learning_rate: 1.6e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.2387	0.0065	1	1.2545	98.1567	40.8419
1.2196	0.0130	2	0.9958	96.3134	38.4042
1.1006	0.0195	3	0.9794	96.3134	38.2443
0.9241	0.0260	4	0.9566	93.3641	36.6858
0.99	0.0325	5	0.9200	89.4931	35.0473
0.9661	0.0390	6	0.8956	86.9124	33.6086
1.1004	0.0455	7	0.8376	88.0184	31.5306
0.9661	0.0519	8	0.8114	83.1336	28.4401
0.9014	0.0584	9	0.7692	97.6959	32.1300
0.8205	0.0649	10	0.7424	88.3871	29.3593
0.7695	0.0714	11	0.7164	90.9677	32.8627
0.8615	0.0779	12	0.6922	87.1889	31.9435
0.7236	0.0844	13	0.6690	81.7512	30.6381
0.6806	0.0909	14	0.6484	94.1935	33.7818
0.6591	0.0974	15	0.6291	90.9677	31.7037
0.722	0.1039	16	0.6170	83.7788	28.5867
0.6306	0.1104	17	0.6027	86.2673	28.2670
0.5101	0.1169	18	0.5898	80.4608	25.6827
0.7152	0.1234	19	0.5878	77.9724	24.5238
0.583	0.1299	20	0.5780	77.3272	24.5904
0.5382	0.1364	21	0.5721	81.0138	26.1889
0.5992	0.1429	22	0.5631	75.6682	24.2041
0.6984	0.1494	23	0.5572	80.5530	25.0833
0.5767	0.1558	24	0.5537	82.6728	27.0414
0.6484	0.1623	25	0.5485	86.6359	27.5476
0.5637	0.1688	26	0.5488	82.1198	26.5352
0.5858	0.1753	27	0.5434	84.3318	27.0281
0.5671	0.1818	28	0.5388	79.9078	24.5105
0.6436	0.1883	29	0.5398	81.0138	24.5105
0.5519	0.1948	30	0.5338	81.8433	24.4705
0.51	0.2013	31	0.5316	74.5622	22.1527
0.6544	0.2078	32	0.5246	73.3641	23.1118
0.5147	0.2143	33	0.5188	76.4977	23.1517
0.513	0.2208	34	0.5129	75.5760	23.0851
0.4918	0.2273	35	0.5104	78.0645	23.4981
0.6463	0.2338	36	0.5097	77.7880	23.6579
0.4954	0.2403	37	0.5121	70.9677	21.6864
0.4681	0.2468	38	0.5097	69.9539	21.8729
0.5832	0.2532	39	0.5047	69.6774	21.4333
0.5182	0.2597	40	0.5022	70.9677	21.7131
0.5806	0.2662	41	0.5013	72.7189	21.8596
0.632	0.2727	42	0.5043	75.7604	22.1926
0.5395	0.2792	43	0.5010	77.4194	22.4590
0.5481	0.2857	44	0.5004	78.7097	22.3791
0.47	0.2922	45	0.5038	75.0230	21.5665
0.4875	0.2987	46	0.5047	73.4562	21.7530
0.6252	0.3052	47	0.5005	71.6129	21.7397
0.5643	0.3117	48	0.4959	73.8249	24.7769
0.5637	0.3182	49	0.4933	72.7189	21.9262
0.546	0.3247	50	0.4950	73.8249	21.8596
0.4235	0.3312	51	0.4933	80.7373	24.1508
0.4909	0.3377	52	0.4887	77.4194	23.2716
0.4799	0.3442	53	0.4889	73.1797	22.7654
0.5994	0.3506	54	0.4870	69.8618	21.2069
0.4769	0.3571	55	0.4849	68.5714	21.0870
0.4404	0.3636	56	0.4821	73.4562	22.5390
0.4687	0.3701	57	0.4794	72.8111	21.9662
0.5698	0.3766	58	0.4758	78.3410	23.7911
0.4534	0.3831	59	0.4763	83.2258	26.7750
0.4706	0.3896	60	0.4769	84.7005	26.8416
0.3964	0.3961	61	0.4753	77.3272	24.6570
0.4709	0.4026	62	0.4717	68.7558	19.7016
0.4641	0.4091	63	0.4673	70.8756	22.3258
0.5424	0.4156	64	0.4650	67.7419	19.8881
0.4091	0.4221	65	0.4648	69.4931	19.9281
0.4659	0.4286	66	0.4695	73.8249	20.2744
0.5311	0.4351	67	0.4693	74.4700	20.5142
0.5752	0.4416	68	0.4638	73.0876	20.5808
0.4713	0.4481	69	0.4597	71.2442	20.5408
0.5734	0.4545	70	0.4608	69.7696	22.5523
0.421	0.4610	71	0.4607	67.7419	22.0594
0.489	0.4675	72	0.4566	67.8341	19.9414
0.4321	0.4740	73	0.4562	68.9401	20.2344
0.4785	0.4805	74	0.4569	70.6912	20.3677
0.4508	0.4870	75	0.4553	72.2581	20.4609
0.444	0.4935	76	0.4520	73.9171	21.0870
0.5421	0.5	77	0.4509	77.6037	22.9386
0.456	0.5065	78	0.4503	72.5346	21.6731
0.3852	0.5130	79	0.4510	71.7972	21.5399
0.4616	0.5195	80	0.4474	71.7972	22.1527
0.416	0.5260	81	0.4490	70.6912	20.3810
0.4324	0.5325	82	0.4518	69.4931	20.4076
0.4694	0.5390	83	0.4533	69.6774	21.2735
0.4746	0.5455	84	0.4555	68.3871	20.8739
0.4624	0.5519	85	0.4557	77.8802	24.3772
0.4824	0.5584	86	0.4539	78.1567	24.4705
0.4741	0.5649	87	0.4537	80.2765	25.3364
0.5567	0.5714	88	0.4534	71.7972	22.1127
0.4572	0.5779	89	0.4508	70.8756	20.9271
0.5162	0.5844	90	0.4478	70.5991	20.5009
0.5233	0.5909	91	0.4458	70.7834	20.3677
0.5731	0.5974	92	0.4428	69.6774	20.3144
0.5691	0.6039	93	0.4418	69.1244	19.8881
0.3979	0.6104	94	0.4428	68.2949	20.7273
0.4738	0.6169	95	0.4477	69.1244	20.5675
0.4749	0.6234	96	0.4474	69.9539	20.1279
0.5224	0.6299	97	0.4414	72.4424	20.5408
0.5212	0.6364	98	0.4450	75.3917	20.8072
0.401	0.6429	99	0.4502	76.6820	21.0470
0.329	0.6494	100	0.4453	74.6544	20.8739
0.5461	0.6558	101	0.4403	70.7834	21.1136
0.4642	0.6623	102	0.4397	73.4562	22.9386
0.4418	0.6688	103	0.4417	67.8341	20.7806
0.414	0.6753	104	0.4413	67.5576	20.6074
0.5235	0.6818	105	0.4397	68.2949	20.5275
0.5116	0.6883	106	0.4375	68.6636	20.5675
0.4698	0.6948	107	0.4354	69.6774	20.5941
0.4208	0.7013	108	0.4322	71.6129	20.9138
0.4782	0.7078	109	0.4303	70.3226	20.6474
0.4716	0.7143	110	0.4296	71.5207	20.4609
0.3989	0.7208	111	0.4288	72.0737	20.4875
0.4794	0.7273	112	0.4278	72.4424	20.6874
0.4673	0.7338	113	0.4268	72.6267	20.6474
0.6382	0.7403	114	0.4256	72.2581	19.7283
0.4138	0.7468	115	0.4225	69.4931	18.9556
0.3964	0.7532	116	0.4185	66.3594	19.4752
0.4534	0.7597	117	0.4166	65.6221	18.8624
0.3769	0.7662	118	0.4172	67.3733	19.3952
0.5426	0.7727	119	0.4174	67.7419	19.4219
0.4642	0.7792	120	0.4161	68.2028	19.4752
0.4441	0.7857	121	0.4175	70.3226	19.6883
0.4443	0.7922	122	0.4204	70.5069	19.8481
0.3693	0.7987	123	0.4221	70.3226	19.9014
0.4469	0.8052	124	0.4233	71.2442	19.8881
0.4014	0.8117	125	0.4246	73.4562	19.9680
0.4064	0.8182	126	0.4285	74.4700	19.9947
0.4343	0.8247	127	0.4261	72.4424	19.6084
0.6039	0.8312	128	0.4213	75.1152	20.7273
0.4587	0.8377	129	0.4166	73.2719	20.5541
0.4326	0.8442	130	0.4143	72.4424	20.2611
0.4437	0.8506	131	0.4147	72.1659	20.1412
0.408	0.8571	132	0.4160	72.4424	20.2211
0.454	0.8636	133	0.4172	67.2811	18.5427
0.4508	0.8701	134	0.4180	72.5346	20.4209
0.4805	0.8766	135	0.4172	72.8111	20.9138
0.519	0.8831	136	0.4168	74.1014	21.2602
0.3863	0.8896	137	0.4178	73.4562	21.0603
0.4316	0.8961	138	0.4171	73.2719	20.7140
0.4391	0.9026	139	0.4169	75.1152	20.7673
0.3421	0.9091	140	0.4163	77.8802	22.2992
0.3977	0.9156	141	0.4149	78.6175	22.3658
0.4088	0.9221	142	0.4138	75.4839	21.1003
0.3797	0.9286	143	0.4132	74.3779	20.3810
0.4999	0.9351	144	0.4142	70.5991	19.0356
0.4431	0.9416	145	0.4139	72.5346	20.2078
0.371	0.9481	146	0.4134	67.9263	18.7691
0.5052	0.9545	147	0.4130	65.2535	18.3828
0.3963	0.9610	148	0.4119	64.6083	18.5294
0.3631	0.9675	149	0.4113	69.3088	20.2744
0.4523	0.9740	150	0.4113	71.3364	20.3810
0.3631	0.9805	151	0.4132	69.4931	19.1954
0.3845	0.9870	152	0.4132	72.2581	19.6350
0.4917	0.9935	153	0.4141	76.3134	21.3534
0.4472	1.0	154	0.4141	76.5899	21.4733
0.2408	1.0065	155	0.4125	71.6129	19.6483
0.3687	1.0130	156	0.4097	68.9401	19.3020
0.2867	1.0195	157	0.4081	68.5714	19.2487
0.2534	1.0260	158	0.4077	66.9124	19.0222
0.3172	1.0325	159	0.4079	67.0046	18.8757
0.2742	1.0390	160	0.4091	67.6498	19.0622
0.2634	1.0455	161	0.4120	69.4009	18.9556
0.2609	1.0519	162	0.4186	72.1659	19.0889
0.2974	1.0584	163	0.4223	74.1935	19.2087
0.2851	1.0649	164	0.4203	72.7189	19.2087
0.3147	1.0714	165	0.4139	70.1382	19.0222
0.279	1.0779	166	0.4095	66.6359	18.8091
0.2568	1.0844	167	0.4078	65.1613	18.5427
0.2167	1.0909	168	0.4062	64.7005	18.3296
0.2681	1.0974	169	0.4055	63.8710	17.9965
0.2338	1.1039	170	0.4086	67.2811	18.3562
0.3016	1.1104	171	0.4140	70.7834	18.5161
0.2364	1.1169	172	0.4171	72.8111	19.6084
0.2794	1.1234	173	0.4182	74.1014	19.9947
0.3178	1.1299	174	0.4155	72.6267	19.8881
0.2846	1.1364	175	0.4134	69.2166	19.0622
0.2727	1.1429	176	0.4125	67.5576	19.0889
0.2794	1.1494	177	0.4118	67.1889	19.1022
0.2829	1.1558	178	0.4112	73.0876	20.9671
0.2639	1.1623	179	0.4096	68.2028	19.2753
0.2695	1.1688	180	0.4109	70.2304	19.1288
0.2506	1.1753	181	0.4143	77.0507	21.0870
0.245	1.1818	182	0.4168	73.2719	19.3153
0.2728	1.1883	183	0.4152	72.2581	19.2887
0.2641	1.1948	184	0.4136	70.7834	19.2087
0.3139	1.2013	185	0.4110	67.2811	18.3029
0.2621	1.2078	186	0.4091	65.8986	18.2896
0.2447	1.2143	187	0.4093	67.0046	18.4228
0.2118	1.2208	188	0.4101	66.7281	18.1697
0.2103	1.2273	189	0.4129	71.9816	20.2478
0.2338	1.2338	190	0.4160	70.0461	18.7159
0.2511	1.2403	191	0.4196	72.1659	19.0755
0.2415	1.2468	192	0.4224	73.0876	19.2620
0.2923	1.2532	193	0.4226	72.7189	19.6350
0.2461	1.2597	194	0.4207	72.2581	19.5817
0.2959	1.2662	195	0.4177	70.1382	19.3419
0.2445	1.2727	196	0.4161	69.4009	19.3553
0.2785	1.2792	197	0.4150	69.4931	19.3553
0.2576	1.2857	198	0.4144	68.7558	19.1155
0.2492	1.2922	199	0.4146	69.8618	18.9823
0.2396	1.2987	200	0.4178	72.9954	19.2087
0.277	1.3052	201	0.4203	73.7327	19.3286
0.2385	1.3117	202	0.4196	73.4562	19.3286
0.2595	1.3182	203	0.4173	72.3502	19.3286
0.2987	1.3247	204	0.4156	68.9401	18.9956
0.2617	1.3312	205	0.4157	70.3226	19.2354
0.2736	1.3377	206	0.4161	70.5069	19.3020
0.3629	1.3442	207	0.4164	71.5207	19.1421
0.2704	1.3506	208	0.4179	72.6267	19.1555
0.2138	1.3571	209	0.4210	74.4700	19.2087
0.2846	1.3636	210	0.4221	76.1290	19.5817
0.2304	1.3701	211	0.4212	77.3272	19.6217
0.2563	1.3766	212	0.4172	75.0230	19.3419
0.291	1.3831	213	0.4136	72.7189	19.0089
0.2646	1.3896	214	0.4102	69.4931	18.4361
0.2465	1.3961	215	0.4076	68.4793	18.4761
0.2516	1.4026	216	0.4065	68.3871	18.5027
0.2194	1.4091	217	0.4056	67.6498	18.2630
0.2653	1.4156	218	0.4052	67.3733	18.4228
0.2851	1.4221	219	0.4059	67.5576	18.4494
0.2308	1.4286	220	0.4074	68.2949	18.6626
0.2927	1.4351	221	0.4086	70.9677	19.0889
0.2841	1.4416	222	0.4096	71.1521	19.1555
0.2528	1.4481	223	0.4098	71.1521	19.2354
0.2846	1.4545	224	0.4094	71.6129	19.1022
0.2913	1.4610	225	0.4086	71.1521	19.0089
0.3013	1.4675	226	0.4083	70.8756	19.0755
0.2181	1.4740	227	0.4085	70.5069	19.1688
0.3315	1.4805	228	0.4087	70.9677	19.1954
0.2471	1.4870	229	0.4080	70.6912	19.1421
0.2304	1.4935	230	0.4068	70.4147	19.0622
0.2326	1.5	231	0.4055	70.2304	19.0222
0.256	1.5065	232	0.4047	71.3364	19.1555
0.2129	1.5130	233	0.4041	70.4147	19.0755
0.2784	1.5195	234	0.4033	70.5069	19.1288
0.2032	1.5260	235	0.4032	70.1382	18.8890
0.239	1.5325	236	0.4029	70.0461	19.0489
0.3072	1.5390	237	0.4023	70.2304	18.9157
0.2371	1.5455	238	0.4017	69.9539	18.7025
0.2764	1.5519	239	0.4011	69.9539	18.7025
0.2629	1.5584	240	0.4005	70.1382	18.5693
0.2587	1.5649	241	0.4000	70.6912	18.6759
0.2566	1.5714	242	0.3998	71.1521	18.7958
0.1886	1.5779	243	0.3992	70.4147	18.4361
0.2412	1.5844	244	0.3984	69.8618	18.4761
0.2344	1.5909	245	0.3976	69.8618	18.4095
0.2933	1.5974	246	0.3966	68.3871	18.2097
0.3238	1.6039	247	0.3963	67.6498	18.1431
0.2641	1.6104	248	0.3959	67.2811	18.1164
0.3057	1.6169	249	0.3960	67.7419	18.1431
0.3191	1.6234	250	0.3960	67.8341	18.3429
0.2733	1.6299	251	0.3959	67.6498	18.2363
0.2387	1.6364	252	0.3962	68.0184	18.3562
0.2733	1.6429	253	0.3963	68.0184	18.4361
0.214	1.6494	254	0.3966	68.0184	18.2630
0.2324	1.6558	255	0.3969	67.9263	18.2496
0.242	1.6623	256	0.3977	68.1106	18.2097
0.2818	1.6688	257	0.3980	69.4009	18.3828
0.2676	1.6753	258	0.3987	70.8756	18.5960
0.2188	1.6818	259	0.3999	72.6267	18.7025
0.2682	1.6883	260	0.4007	72.7189	18.7292
0.2896	1.6948	261	0.4010	72.8111	18.7558
0.2165	1.7013	262	0.4009	72.9954	18.8224
0.1956	1.7078	263	0.4007	72.4424	18.7292
0.2727	1.7143	264	0.4001	72.0737	18.5960
0.245	1.7208	265	0.3995	71.1521	18.5427
0.2158	1.7273	266	0.3994	71.3364	18.5560
0.3231	1.7338	267	0.3986	70.6912	18.5560
0.1893	1.7403	268	0.3983	70.4147	18.4361
0.2225	1.7468	269	0.3975	69.4009	18.3162
0.2203	1.7532	270	0.3974	68.7558	18.3828
0.2403	1.7597	271	0.3970	68.3871	18.3562
0.244	1.7662	272	0.3967	68.4793	18.3429
0.2422	1.7727	273	0.3967	68.2949	18.3962
0.2688	1.7792	274	0.3968	68.2028	18.3695
0.308	1.7857	275	0.3968	68.4793	18.4228
0.2454	1.7922	276	0.3967	68.9401	18.3695
0.2237	1.7987	277	0.3969	69.2166	18.4095
0.2819	1.8052	278	0.3971	69.1244	18.3828
0.3044	1.8117	279	0.3971	69.3088	18.5027
0.2516	1.8182	280	0.3975	69.4931	18.5161
0.3033	1.8247	281	0.3975	69.7696	18.5427
0.1918	1.8312	282	0.3975	70.3226	18.5827
0.2426	1.8377	283	0.3977	70.5069	18.6626
0.2825	1.8442	284	0.3978	70.6912	18.6626
0.2012	1.8506	285	0.3975	70.9677	18.7825
0.2235	1.8571	286	0.3978	71.1521	18.7025
0.2231	1.8636	287	0.3974	70.7834	18.6493
0.2484	1.8701	288	0.3977	70.9677	18.6359
0.3007	1.8766	289	0.3979	71.2442	18.6493
0.2409	1.8831	290	0.3979	71.4286	18.7825
0.3397	1.8896	291	0.3976	71.2442	18.7425
0.2788	1.8961	292	0.3983	71.2442	18.7558
0.2743	1.9026	293	0.3978	71.2442	18.6759
0.203	1.9091	294	0.3977	71.6129	18.8091
0.2711	1.9156	295	0.3980	71.7051	18.8358
0.2243	1.9221	296	0.3979	71.3364	18.6759
0.2131	1.9286	297	0.3980	71.4286	18.7292
0.3002	1.9351	298	0.3981	71.3364	18.7159
0.2711	1.9416	299	0.3979	71.4286	18.7558
0.2447	1.9481	300	0.3976	71.1521	18.6626
0.2347	1.9545	301	0.3982	71.2442	18.6626
0.271	1.9610	302	0.3980	71.2442	18.6892
0.3027	1.9675	303	0.3979	71.4286	18.7825
0.3127	1.9740	304	0.3979	71.3364	18.7159
0.2311	1.9805	305	0.3980	71.5207	18.7691
0.2261	1.9870	306	0.3980	71.4286	18.7292
0.2446	1.9935	307	0.3978	71.2442	18.6759
0.2978	2.0	308	0.3978	71.7051	18.8491

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1

nkkbr/whisper-large-v3-zatoichi-ja-JDG_ver_20260217_lr_1.6e-5

Whisper Large v3 - Japanese Zatoichi ASR

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

nkkbr/
whisper-large-v3-zatoichi-ja-JDG_ver_20260217_lr_1.6e-5