rahul77/t5-small-finetuned-thehindu1

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.4672
Validation Loss: 0.7612
Train Rouge1: 29.6559
Train Rouge2: 24.0992
Train Rougel: 27.7417
Train Rougelsum: 28.4408
Train Gen Len: 19.0
Epoch: 49

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:

optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
1.2252	0.9927	25.8031	17.7261	23.4483	25.0648	19.0	0
1.0509	0.9137	28.0482	20.6823	25.5396	27.0125	19.0	1
0.9961	0.8638	28.2964	22.1783	26.4157	27.4368	19.0	2
0.9266	0.8321	27.7054	21.8853	26.0306	26.9068	19.0	3
0.8851	0.8117	28.3740	22.8198	26.8479	27.5047	19.0	4
0.8505	0.7975	28.7979	23.1437	27.0745	27.7887	19.0	5
0.8247	0.7890	28.9634	23.3567	27.3117	28.0320	19.0	6
0.8154	0.7827	28.8667	23.4468	27.1404	27.8453	19.0	7
0.7889	0.7813	29.0498	23.6403	27.5662	28.1518	19.0	8
0.7676	0.7774	29.1829	23.5778	27.7014	28.3268	19.0	9
0.7832	0.7714	29.1040	23.3700	27.6605	28.2650	19.0	10
0.7398	0.7676	29.1040	23.3700	27.6605	28.2650	19.0	11
0.7473	0.7644	29.4387	24.1983	27.9842	28.5700	19.0	12
0.7270	0.7628	29.3128	24.1484	27.8565	28.4215	19.0	13
0.7174	0.7615	29.3128	24.1484	27.8565	28.4215	19.0	14
0.7231	0.7577	29.3838	23.9483	27.6550	28.3416	19.0	15
0.7099	0.7558	29.4866	24.1703	27.8649	28.4404	19.0	16
0.7060	0.7548	29.4866	24.1703	27.8649	28.4404	19.0	17
0.6884	0.7539	29.4866	24.1703	27.8649	28.4404	19.0	18
0.6778	0.7546	29.4866	24.1703	27.8649	28.4404	19.0	19
0.6586	0.7519	29.4866	24.1703	27.8649	28.4404	19.0	20
0.6474	0.7521	29.4866	24.1703	27.8649	28.4404	19.0	21
0.6392	0.7527	29.4866	24.1703	27.8649	28.4404	19.0	22
0.6424	0.7537	29.4866	24.1703	27.8649	28.4404	19.0	23
0.6184	0.7536	29.4866	24.1703	27.8649	28.4404	19.0	24
0.6164	0.7520	29.4866	24.0547	27.7388	28.3416	19.0	25
0.6115	0.7502	29.4866	23.9746	27.8232	28.4227	19.0	26
0.6056	0.7498	29.4866	23.9746	27.8232	28.4227	19.0	27
0.6004	0.7488	29.4451	23.7671	27.5435	28.2982	19.0	28
0.5851	0.7478	29.4451	23.7671	27.5435	28.2982	19.0	29
0.5777	0.7496	29.4866	23.9746	27.8232	28.4227	19.0	30
0.5751	0.7486	29.4866	23.9746	27.8232	28.4227	19.0	31
0.5730	0.7485	29.4866	23.9746	27.8232	28.4227	19.0	32
0.5487	0.7499	29.4962	24.0563	27.8422	28.4356	19.0	33
0.5585	0.7517	29.4962	24.0563	27.8422	28.4356	19.0	34
0.5450	0.7538	29.4962	24.0563	27.8422	28.4356	19.0	35
0.5427	0.7509	29.4962	24.0563	27.8422	28.4356	19.0	36
0.5287	0.7500	29.4962	24.0563	27.8422	28.4356	19.0	37
0.5231	0.7486	29.4962	24.0563	27.8422	28.4356	19.0	38
0.5155	0.7523	29.4962	24.0563	27.8422	28.4356	19.0	39
0.5105	0.7550	29.4962	24.0563	27.8422	28.4356	19.0	40
0.5175	0.7557	29.6736	24.3120	28.0332	28.5828	19.0	41
0.5053	0.7560	29.6736	24.3120	28.0332	28.5828	19.0	42
0.4928	0.7548	29.6736	24.3120	28.0332	28.5828	19.0	43
0.4913	0.7568	29.6559	24.0992	27.7417	28.4408	19.0	44
0.4841	0.7574	29.6559	24.0992	27.7417	28.4408	19.0	45
0.4770	0.7583	29.6736	24.3120	28.0332	28.5828	19.0	46
0.4727	0.7581	29.6736	24.3120	28.0332	28.5828	19.0	47
0.4612	0.7623	29.6736	24.3120	28.0332	28.5828	19.0	48
0.4672	0.7612	29.6559	24.0992	27.7417	28.4408	19.0	49

Framework versions

Transformers 4.23.1
TensorFlow 2.9.2
Datasets 2.6.1
Tokenizers 0.13.1

rahul77/t5-small-finetuned-thehindu1

rahul77/t5-small-finetuned-thehindu1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Seed this model