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: 1.2337
• Bleu: 37.5629
• Gen Len: 15.215

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	2.0122	27.3045	15.4416
No log	2.0	214	1.8166	32.1348	15.285
No log	3.0	321	1.7273	32.6473	15.4603
No log	4.0	428	1.6669	32.8528	15.514
1.9696	5.0	535	1.6214	33.6367	15.507
1.9696	6.0	642	1.5815	33.5927	15.4743
1.9696	7.0	749	1.5481	34.0762	15.5
1.9696	8.0	856	1.5236	34.3891	15.4416
1.9696	9.0	963	1.4948	34.0203	15.4673
1.56	10.0	1070	1.4733	33.9927	15.4416
1.56	11.0	1177	1.4559	34.468	15.3972
1.56	12.0	1284	1.4334	34.3625	15.3785
1.56	13.0	1391	1.4167	34.721	15.3388
1.56	14.0	1498	1.4017	34.7409	15.4136
1.4159	15.0	1605	1.3886	34.7995	15.3738
1.4159	16.0	1712	1.3733	34.7944	15.3879
1.4159	17.0	1819	1.3627	35.0969	15.4089
1.4159	18.0	1926	1.3517	35.157	15.3505
1.3203	19.0	2033	1.3452	34.9134	15.2126
1.3203	20.0	2140	1.3325	35.5535	15.3084
1.3203	21.0	2247	1.3268	35.9899	15.2056
1.3203	22.0	2354	1.3163	36.1116	15.243
1.3203	23.0	2461	1.3115	36.2296	15.1752
1.2505	24.0	2568	1.3038	36.5635	15.2056
1.2505	25.0	2675	1.2996	36.7848	15.2243
1.2505	26.0	2782	1.2914	36.3015	15.2336
1.2505	27.0	2889	1.2856	36.73	15.2664
1.2505	28.0	2996	1.2810	36.8486	15.2897
1.1949	29.0	3103	1.2780	37.1042	15.243
1.1949	30.0	3210	1.2729	37.1394	15.2617
1.1949	31.0	3317	1.2673	36.9584	15.2967
1.1949	32.0	3424	1.2637	37.4488	15.2547
1.156	33.0	3531	1.2607	37.3112	15.278
1.156	34.0	3638	1.2573	37.5048	15.2313
1.156	35.0	3745	1.2532	37.4771	15.2967
1.156	36.0	3852	1.2512	37.4967	15.3014
1.156	37.0	3959	1.2494	37.5326	15.236
1.1272	38.0	4066	1.2470	37.5807	15.2266
1.1272	39.0	4173	1.2455	37.5478	15.229
1.1272	40.0	4280	1.2435	37.7117	15.236
1.1272	41.0	4387	1.2402	37.3874	15.2547
1.1272	42.0	4494	1.2389	37.584	15.243
1.11	43.0	4601	1.2377	37.5384	15.2336
1.11	44.0	4708	1.2364	37.5339	15.2453
1.11	45.0	4815	1.2362	37.5626	15.229
1.11	46.0	4922	1.2355	37.518	15.222
1.0999	47.0	5029	1.2343	37.5847	15.243
1.0999	48.0	5136	1.2339	37.5871	15.2313
1.0999	49.0	5243	1.2338	37.5592	15.236
1.0999	50.0	5350	1.2337	37.5629	15.215

Framework versions

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