t5-small-entailement-Writer-T5-base

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

• Loss: 0.5697

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 250
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	42	1.8185
No log	2.0	84	1.1957
No log	3.0	126	0.9771
No log	4.0	168	0.8964
No log	5.0	210	0.8380
No log	6.0	252	0.8109
No log	7.0	294	0.7886
No log	8.0	336	0.7760
No log	9.0	378	0.7577
No log	10.0	420	0.7483
No log	11.0	462	0.7364
1.2044	12.0	504	0.7267
1.2044	13.0	546	0.7205
1.2044	14.0	588	0.7102
1.2044	15.0	630	0.7048
1.2044	16.0	672	0.7015
1.2044	17.0	714	0.6958
1.2044	18.0	756	0.6892
1.2044	19.0	798	0.6877
1.2044	20.0	840	0.6825
1.2044	21.0	882	0.6790
1.2044	22.0	924	0.6732
1.2044	23.0	966	0.6676
0.736	24.0	1008	0.6640
0.736	25.0	1050	0.6631
0.736	26.0	1092	0.6617
0.736	27.0	1134	0.6556
0.736	28.0	1176	0.6551
0.736	29.0	1218	0.6545
0.736	30.0	1260	0.6483
0.736	31.0	1302	0.6493
0.736	32.0	1344	0.6488
0.736	33.0	1386	0.6434
0.736	34.0	1428	0.6427
0.736	35.0	1470	0.6403
0.6568	36.0	1512	0.6364
0.6568	37.0	1554	0.6342
0.6568	38.0	1596	0.6325
0.6568	39.0	1638	0.6300
0.6568	40.0	1680	0.6302
0.6568	41.0	1722	0.6292
0.6568	42.0	1764	0.6264
0.6568	43.0	1806	0.6272
0.6568	44.0	1848	0.6252
0.6568	45.0	1890	0.6229
0.6568	46.0	1932	0.6221
0.6568	47.0	1974	0.6202
0.602	48.0	2016	0.6193
0.602	49.0	2058	0.6196
0.602	50.0	2100	0.6174
0.602	51.0	2142	0.6175
0.602	52.0	2184	0.6162
0.602	53.0	2226	0.6155
0.602	54.0	2268	0.6129
0.602	55.0	2310	0.6139
0.602	56.0	2352	0.6124
0.602	57.0	2394	0.6128
0.602	58.0	2436	0.6109
0.602	59.0	2478	0.6111
0.5653	60.0	2520	0.6097
0.5653	61.0	2562	0.6086
0.5653	62.0	2604	0.6083
0.5653	63.0	2646	0.6086
0.5653	64.0	2688	0.6090
0.5653	65.0	2730	0.6074
0.5653	66.0	2772	0.6064
0.5653	67.0	2814	0.6056
0.5653	68.0	2856	0.6039
0.5653	69.0	2898	0.6051
0.5653	70.0	2940	0.6043
0.5653	71.0	2982	0.6034
0.5368	72.0	3024	0.6020
0.5368	73.0	3066	0.6047
0.5368	74.0	3108	0.6031
0.5368	75.0	3150	0.6011
0.5368	76.0	3192	0.6027
0.5368	77.0	3234	0.6009
0.5368	78.0	3276	0.6003
0.5368	79.0	3318	0.6001
0.5368	80.0	3360	0.6008
0.5368	81.0	3402	0.6005
0.5368	82.0	3444	0.6007
0.5368	83.0	3486	0.5988
0.5055	84.0	3528	0.5991
0.5055	85.0	3570	0.6004
0.5055	86.0	3612	0.5989
0.5055	87.0	3654	0.5975
0.5055	88.0	3696	0.5977
0.5055	89.0	3738	0.5982
0.5055	90.0	3780	0.5964
0.5055	91.0	3822	0.5979
0.5055	92.0	3864	0.5996
0.5055	93.0	3906	0.5936
0.5055	94.0	3948	0.5956
0.5055	95.0	3990	0.5940
0.4866	96.0	4032	0.5961
0.4866	97.0	4074	0.5955
0.4866	98.0	4116	0.5949
0.4866	99.0	4158	0.5971
0.4866	100.0	4200	0.5958
0.4866	101.0	4242	0.5978
0.4866	102.0	4284	0.5971
0.4866	103.0	4326	0.5954
0.4866	104.0	4368	0.5933
0.4866	105.0	4410	0.5944
0.4866	106.0	4452	0.5952
0.4866	107.0	4494	0.5948
0.4657	108.0	4536	0.5951
0.4657	109.0	4578	0.5948
0.4657	110.0	4620	0.5948
0.4657	111.0	4662	0.5927
0.4657	112.0	4704	0.5931
0.4657	113.0	4746	0.5919
0.4657	114.0	4788	0.5939
0.4657	115.0	4830	0.5922
0.4657	116.0	4872	0.5921
0.4657	117.0	4914	0.5917
0.4657	118.0	4956	0.5913
0.4657	119.0	4998	0.5908
0.4468	120.0	5040	0.5929
0.4468	121.0	5082	0.5915
0.4468	122.0	5124	0.5926
0.4468	123.0	5166	0.5929
0.4468	124.0	5208	0.5911
0.4468	125.0	5250	0.5907
0.4468	126.0	5292	0.5921
0.4468	127.0	5334	0.5917
0.4468	128.0	5376	0.5923
0.4468	129.0	5418	0.5912
0.4468	130.0	5460	0.5930
0.4346	131.0	5502	0.5924
0.4346	132.0	5544	0.5933
0.4346	133.0	5586	0.5920
0.4346	134.0	5628	0.5937
0.4346	135.0	5670	0.5930
0.4346	136.0	5712	0.5930
0.4346	137.0	5754	0.5929
0.4346	138.0	5796	0.5916
0.4346	139.0	5838	0.5935
0.4346	140.0	5880	0.5947
0.4346	141.0	5922	0.5926
0.4346	142.0	5964	0.5930
0.4247	143.0	6006	0.5911
0.4247	144.0	6048	0.5916
0.4247	145.0	6090	0.5929
0.4247	146.0	6132	0.5926
0.4247	147.0	6174	0.5917
0.4247	148.0	6216	0.5913
0.4247	149.0	6258	0.5907
0.4247	150.0	6300	0.5930
0.4247	151.0	6342	0.5928
0.4247	152.0	6384	0.5922
0.4247	153.0	6426	0.5921
0.4247	154.0	6468	0.5925
0.4139	155.0	6510	0.5923
0.4139	156.0	6552	0.5919
0.4139	157.0	6594	0.5920
0.4139	158.0	6636	0.5935
0.4139	159.0	6678	0.5926
0.4139	160.0	6720	0.5926
0.4139	161.0	6762	0.5925
0.4139	162.0	6804	0.5927
0.4139	163.0	6846	0.5918
0.4139	164.0	6888	0.5925
0.4139	165.0	6930	0.5935
0.4139	166.0	6972	0.5926
0.4049	167.0	7014	0.5919
0.4049	168.0	7056	0.5917
0.4049	169.0	7098	0.5916
0.4049	170.0	7140	0.5925
0.4049	171.0	7182	0.5931
0.4049	172.0	7224	0.5938
0.4049	173.0	7266	0.5932
0.4049	174.0	7308	0.5927
0.4049	175.0	7350	0.5934
0.4049	176.0	7392	0.5931
0.4049	177.0	7434	0.5937
0.4049	178.0	7476	0.5939
0.397	179.0	7518	0.5939
0.397	180.0	7560	0.5932
0.397	181.0	7602	0.5935
0.397	182.0	7644	0.5939
0.397	183.0	7686	0.5935
0.397	184.0	7728	0.5945
0.397	185.0	7770	0.5932
0.397	186.0	7812	0.5931
0.397	187.0	7854	0.5925
0.397	188.0	7896	0.5934
0.397	189.0	7938	0.5941
0.397	190.0	7980	0.5939
0.3891	191.0	8022	0.5933
0.3891	192.0	8064	0.5934
0.3891	193.0	8106	0.5938
0.3891	194.0	8148	0.5944
0.3891	195.0	8190	0.5937
0.3891	196.0	8232	0.5939
0.3891	197.0	8274	0.5937
0.3891	198.0	8316	0.5947
0.3891	199.0	8358	0.5945
0.3891	200.0	8400	0.5946
0.3891	201.0	8442	0.5945
0.3891	202.0	8484	0.5938
0.3842	203.0	8526	0.5947
0.3842	204.0	8568	0.5945
0.3842	205.0	8610	0.5935
0.3842	206.0	8652	0.5935
0.3842	207.0	8694	0.5939
0.3842	208.0	8736	0.5938
0.3842	209.0	8778	0.5939
0.3842	210.0	8820	0.5940
0.3842	211.0	8862	0.5943
0.3842	212.0	8904	0.5943
0.3842	213.0	8946	0.5946
0.3842	214.0	8988	0.5946
0.3802	215.0	9030	0.5947
0.3802	216.0	9072	0.5949
0.3802	217.0	9114	0.5944
0.3802	218.0	9156	0.5946
0.3802	219.0	9198	0.5950
0.3802	220.0	9240	0.5950
0.3802	221.0	9282	0.5953
0.3802	222.0	9324	0.5951
0.3802	223.0	9366	0.5956
0.3802	224.0	9408	0.5952
0.3802	225.0	9450	0.5955
0.3802	226.0	9492	0.5958
0.3791	227.0	9534	0.5954
0.3791	228.0	9576	0.5953
0.3791	229.0	9618	0.5959
0.3791	230.0	9660	0.5959
0.3791	231.0	9702	0.5957
0.3791	232.0	9744	0.5957
0.3791	233.0	9786	0.5956
0.3791	234.0	9828	0.5956
0.3791	235.0	9870	0.5956
0.3791	236.0	9912	0.5956
0.3791	237.0	9954	0.5957
0.3791	238.0	9996	0.5960
0.3764	239.0	10038	0.5956
0.3764	240.0	10080	0.5956
0.3764	241.0	10122	0.5955
0.3764	242.0	10164	0.5956
0.3764	243.0	10206	0.5955
0.3764	244.0	10248	0.5957
0.3764	245.0	10290	0.5956
0.3764	246.0	10332	0.5955
0.3764	247.0	10374	0.5954
0.3764	248.0	10416	0.5955
0.3764	249.0	10458	0.5954
0.3763	250.0	10500	0.5954

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2