learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	82	2.1684
No log	2.0	164	2.1312
No log	3.0	246	2.0932
No log	4.0	328	2.0737
No log	5.0	410	2.0344
No log	6.0	492	2.0196
2.1527	7.0	574	1.9924
2.1527	8.0	656	1.9714
2.1527	9.0	738	1.9546
2.1527	10.0	820	1.9446
2.1527	11.0	902	1.9269
2.1527	12.0	984	1.9231
1.9287	13.0	1066	1.9101
1.9287	14.0	1148	1.9019
1.9287	15.0	1230	1.9044
1.9287	16.0	1312	1.8904
1.9287	17.0	1394	1.8933
1.9287	18.0	1476	1.8876
1.7373	19.0	1558	1.8850
1.7373	20.0	1640	1.8818
1.7373	21.0	1722	1.8854
1.7373	22.0	1804	1.8764
1.7373	23.0	1886	1.8730
1.7373	24.0	1968	1.8764
1.6017	25.0	2050	1.8674
1.6017	26.0	2132	1.8720
1.6017	27.0	2214	1.8690
1.6017	28.0	2296	1.8734
1.6017	29.0	2378	1.8708
1.6017	30.0	2460	1.8718
1.5047	31.0	2542	1.8901
1.5047	32.0	2624	1.8850
1.5047	33.0	2706	1.8807
1.5047	34.0	2788	1.8847
1.5047	35.0	2870	1.8865
1.5047	36.0	2952	1.8942
1.4277	37.0	3034	1.8941
1.4277	38.0	3116	1.8973
1.4277	39.0	3198	1.9002
1.4277	40.0	3280	1.8985
1.4277	41.0	3362	1.9005
1.4277	42.0	3444	1.9045
1.3555	43.0	3526	1.9133
1.3555	44.0	3608	1.9097
1.3555	45.0	3690	1.9189
1.3555	46.0	3772	1.9140
1.3555	47.0	3854	1.9214
1.3555	48.0	3936	1.9201
1.3069	49.0	4018	1.9218
1.3069	50.0	4100	1.9247
1.3069	51.0	4182	1.9265
1.3069	52.0	4264	1.9236
1.3069	53.0	4346	1.9260
1.3069	54.0	4428	1.9343
1.2576	55.0	4510	1.9364
1.2576	56.0	4592	1.9369
1.2576	57.0	4674	1.9334
1.2576	58.0	4756	1.9439
1.2576	59.0	4838	1.9476
1.2576	60.0	4920	1.9528
1.2212	61.0	5002	1.9630
1.2212	62.0	5084	1.9589
1.2212	63.0	5166	1.9475
1.2212	64.0	5248	1.9526
1.2212	65.0	5330	1.9600
1.2212	66.0	5412	1.9557
1.2212	67.0	5494	1.9600
1.1924	68.0	5576	1.9682
1.1924	69.0	5658	1.9643
1.1924	70.0	5740	1.9669
1.1924	71.0	5822	1.9683
1.1924	72.0	5904	1.9734
1.1924	73.0	5986	1.9710
1.1678	74.0	6068	1.9714
1.1678	75.0	6150	1.9735
1.1678	76.0	6232	1.9766
1.1678	77.0	6314	1.9753
1.1678	78.0	6396	1.9773
1.1678	79.0	6478	1.9766
1.1472	80.0	6560	1.9798
1.1472	81.0	6642	1.9801
1.1472	82.0	6724	1.9787
1.1472	83.0	6806	1.9799
1.1472	84.0	6888	1.9783
1.1472	85.0	6970	1.9829
1.1283	86.0	7052	1.9852
1.1283	87.0	7134	1.9851
1.1283	88.0	7216	1.9842
1.1283	89.0	7298	1.9838
1.1283	90.0	7380	1.9855
1.1283	91.0	7462	1.9866
1.124	92.0	7544	1.9881
1.124	93.0	7626	1.9879
1.124	94.0	7708	1.9880
1.124	95.0	7790	1.9882
1.124	96.0	7872	1.9878
1.124	97.0	7954	1.9881
1.1116	98.0	8036	1.9884
1.1116	99.0	8118	1.9884
1.1116	100.0	8200	1.9884

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu118
Datasets 3.3.1
Tokenizers 0.21.0

javedonline/t5-small-finetuned-xsum

t5-small-finetuned-xsum

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

javedonline/
t5-small-finetuned-xsum