
10.0038	5.0	220	10.5784
9.8548	6.0	264	10.4290
9.7749	7.0	308	10.2568
9.4275	8.0	352	9.8102
8.8894	9.0	396	9.2370
8.4944	10.0	440	8.9575
8.4109	11.0	484	8.7954
8.3217	12.0	528	8.6723
7.8791	13.0	572	8.5306
1.0442	14.0	616	0.8718
0.9076	15.0	660	0.8507
0.9013	16.0	704	0.8517
0.9	17.0	748	0.8475
0.8835	18.0	792	0.8480
0.8842	19.0	836	0.8525
0.8836	20.0	880	0.8532
0.8845	21.0	924	0.8458
0.8941	22.0	968	0.8485
0.8819	23.0	1012	0.8450
0.8921	24.0	1056	0.8513
0.888	25.0	1100	0.8444
0.8857	26.0	1144	0.8486
0.8737	27.0	1188	0.8424
0.8766	28.0	1232	0.8423
0.8746	29.0	1276	0.8430
0.8829	30.0	1320	0.8402
0.862	31.0	1364	0.8366
0.8601	32.0	1408	0.8386
0.8658	33.0	1452	0.8326
0.8737	34.0	1496	0.8342
0.8662	35.0	1540	0.8309
0.8722	36.0	1584	0.8290
0.8682	37.0	1628	0.8216
0.859	38.0	1672	0.8430
0.8554	39.0	1716	0.8170
0.8565	40.0	1760	0.8114
0.8402	41.0	1804	0.8079
0.848	42.0	1848	0.8178
0.8458	43.0	1892	0.8123
0.842	44.0	1936	0.8026
0.8259	45.0	1980	0.7977
0.8313	46.0	2024	0.7931
0.8418	47.0	2068	0.7935
0.8253	48.0	2112	0.7892
0.8251	49.0	2156	0.7851
0.8153	50.0	2200	0.7833
0.809	51.0	2244	0.7822
0.8137	52.0	2288	0.7759
0.8152	53.0	2332	0.7781
0.8201	54.0	2376	0.7812
0.8049	55.0	2420	0.7795
0.8003	56.0	2464	0.7730
0.797	57.0	2508	0.7692
0.8031	58.0	2552	0.7696
0.7907	59.0	2596	0.7685
0.7935	60.0	2640	0.7612
0.7958	61.0	2684	0.7558
0.7932	62.0	2728	0.7539
0.7944	63.0	2772	0.7510
0.7952	64.0	2816	0.7500
0.7838	65.0	2860	0.7551
0.7797	66.0	2904	0.7417
0.7821	67.0	2948	0.7399
0.7739	68.0	2992	0.7440
0.7697	69.0	3036	0.7331
0.7709	70.0	3080	0.7343
0.7679	71.0	3124	0.7389
0.7506	72.0	3168	0.7296
0.7645	73.0	3212	0.7336
0.7501	74.0	3256	0.7278
0.7602	75.0	3300	0.7268
0.7475	76.0	3344	0.7221
0.7561	77.0	3388	0.7211
0.7534	78.0	3432	0.7135
0.7582	79.0	3476	0.7173
0.734	80.0	3520	0.7096
0.7481	81.0	3564	0.7094
0.7454	82.0	3608	0.7053
0.7408	83.0	3652	0.6956
0.7189	84.0	3696	0.6943
0.7467	85.0	3740	0.6997
0.7544	86.0	3784	0.7049
0.7221	87.0	3828	0.6903
0.7358	88.0	3872	0.6851
0.727	89.0	3916	0.6807
0.7127	90.0	3960	0.6828
0.7158	91.0	4004	0.6837
0.7284	92.0	4048	0.6818
0.7153	93.0	4092	0.6906
0.7172	94.0	4136	0.6804
0.7076	95.0	4180	0.6694
0.7009	96.0	4224	0.6722
0.6915	97.0	4268	0.6775
0.6997	98.0	4312	0.6596
0.6924	99.0	4356	0.6595
0.704	100.0	4400	0.6598
0.6889	101.0	4444	0.6504
0.6932	102.0	4488	0.6570
0.6847	103.0	4532	0.6477
0.6851	104.0	4576	0.6408
0.6843	105.0	4620	0.6392
0.6925	106.0	4664	0.6330
0.6648	107.0	4708	0.6289
0.6744	108.0	4752	0.6258
0.6752	109.0	4796	0.6439
0.6729	110.0	4840	0.6228
0.6649	111.0	4884	0.6388
0.6567	112.0	4928	0.6248
0.6556	113.0	4972	0.6196
0.6607	114.0	5016	0.6133
0.6487	115.0	5060	0.6235
0.6636	116.0	5104	0.6159
0.6625	117.0	5148	0.6030
0.6363	118.0	5192	0.6072
0.6504	119.0	5236	0.5983
0.6406	120.0	5280	0.6009
0.6283	121.0	5324	0.5955
0.612	122.0	5368	0.5883
0.6295	123.0	5412	0.5879
0.6392	124.0	5456	0.5848
0.6144	125.0	5500	0.5814
0.6204	126.0	5544	0.5856
0.6144	127.0	5588	0.5826
0.6119	128.0	5632	0.5788
0.6125	129.0	5676	0.5814
0.6093	130.0	5720	0.5729
0.6035	131.0	5764	0.5702
0.6227	132.0	5808	0.5663
0.6287	133.0	5852	0.5608
0.6092	134.0	5896	0.5554
0.6158	135.0	5940	0.5507
0.6113	136.0	5984	0.5555
0.5976	137.0	6028	0.5547
0.595	138.0	6072	0.5436
0.5891	139.0	6116	0.5417
0.583	140.0	6160	0.5375
0.5915	141.0	6204	0.5304
0.5855	142.0	6248	0.5253
0.5875	143.0	6292	0.5364
0.581	144.0	6336	0.5245
0.5806	145.0	6380	0.5220
0.5589	146.0	6424	0.5150
0.573	147.0	6468	0.5252
0.5843	148.0	6512	0.5169
0.5705	149.0	6556	0.5156
0.5756	150.0	6600	0.5208
0.5575	151.0	6644	0.5028
0.5574	152.0	6688	0.5049
0.5598	153.0	6732	0.5054
0.5571	154.0	6776	0.5096
0.5673	155.0	6820	0.5012
0.5634	156.0	6864	0.4902
0.5601	157.0	6908	0.4949
0.5423	158.0	6952	0.4851
0.5568	159.0	6996	0.5020
0.5664	160.0	7040	0.4846
0.5523	161.0	7084	0.4865
0.5502	162.0	7128	0.4797
0.5374	163.0	7172	0.4735
0.557	164.0	7216	0.4784
0.5481	165.0	7260	0.4771
0.5509	166.0	7304	0.4688
0.5285	167.0	7348	0.4849
0.5312	168.0	7392	0.4741
0.5383	169.0	7436	0.4645
0.5413	170.0	7480	0.4724
0.524	171.0	7524	0.4583
0.5129	172.0	7568	0.4674
0.5302	173.0	7612	0.4565
0.5218	174.0	7656	0.4552
0.5189	175.0	7700	0.4583
0.5257	176.0	7744	0.4529
0.5216	177.0	7788	0.4489
0.5206	178.0	7832	0.4460
0.5241	179.0	7876	0.4431
0.5158	180.0	7920	0.4413
0.509	181.0	7964	0.4492
0.5111	182.0	8008	0.4431
0.5174	183.0	8052	0.4382
0.5122	184.0	8096	0.4305
0.4983	185.0	8140	0.4346
0.5022	186.0	8184	0.4358
0.4951	187.0	8228	0.4357
0.4989	188.0	8272	0.4325
0.5096	189.0	8316	0.4291
0.503	190.0	8360	0.4324
0.4954	191.0	8404	0.4277
0.5071	192.0	8448	0.4210
0.505	193.0	8492	0.4269
0.5002	194.0	8536	0.4292
0.5039	195.0	8580	0.4219
0.5107	196.0	8624	0.4191
0.5008	197.0	8668	0.4230
0.5024	198.0	8712	0.4226
0.4851	199.0	8756	0.4196
0.5026	200.0	8800	0.4164

Framework versions

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