learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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_steps: 500
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	F0.5
0.2671	0.0340	1000	0.2442	0.9172	0.9081	0.9273	0.9176	0.9119
0.2188	0.0680	2000	0.2383	0.9241	0.9114	0.9387	0.9248	0.9167
0.2204	0.1020	3000	0.2081	0.9287	0.9449	0.9098	0.9270	0.9376
0.2101	0.1360	4000	0.2258	0.93	0.9294	0.9299	0.9297	0.9295
0.2087	0.1700	5000	0.2156	0.9238	0.9566	0.8871	0.9206	0.9419
0.2006	0.2040	6000	0.2123	0.9331	0.9307	0.9351	0.9329	0.9316
0.1973	0.2380	7000	0.1832	0.9387	0.9377	0.9392	0.9384	0.9380
0.2055	0.2720	8000	0.2003	0.9338	0.9399	0.9263	0.9330	0.9371
0.2002	0.3060	9000	0.2280	0.9351	0.9271	0.9438	0.9354	0.9304
0.1927	0.3400	10000	0.2304	0.9333	0.9106	0.9603	0.9348	0.9201
0.2001	0.3740	11000	0.1964	0.9349	0.9395	0.9289	0.9342	0.9374
0.1918	0.4080	12000	0.1843	0.9356	0.9364	0.9340	0.9352	0.9360
0.1913	0.4420	13000	0.2252	0.9321	0.9609	0.9	0.9295	0.9481
0.1852	0.4760	14000	0.1806	0.9362	0.9272	0.9459	0.9365	0.9309
0.1796	0.5100	15000	0.2018	0.9423	0.9482	0.9351	0.9416	0.9456
0.1862	0.5441	16000	0.2066	0.9344	0.9446	0.9222	0.9332	0.9400
0.1942	0.5781	17000	0.2123	0.9367	0.9189	0.9572	0.9376	0.9263
0.1864	0.6121	18000	0.1822	0.9377	0.9564	0.9165	0.9360	0.9482
0.1939	0.6461	19000	0.2125	0.9359	0.9447	0.9253	0.9349	0.9408
0.185	0.6801	20000	0.2039	0.9364	0.9312	0.9418	0.9364	0.9333
0.1844	0.7141	21000	0.1742	0.9392	0.9396	0.9381	0.9389	0.9393
0.1818	0.7481	22000	0.1892	0.9405	0.9407	0.9397	0.9402	0.9405
0.1828	0.7821	23000	0.2015	0.9379	0.9502	0.9237	0.9367	0.9447
0.1771	0.8161	24000	0.1985	0.94	0.9452	0.9335	0.9393	0.9428
0.1772	0.8501	25000	0.1672	0.9426	0.9540	0.9294	0.9415	0.9489
0.1859	0.8841	26000	0.1748	0.9362	0.9126	0.9639	0.9376	0.9225
0.189	0.9181	27000	0.1642	0.9464	0.9427	0.95	0.9463	0.9442
0.1774	0.9521	28000	0.1767	0.9462	0.9369	0.9562	0.9464	0.9407
0.1658	0.9861	29000	0.1958	0.9431	0.9343	0.9526	0.9433	0.9379
0.1574	1.0201	30000	0.2119	0.9428	0.9329	0.9536	0.9432	0.9370
0.1588	1.0541	31000	0.1801	0.9408	0.9548	0.9247	0.9395	0.9486
0.1578	1.0881	32000	0.2292	0.9418	0.9525	0.9294	0.9408	0.9478
0.1597	1.1221	33000	0.1971	0.9415	0.9417	0.9407	0.9412	0.9415
0.155	1.1561	34000	0.2235	0.9426	0.9409	0.9438	0.9424	0.9415
0.1594	1.1901	35000	0.1763	0.9449	0.9425	0.9469	0.9447	0.9434
0.1655	1.2241	36000	0.1773	0.9444	0.9420	0.9464	0.9442	0.9429
0.1682	1.2581	37000	0.2021	0.94	0.9383	0.9412	0.9398	0.9389
0.1495	1.2921	38000	0.1954	0.9421	0.9364	0.9479	0.9421	0.9386
0.1567	1.3261	39000	0.2083	0.9451	0.9481	0.9412	0.9446	0.9467
0.1687	1.3601	40000	0.1800	0.9415	0.9573	0.9237	0.9402	0.9504
0.1599	1.3941	41000	0.1816	0.9444	0.9580	0.9289	0.9432	0.9520
0.1655	1.4281	42000	0.1852	0.9472	0.9423	0.9521	0.9472	0.9443
0.1579	1.4621	43000	0.1888	0.9446	0.9452	0.9433	0.9443	0.9449
0.1606	1.4961	44000	0.1880	0.9456	0.9381	0.9536	0.9458	0.9412
0.1522	1.5301	45000	0.2139	0.9464	0.9464	0.9459	0.9461	0.9463
0.1497	1.5641	46000	0.1971	0.9436	0.9470	0.9392	0.9431	0.9454
0.159	1.5982	47000	0.1935	0.9418	0.9192	0.9680	0.9430	0.9286
0.1582	1.6322	48000	0.1841	0.9441	0.9344	0.9546	0.9444	0.9384
0.1505	1.6662	49000	0.2033	0.9405	0.9322	0.9495	0.9408	0.9356
0.1503	1.7002	50000	0.1974	0.9454	0.9377	0.9536	0.9456	0.9408
0.1651	1.7342	51000	0.1995	0.9438	0.9335	0.9552	0.9442	0.9378
0.1544	1.7682	52000	0.1831	0.9462	0.9325	0.9613	0.9467	0.9381
0.1618	1.8022	53000	0.2018	0.9413	0.9577	0.9227	0.9399	0.9505
0.1585	1.8362	54000	0.1897	0.9456	0.9342	0.9582	0.9461	0.9389
0.1604	1.8702	55000	0.1774	0.9472	0.9478	0.9459	0.9469	0.9474
0.1598	1.9042	56000	0.1740	0.9451	0.9556	0.9330	0.9442	0.9510
0.1522	1.9382	57000	0.2008	0.9449	0.9499	0.9387	0.9443	0.9476
0.1477	1.9722	58000	0.1893	0.9449	0.9389	0.9510	0.9449	0.9413
0.1414	2.0062	59000	0.2214	0.9459	0.9454	0.9459	0.9456	0.9455
0.1263	2.0402	60000	0.2393	0.9464	0.9543	0.9371	0.9456	0.9508
0.1281	2.0742	61000	0.2349	0.9479	0.9461	0.9495	0.9478	0.9468
0.1368	2.1082	62000	0.2080	0.9449	0.9444	0.9448	0.9446	0.9445
0.1299	2.1422	63000	0.2494	0.9421	0.9478	0.9351	0.9414	0.9452
0.1315	2.1762	64000	0.2268	0.9464	0.9515	0.9402	0.9458	0.9492
0.1385	2.2102	65000	0.2346	0.9464	0.9510	0.9407	0.9458	0.9489
0.1314	2.2442	66000	0.2218	0.9428	0.9564	0.9273	0.9416	0.9504
0.1404	2.2782	67000	0.2182	0.9454	0.9368	0.9546	0.9456	0.9403
0.1388	2.3122	68000	0.2175	0.9469	0.9370	0.9577	0.9472	0.9410
0.1318	2.3462	69000	0.2439	0.9423	0.9530	0.9299	0.9413	0.9483
0.1302	2.3802	70000	0.2290	0.9456	0.9472	0.9433	0.9452	0.9464
0.1249	2.4142	71000	0.2438	0.9433	0.9470	0.9387	0.9428	0.9453
0.1424	2.4482	72000	0.2356	0.9423	0.9273	0.9593	0.9430	0.9335
0.1378	2.4822	73000	0.2081	0.9467	0.9473	0.9454	0.9463	0.9469
0.1305	2.5162	74000	0.2488	0.9446	0.9504	0.9376	0.9440	0.9478
0.1257	2.5502	75000	0.2489	0.9454	0.9472	0.9428	0.9450	0.9463
0.1249	2.5842	76000	0.2599	0.9428	0.9623	0.9211	0.9413	0.9538
0.1314	2.6182	77000	0.2259	0.9472	0.9520	0.9412	0.9466	0.9499
0.1301	2.6522	78000	0.2352	0.9472	0.9464	0.9474	0.9469	0.9466
0.1287	2.6863	79000	0.2348	0.9436	0.9484	0.9376	0.9430	0.9462
0.1252	2.7203	80000	0.2225	0.9462	0.9454	0.9464	0.9459	0.9456
0.1258	2.7543	81000	0.2302	0.9454	0.9399	0.9510	0.9454	0.9421
0.1345	2.7883	82000	0.2191	0.9479	0.9479	0.9474	0.9477	0.9478
0.1344	2.8223	83000	0.2374	0.9459	0.9552	0.9351	0.9450	0.9511
0.1219	2.8563	84000	0.2361	0.9454	0.9542	0.9351	0.9445	0.9503
0.1346	2.8903	85000	0.2135	0.9472	0.9568	0.9361	0.9463	0.9526
0.1323	2.9243	86000	0.2245	0.9449	0.9561	0.9320	0.9439	0.9512
0.1341	2.9583	87000	0.2200	0.9444	0.9518	0.9356	0.9436	0.9485
0.1257	2.9923	88000	0.2280	0.9492	0.9508	0.9469	0.9489	0.9500
0.1126	3.0263	89000	0.2499	0.9469	0.9525	0.9402	0.9463	0.95
0.0964	3.0603	90000	0.2556	0.9467	0.9520	0.9402	0.9461	0.9496
0.1104	3.0943	91000	0.2575	0.9451	0.9533	0.9356	0.9443	0.9497
0.105	3.1283	92000	0.2610	0.9469	0.9520	0.9407	0.9463	0.9497
0.1098	3.1623	93000	0.2514	0.9459	0.9431	0.9485	0.9458	0.9442
0.0875	3.1963	94000	0.2900	0.9441	0.9489	0.9381	0.9435	0.9467
0.103	3.2303	95000	0.2538	0.9487	0.9536	0.9428	0.9482	0.9514
0.1037	3.2643	96000	0.2641	0.9436	0.9428	0.9438	0.9433	0.9430
0.1132	3.2983	97000	0.2516	0.9433	0.9456	0.9402	0.9429	0.9445
0.1034	3.3323	98000	0.2816	0.9433	0.9451	0.9407	0.9429	0.9442
0.1157	3.3663	99000	0.2556	0.9467	0.9510	0.9412	0.9461	0.9491
0.1086	3.4003	100000	0.2515	0.9469	0.9506	0.9423	0.9464	0.9489
0.1002	3.4343	101000	0.2601	0.9459	0.9463	0.9448	0.9456	0.9460
0.1065	3.4683	102000	0.2547	0.9464	0.9491	0.9428	0.9460	0.9479
0.1048	3.5023	103000	0.2578	0.9462	0.9510	0.9402	0.9456	0.9488
0.097	3.5363	104000	0.2672	0.9474	0.9497	0.9443	0.9470	0.9486
0.1078	3.5703	105000	0.2575	0.9449	0.9495	0.9392	0.9443	0.9474
0.1043	3.6043	106000	0.2617	0.9462	0.9440	0.9479	0.9460	0.9448
0.0972	3.6383	107000	0.2604	0.9449	0.9462	0.9428	0.9445	0.9455
0.0907	3.6723	108000	0.2635	0.9456	0.9481	0.9423	0.9452	0.9470
0.1044	3.7063	109000	0.2697	0.9449	0.9476	0.9412	0.9444	0.9463
0.1106	3.7404	110000	0.2588	0.9459	0.9500	0.9407	0.9454	0.9482
0.1021	3.7744	111000	0.2723	0.9449	0.9495	0.9392	0.9443	0.9474
0.0958	3.8084	112000	0.2674	0.9449	0.9439	0.9454	0.9446	0.9442
0.1042	3.8424	113000	0.2661	0.9446	0.9430	0.9459	0.9444	0.9435
0.0943	3.8764	114000	0.2673	0.9454	0.9467	0.9433	0.9450	0.9460
0.094	3.9104	115000	0.2670	0.9462	0.9473	0.9443	0.9458	0.9467
0.1024	3.9444	116000	0.2683	0.9459	0.9458	0.9454	0.9456	0.9458
0.0957	3.9784	117000	0.2672	0.9451	0.9448	0.9448	0.9448	0.9448

Framework versions

Transformers 4.46.2
Pytorch 2.4.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

tom-010/judge_answer___35_deberta_large_enwiki-answerability-2411

judge_answer___35_deberta_large_enwiki-answerability-2411

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tom-010/
judge_answer___35_deberta_large_enwiki-answerability-2411