README.md

metadata

base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task7_fold1
    results: []

arabert_cross_relevance_task7_fold1

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3047
• Qwk: 0.0332
• Mse: 0.3047

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse
No log	0.1333	2	1.2830	0.0016	1.2830
No log	0.2667	4	0.3134	0.0127	0.3134
No log	0.4	6	0.1648	0.1104	0.1648
No log	0.5333	8	0.1251	0.0517	0.1251
No log	0.6667	10	0.2224	0.0017	0.2224
No log	0.8	12	0.2590	0.0094	0.2590
No log	0.9333	14	0.1796	0.0127	0.1796
No log	1.0667	16	0.1308	0.0397	0.1308
No log	1.2	18	0.1449	0.0303	0.1449
No log	1.3333	20	0.1645	0.0288	0.1645
No log	1.4667	22	0.1859	0.0270	0.1859
No log	1.6	24	0.1923	0.0425	0.1923
No log	1.7333	26	0.1918	0.0319	0.1918
No log	1.8667	28	0.2199	0.0290	0.2199
No log	2.0	30	0.2212	0.0273	0.2212
No log	2.1333	32	0.1858	0.0273	0.1858
No log	2.2667	34	0.1779	0.0270	0.1779
No log	2.4	36	0.2133	0.0270	0.2133
No log	2.5333	38	0.2467	0.0339	0.2467
No log	2.6667	40	0.2211	0.0355	0.2211
No log	2.8	42	0.1890	0.0355	0.1890
No log	2.9333	44	0.2091	0.0270	0.2091
No log	3.0667	46	0.2659	0.0254	0.2659
No log	3.2	48	0.2479	0.0235	0.2479
No log	3.3333	50	0.2076	0.0284	0.2076
No log	3.4667	52	0.1978	0.0351	0.1978
No log	3.6	54	0.2247	0.0334	0.2247
No log	3.7333	56	0.2784	0.0319	0.2784
No log	3.8667	58	0.2815	0.0217	0.2815
No log	4.0	60	0.2597	0.0235	0.2597
No log	4.1333	62	0.2093	0.0304	0.2093
No log	4.2667	64	0.2137	0.0287	0.2137
No log	4.4	66	0.2532	0.0235	0.2532
No log	4.5333	68	0.2399	0.0251	0.2399
No log	4.6667	70	0.2137	0.0338	0.2137
No log	4.8	72	0.2516	0.0235	0.2516
No log	4.9333	74	0.2786	0.0319	0.2786
No log	5.0667	76	0.3017	0.0319	0.3017
No log	5.2	78	0.2701	0.0235	0.2701
No log	5.3333	80	0.2234	0.0301	0.2234
No log	5.4667	82	0.2231	0.0301	0.2231
No log	5.6	84	0.2419	0.0284	0.2419
No log	5.7333	86	0.2839	0.0233	0.2839
No log	5.8667	88	0.2964	0.0233	0.2964
No log	6.0	90	0.2986	0.0214	0.2986
No log	6.1333	92	0.2565	0.0317	0.2565
No log	6.2667	94	0.2203	0.0334	0.2203
No log	6.4	96	0.2553	0.0317	0.2553
No log	6.5333	98	0.3609	0.0193	0.3609
No log	6.6667	100	0.4216	0.0206	0.4216
No log	6.8	102	0.3627	0.0225	0.3627
No log	6.9333	104	0.2543	0.0317	0.2543
No log	7.0667	106	0.2003	0.0312	0.2003
No log	7.2	108	0.2014	0.0295	0.2014
No log	7.3333	110	0.2374	0.0301	0.2374
No log	7.4667	112	0.3176	0.0263	0.3176
No log	7.6	114	0.3811	0.0237	0.3811
No log	7.7333	116	0.3686	0.0285	0.3686
No log	7.8667	118	0.3010	0.0260	0.3010
No log	8.0	120	0.2467	0.0317	0.2467
No log	8.1333	122	0.2371	0.0334	0.2371
No log	8.2667	124	0.2613	0.0361	0.2613
No log	8.4	126	0.2959	0.0310	0.2959
No log	8.5333	128	0.3317	0.0225	0.3317
No log	8.6667	130	0.3288	0.0240	0.3288
No log	8.8	132	0.2998	0.0370	0.2998
No log	8.9333	134	0.2797	0.0341	0.2797
No log	9.0667	136	0.2625	0.0441	0.2625
No log	9.2	138	0.2672	0.0421	0.2672
No log	9.3333	140	0.2738	0.0421	0.2738
No log	9.4667	142	0.2892	0.0401	0.2892
No log	9.6	144	0.3017	0.0366	0.3017
No log	9.7333	146	0.3079	0.0332	0.3079
No log	9.8667	148	0.3065	0.0332	0.3065
No log	10.0	150	0.3047	0.0332	0.3047

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1