tuned-albert-tiny

This model is a fine-tuned version of ckiplab/albert-tiny-chinese on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0039
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 1.0

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.698	0.2	1	0.6885	0.4375	0.2188	0.5	0.3043
0.6793	0.4	2	0.6837	0.4375	0.2188	0.5	0.3043
0.6833	0.6	3	0.6783	0.875	0.8889	0.8889	0.875
0.6739	0.8	4	0.6724	0.9375	0.9375	0.9444	0.9373
0.6703	1.0	5	0.6671	0.9375	0.9375	0.9444	0.9373
0.6599	1.2	6	0.6605	0.9375	0.9375	0.9444	0.9373
0.654	1.4	7	0.6526	0.9375	0.9375	0.9444	0.9373
0.6426	1.6	8	0.6437	0.9375	0.9375	0.9444	0.9373
0.6378	1.8	9	0.6344	0.9375	0.9375	0.9444	0.9373
0.6327	2.0	10	0.6236	0.9375	0.9375	0.9444	0.9373
0.6305	2.2	11	0.6111	0.9375	0.9375	0.9444	0.9373
0.5902	2.4	12	0.5976	0.9375	0.9375	0.9444	0.9373
0.5765	2.6	13	0.5827	0.875	0.8730	0.8730	0.8730
0.5619	2.8	14	0.5664	0.875	0.8730	0.8730	0.8730
0.5529	3.0	15	0.5495	0.875	0.8730	0.8730	0.8730
0.5189	3.2	16	0.5325	0.875	0.8730	0.8730	0.8730
0.5294	3.4	17	0.5156	0.875	0.8730	0.8730	0.8730
0.499	3.6	18	0.4994	0.875	0.8730	0.8730	0.8730
0.457	3.8	19	0.4840	0.875	0.8730	0.8730	0.8730
0.4422	4.0	20	0.4693	0.875	0.8730	0.8730	0.8730
0.4423	4.2	21	0.4551	0.9375	0.9375	0.9444	0.9373
0.3861	4.4	22	0.4416	0.9375	0.9375	0.9444	0.9373
0.4059	4.6	23	0.4283	0.9375	0.9375	0.9444	0.9373
0.4159	4.8	24	0.4149	0.9375	0.9375	0.9444	0.9373
0.3541	5.0	25	0.4023	0.9375	0.9375	0.9444	0.9373
0.3483	5.2	26	0.3902	0.9375	0.9375	0.9444	0.9373
0.3873	5.4	27	0.3782	0.9375	0.9375	0.9444	0.9373
0.3213	5.6	28	0.3668	0.9375	0.9375	0.9444	0.9373
0.2977	5.8	29	0.3559	0.9375	0.9375	0.9444	0.9373
0.2864	6.0	30	0.3449	0.9375	0.9375	0.9444	0.9373
0.2746	6.2	31	0.3344	0.9375	0.9375	0.9444	0.9373
0.299	6.4	32	0.3239	0.9375	0.9375	0.9444	0.9373
0.2817	6.6	33	0.3133	0.9375	0.9375	0.9444	0.9373
0.2429	6.8	34	0.3035	0.9375	0.9375	0.9444	0.9373
0.2244	7.0	35	0.2940	0.9375	0.9375	0.9444	0.9373
0.2126	7.2	36	0.2852	0.9375	0.9375	0.9444	0.9373
0.2422	7.4	37	0.2758	0.9375	0.9375	0.9444	0.9373
0.2007	7.6	38	0.2675	0.9375	0.9375	0.9444	0.9373
0.2312	7.8	39	0.2584	0.9375	0.9375	0.9444	0.9373
0.1849	8.0	40	0.2507	0.9375	0.9375	0.9444	0.9373
0.2149	8.2	41	0.2416	0.9375	0.9375	0.9444	0.9373
0.167	8.4	42	0.2331	0.9375	0.9375	0.9444	0.9373
0.1966	8.6	43	0.2222	0.9375	0.9375	0.9444	0.9373
0.1516	8.8	44	0.2125	0.9375	0.9375	0.9444	0.9373
0.1444	9.0	45	0.2037	0.9375	0.9375	0.9444	0.9373
0.1379	9.2	46	0.1960	0.9375	0.9375	0.9444	0.9373
0.1338	9.4	47	0.1893	0.9375	0.9375	0.9444	0.9373
0.1563	9.6	48	0.1777	0.9375	0.9375	0.9444	0.9373
0.1445	9.8	49	0.1618	0.9375	0.9375	0.9444	0.9373
0.1138	10.0	50	0.1483	0.9375	0.9375	0.9444	0.9373
0.1273	10.2	51	0.1332	1.0	1.0	1.0	1.0
0.1037	10.4	52	0.1220	1.0	1.0	1.0	1.0
0.1031	10.6	53	0.1132	1.0	1.0	1.0	1.0
0.0972	10.8	54	0.1064	1.0	1.0	1.0	1.0
0.1086	11.0	55	0.0994	1.0	1.0	1.0	1.0
0.0884	11.2	56	0.0938	1.0	1.0	1.0	1.0
0.0906	11.4	57	0.0886	1.0	1.0	1.0	1.0
0.0797	11.6	58	0.0841	1.0	1.0	1.0	1.0
0.0806	11.8	59	0.0801	1.0	1.0	1.0	1.0
0.0789	12.0	60	0.0762	1.0	1.0	1.0	1.0
0.0724	12.2	61	0.0727	1.0	1.0	1.0	1.0
0.0693	12.4	62	0.0694	1.0	1.0	1.0	1.0
0.0658	12.6	63	0.0665	1.0	1.0	1.0	1.0
0.0632	12.8	64	0.0637	1.0	1.0	1.0	1.0
0.0561	13.0	65	0.0611	1.0	1.0	1.0	1.0
0.0577	13.2	66	0.0587	1.0	1.0	1.0	1.0
0.0598	13.4	67	0.0564	1.0	1.0	1.0	1.0
0.0532	13.6	68	0.0542	1.0	1.0	1.0	1.0
0.0516	13.8	69	0.0522	1.0	1.0	1.0	1.0
0.0492	14.0	70	0.0503	1.0	1.0	1.0	1.0
0.0483	14.2	71	0.0485	1.0	1.0	1.0	1.0
0.0465	14.4	72	0.0468	1.0	1.0	1.0	1.0
0.0453	14.6	73	0.0452	1.0	1.0	1.0	1.0
0.0438	14.8	74	0.0437	1.0	1.0	1.0	1.0
0.0405	15.0	75	0.0423	1.0	1.0	1.0	1.0
0.0398	15.2	76	0.0409	1.0	1.0	1.0	1.0
0.0383	15.4	77	0.0397	1.0	1.0	1.0	1.0
0.0354	15.6	78	0.0385	1.0	1.0	1.0	1.0
0.0372	15.8	79	0.0373	1.0	1.0	1.0	1.0
0.0355	16.0	80	0.0362	1.0	1.0	1.0	1.0
0.0364	16.2	81	0.0352	1.0	1.0	1.0	1.0
0.0338	16.4	82	0.0342	1.0	1.0	1.0	1.0
0.0324	16.6	83	0.0333	1.0	1.0	1.0	1.0
0.0319	16.8	84	0.0324	1.0	1.0	1.0	1.0
0.0316	17.0	85	0.0316	1.0	1.0	1.0	1.0
0.0314	17.2	86	0.0308	1.0	1.0	1.0	1.0
0.0305	17.4	87	0.0300	1.0	1.0	1.0	1.0
0.0275	17.6	88	0.0293	1.0	1.0	1.0	1.0
0.0278	17.8	89	0.0286	1.0	1.0	1.0	1.0
0.0282	18.0	90	0.0280	1.0	1.0	1.0	1.0
0.0263	18.2	91	0.0274	1.0	1.0	1.0	1.0
0.0269	18.4	92	0.0268	1.0	1.0	1.0	1.0
0.0249	18.6	93	0.0262	1.0	1.0	1.0	1.0
0.0256	18.8	94	0.0256	1.0	1.0	1.0	1.0
0.023	19.0	95	0.0251	1.0	1.0	1.0	1.0
0.0255	19.2	96	0.0246	1.0	1.0	1.0	1.0
0.0245	19.4	97	0.0241	1.0	1.0	1.0	1.0
0.0235	19.6	98	0.0236	1.0	1.0	1.0	1.0
0.0213	19.8	99	0.0232	1.0	1.0	1.0	1.0
0.0218	20.0	100	0.0228	1.0	1.0	1.0	1.0
0.0228	20.2	101	0.0224	1.0	1.0	1.0	1.0
0.0205	20.4	102	0.0220	1.0	1.0	1.0	1.0
0.0213	20.6	103	0.0216	1.0	1.0	1.0	1.0
0.0205	20.8	104	0.0212	1.0	1.0	1.0	1.0
0.0223	21.0	105	0.0208	1.0	1.0	1.0	1.0
0.0211	21.2	106	0.0205	1.0	1.0	1.0	1.0
0.0198	21.4	107	0.0202	1.0	1.0	1.0	1.0
0.0198	21.6	108	0.0198	1.0	1.0	1.0	1.0
0.0187	21.8	109	0.0195	1.0	1.0	1.0	1.0
0.0183	22.0	110	0.0192	1.0	1.0	1.0	1.0
0.0181	22.2	111	0.0189	1.0	1.0	1.0	1.0
0.0197	22.4	112	0.0186	1.0	1.0	1.0	1.0
0.0179	22.6	113	0.0184	1.0	1.0	1.0	1.0
0.019	22.8	114	0.0181	1.0	1.0	1.0	1.0
0.0186	23.0	115	0.0178	1.0	1.0	1.0	1.0
0.0181	23.2	116	0.0176	1.0	1.0	1.0	1.0
0.0174	23.4	117	0.0173	1.0	1.0	1.0	1.0
0.0163	23.6	118	0.0171	1.0	1.0	1.0	1.0
0.0164	23.8	119	0.0169	1.0	1.0	1.0	1.0
0.016	24.0	120	0.0166	1.0	1.0	1.0	1.0
0.0161	24.2	121	0.0164	1.0	1.0	1.0	1.0
0.0155	24.4	122	0.0162	1.0	1.0	1.0	1.0
0.0152	24.6	123	0.0160	1.0	1.0	1.0	1.0
0.0151	24.8	124	0.0158	1.0	1.0	1.0	1.0
0.0161	25.0	125	0.0156	1.0	1.0	1.0	1.0
0.0152	25.2	126	0.0154	1.0	1.0	1.0	1.0
0.0146	25.4	127	0.0152	1.0	1.0	1.0	1.0
0.0145	25.6	128	0.0151	1.0	1.0	1.0	1.0
0.0148	25.8	129	0.0149	1.0	1.0	1.0	1.0
0.0139	26.0	130	0.0147	1.0	1.0	1.0	1.0
0.0144	26.2	131	0.0145	1.0	1.0	1.0	1.0
0.0143	26.4	132	0.0144	1.0	1.0	1.0	1.0
0.0139	26.6	133	0.0142	1.0	1.0	1.0	1.0
0.014	26.8	134	0.0141	1.0	1.0	1.0	1.0
0.0129	27.0	135	0.0139	1.0	1.0	1.0	1.0
0.0136	27.2	136	0.0138	1.0	1.0	1.0	1.0
0.0129	27.4	137	0.0136	1.0	1.0	1.0	1.0
0.0135	27.6	138	0.0135	1.0	1.0	1.0	1.0
0.0128	27.8	139	0.0133	1.0	1.0	1.0	1.0
0.0131	28.0	140	0.0132	1.0	1.0	1.0	1.0
0.0132	28.2	141	0.0131	1.0	1.0	1.0	1.0
0.0122	28.4	142	0.0129	1.0	1.0	1.0	1.0
0.0128	28.6	143	0.0128	1.0	1.0	1.0	1.0
0.0125	28.8	144	0.0127	1.0	1.0	1.0	1.0
0.0122	29.0	145	0.0125	1.0	1.0	1.0	1.0
0.0121	29.2	146	0.0124	1.0	1.0	1.0	1.0
0.0126	29.4	147	0.0123	1.0	1.0	1.0	1.0
0.0127	29.6	148	0.0122	1.0	1.0	1.0	1.0
0.0116	29.8	149	0.0121	1.0	1.0	1.0	1.0
0.0118	30.0	150	0.0120	1.0	1.0	1.0	1.0
0.0125	30.2	151	0.0118	1.0	1.0	1.0	1.0
0.0112	30.4	152	0.0117	1.0	1.0	1.0	1.0
0.0117	30.6	153	0.0116	1.0	1.0	1.0	1.0
0.0113	30.8	154	0.0115	1.0	1.0	1.0	1.0
0.0112	31.0	155	0.0114	1.0	1.0	1.0	1.0
0.0112	31.2	156	0.0113	1.0	1.0	1.0	1.0
0.0104	31.4	157	0.0112	1.0	1.0	1.0	1.0
0.0112	31.6	158	0.0111	1.0	1.0	1.0	1.0
0.0108	31.8	159	0.0110	1.0	1.0	1.0	1.0
0.0105	32.0	160	0.0109	1.0	1.0	1.0	1.0
0.0106	32.2	161	0.0108	1.0	1.0	1.0	1.0
0.0109	32.4	162	0.0108	1.0	1.0	1.0	1.0
0.0104	32.6	163	0.0107	1.0	1.0	1.0	1.0
0.0102	32.8	164	0.0106	1.0	1.0	1.0	1.0
0.0101	33.0	165	0.0105	1.0	1.0	1.0	1.0
0.0099	33.2	166	0.0104	1.0	1.0	1.0	1.0
0.0098	33.4	167	0.0103	1.0	1.0	1.0	1.0
0.0095	33.6	168	0.0103	1.0	1.0	1.0	1.0
0.0097	33.8	169	0.0102	1.0	1.0	1.0	1.0
0.01	34.0	170	0.0101	1.0	1.0	1.0	1.0
0.01	34.2	171	0.0100	1.0	1.0	1.0	1.0
0.0097	34.4	172	0.0099	1.0	1.0	1.0	1.0
0.0097	34.6	173	0.0099	1.0	1.0	1.0	1.0
0.0095	34.8	174	0.0098	1.0	1.0	1.0	1.0
0.0091	35.0	175	0.0097	1.0	1.0	1.0	1.0
0.0095	35.2	176	0.0096	1.0	1.0	1.0	1.0
0.009	35.4	177	0.0096	1.0	1.0	1.0	1.0
0.0095	35.6	178	0.0095	1.0	1.0	1.0	1.0
0.0091	35.8	179	0.0094	1.0	1.0	1.0	1.0
0.0092	36.0	180	0.0094	1.0	1.0	1.0	1.0
0.0091	36.2	181	0.0093	1.0	1.0	1.0	1.0
0.0095	36.4	182	0.0092	1.0	1.0	1.0	1.0
0.0089	36.6	183	0.0092	1.0	1.0	1.0	1.0
0.0095	36.8	184	0.0091	1.0	1.0	1.0	1.0
0.0092	37.0	185	0.0091	1.0	1.0	1.0	1.0
0.0088	37.2	186	0.0090	1.0	1.0	1.0	1.0
0.0088	37.4	187	0.0089	1.0	1.0	1.0	1.0
0.0092	37.6	188	0.0089	1.0	1.0	1.0	1.0
0.0083	37.8	189	0.0088	1.0	1.0	1.0	1.0
0.0091	38.0	190	0.0088	1.0	1.0	1.0	1.0
0.0084	38.2	191	0.0087	1.0	1.0	1.0	1.0
0.0082	38.4	192	0.0086	1.0	1.0	1.0	1.0
0.0086	38.6	193	0.0086	1.0	1.0	1.0	1.0
0.0085	38.8	194	0.0085	1.0	1.0	1.0	1.0
0.0086	39.0	195	0.0085	1.0	1.0	1.0	1.0
0.0086	39.2	196	0.0084	1.0	1.0	1.0	1.0
0.0085	39.4	197	0.0084	1.0	1.0	1.0	1.0
0.0083	39.6	198	0.0083	1.0	1.0	1.0	1.0
0.0083	39.8	199	0.0083	1.0	1.0	1.0	1.0
0.008	40.0	200	0.0082	1.0	1.0	1.0	1.0
0.008	40.2	201	0.0082	1.0	1.0	1.0	1.0
0.0083	40.4	202	0.0081	1.0	1.0	1.0	1.0
0.0076	40.6	203	0.0081	1.0	1.0	1.0	1.0
0.0079	40.8	204	0.0080	1.0	1.0	1.0	1.0
0.0079	41.0	205	0.0080	1.0	1.0	1.0	1.0
0.0079	41.2	206	0.0079	1.0	1.0	1.0	1.0
0.0078	41.4	207	0.0079	1.0	1.0	1.0	1.0
0.0079	41.6	208	0.0078	1.0	1.0	1.0	1.0
0.0078	41.8	209	0.0078	1.0	1.0	1.0	1.0
0.0076	42.0	210	0.0077	1.0	1.0	1.0	1.0
0.008	42.2	211	0.0077	1.0	1.0	1.0	1.0
0.0074	42.4	212	0.0076	1.0	1.0	1.0	1.0
0.0076	42.6	213	0.0076	1.0	1.0	1.0	1.0
0.0076	42.8	214	0.0076	1.0	1.0	1.0	1.0
0.0073	43.0	215	0.0075	1.0	1.0	1.0	1.0
0.0077	43.2	216	0.0075	1.0	1.0	1.0	1.0
0.0071	43.4	217	0.0074	1.0	1.0	1.0	1.0
0.0069	43.6	218	0.0074	1.0	1.0	1.0	1.0
0.0071	43.8	219	0.0074	1.0	1.0	1.0	1.0
0.0072	44.0	220	0.0073	1.0	1.0	1.0	1.0
0.0075	44.2	221	0.0073	1.0	1.0	1.0	1.0
0.0065	44.4	222	0.0072	1.0	1.0	1.0	1.0
0.0072	44.6	223	0.0072	1.0	1.0	1.0	1.0
0.0066	44.8	224	0.0072	1.0	1.0	1.0	1.0
0.0068	45.0	225	0.0071	1.0	1.0	1.0	1.0
0.0073	45.2	226	0.0071	1.0	1.0	1.0	1.0
0.0068	45.4	227	0.0071	1.0	1.0	1.0	1.0
0.0069	45.6	228	0.0070	1.0	1.0	1.0	1.0
0.0066	45.8	229	0.0070	1.0	1.0	1.0	1.0
0.0061	46.0	230	0.0070	1.0	1.0	1.0	1.0
0.007	46.2	231	0.0069	1.0	1.0	1.0	1.0
0.0069	46.4	232	0.0069	1.0	1.0	1.0	1.0
0.0068	46.6	233	0.0069	1.0	1.0	1.0	1.0
0.0065	46.8	234	0.0068	1.0	1.0	1.0	1.0
0.0065	47.0	235	0.0068	1.0	1.0	1.0	1.0
0.0065	47.2	236	0.0068	1.0	1.0	1.0	1.0
0.0062	47.4	237	0.0067	1.0	1.0	1.0	1.0
0.0062	47.6	238	0.0067	1.0	1.0	1.0	1.0
0.0064	47.8	239	0.0067	1.0	1.0	1.0	1.0
0.0065	48.0	240	0.0066	1.0	1.0	1.0	1.0
0.0063	48.2	241	0.0066	1.0	1.0	1.0	1.0
0.0063	48.4	242	0.0066	1.0	1.0	1.0	1.0
0.0064	48.6	243	0.0066	1.0	1.0	1.0	1.0
0.0063	48.8	244	0.0065	1.0	1.0	1.0	1.0
0.0064	49.0	245	0.0065	1.0	1.0	1.0	1.0
0.0064	49.2	246	0.0065	1.0	1.0	1.0	1.0
0.0066	49.4	247	0.0064	1.0	1.0	1.0	1.0
0.0064	49.6	248	0.0064	1.0	1.0	1.0	1.0
0.0059	49.8	249	0.0064	1.0	1.0	1.0	1.0
0.0057	50.0	250	0.0064	1.0	1.0	1.0	1.0
0.006	50.2	251	0.0063	1.0	1.0	1.0	1.0
0.006	50.4	252	0.0063	1.0	1.0	1.0	1.0
0.006	50.6	253	0.0063	1.0	1.0	1.0	1.0
0.0061	50.8	254	0.0062	1.0	1.0	1.0	1.0
0.0062	51.0	255	0.0062	1.0	1.0	1.0	1.0
0.0063	51.2	256	0.0062	1.0	1.0	1.0	1.0
0.0059	51.4	257	0.0062	1.0	1.0	1.0	1.0
0.006	51.6	258	0.0061	1.0	1.0	1.0	1.0
0.0061	51.8	259	0.0061	1.0	1.0	1.0	1.0
0.0064	52.0	260	0.0061	1.0	1.0	1.0	1.0
0.006	52.2	261	0.0061	1.0	1.0	1.0	1.0
0.0064	52.4	262	0.0060	1.0	1.0	1.0	1.0
0.0063	52.6	263	0.0060	1.0	1.0	1.0	1.0
0.006	52.8	264	0.0060	1.0	1.0	1.0	1.0
0.0063	53.0	265	0.0060	1.0	1.0	1.0	1.0
0.0059	53.2	266	0.0059	1.0	1.0	1.0	1.0
0.006	53.4	267	0.0059	1.0	1.0	1.0	1.0
0.0059	53.6	268	0.0059	1.0	1.0	1.0	1.0
0.0061	53.8	269	0.0059	1.0	1.0	1.0	1.0
0.006	54.0	270	0.0059	1.0	1.0	1.0	1.0
0.0059	54.2	271	0.0058	1.0	1.0	1.0	1.0
0.0061	54.4	272	0.0058	1.0	1.0	1.0	1.0
0.0056	54.6	273	0.0058	1.0	1.0	1.0	1.0
0.006	54.8	274	0.0058	1.0	1.0	1.0	1.0
0.006	55.0	275	0.0057	1.0	1.0	1.0	1.0
0.0057	55.2	276	0.0057	1.0	1.0	1.0	1.0
0.0059	55.4	277	0.0057	1.0	1.0	1.0	1.0
0.0056	55.6	278	0.0057	1.0	1.0	1.0	1.0
0.0058	55.8	279	0.0057	1.0	1.0	1.0	1.0
0.0059	56.0	280	0.0056	1.0	1.0	1.0	1.0
0.0057	56.2	281	0.0056	1.0	1.0	1.0	1.0
0.0056	56.4	282	0.0056	1.0	1.0	1.0	1.0
0.0055	56.6	283	0.0056	1.0	1.0	1.0	1.0
0.0055	56.8	284	0.0056	1.0	1.0	1.0	1.0
0.0055	57.0	285	0.0055	1.0	1.0	1.0	1.0
0.0054	57.2	286	0.0055	1.0	1.0	1.0	1.0
0.0054	57.4	287	0.0055	1.0	1.0	1.0	1.0
0.0054	57.6	288	0.0055	1.0	1.0	1.0	1.0
0.0052	57.8	289	0.0055	1.0	1.0	1.0	1.0
0.0059	58.0	290	0.0054	1.0	1.0	1.0	1.0
0.0053	58.2	291	0.0054	1.0	1.0	1.0	1.0
0.0055	58.4	292	0.0054	1.0	1.0	1.0	1.0
0.0052	58.6	293	0.0054	1.0	1.0	1.0	1.0
0.0053	58.8	294	0.0054	1.0	1.0	1.0	1.0
0.0049	59.0	295	0.0054	1.0	1.0	1.0	1.0
0.0049	59.2	296	0.0053	1.0	1.0	1.0	1.0
0.0053	59.4	297	0.0053	1.0	1.0	1.0	1.0
0.0055	59.6	298	0.0053	1.0	1.0	1.0	1.0
0.0053	59.8	299	0.0053	1.0	1.0	1.0	1.0
0.0053	60.0	300	0.0053	1.0	1.0	1.0	1.0
0.0049	60.2	301	0.0053	1.0	1.0	1.0	1.0
0.005	60.4	302	0.0052	1.0	1.0	1.0	1.0
0.0052	60.6	303	0.0052	1.0	1.0	1.0	1.0
0.0051	60.8	304	0.0052	1.0	1.0	1.0	1.0
0.0054	61.0	305	0.0052	1.0	1.0	1.0	1.0
0.005	61.2	306	0.0052	1.0	1.0	1.0	1.0
0.0053	61.4	307	0.0052	1.0	1.0	1.0	1.0
0.0052	61.6	308	0.0051	1.0	1.0	1.0	1.0
0.005	61.8	309	0.0051	1.0	1.0	1.0	1.0
0.0051	62.0	310	0.0051	1.0	1.0	1.0	1.0
0.0047	62.2	311	0.0051	1.0	1.0	1.0	1.0
0.0049	62.4	312	0.0051	1.0	1.0	1.0	1.0
0.0051	62.6	313	0.0051	1.0	1.0	1.0	1.0
0.0051	62.8	314	0.0051	1.0	1.0	1.0	1.0
0.0052	63.0	315	0.0050	1.0	1.0	1.0	1.0
0.0052	63.2	316	0.0050	1.0	1.0	1.0	1.0
0.0049	63.4	317	0.0050	1.0	1.0	1.0	1.0
0.005	63.6	318	0.0050	1.0	1.0	1.0	1.0
0.0048	63.8	319	0.0050	1.0	1.0	1.0	1.0
0.0047	64.0	320	0.0050	1.0	1.0	1.0	1.0
0.0048	64.2	321	0.0050	1.0	1.0	1.0	1.0
0.0048	64.4	322	0.0049	1.0	1.0	1.0	1.0
0.0047	64.6	323	0.0049	1.0	1.0	1.0	1.0
0.0048	64.8	324	0.0049	1.0	1.0	1.0	1.0
0.0049	65.0	325	0.0049	1.0	1.0	1.0	1.0
0.0046	65.2	326	0.0049	1.0	1.0	1.0	1.0
0.0049	65.4	327	0.0049	1.0	1.0	1.0	1.0
0.0047	65.6	328	0.0049	1.0	1.0	1.0	1.0
0.005	65.8	329	0.0049	1.0	1.0	1.0	1.0
0.005	66.0	330	0.0048	1.0	1.0	1.0	1.0
0.0045	66.2	331	0.0048	1.0	1.0	1.0	1.0
0.0049	66.4	332	0.0048	1.0	1.0	1.0	1.0
0.0048	66.6	333	0.0048	1.0	1.0	1.0	1.0
0.0044	66.8	334	0.0048	1.0	1.0	1.0	1.0
0.0046	67.0	335	0.0048	1.0	1.0	1.0	1.0
0.0049	67.2	336	0.0048	1.0	1.0	1.0	1.0
0.0045	67.4	337	0.0048	1.0	1.0	1.0	1.0
0.0047	67.6	338	0.0047	1.0	1.0	1.0	1.0
0.0045	67.8	339	0.0047	1.0	1.0	1.0	1.0
0.0049	68.0	340	0.0047	1.0	1.0	1.0	1.0
0.0044	68.2	341	0.0047	1.0	1.0	1.0	1.0
0.0042	68.4	342	0.0047	1.0	1.0	1.0	1.0
0.0048	68.6	343	0.0047	1.0	1.0	1.0	1.0
0.0048	68.8	344	0.0047	1.0	1.0	1.0	1.0
0.0044	69.0	345	0.0047	1.0	1.0	1.0	1.0
0.0044	69.2	346	0.0047	1.0	1.0	1.0	1.0
0.0047	69.4	347	0.0046	1.0	1.0	1.0	1.0
0.0046	69.6	348	0.0046	1.0	1.0	1.0	1.0
0.0047	69.8	349	0.0046	1.0	1.0	1.0	1.0
0.0043	70.0	350	0.0046	1.0	1.0	1.0	1.0
0.0047	70.2	351	0.0046	1.0	1.0	1.0	1.0
0.0046	70.4	352	0.0046	1.0	1.0	1.0	1.0
0.0047	70.6	353	0.0046	1.0	1.0	1.0	1.0
0.0045	70.8	354	0.0046	1.0	1.0	1.0	1.0
0.0048	71.0	355	0.0046	1.0	1.0	1.0	1.0
0.0044	71.2	356	0.0046	1.0	1.0	1.0	1.0
0.0044	71.4	357	0.0046	1.0	1.0	1.0	1.0
0.0043	71.6	358	0.0045	1.0	1.0	1.0	1.0
0.0047	71.8	359	0.0045	1.0	1.0	1.0	1.0
0.0043	72.0	360	0.0045	1.0	1.0	1.0	1.0
0.0042	72.2	361	0.0045	1.0	1.0	1.0	1.0
0.0041	72.4	362	0.0045	1.0	1.0	1.0	1.0
0.0048	72.6	363	0.0045	1.0	1.0	1.0	1.0
0.0044	72.8	364	0.0045	1.0	1.0	1.0	1.0
0.0046	73.0	365	0.0045	1.0	1.0	1.0	1.0
0.0044	73.2	366	0.0045	1.0	1.0	1.0	1.0
0.0045	73.4	367	0.0045	1.0	1.0	1.0	1.0
0.0046	73.6	368	0.0045	1.0	1.0	1.0	1.0
0.0046	73.8	369	0.0044	1.0	1.0	1.0	1.0
0.0042	74.0	370	0.0044	1.0	1.0	1.0	1.0
0.0044	74.2	371	0.0044	1.0	1.0	1.0	1.0
0.0044	74.4	372	0.0044	1.0	1.0	1.0	1.0
0.0044	74.6	373	0.0044	1.0	1.0	1.0	1.0
0.0044	74.8	374	0.0044	1.0	1.0	1.0	1.0
0.0044	75.0	375	0.0044	1.0	1.0	1.0	1.0
0.0044	75.2	376	0.0044	1.0	1.0	1.0	1.0
0.0042	75.4	377	0.0044	1.0	1.0	1.0	1.0
0.004	75.6	378	0.0044	1.0	1.0	1.0	1.0
0.0043	75.8	379	0.0044	1.0	1.0	1.0	1.0
0.0046	76.0	380	0.0044	1.0	1.0	1.0	1.0
0.0043	76.2	381	0.0043	1.0	1.0	1.0	1.0
0.0044	76.4	382	0.0043	1.0	1.0	1.0	1.0
0.0044	76.6	383	0.0043	1.0	1.0	1.0	1.0
0.0042	76.8	384	0.0043	1.0	1.0	1.0	1.0
0.0041	77.0	385	0.0043	1.0	1.0	1.0	1.0
0.0045	77.2	386	0.0043	1.0	1.0	1.0	1.0
0.0043	77.4	387	0.0043	1.0	1.0	1.0	1.0
0.0041	77.6	388	0.0043	1.0	1.0	1.0	1.0
0.0042	77.8	389	0.0043	1.0	1.0	1.0	1.0
0.0041	78.0	390	0.0043	1.0	1.0	1.0	1.0
0.0043	78.2	391	0.0043	1.0	1.0	1.0	1.0
0.0043	78.4	392	0.0043	1.0	1.0	1.0	1.0
0.0042	78.6	393	0.0043	1.0	1.0	1.0	1.0
0.0039	78.8	394	0.0043	1.0	1.0	1.0	1.0
0.0042	79.0	395	0.0042	1.0	1.0	1.0	1.0
0.0042	79.2	396	0.0042	1.0	1.0	1.0	1.0
0.0044	79.4	397	0.0042	1.0	1.0	1.0	1.0
0.0043	79.6	398	0.0042	1.0	1.0	1.0	1.0
0.0041	79.8	399	0.0042	1.0	1.0	1.0	1.0
0.0045	80.0	400	0.0042	1.0	1.0	1.0	1.0
0.0041	80.2	401	0.0042	1.0	1.0	1.0	1.0
0.004	80.4	402	0.0042	1.0	1.0	1.0	1.0
0.0043	80.6	403	0.0042	1.0	1.0	1.0	1.0
0.0042	80.8	404	0.0042	1.0	1.0	1.0	1.0
0.0042	81.0	405	0.0042	1.0	1.0	1.0	1.0
0.004	81.2	406	0.0042	1.0	1.0	1.0	1.0
0.0041	81.4	407	0.0042	1.0	1.0	1.0	1.0
0.0042	81.6	408	0.0042	1.0	1.0	1.0	1.0
0.0046	81.8	409	0.0042	1.0	1.0	1.0	1.0
0.0044	82.0	410	0.0042	1.0	1.0	1.0	1.0
0.0039	82.2	411	0.0042	1.0	1.0	1.0	1.0
0.0041	82.4	412	0.0041	1.0	1.0	1.0	1.0
0.0044	82.6	413	0.0041	1.0	1.0	1.0	1.0
0.004	82.8	414	0.0041	1.0	1.0	1.0	1.0
0.0038	83.0	415	0.0041	1.0	1.0	1.0	1.0
0.0042	83.2	416	0.0041	1.0	1.0	1.0	1.0
0.0042	83.4	417	0.0041	1.0	1.0	1.0	1.0
0.0041	83.6	418	0.0041	1.0	1.0	1.0	1.0
0.0042	83.8	419	0.0041	1.0	1.0	1.0	1.0
0.0043	84.0	420	0.0041	1.0	1.0	1.0	1.0
0.0044	84.2	421	0.0041	1.0	1.0	1.0	1.0
0.0038	84.4	422	0.0041	1.0	1.0	1.0	1.0
0.0039	84.6	423	0.0041	1.0	1.0	1.0	1.0
0.0041	84.8	424	0.0041	1.0	1.0	1.0	1.0
0.0039	85.0	425	0.0041	1.0	1.0	1.0	1.0
0.0041	85.2	426	0.0041	1.0	1.0	1.0	1.0
0.0038	85.4	427	0.0041	1.0	1.0	1.0	1.0
0.0039	85.6	428	0.0041	1.0	1.0	1.0	1.0
0.0038	85.8	429	0.0041	1.0	1.0	1.0	1.0
0.0039	86.0	430	0.0041	1.0	1.0	1.0	1.0
0.0039	86.2	431	0.0041	1.0	1.0	1.0	1.0
0.0041	86.4	432	0.0041	1.0	1.0	1.0	1.0
0.004	86.6	433	0.0040	1.0	1.0	1.0	1.0
0.0042	86.8	434	0.0040	1.0	1.0	1.0	1.0
0.0039	87.0	435	0.0040	1.0	1.0	1.0	1.0
0.0042	87.2	436	0.0040	1.0	1.0	1.0	1.0
0.0041	87.4	437	0.0040	1.0	1.0	1.0	1.0
0.004	87.6	438	0.0040	1.0	1.0	1.0	1.0
0.0039	87.8	439	0.0040	1.0	1.0	1.0	1.0
0.004	88.0	440	0.0040	1.0	1.0	1.0	1.0
0.004	88.2	441	0.0040	1.0	1.0	1.0	1.0
0.004	88.4	442	0.0040	1.0	1.0	1.0	1.0
0.004	88.6	443	0.0040	1.0	1.0	1.0	1.0
0.0039	88.8	444	0.0040	1.0	1.0	1.0	1.0
0.004	89.0	445	0.0040	1.0	1.0	1.0	1.0
0.0043	89.2	446	0.0040	1.0	1.0	1.0	1.0
0.0039	89.4	447	0.0040	1.0	1.0	1.0	1.0
0.0039	89.6	448	0.0040	1.0	1.0	1.0	1.0
0.004	89.8	449	0.0040	1.0	1.0	1.0	1.0
0.0039	90.0	450	0.0040	1.0	1.0	1.0	1.0
0.0039	90.2	451	0.0040	1.0	1.0	1.0	1.0
0.0038	90.4	452	0.0040	1.0	1.0	1.0	1.0
0.0039	90.6	453	0.0040	1.0	1.0	1.0	1.0
0.004	90.8	454	0.0040	1.0	1.0	1.0	1.0
0.004	91.0	455	0.0040	1.0	1.0	1.0	1.0
0.004	91.2	456	0.0040	1.0	1.0	1.0	1.0
0.0041	91.4	457	0.0040	1.0	1.0	1.0	1.0
0.0038	91.6	458	0.0040	1.0	1.0	1.0	1.0
0.0038	91.8	459	0.0040	1.0	1.0	1.0	1.0
0.004	92.0	460	0.0040	1.0	1.0	1.0	1.0
0.0037	92.2	461	0.0040	1.0	1.0	1.0	1.0
0.0037	92.4	462	0.0040	1.0	1.0	1.0	1.0
0.0041	92.6	463	0.0040	1.0	1.0	1.0	1.0
0.0037	92.8	464	0.0040	1.0	1.0	1.0	1.0
0.0037	93.0	465	0.0040	1.0	1.0	1.0	1.0
0.0039	93.2	466	0.0040	1.0	1.0	1.0	1.0
0.0039	93.4	467	0.0039	1.0	1.0	1.0	1.0
0.004	93.6	468	0.0039	1.0	1.0	1.0	1.0
0.004	93.8	469	0.0039	1.0	1.0	1.0	1.0
0.0035	94.0	470	0.0039	1.0	1.0	1.0	1.0
0.004	94.2	471	0.0039	1.0	1.0	1.0	1.0
0.0037	94.4	472	0.0039	1.0	1.0	1.0	1.0
0.0037	94.6	473	0.0039	1.0	1.0	1.0	1.0
0.004	94.8	474	0.0039	1.0	1.0	1.0	1.0
0.0038	95.0	475	0.0039	1.0	1.0	1.0	1.0
0.0038	95.2	476	0.0039	1.0	1.0	1.0	1.0
0.0038	95.4	477	0.0039	1.0	1.0	1.0	1.0
0.0038	95.6	478	0.0039	1.0	1.0	1.0	1.0
0.0039	95.8	479	0.0039	1.0	1.0	1.0	1.0
0.0042	96.0	480	0.0039	1.0	1.0	1.0	1.0
0.0038	96.2	481	0.0039	1.0	1.0	1.0	1.0
0.0042	96.4	482	0.0039	1.0	1.0	1.0	1.0
0.0041	96.6	483	0.0039	1.0	1.0	1.0	1.0
0.004	96.8	484	0.0039	1.0	1.0	1.0	1.0
0.0037	97.0	485	0.0039	1.0	1.0	1.0	1.0
0.0041	97.2	486	0.0039	1.0	1.0	1.0	1.0
0.0039	97.4	487	0.0039	1.0	1.0	1.0	1.0
0.0039	97.6	488	0.0039	1.0	1.0	1.0	1.0
0.004	97.8	489	0.0039	1.0	1.0	1.0	1.0
0.004	98.0	490	0.0039	1.0	1.0	1.0	1.0
0.0036	98.2	491	0.0039	1.0	1.0	1.0	1.0
0.0038	98.4	492	0.0039	1.0	1.0	1.0	1.0
0.0038	98.6	493	0.0039	1.0	1.0	1.0	1.0
0.0037	98.8	494	0.0039	1.0	1.0	1.0	1.0
0.0036	99.0	495	0.0039	1.0	1.0	1.0	1.0
0.0038	99.2	496	0.0039	1.0	1.0	1.0	1.0
0.0039	99.4	497	0.0039	1.0	1.0	1.0	1.0
0.004	99.6	498	0.0039	1.0	1.0	1.0	1.0
0.0039	99.8	499	0.0039	1.0	1.0	1.0	1.0
0.0036	100.0	500	0.0039	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0