Terjman-Ultra-v2.0

This model is a fine-tuned version of facebook/nllb-200-1.3B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.9337
• Bleu: 4.8885
• Gen Len: 16.0459

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: 0.0005
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
6.6891	0.0704	1000	3.4459	0.8596	14.2551
6.2545	0.1409	2000	3.0822	2.9243	16.4507
5.4107	0.2113	3000	2.9860	2.9056	16.7177
5.0102	0.2818	4000	2.9148	3.1886	16.3061
4.6213	0.3522	5000	2.8432	3.5032	16.7296
4.9863	0.4227	6000	2.7857	4.187	15.9983
4.5614	0.4931	7000	2.7248	3.5208	16.7194
4.1469	0.5636	8000	2.6843	4.184	16.3231
4.3793	0.6340	9000	2.6342	3.8132	17.2228
4.2737	0.7045	10000	2.6079	4.07	15.7415
4.0098	0.7749	11000	2.5870	4.2071	16.3656
3.8309	0.8454	12000	2.5269	3.3605	15.4371
3.9713	0.9158	13000	2.5155	4.3242	15.9575
4.0241	0.9862	14000	2.5326	4.0751	15.9575
3.4632	1.0566	15000	2.5462	3.8197	17.0799
3.5382	1.1271	16000	2.5220	4.0743	15.3503
3.5187	1.1975	17000	2.4616	5.4764	15.6224
3.5793	1.2680	18000	2.4852	3.3537	16.5578
3.6452	1.3384	19000	2.4461	3.519	16.3265
3.4359	1.4089	20000	2.4600	5.5669	15.2058
3.6518	1.4793	21000	2.4186	6.0195	15.4677
3.7683	1.5498	22000	2.3694	5.2203	15.8895
3.4833	1.6202	23000	2.4486	4.9786	15.9422
3.6165	1.6907	24000	2.3710	4.5996	16.0816
3.4191	1.7611	25000	2.3666	4.7903	16.5034
3.4423	1.8315	26000	2.3718	4.754	16.0187
3.4295	1.9020	27000	2.3907	4.6428	16.5085
3.4198	1.9724	28000	2.3725	4.5755	16.2092
2.7484	2.0428	29000	2.4854	4.8861	16.1276
3.0305	2.1133	30000	2.5031	3.5595	16.0986
2.7704	2.1837	31000	2.4430	4.1298	16.3776
2.6773	2.2542	32000	2.4557	5.0114	15.7092
2.7246	2.3246	33000	2.4671	5.2066	16.0697
2.8579	2.3951	34000	2.4292	3.5896	16.4422
2.6129	2.4655	35000	2.4293	4.791	15.9847
2.8967	2.5360	36000	2.3727	4.6733	15.6684
2.6233	2.6064	37000	2.4040	4.2326	16.4609
2.6149	2.6768	38000	2.3888	4.3608	15.8844
2.6728	2.7473	39000	2.3491	4.6057	16.1956
2.6636	2.8177	40000	2.3783	5.6461	15.6088
2.6735	2.8882	41000	2.3799	5.073	16.1241
2.7241	2.9586	42000	2.3670	5.1342	15.9983
2.5328	3.0290	43000	2.5021	4.9602	16.2194
1.9145	3.0995	44000	2.4558	4.7993	15.5102
2.2244	3.1699	45000	2.4524	4.1162	16.3248
2.2567	3.2404	46000	2.5178	4.5245	15.9558
2.294	3.3108	47000	2.4983	4.4901	16.2058
2.3862	3.3813	48000	2.5095	5.1193	15.8571
2.2477	3.4517	49000	2.4858	4.1379	16.9881
2.3509	3.5221	50000	2.5032	4.1952	16.1531
2.3102	3.5926	51000	2.5023	4.4216	15.9847
2.441	3.6630	52000	2.4936	3.7096	16.4065
2.3019	3.7335	53000	2.4234	3.8684	16.1769
2.2024	3.8039	54000	2.4291	5.0116	16.0578
2.2689	3.8744	55000	2.4430	4.0043	16.7755
2.1577	3.9448	56000	2.4509	4.8633	15.9592
1.785	4.0152	57000	2.5746	4.5874	16.1361
1.9347	4.0857	58000	2.5649	5.0178	16.0527
1.9808	4.1561	59000	2.6009	4.4131	16.4116
1.9854	4.2266	60000	2.5873	4.7677	15.7228
2.0202	4.2970	61000	2.5422	5.0606	15.6599
2.0033	4.3674	62000	2.5518	4.4881	16.2653
1.9158	4.4379	63000	2.5387	5.0229	16.2483
2.125	4.5083	64000	2.5571	4.1656	16.6088
2.0137	4.5788	65000	2.5340	4.7292	16.1701
1.8723	4.6492	66000	2.5842	4.9087	15.7568
2.0225	4.7197	67000	2.5545	4.1429	16.1497
1.8679	4.7901	68000	2.5638	5.2609	15.7738
1.8472	4.8606	69000	2.5156	4.5735	15.9218
1.9543	4.9310	70000	2.5079	4.906	15.9881
1.8092	5.0014	71000	2.5642	4.5605	16.2432
1.7592	5.0719	72000	2.5777	3.6716	16.4711
1.7159	5.1423	73000	2.6072	4.9653	16.1905
1.6754	5.2127	74000	2.6316	4.4122	15.898
1.6195	5.2832	75000	2.6771	4.0431	16.3861
1.6384	5.3536	76000	2.6935	5.0551	16.1429
1.7632	5.4241	77000	2.6253	4.4743	15.9388
1.688	5.4945	78000	2.6665	5.5042	15.9915
1.8595	5.5650	79000	2.5445	4.6794	15.9252
1.7015	5.6354	80000	2.6624	4.0659	16.4779
1.7354	5.7059	81000	2.6133	4.1619	16.2857
1.6104	5.7763	82000	2.6379	5.4246	15.9677
1.6839	5.8468	83000	2.6113	4.6878	16.8588
1.7686	5.9172	84000	2.6445	5.257	16.0663
1.8399	5.9877	85000	2.5868	4.9363	16.2908
1.6455	6.0580	86000	2.6474	4.6206	17.1259
1.6718	6.1285	87000	2.7320	4.7892	16.6633
1.4533	6.1989	88000	2.7056	3.8676	16.682
1.5536	6.2694	89000	2.7091	3.9213	16.6905
1.7204	6.3398	90000	2.7463	4.1039	16.4694
1.4792	6.4103	91000	2.7154	4.3398	16.648
1.537	6.4807	92000	2.7253	4.1753	16.3401
1.6187	6.5512	93000	2.6663	4.2894	16.1905
1.5657	6.6216	94000	2.7418	4.4755	16.6888
1.6295	6.6921	95000	2.6779	4.848	16.6412
1.5306	6.7625	96000	2.6492	5.3122	16.3027
1.6697	6.8330	97000	2.6867	4.4343	16.1446
1.4721	6.9034	98000	2.6813	4.6101	16.6446
1.5329	6.9738	99000	2.6823	4.5033	16.216
1.4067	7.0442	100000	2.7103	5.0443	15.835
1.3816	7.1147	101000	2.7325	5.0789	15.8316
1.311	7.1851	102000	2.7555	5.1451	16.284
1.4664	7.2556	103000	2.6874	3.9283	16.5935
1.5453	7.3260	104000	2.7086	4.8347	16.5289
1.5727	7.3965	105000	2.7367	5.0641	16.0323
1.5675	7.4669	106000	2.7503	4.6161	16.3078
1.3378	7.5374	107000	2.6980	5.0656	15.9507
1.3199	7.6078	108000	2.7340	4.6829	16.5612
1.6347	7.6783	109000	2.7229	4.8785	16.1633
1.4015	7.7487	110000	2.7497	4.1889	16.9473
1.3633	7.8191	111000	2.7426	4.4075	16.4422
1.5624	7.8896	112000	2.7186	4.8255	16.182
1.4975	7.9600	113000	2.7391	4.6228	16.568
1.3337	8.0304	114000	2.7663	4.3132	15.9031
1.4006	8.1009	115000	2.8008	4.2014	16.9728
1.3132	8.1713	116000	2.7794	4.4158	17.085
1.3336	8.2418	117000	2.7910	4.6605	16.2636
1.5381	8.3122	118000	2.7812	4.4988	16.2925
1.1517	8.3827	119000	2.7493	4.3933	15.9235
1.3308	8.4531	120000	2.7946	4.3191	15.9932
1.1764	8.5236	121000	2.7740	4.6101	16.1922
1.5374	8.5940	122000	2.7745	4.5565	17.1054
1.3018	8.6644	123000	2.7314	4.9639	16.2483
1.5729	8.7349	124000	2.7698	4.5458	16.0765
1.3693	8.8053	125000	2.7791	5.0225	16.0527
1.4307	8.8758	126000	2.7799	4.3834	16.3027
1.3749	8.9462	127000	2.7915	3.9254	16.9167
1.2609	9.0166	128000	2.7618	4.6557	16.8673
1.2557	9.0871	129000	2.8244	4.1262	16.1973
1.4725	9.1575	130000	2.8066	4.1449	16.284
1.4284	9.2280	131000	2.8090	5.1354	15.9779
1.3322	9.2984	132000	2.7639	4.6588	16.5493
1.1489	9.3689	133000	2.7769	5.2266	15.9167
1.262	9.4393	134000	2.8134	4.8189	16.0663
1.2346	9.5097	135000	2.7695	4.6959	16.1599
1.0491	9.5802	136000	2.8189	4.845	16.2653
1.3537	9.6506	137000	2.8207	4.2376	16.7347
1.4438	9.7211	138000	2.8136	4.3241	16.0544
1.2883	9.7915	139000	2.7900	4.4662	15.9796
1.3381	9.8620	140000	2.8331	4.3003	16.5068
1.2796	9.9324	141000	2.8247	4.6965	16.4439
1.2652	10.0028	142000	2.8077	5.1233	16.3707
1.1795	10.0733	143000	2.8172	5.1804	16.8793
1.2217	10.1437	144000	2.8104	5.3087	16.7806
1.3016	10.2142	145000	2.8293	5.2817	16.3997
1.1564	10.2846	146000	2.8465	5.1377	17.0221
1.2114	10.3550	147000	2.8405	5.0125	15.9269
1.3504	10.4255	148000	2.8711	4.7917	16.0068
1.3335	10.4959	149000	2.8585	4.57	16.1378
1.3274	10.5664	150000	2.8456	4.7502	16.3367
1.0467	10.6368	151000	2.8633	5.0383	15.9609
1.309	10.7073	152000	2.8229	4.3156	16.1429
1.1062	10.7777	153000	2.8184	5.2082	16.0731
1.1758	10.8482	154000	2.7997	5.2245	15.9643
1.2653	10.9186	155000	2.8498	5.2846	16.216
1.3163	10.9891	156000	2.8200	4.2698	16.869
1.3715	11.0595	157000	2.8605	5.0849	16.0986
0.9987	11.1299	158000	2.8596	4.4933	16.2976
1.2691	11.2003	159000	2.8512	4.7941	16.1412
1.1751	11.2708	160000	2.8393	5.1037	16.1361
1.2791	11.3412	161000	2.8499	5.6369	15.8095
1.0566	11.4117	162000	2.8406	4.6493	15.9966
1.2363	11.4821	163000	2.8612	4.4807	16.4014
1.345	11.5526	164000	2.8590	4.0666	16.1854
1.1792	11.6230	165000	2.8839	4.5874	16.0952
1.0981	11.6935	166000	2.8610	4.5198	15.9779
1.0925	11.7639	167000	2.8518	5.0022	15.9745
1.1742	11.8344	168000	2.8558	4.9338	15.9558
1.3488	11.9048	169000	2.8372	4.9993	15.9677
1.1964	11.9753	170000	2.8516	4.5687	16.1616
1.1715	12.0456	171000	2.8886	4.5276	16.3469
1.128	12.1161	172000	2.8819	4.8863	16.0306
1.2115	12.1865	173000	2.8719	4.7423	16.4048
1.1281	12.2570	174000	2.8919	4.3191	16.034
1.0576	12.3274	175000	2.9072	4.8987	16.2075
1.1515	12.3979	176000	2.8568	5.1984	16.034
1.1296	12.4683	177000	2.8684	5.2174	16.3724
1.456	12.5388	178000	2.8639	4.8868	16.3401
1.2807	12.6092	179000	2.8785	5.018	16.3486
1.1866	12.6797	180000	2.8733	4.9576	16.0544
1.1931	12.7501	181000	2.8401	4.7177	16.2534
1.1486	12.8206	182000	2.8685	5.1032	16.0459
1.2104	12.8910	183000	2.8631	4.8783	15.9949
1.1428	12.9614	184000	2.8668	4.7645	16.0459
1.0976	13.0318	185000	2.8846	4.6642	16.2007
1.0611	13.1023	186000	2.8810	4.5067	16.0425
1.0711	13.1727	187000	2.8775	4.9743	16.0051
1.2712	13.2432	188000	2.8670	5.0352	16.2177
1.0516	13.3136	189000	2.8558	4.1672	16.2806
1.2	13.3841	190000	2.8619	4.9017	16.3452
1.0126	13.4545	191000	2.8759	4.6954	16.2874
1.0652	13.5250	192000	2.8789	5.3468	16.4456
1.1844	13.5954	193000	2.8962	4.6962	16.1037
1.1374	13.6659	194000	2.8838	4.9879	15.9065
1.1999	13.7363	195000	2.8725	4.2651	16.1105
0.9954	13.8067	196000	2.8756	5.0682	15.9949
1.163	13.8772	197000	2.8974	4.1723	16.0391
1.1738	13.9476	198000	2.8713	4.6712	16.1361
1.0899	14.0180	199000	2.9027	4.9822	15.9762
1.2346	14.0885	200000	2.9010	5.0864	16.1207
1.0956	14.1589	201000	2.9035	4.4055	16.0544
1.1446	14.2294	202000	2.9002	4.582	16.3588
0.9949	14.2998	203000	2.8951	5.1352	16.0527
1.2153	14.3703	204000	2.8813	4.5622	16.0085
1.1138	14.4407	205000	2.8773	4.5463	15.9643
1.2021	14.5112	206000	2.9026	4.5149	16.1003
1.0817	14.5816	207000	2.8985	5.0807	15.7789
1.1802	14.6520	208000	2.9088	4.5588	16.0918
1.3543	14.7225	209000	2.8903	4.2761	15.9014
1.0815	14.7929	210000	2.9270	4.4964	16.1463
1.0905	14.8634	211000	2.8993	4.3412	16.1395
1.1252	14.9338	212000	2.8988	4.9343	15.9796
1.0231	15.0042	213000	2.8733	4.4952	16.2908
1.2023	15.0747	214000	2.8921	4.4615	16.0391
1.2546	15.1451	215000	2.8837	4.7048	16.2517
1.0258	15.2156	216000	2.9075	4.2096	16.3112
1.1917	15.2860	217000	2.9084	4.818	16.0697
1.1694	15.3565	218000	2.9049	4.843	16.0034
1.0451	15.4269	219000	2.9146	4.5113	16.1531
1.1279	15.4973	220000	2.9020	4.489	16.0459
1.174	15.5678	221000	2.9061	4.7477	16.0391
1.1274	15.6382	222000	2.9042	4.5273	16.1071
1.0846	15.7087	223000	2.9003	4.5379	16.0221
1.139	15.7791	224000	2.8999	4.7583	16.1395
1.0993	15.8496	225000	2.8933	4.9551	15.9711
1.0882	15.9200	226000	2.9055	5.4251	16.0408
0.9254	15.9905	227000	2.9071	4.5936	16.0578
1.0445	16.0609	228000	2.8906	5.2254	16.0561
1.2771	16.1313	229000	2.9068	5.0882	16.0731
0.9633	16.2018	230000	2.9259	4.9449	16.0969
1.1984	16.2722	231000	2.9079	5.3876	16.0374
1.0531	16.3426	232000	2.9248	5.1192	16.1037
1.1539	16.4131	233000	2.9392	4.7122	16.1207
0.9931	16.4835	234000	2.9241	4.8306	16.2993
1.0548	16.5540	235000	2.8957	4.6001	16.4201
0.9867	16.6244	236000	2.9092	5.1751	16.0374
1.1337	16.6949	237000	2.9106	3.9361	16.648
1.087	16.7653	238000	2.9122	4.8122	16.3418
1.2067	16.8358	239000	2.9233	4.5164	16.3639
0.9976	16.9062	240000	2.9053	4.9985	16.2789
1.0627	16.9767	241000	2.9000	4.9112	16.2653
1.1295	17.0471	242000	2.9291	4.4967	16.0425
0.9967	17.1175	243000	2.9282	4.6972	16.1412
1.0997	17.1880	244000	2.9184	4.9748	16.0544
1.0444	17.2584	245000	2.9286	4.8878	16.0017
1.0748	17.3288	246000	2.9201	4.4368	16.3827
1.0679	17.3993	247000	2.9141	5.3541	15.9966
0.8814	17.4697	248000	2.9165	5.1777	15.9983
1.0072	17.5402	249000	2.9130	5.1468	16.0374
1.1415	17.6106	250000	2.9204	4.9025	16.3384
1.031	17.6811	251000	2.9025	5.1009	16.3061
1.0673	17.7515	252000	2.9090	5.1812	15.7891
0.8635	17.8220	253000	2.9160	5.1568	15.9949
1.2725	17.8924	254000	2.9186	5.3835	16.1276
1.1684	17.9629	255000	2.9238	5.1239	16.3486
1.1006	18.0333	256000	2.9155	5.2746	16.1088
0.9955	18.1037	257000	2.9204	5.2604	16.0323
1.1708	18.1741	258000	2.9262	5.19	16.6173
1.0442	18.2446	259000	2.9266	5.0004	16.5442
1.141	18.3150	260000	2.9210	5.1213	16.3469
1.1163	18.3855	261000	2.9348	5.1672	16.131
1.085	18.4559	262000	2.9151	5.2033	16.2789
1.0033	18.5264	263000	2.9302	5.0061	16.0901
1.0073	18.5968	264000	2.9280	4.6995	16.0748
1.1814	18.6673	265000	2.9186	4.7896	16.3554
0.9287	18.7377	266000	2.9288	4.9969	16.0221
1.1234	18.8082	267000	2.9133	5.1568	16.0748
1.0378	18.8786	268000	2.9153	4.8344	16.5646
1.064	18.9490	269000	2.9150	5.254	15.9558
1.2062	19.0194	270000	2.9148	5.0728	16.0544
1.1069	19.0899	271000	2.9136	5.4229	16.0612
1.1096	19.1603	272000	2.9186	5.3152	16.3605
1.0369	19.2308	273000	2.9200	5.281	15.8044
0.8743	19.3012	274000	2.9185	4.8795	16.3418
0.9482	19.3717	275000	2.9238	5.2526	16.0765
1.1007	19.4421	276000	2.9170	5.2618	16.0799
1.0224	19.5126	277000	2.9287	5.2919	16.0085
0.9918	19.5830	278000	2.9296	5.5088	15.8299
1.0817	19.6535	279000	2.9321	4.9857	16.0272
1.1075	19.7239	280000	2.9310	5.0935	15.8367
1.0768	19.7944	281000	2.9308	4.7035	16.4031
1.1408	19.8648	282000	2.9368	4.7911	16.3741
1.0251	19.9352	283000	2.9304	4.7622	16.6701
0.9346	20.0056	284000	2.9225	4.7329	16.0595
1.2284	20.0761	285000	2.9314	5.0146	16.0714
1.2118	20.1465	286000	2.9265	5.2616	16.1037
0.9837	20.2170	287000	2.9364	4.9266	16.1156
1.0224	20.2874	288000	2.9228	5.2119	16.0952
1.1366	20.3579	289000	2.9222	5.434	15.7568
1.0418	20.4283	290000	2.9332	5.0331	15.8316
1.0098	20.4988	291000	2.9282	4.1982	16.3282
1.1775	20.5692	292000	2.9349	4.9446	16.1378
0.9572	20.6397	293000	2.9383	5.1175	16.3724
1.0786	20.7101	294000	2.9220	5.1348	16.3163
1.1096	20.7805	295000	2.9269	5.0591	16.0765
0.9558	20.8510	296000	2.9338	4.7023	16.5901
1.0308	20.9214	297000	2.9247	5.0225	15.7959
1.0042	20.9919	298000	2.9341	4.8961	16.0765
1.0267	21.0623	299000	2.9278	5.1071	16.0731
1.2155	21.1327	300000	2.9314	4.9309	16.0646
1.2004	21.2032	301000	2.9247	4.8481	16.335
1.0165	21.2736	302000	2.9294	4.9122	16.0527
1.1247	21.3441	303000	2.9365	4.8783	16.1412
1.0666	21.4145	304000	2.9349	5.1393	16.3571
1.0375	21.4850	305000	2.9365	4.8797	16.3844
1.1734	21.5554	306000	2.9319	4.5563	16.3656
1.1414	21.6258	307000	2.9287	5.0586	16.1122
0.8809	21.6963	308000	2.9280	4.913	16.3571
0.891	21.7667	309000	2.9328	4.9783	16.0714
1.1583	21.8372	310000	2.9281	5.2954	16.3163
1.1143	21.9076	311000	2.9381	4.4317	16.3673
1.0738	21.9781	312000	2.9278	5.1005	16.0561
1.0462	22.0485	313000	2.9269	5.0991	16.3776
1.0469	22.1189	314000	2.9305	5.0457	16.3537
1.0301	22.1894	315000	2.9266	4.8626	16.2976
1.0643	22.2598	316000	2.9292	4.8589	16.318
1.1818	22.3303	317000	2.9278	4.9165	16.3299
0.9349	22.4007	318000	2.9274	5.421	15.8231
1.0025	22.4711	319000	2.9329	5.0132	16.3401
1.1008	22.5416	320000	2.9312	5.102	16.1037
0.9837	22.6120	321000	2.9317	5.3437	15.9983
0.9487	22.6825	322000	2.9298	4.9865	16.3673
1.2555	22.7529	323000	2.9371	5.5376	15.7925
1.0052	22.8234	324000	2.9270	4.6871	16.1395
0.9734	22.8938	325000	2.9208	5.1808	15.9966
0.9408	22.9643	326000	2.9210	4.8337	16.0408
0.9675	23.0347	327000	2.9295	5.1529	16.0663
0.9617	23.1051	328000	2.9315	4.6056	16.051
0.9561	23.1756	329000	2.9274	4.8682	16.3418
0.9879	23.2460	330000	2.9346	5.0841	16.0714
1.0884	23.3164	331000	2.9243	5.1953	16.3112
0.8401	23.3869	332000	2.9278	4.8003	16.3707
1.2766	23.4573	333000	2.9343	4.8876	16.0697
1.1677	23.5278	334000	2.9362	4.887	16.0493
0.9774	23.5982	335000	2.9311	4.896	16.0799
1.0608	23.6687	336000	2.9386	4.6856	16.3673
0.8934	23.7391	337000	2.9397	4.8809	16.3265
1.1396	23.8096	338000	2.9304	5.0543	16.0459
1.0944	23.8800	339000	2.9324	5.0194	16.3486
0.984	23.9505	340000	2.9352	4.7387	16.3537
1.1456	24.0209	341000	2.9383	4.8138	16.3401
1.1322	24.0913	342000	2.9410	4.7429	16.0663
0.905	24.1617	343000	2.9338	4.9936	16.3724
1.0333	24.2322	344000	2.9328	5.0091	16.3741
0.9525	24.3026	345000	2.9395	4.8653	16.0799
1.1309	24.3731	346000	2.9381	4.8656	16.0629
0.963	24.4435	347000	2.9335	5.1557	16.034
1.0025	24.5140	348000	2.9353	4.9638	16.0731
0.9965	24.5844	349000	2.9339	5.1535	16.0323
1.0682	24.6549	350000	2.9319	5.0452	16.0595
1.031	24.7253	351000	2.9324	4.9694	16.0561
1.0942	24.7958	352000	2.9335	4.7568	16.3622
0.9532	24.8662	353000	2.9332	4.8012	16.381
1.0247	24.9367	354000	2.9298	4.6234	16.1293
1.0779	25.0070	355000	2.9304	4.7035	16.0425
1.0487	25.0775	356000	2.9345	5.0451	16.1105
1.1426	25.1479	357000	2.9351	4.8482	16.0714
0.913	25.2184	358000	2.9383	4.9993	16.0782
0.9917	25.2888	359000	2.9368	4.798	16.0765
0.9222	25.3593	360000	2.9338	5.0204	16.034
1.1049	25.4297	361000	2.9327	4.8632	16.0799
0.9763	25.5002	362000	2.9315	4.867	16.0935
0.931	25.5706	363000	2.9334	4.8458	16.0697
0.935	25.6411	364000	2.9335	4.9935	16.0646
0.9747	25.7115	365000	2.9298	5.0908	16.0408
1.0824	25.7820	366000	2.9292	5.1439	16.0425
1.0177	25.8524	367000	2.9265	5.3954	16.051
1.0008	25.9228	368000	2.9289	5.2655	16.0
0.9565	25.9933	369000	2.9306	5.0133	16.0272
1.0475	26.0637	370000	2.9320	5.2138	16.318
0.9048	26.1341	371000	2.9326	4.9529	16.352
1.0166	26.2046	372000	2.9332	4.9885	16.0408
1.0456	26.2750	373000	2.9316	4.8559	16.352
1.1897	26.3455	374000	2.9296	5.2049	16.3435
1.0344	26.4159	375000	2.9305	5.01	16.3299
1.0596	26.4864	376000	2.9304	4.851	16.3384
1.0694	26.5568	377000	2.9302	4.6993	16.3401
1.0411	26.6273	378000	2.9322	4.8344	16.318
1.0634	26.6977	379000	2.9313	4.8518	16.3282
1.0566	26.7681	380000	2.9317	5.2275	16.3401
1.179	26.8386	381000	2.9322	4.6902	16.3673
1.0528	26.9090	382000	2.9287	4.7733	16.352
0.9514	26.9795	383000	2.9323	5.0822	16.0544
1.0685	27.0499	384000	2.9339	4.9152	16.3231
0.876	27.1203	385000	2.9336	4.9237	16.0391
0.9887	27.1908	386000	2.9353	4.8213	16.352
0.8493	27.2612	387000	2.9361	4.9265	16.3299
1.0028	27.3317	388000	2.9355	4.9826	16.0442
1.0236	27.4021	389000	2.9363	4.7092	16.2993
1.039	27.4726	390000	2.9359	4.7759	16.3282
1.0936	27.5430	391000	2.9353	5.03	16.0102
1.1139	27.6134	392000	2.9324	4.9901	16.0442
1.1163	27.6839	393000	2.9338	5.0953	16.0425
0.9756	27.7543	394000	2.9329	4.8934	16.3095
1.0898	27.8248	395000	2.9339	4.9609	16.0068
0.9132	27.8952	396000	2.9343	4.953	16.0612
0.9844	27.9657	397000	2.9342	4.8338	16.0442
1.0955	28.0361	398000	2.9351	5.0458	16.0374
1.0665	28.1065	399000	2.9341	4.8638	16.3588
1.1509	28.1770	400000	2.9348	4.9702	16.0
1.0704	28.2474	401000	2.9349	4.9021	16.3282
0.9899	28.3179	402000	2.9341	5.158	16.0442
1.0594	28.3883	403000	2.9337	4.9649	16.0935
0.9158	28.4587	404000	2.9340	4.8808	16.3282
1.032	28.5292	405000	2.9327	4.8547	16.3197
0.925	28.5996	406000	2.9339	4.8705	16.3163
1.0657	28.6701	407000	2.9331	4.9936	16.0306
1.0144	28.7405	408000	2.9330	4.9811	16.0187
0.9437	28.8110	409000	2.9346	4.9979	16.0085
0.9643	28.8814	410000	2.9338	4.9682	16.0442
1.0702	28.9519	411000	2.9334	5.1245	16.0459
1.0072	29.0223	412000	2.9342	4.9582	16.0646
1.0488	29.0927	413000	2.9331	5.0087	16.034
0.9643	29.1632	414000	2.9339	4.9143	16.0646
1.0709	29.2336	415000	2.9335	4.9751	16.0544
1.0575	29.3040	416000	2.9345	4.9501	16.3656
1.0033	29.3745	417000	2.9340	4.8056	16.3571
0.9961	29.4449	418000	2.9337	4.9987	16.0272
0.96	29.5154	419000	2.9336	4.8117	16.3554
1.0353	29.5858	420000	2.9339	4.7601	16.3027
0.9832	29.6563	421000	2.9348	4.9861	16.0425
1.1156	29.7267	422000	2.9342	4.7668	16.3503
1.2103	29.7972	423000	2.9337	4.8112	16.3418
0.988	29.8676	424000	2.9338	4.9124	16.0374
0.902	29.9381	425000	2.9337	4.8885	16.0459

Framework versions

• Transformers 4.48.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.21.0