T6

This model is a fine-tuned version of eslamxm/mt5-base-finetuned-arur on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5941

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 64

Training results

Training Loss	Epoch	Step	Validation Loss
0.2591	1.0	37	0.2616
0.1639	2.0	74	0.2497
0.1771	3.0	111	0.2448
0.1465	4.0	148	0.2486
0.1294	5.0	185	0.2499
0.118	6.0	222	0.2520
0.1014	7.0	259	0.2582
0.0986	8.0	296	0.2631
0.1021	9.0	333	0.2775
0.0783	10.0	370	0.2867
0.0699	11.0	407	0.2906
0.062	12.0	444	0.3010
0.059	13.0	481	0.3144
0.0592	14.0	518	0.3265
0.0513	15.0	555	0.3365
0.0404	16.0	592	0.3550
0.0417	17.0	629	0.3552
0.0385	18.0	666	0.3682
0.0303	19.0	703	0.3728
0.0355	20.0	740	0.3947
0.0232	21.0	777	0.4208
0.024	22.0	814	0.4080
0.023	23.0	851	0.4265
0.0169	24.0	888	0.4233
0.0185	25.0	925	0.4450
0.0214	26.0	962	0.4528
0.0159	27.0	999	0.4486
0.0156	28.0	1036	0.4926
0.017	29.0	1073	0.4927
0.0137	30.0	1110	0.4886
0.0139	31.0	1147	0.5205
0.0108	32.0	1184	0.4953
0.0136	33.0	1221	0.4925
0.0129	34.0	1258	0.5081
0.0099	35.0	1295	0.5252
0.0116	36.0	1332	0.5241
0.0134	37.0	1369	0.5352
0.0111	38.0	1406	0.5469
0.0089	39.0	1443	0.5618
0.0103	40.0	1480	0.5781
0.0083	41.0	1517	0.5896
0.0091	42.0	1554	0.5287
0.0115	43.0	1591	0.5556
0.0069	44.0	1628	0.5497
0.0069	45.0	1665	0.5896
0.0089	46.0	1702	0.5799
0.0056	47.0	1739	0.5654
0.0072	48.0	1776	0.5683
0.0097	49.0	1813	0.5642
0.0065	50.0	1850	0.5623
0.0073	51.0	1887	0.5906
0.0078	52.0	1924	0.5932
0.0068	53.0	1961	0.5923
0.006	54.0	1998	0.5978
0.005	55.0	2035	0.5846
0.0082	56.0	2072	0.5886
0.0081	57.0	2109	0.5844
0.0056	58.0	2146	0.5878
0.0069	59.0	2183	0.5890
0.0075	60.0	2220	0.5946
0.0077	61.0	2257	0.5897
0.0064	62.0	2294	0.5908
0.0049	63.0	2331	0.5934
0.005	64.0	2368	0.5941

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1