genz_model1

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

• Loss: 1.1491
• Bleu: 40.8929
• Gen Len: 14.9556

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	107	1.7641	33.597	15.1495
No log	2.0	214	1.6673	34.361	15.3435
No log	3.0	321	1.6087	34.5695	15.4369
No log	4.0	428	1.5600	35.2399	15.3528
1.8047	5.0	535	1.5171	35.6103	15.4743
1.8047	6.0	642	1.4851	36.0011	15.4369
1.8047	7.0	749	1.4512	35.9925	15.5234
1.8047	8.0	856	1.4261	36.2647	15.5117
1.8047	9.0	963	1.3992	36.0587	15.6005
1.5488	10.0	1070	1.3831	36.1956	15.4836
1.5488	11.0	1177	1.3626	36.409	15.4743
1.5488	12.0	1284	1.3432	36.6838	15.486
1.5488	13.0	1391	1.3293	36.4639	15.4696
1.5488	14.0	1498	1.3148	36.7266	15.4416
1.4212	15.0	1605	1.3005	36.8887	15.4556
1.4212	16.0	1712	1.2903	37.1891	15.3902
1.4212	17.0	1819	1.2763	37.6121	15.3972
1.4212	18.0	1926	1.2620	37.5425	15.4743
1.3223	19.0	2033	1.2561	37.9319	15.3341
1.3223	20.0	2140	1.2492	38.1299	15.2874
1.3223	21.0	2247	1.2381	38.364	15.3061
1.3223	22.0	2354	1.2314	38.9094	15.2523
1.3223	23.0	2461	1.2265	38.5676	15.2383
1.2631	24.0	2568	1.2159	39.0735	15.25
1.2631	25.0	2675	1.2125	38.7736	15.2383
1.2631	26.0	2782	1.2052	39.4841	15.1308
1.2631	27.0	2889	1.1987	39.3427	15.1612
1.2631	28.0	2996	1.1952	39.5887	15.1285
1.2042	29.0	3103	1.1932	39.4991	15.1192
1.2042	30.0	3210	1.1867	40.1521	15.1005
1.2042	31.0	3317	1.1812	40.3359	15.1285
1.2042	32.0	3424	1.1777	40.2795	15.0748
1.1701	33.0	3531	1.1748	40.3198	15.0561
1.1701	34.0	3638	1.1711	40.2025	15.0397
1.1701	35.0	3745	1.1693	40.4234	15.0514
1.1701	36.0	3852	1.1678	40.5943	14.9977
1.1701	37.0	3959	1.1645	40.6919	15.0023
1.1371	38.0	4066	1.1612	40.6628	14.9743
1.1371	39.0	4173	1.1592	40.6584	14.965
1.1371	40.0	4280	1.1581	40.5589	14.9626
1.1371	41.0	4387	1.1555	40.6157	14.9907
1.1371	42.0	4494	1.1546	40.868	14.9743
1.1203	43.0	4601	1.1527	40.6054	14.9977
1.1203	44.0	4708	1.1518	40.7963	14.9883
1.1203	45.0	4815	1.1509	40.7776	14.9766
1.1203	46.0	4922	1.1502	40.7738	14.9556
1.1103	47.0	5029	1.1499	40.8814	14.9579
1.1103	48.0	5136	1.1495	40.9137	14.9533
1.1103	49.0	5243	1.1493	40.8929	14.9556
1.1103	50.0	5350	1.1491	40.8929	14.9556

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.3
• Tokenizers 0.13.3