results

This model is a fine-tuned version of abhi317/fine_tuned_t5_model on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.5021

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	42.0556
No log	2.0	2	38.9852
No log	3.0	3	36.7956
No log	4.0	4	35.4292
No log	5.0	5	33.7279
No log	6.0	6	31.4091
No log	7.0	7	28.8833
No log	8.0	8	27.1638
No log	9.0	9	25.8978
No log	10.0	10	25.0016
No log	11.0	11	24.2730
No log	12.0	12	23.6733
No log	13.0	13	23.2065
No log	14.0	14	22.7518
No log	15.0	15	22.2969
No log	16.0	16	21.8050
No log	17.0	17	21.2434
No log	18.0	18	20.6862
No log	19.0	19	20.0804
No log	20.0	20	19.4932
No log	21.0	21	18.8996
No log	22.0	22	18.3365
No log	23.0	23	17.7677
No log	24.0	24	17.1920
No log	25.0	25	16.6171
No log	26.0	26	16.0761
No log	27.0	27	15.5945
No log	28.0	28	15.1259
No log	29.0	29	14.6276
No log	30.0	30	14.1001
No log	31.0	31	13.5355
No log	32.0	32	12.9060
No log	33.0	33	12.2622
No log	34.0	34	11.6173
No log	35.0	35	10.9521
No log	36.0	36	10.2559
No log	37.0	37	9.5633
No log	38.0	38	8.8638
No log	39.0	39	8.1318
No log	40.0	40	7.3948
No log	41.0	41	6.7363
No log	42.0	42	6.1963
No log	43.0	43	5.7837
No log	44.0	44	5.4856
No log	45.0	45	5.2822
No log	46.0	46	5.1536
No log	47.0	47	5.0731
No log	48.0	48	5.0201
No log	49.0	49	4.9832
No log	50.0	50	4.9554
No log	51.0	51	4.9339
No log	52.0	52	4.9187
No log	53.0	53	4.9072
No log	54.0	54	4.8975
No log	55.0	55	4.8873
No log	56.0	56	4.8772
No log	57.0	57	4.8669
No log	58.0	58	4.8561
No log	59.0	59	4.8458
No log	60.0	60	4.8352
No log	61.0	61	4.8248
No log	62.0	62	4.8140
No log	63.0	63	4.8033
No log	64.0	64	4.7903
No log	65.0	65	4.7769
No log	66.0	66	4.7630
No log	67.0	67	4.7487
No log	68.0	68	4.7321
No log	69.0	69	4.7153
No log	70.0	70	4.6993
No log	71.0	71	4.6846
No log	72.0	72	4.6710
No log	73.0	73	4.6572
No log	74.0	74	4.6446
No log	75.0	75	4.6325
No log	76.0	76	4.6211
No log	77.0	77	4.6105
No log	78.0	78	4.6006
No log	79.0	79	4.5911
No log	80.0	80	4.5819
No log	81.0	81	4.5734
No log	82.0	82	4.5653
No log	83.0	83	4.5582
No log	84.0	84	4.5522
No log	85.0	85	4.5464
No log	86.0	86	4.5412
No log	87.0	87	4.5365
No log	88.0	88	4.5318
No log	89.0	89	4.5274
No log	90.0	90	4.5231
No log	91.0	91	4.5193
No log	92.0	92	4.5159
No log	93.0	93	4.5129
No log	94.0	94	4.5103
No log	95.0	95	4.5079
No log	96.0	96	4.5060
No log	97.0	97	4.5045
No log	98.0	98	4.5033
No log	99.0	99	4.5025
No log	100.0	100	4.5021

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2