ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k15_task3_organization

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: 0.6406
• Qwk: 0.3092
• Mse: 0.6406
• Rmse: 0.8004

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0308	2	3.1184	0.0097	3.1184	1.7659
No log	0.0615	4	1.7661	0.0438	1.7661	1.3289
No log	0.0923	6	0.9263	0.0744	0.9263	0.9625
No log	0.1231	8	0.7490	-0.1733	0.7490	0.8654
No log	0.1538	10	0.6176	-0.0159	0.6176	0.7858
No log	0.1846	12	0.5534	0.0569	0.5534	0.7439
No log	0.2154	14	0.5366	0.0476	0.5366	0.7326
No log	0.2462	16	0.8191	0.1111	0.8191	0.9051
No log	0.2769	18	1.0757	0.0244	1.0757	1.0372
No log	0.3077	20	0.5863	0.1773	0.5863	0.7657
No log	0.3385	22	0.6057	0.0	0.6057	0.7783
No log	0.3692	24	0.6686	0.0	0.6686	0.8177
No log	0.4	26	0.6770	0.0	0.6770	0.8228
No log	0.4308	28	0.6263	0.0	0.6263	0.7914
No log	0.4615	30	0.5913	0.0388	0.5913	0.7689
No log	0.4923	32	0.9717	0.0933	0.9717	0.9857
No log	0.5231	34	0.7350	0.1264	0.7350	0.8573
No log	0.5538	36	0.8705	0.0095	0.8705	0.9330
No log	0.5846	38	0.7014	0.0769	0.7014	0.8375
No log	0.6154	40	0.6777	0.1233	0.6777	0.8232
No log	0.6462	42	0.6041	0.0423	0.6041	0.7773
No log	0.6769	44	0.5870	0.0504	0.5870	0.7661
No log	0.7077	46	0.6686	0.2542	0.6686	0.8177
No log	0.7385	48	0.6411	0.1515	0.6411	0.8007
No log	0.7692	50	0.6361	0.1515	0.6361	0.7976
No log	0.8	52	0.5811	0.0448	0.5811	0.7623
No log	0.8308	54	0.7479	0.1445	0.7479	0.8648
No log	0.8615	56	0.9074	0.1855	0.9074	0.9526
No log	0.8923	58	0.6808	0.1111	0.6808	0.8251
No log	0.9231	60	0.9613	0.1055	0.9613	0.9804
No log	0.9538	62	1.2984	0.0698	1.2984	1.1395
No log	0.9846	64	1.0584	0.0745	1.0584	1.0288
No log	1.0154	66	0.6519	0.0476	0.6519	0.8074
No log	1.0462	68	0.5777	-0.0159	0.5777	0.7600
No log	1.0769	70	0.7756	0.3200	0.7756	0.8807
No log	1.1077	72	0.6932	0.3455	0.6932	0.8326
No log	1.1385	74	0.5303	0.0476	0.5303	0.7282
No log	1.1692	76	0.6123	0.3224	0.6123	0.7825
No log	1.2	78	0.7250	0.2877	0.7250	0.8515
No log	1.2308	80	0.5312	0.2683	0.5312	0.7288
No log	1.2615	82	0.6581	0.2889	0.6581	0.8112
No log	1.2923	84	1.1864	0.0915	1.1864	1.0892
No log	1.3231	86	1.1472	0.0857	1.1472	1.0711
No log	1.3538	88	0.6300	0.3369	0.6300	0.7937
No log	1.3846	90	0.5897	0.2842	0.5897	0.7679
No log	1.4154	92	0.5222	0.2883	0.5222	0.7226
No log	1.4462	94	0.6801	0.2809	0.6801	0.8247
No log	1.4769	96	0.8304	0.28	0.8304	0.9113
No log	1.5077	98	0.6015	0.2393	0.6015	0.7755
No log	1.5385	100	0.5228	0.3000	0.5228	0.7230
No log	1.5692	102	0.5276	0.3000	0.5276	0.7264
No log	1.6	104	0.5605	0.3412	0.5605	0.7487
No log	1.6308	106	0.6707	0.1461	0.6707	0.8190
No log	1.6615	108	0.6421	0.3103	0.6421	0.8013
No log	1.6923	110	0.6683	0.2088	0.6683	0.8175
No log	1.7231	112	0.8358	0.1504	0.8358	0.9142
No log	1.7538	114	0.6452	0.3258	0.6452	0.8032
No log	1.7846	116	0.6127	0.2914	0.6127	0.7827
No log	1.8154	118	0.5734	0.3757	0.5734	0.7572
No log	1.8462	120	0.5934	0.2093	0.5934	0.7703
No log	1.8769	122	0.7742	0.1560	0.7742	0.8799
No log	1.9077	124	0.7781	0.1636	0.7781	0.8821
No log	1.9385	126	0.5637	0.2941	0.5637	0.7508
No log	1.9692	128	0.5536	0.5111	0.5536	0.7440
No log	2.0	130	0.6978	0.1005	0.6978	0.8354
No log	2.0308	132	1.2406	0.1724	1.2406	1.1138
No log	2.0615	134	0.9589	0.1613	0.9589	0.9792
No log	2.0923	136	0.6155	0.3913	0.6155	0.7846
No log	2.1231	138	0.6732	0.2653	0.6732	0.8205
No log	2.1538	140	0.5981	0.3730	0.5981	0.7734
No log	2.1846	142	0.8859	0.2275	0.8859	0.9412
No log	2.2154	144	0.8449	0.1560	0.8449	0.9192
No log	2.2462	146	0.6622	0.2577	0.6622	0.8138
No log	2.2769	148	0.8124	0.1527	0.8124	0.9014
No log	2.3077	150	0.9355	0.1605	0.9355	0.9672
No log	2.3385	152	0.7611	0.1919	0.7611	0.8724
No log	2.3692	154	0.5818	0.3253	0.5818	0.7627
No log	2.4	156	0.5267	0.2632	0.5267	0.7257
No log	2.4308	158	0.5885	0.3182	0.5885	0.7671
No log	2.4615	160	0.9123	0.2333	0.9123	0.9551
No log	2.4923	162	0.9267	0.2327	0.9267	0.9626
No log	2.5231	164	0.5771	0.3333	0.5771	0.7597
No log	2.5538	166	0.6101	0.4167	0.6101	0.7811
No log	2.5846	168	0.6751	0.3575	0.6751	0.8216
No log	2.6154	170	0.6280	0.2332	0.6280	0.7924
No log	2.6462	172	1.0889	0.2925	1.0889	1.0435
No log	2.6769	174	1.0519	0.2593	1.0519	1.0256
No log	2.7077	176	0.6687	0.2727	0.6687	0.8177
No log	2.7385	178	0.7168	0.3333	0.7168	0.8466
No log	2.7692	180	0.6500	0.375	0.6500	0.8063
No log	2.8	182	0.6126	0.2766	0.6126	0.7827
No log	2.8308	184	0.8914	0.136	0.8914	0.9442
No log	2.8615	186	0.8004	0.2364	0.8004	0.8947
No log	2.8923	188	0.5397	0.2418	0.5397	0.7346
No log	2.9231	190	0.5830	0.3073	0.5830	0.7635
No log	2.9538	192	0.8270	0.3846	0.8270	0.9094
No log	2.9846	194	0.6447	0.3769	0.6447	0.8029
No log	3.0154	196	0.5383	0.3216	0.5383	0.7337
No log	3.0462	198	0.7580	0.2405	0.7580	0.8706
No log	3.0769	200	0.8091	0.3016	0.8091	0.8995
No log	3.1077	202	0.6504	0.2696	0.6504	0.8064
No log	3.1385	204	0.5323	0.4098	0.5323	0.7296
No log	3.1692	206	0.6175	0.2811	0.6175	0.7858
No log	3.2	208	0.8600	0.2993	0.8600	0.9274
No log	3.2308	210	0.9637	0.2941	0.9637	0.9817
No log	3.2615	212	0.8717	0.2701	0.8717	0.9336
No log	3.2923	214	0.8460	0.2701	0.8460	0.9198
No log	3.3231	216	0.6458	0.3043	0.6458	0.8036
No log	3.3538	218	0.7551	0.2685	0.7551	0.8690
No log	3.3846	220	0.7926	0.2432	0.7926	0.8903
No log	3.4154	222	0.8139	0.2180	0.8139	0.9021
No log	3.4462	224	0.7255	0.2554	0.7255	0.8518
No log	3.4769	226	0.7173	0.1855	0.7173	0.8469
No log	3.5077	228	0.7065	0.1855	0.7065	0.8406
No log	3.5385	230	0.7086	0.1858	0.7086	0.8418
No log	3.5692	232	0.7987	0.25	0.7987	0.8937
No log	3.6	234	0.6489	0.2762	0.6489	0.8056
No log	3.6308	236	0.6541	0.3427	0.6541	0.8087
No log	3.6615	238	0.7455	0.1864	0.7455	0.8634
No log	3.6923	240	0.9603	0.1655	0.9603	0.9800
No log	3.7231	242	1.1145	0.2000	1.1145	1.0557
No log	3.7538	244	0.8465	0.2481	0.8465	0.9200
No log	3.7846	246	0.5830	0.3769	0.5830	0.7635
No log	3.8154	248	0.6044	0.3433	0.6044	0.7774
No log	3.8462	250	0.7374	0.1429	0.7374	0.8587
No log	3.8769	252	1.0617	0.2000	1.0617	1.0304
No log	3.9077	254	1.0747	0.2000	1.0747	1.0367
No log	3.9385	256	0.6813	0.2072	0.6813	0.8254
No log	3.9692	258	0.5442	0.4396	0.5442	0.7377
No log	4.0	260	0.5497	0.4229	0.5497	0.7414
No log	4.0308	262	0.6772	0.2140	0.6772	0.8229
No log	4.0615	264	0.7035	0.2469	0.7035	0.8388
No log	4.0923	266	0.6777	0.2140	0.6777	0.8232
No log	4.1231	268	0.7267	0.3559	0.7267	0.8525
No log	4.1538	270	0.7342	0.3251	0.7342	0.8569
No log	4.1846	272	0.7518	0.2903	0.7518	0.8670
No log	4.2154	274	0.9059	0.2806	0.9059	0.9518
No log	4.2462	276	0.8817	0.2836	0.8817	0.9390
No log	4.2769	278	0.6359	0.2830	0.6359	0.7974
No log	4.3077	280	0.5068	0.4732	0.5068	0.7119
No log	4.3385	282	0.5670	0.3398	0.5670	0.7530
No log	4.3692	284	0.9128	0.2000	0.9128	0.9554
No log	4.4	286	1.0611	0.1709	1.0611	1.0301
No log	4.4308	288	0.8296	0.2348	0.8296	0.9108
No log	4.4615	290	0.6439	0.3508	0.6439	0.8024
No log	4.4923	292	0.6818	0.2963	0.6818	0.8257
No log	4.5231	294	0.7477	0.2554	0.7477	0.8647
No log	4.5538	296	0.7144	0.2566	0.7144	0.8453
No log	4.5846	298	0.5201	0.4583	0.5201	0.7212
No log	4.6154	300	0.4996	0.4947	0.4996	0.7068
No log	4.6462	302	0.6226	0.2711	0.6226	0.7890
No log	4.6769	304	1.0708	0.2208	1.0708	1.0348
No log	4.7077	306	1.2666	0.1950	1.2666	1.1254
No log	4.7385	308	1.0009	0.2000	1.0009	1.0005
No log	4.7692	310	0.6113	0.3091	0.6113	0.7819
No log	4.8	312	0.5365	0.4340	0.5365	0.7325
No log	4.8308	314	0.5946	0.4128	0.5946	0.7711
No log	4.8615	316	0.7920	0.2829	0.7920	0.8900
No log	4.8923	318	0.9201	0.2000	0.9201	0.9592
No log	4.9231	320	0.9379	0.2000	0.9379	0.9684
No log	4.9538	322	0.7962	0.2510	0.7962	0.8923
No log	4.9846	324	0.5592	0.3091	0.5592	0.7478
No log	5.0154	326	0.5726	0.3091	0.5726	0.7567
No log	5.0462	328	0.5220	0.3962	0.5220	0.7225
No log	5.0769	330	0.4822	0.3939	0.4822	0.6944
No log	5.1077	332	0.4954	0.3892	0.4954	0.7039
No log	5.1385	334	0.5862	0.3665	0.5862	0.7656
No log	5.1692	336	0.5882	0.3628	0.5882	0.7669
No log	5.2	338	0.6060	0.3548	0.6060	0.7784
No log	5.2308	340	0.6860	0.2489	0.6860	0.8283
No log	5.2615	342	0.6432	0.2857	0.6432	0.8020
No log	5.2923	344	0.5614	0.3892	0.5614	0.7492
No log	5.3231	346	0.5875	0.3548	0.5875	0.7665
No log	5.3538	348	0.8163	0.1937	0.8163	0.9035
No log	5.3846	350	1.1911	0.2204	1.1911	1.0914
No log	5.4154	352	1.1864	0.2204	1.1864	1.0892
No log	5.4462	354	0.8757	0.2000	0.8757	0.9358
No log	5.4769	356	0.5575	0.3623	0.5575	0.7467
No log	5.5077	358	0.4415	0.5602	0.4415	0.6644
No log	5.5385	360	0.4384	0.5699	0.4384	0.6621
No log	5.5692	362	0.4737	0.4872	0.4737	0.6883
No log	5.6	364	0.7225	0.2863	0.7225	0.8500
No log	5.6308	366	0.8848	0.2778	0.8848	0.9406
No log	5.6615	368	0.7673	0.3333	0.7673	0.8760
No log	5.6923	370	0.5330	0.3704	0.5330	0.7300
No log	5.7231	372	0.4561	0.5556	0.4561	0.6754
No log	5.7538	374	0.4583	0.5652	0.4583	0.6770
No log	5.7846	376	0.4547	0.5152	0.4547	0.6743
No log	5.8154	378	0.5404	0.4128	0.5404	0.7351
No log	5.8462	380	0.6174	0.3242	0.6174	0.7858
No log	5.8769	382	0.5631	0.3180	0.5631	0.7504
No log	5.9077	384	0.5030	0.4833	0.5030	0.7092
No log	5.9385	386	0.4691	0.48	0.4691	0.6849
No log	5.9692	388	0.4555	0.48	0.4555	0.6749
No log	6.0	390	0.4704	0.48	0.4704	0.6859
No log	6.0308	392	0.5405	0.4341	0.5405	0.7352
No log	6.0615	394	0.6057	0.3514	0.6057	0.7782
No log	6.0923	396	0.7498	0.3103	0.7498	0.8659
No log	6.1231	398	0.7523	0.2797	0.7523	0.8673
No log	6.1538	400	0.7700	0.2782	0.7700	0.8775
No log	6.1846	402	0.6801	0.2134	0.6801	0.8247
No log	6.2154	404	0.5772	0.4389	0.5772	0.7597
No log	6.2462	406	0.5049	0.4930	0.5049	0.7106
No log	6.2769	408	0.5334	0.4340	0.5334	0.7303
No log	6.3077	410	0.7207	0.2131	0.7207	0.8490
No log	6.3385	412	1.0107	0.3121	1.0107	1.0053
No log	6.3692	414	1.0559	0.2648	1.0559	1.0276
No log	6.4	416	0.8892	0.2821	0.8892	0.9430
No log	6.4308	418	0.7859	0.2852	0.7859	0.8865
No log	6.4615	420	0.7545	0.2852	0.7545	0.8686
No log	6.4923	422	0.6946	0.2581	0.6946	0.8334
No log	6.5231	424	0.8121	0.2852	0.8121	0.9011
No log	6.5538	426	1.0072	0.2222	1.0072	1.0036
No log	6.5846	428	1.1055	0.2208	1.1055	1.0514
No log	6.6154	430	0.9696	0.2000	0.9696	0.9847
No log	6.6462	432	0.7619	0.2852	0.7619	0.8728
No log	6.6769	434	0.5679	0.3585	0.5679	0.7536
No log	6.7077	436	0.4745	0.5	0.4745	0.6888
No log	6.7385	438	0.4511	0.5233	0.4511	0.6717
No log	6.7692	440	0.4695	0.5152	0.4695	0.6852
No log	6.8	442	0.5562	0.3242	0.5562	0.7458
No log	6.8308	444	0.7426	0.2558	0.7426	0.8617
No log	6.8615	446	1.0120	0.2483	1.0120	1.0060
No log	6.8923	448	1.2527	0.2566	1.2527	1.1192
No log	6.9231	450	1.2052	0.2393	1.2052	1.0978
No log	6.9538	452	0.9750	0.2281	0.9750	0.9874
No log	6.9846	454	0.7133	0.3359	0.7133	0.8446
No log	7.0154	456	0.6110	0.2961	0.6110	0.7816
No log	7.0462	458	0.5588	0.3271	0.5588	0.7475
No log	7.0769	460	0.5764	0.2489	0.5764	0.7592
No log	7.1077	462	0.6235	0.2787	0.6235	0.7896
No log	7.1385	464	0.6566	0.3277	0.6566	0.8103
No log	7.1692	466	0.7142	0.2996	0.7142	0.8451
No log	7.2	468	0.6593	0.3360	0.6593	0.8120
No log	7.2308	470	0.5668	0.36	0.5668	0.7529
No log	7.2615	472	0.5669	0.36	0.5669	0.7529
No log	7.2923	474	0.5708	0.36	0.5708	0.7555
No log	7.3231	476	0.6007	0.4118	0.6007	0.7751
No log	7.3538	478	0.6517	0.3808	0.6517	0.8073
No log	7.3846	480	0.7393	0.2885	0.7393	0.8598
No log	7.4154	482	0.7817	0.2000	0.7817	0.8842
No log	7.4462	484	0.7650	0.2548	0.7650	0.8747
No log	7.4769	486	0.6590	0.3443	0.6590	0.8118
No log	7.5077	488	0.5599	0.3028	0.5599	0.7482
No log	7.5385	490	0.5230	0.4081	0.5230	0.7232
No log	7.5692	492	0.5390	0.4185	0.5390	0.7342
No log	7.6	494	0.6031	0.3091	0.6031	0.7766
No log	7.6308	496	0.7354	0.3558	0.7354	0.8575
No log	7.6615	498	0.8017	0.3043	0.8017	0.8954
0.4532	7.6923	500	0.7760	0.3043	0.7760	0.8809
0.4532	7.7231	502	0.6979	0.3147	0.6979	0.8354
0.4532	7.7538	504	0.5813	0.3548	0.5813	0.7624
0.4532	7.7846	506	0.5322	0.3398	0.5322	0.7295
0.4532	7.8154	508	0.5178	0.4118	0.5178	0.7196
0.4532	7.8462	510	0.5364	0.3892	0.5364	0.7324
0.4532	7.8769	512	0.6255	0.2963	0.6255	0.7909
0.4532	7.9077	514	0.7270	0.3156	0.7270	0.8526
0.4532	7.9385	516	0.7206	0.3178	0.7206	0.8489
0.4532	7.9692	518	0.6506	0.3527	0.6506	0.8066
0.4532	8.0	520	0.6227	0.3274	0.6227	0.7891
0.4532	8.0308	522	0.6143	0.3274	0.6143	0.7838
0.4532	8.0615	524	0.6237	0.3559	0.6237	0.7898
0.4532	8.0923	526	0.6180	0.3247	0.6180	0.7861
0.4532	8.1231	528	0.6121	0.3188	0.6121	0.7824
0.4532	8.1538	530	0.6633	0.2846	0.6633	0.8144
0.4532	8.1846	532	0.6637	0.3115	0.6637	0.8147
0.4532	8.2154	534	0.6099	0.3739	0.6099	0.7809
0.4532	8.2462	536	0.6064	0.3778	0.6064	0.7787
0.4532	8.2769	538	0.5983	0.3778	0.5983	0.7735
0.4532	8.3077	540	0.5859	0.3684	0.5859	0.7655
0.4532	8.3385	542	0.6300	0.3739	0.6300	0.7937
0.4532	8.3692	544	0.6855	0.2787	0.6855	0.8280
0.4532	8.4	546	0.6787	0.2531	0.6787	0.8238
0.4532	8.4308	548	0.6775	0.2531	0.6775	0.8231
0.4532	8.4615	550	0.6629	0.2531	0.6629	0.8142
0.4532	8.4923	552	0.6600	0.2531	0.6600	0.8124
0.4532	8.5231	554	0.6411	0.2920	0.6411	0.8007
0.4532	8.5538	556	0.6342	0.2920	0.6342	0.7964
0.4532	8.5846	558	0.6239	0.2941	0.6239	0.7899
0.4532	8.6154	560	0.6038	0.2897	0.6038	0.7770
0.4532	8.6462	562	0.5599	0.3242	0.5599	0.7483
0.4532	8.6769	564	0.5344	0.3684	0.5344	0.7310
0.4532	8.7077	566	0.5359	0.3684	0.5359	0.7321
0.4532	8.7385	568	0.5758	0.3143	0.5758	0.7588
0.4532	8.7692	570	0.6150	0.3162	0.6150	0.7842
0.4532	8.8	572	0.6645	0.2829	0.6645	0.8152
0.4532	8.8308	574	0.6757	0.2829	0.6757	0.8220
0.4532	8.8615	576	0.6633	0.3071	0.6633	0.8144
0.4532	8.8923	578	0.6373	0.2771	0.6373	0.7983
0.4532	8.9231	580	0.6185	0.3138	0.6185	0.7865
0.4532	8.9538	582	0.5882	0.2811	0.5882	0.7669
0.4532	8.9846	584	0.6000	0.3103	0.6000	0.7746
0.4532	9.0154	586	0.6383	0.3092	0.6383	0.7989
0.4532	9.0462	588	0.7027	0.3050	0.7027	0.8383
0.4532	9.0769	590	0.7446	0.2490	0.7446	0.8629
0.4532	9.1077	592	0.7486	0.2490	0.7486	0.8652
0.4532	9.1385	594	0.7177	0.2727	0.7177	0.8472
0.4532	9.1692	596	0.6903	0.3071	0.6903	0.8309
0.4532	9.2	598	0.6773	0.3071	0.6773	0.8230
0.4532	9.2308	600	0.6733	0.3071	0.6733	0.8206
0.4532	9.2615	602	0.6693	0.3071	0.6693	0.8181
0.4532	9.2923	604	0.6535	0.3092	0.6535	0.8084
0.4532	9.3231	606	0.6453	0.3443	0.6453	0.8033
0.4532	9.3538	608	0.6257	0.3138	0.6257	0.7910
0.4532	9.3846	610	0.5974	0.2857	0.5974	0.7729
0.4532	9.4154	612	0.5809	0.2727	0.5809	0.7622
0.4532	9.4462	614	0.5616	0.4	0.5616	0.7494
0.4532	9.4769	616	0.5569	0.4051	0.5569	0.7463
0.4532	9.5077	618	0.5565	0.36	0.5565	0.7460
0.4532	9.5385	620	0.5662	0.2744	0.5662	0.7525
0.4532	9.5692	622	0.5893	0.2511	0.5893	0.7676
0.4532	9.6	624	0.6212	0.3162	0.6212	0.7882
0.4532	9.6308	626	0.6539	0.3092	0.6539	0.8086
0.4532	9.6615	628	0.6780	0.3092	0.6780	0.8234
0.4532	9.6923	630	0.6887	0.3092	0.6887	0.8299
0.4532	9.7231	632	0.6871	0.3092	0.6871	0.8289
0.4532	9.7538	634	0.6882	0.3092	0.6882	0.8296
0.4532	9.7846	636	0.6860	0.3092	0.6860	0.8282
0.4532	9.8154	638	0.6772	0.3092	0.6772	0.8229
0.4532	9.8462	640	0.6645	0.3092	0.6645	0.8152
0.4532	9.8769	642	0.6541	0.3092	0.6541	0.8088
0.4532	9.9077	644	0.6476	0.3092	0.6476	0.8048
0.4532	9.9385	646	0.6434	0.3092	0.6434	0.8021
0.4532	9.9692	648	0.6417	0.3092	0.6417	0.8011
0.4532	10.0	650	0.6406	0.3092	0.6406	0.8004

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1