Modelpublic

ferrazzipietro/crfTask-gemma-3-1b-it-all

sourceHugging Facegemmaupdated 7mo agoView on Hugging Face

0likes12downloads

Model Card

crfTask-gemma-3-1b-it-all

This model is a fine-tuned version of google/gemma-3-1b-it on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.0442
—F1 Micro: 0.9286
—F1 Macro: 0.3499
—F1 Weighted: 0.9322

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: 0.0003
—trainbatchsize: 16
—evalbatchsize: 64
—seed: 42
—distributed_type: multi-GPU
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 64
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-07 and optimizerargs=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_ratio: 0.1
—num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	F1 Weighted
21.5	0.0024	2	5.8405	0.0	0.0	0.0
21.5	0.0047	4	5.8357	0.0	0.0	0.0
21.4922	0.0071	6	5.8087	0.0	0.0	0.0
21.4922	0.0095	8	5.7349	0.0	0.0	0.0
21.65	0.0118	10	5.5824	0.0	0.0	0.0
21.65	0.0142	12	5.3438	0.0	0.0	0.0
21.65	0.0166	14	5.0625	0.0	0.0	0.0
20.0562	0.0189	16	4.8033	0.0	0.0	0.0
20.0562	0.0213	18	4.5711	0.0	0.0	0.0
17.675	0.0236	20	4.3858	0.0	0.0	0.0
17.675	0.0260	22	4.2398	0.0	0.0	0.0
17.675	0.0284	24	4.1115	0.0	0.0	0.0
16.3813	0.0307	26	3.9795	0.0	0.0	0.0
16.3813	0.0331	28	3.8429	0.0	0.0	0.0
15.3625	0.0355	30	3.6977	0.0	0.0	0.0
15.3625	0.0378	32	3.5517	0.0	0.0	0.0
15.3625	0.0402	34	3.4170	0.0	0.0	0.0
14.3594	0.0426	36	3.2934	0.0	0.0	0.0
14.3594	0.0449	38	3.1956	0.0	0.0	0.0
13.3812	0.0473	40	3.1282	0.0	0.0	0.0
13.3812	0.0497	42	3.0773	0.0	0.0	0.0
13.3812	0.0520	44	3.0396	0.0008	0.0000	0.0016
12.8375	0.0544	46	3.0011	0.3741	0.0008	0.4275
12.8375	0.0568	48	2.9655	0.1015	0.0001	0.1618
12.7094	0.0591	50	2.9006	0.4316	0.0033	0.4920
12.7094	0.0615	52	2.8524	0.1864	0.0022	0.2383
12.7094	0.0638	54	2.8050	0.2036	0.0043	0.3007
12.4094	0.0662	56	2.7592	0.3046	0.0097	0.3073
12.4094	0.0686	58	2.7099	0.4899	0.0224	0.5202
11.8625	0.0709	60	2.6622	0.5063	0.0043	0.4674
11.8625	0.0733	62	2.6105	0.5101	0.0073	0.5237
11.8625	0.0757	64	2.5439	0.4830	0.0201	0.4382
11.5594	0.0780	66	2.4652	0.4083	0.0298	0.4237
11.5594	0.0804	68	2.3952	0.3599	0.0304	0.3417
10.7844	0.0828	70	2.3230	0.3878	0.0304	0.4390
10.7844	0.0851	72	2.2557	0.5345	0.0341	0.6020
10.7844	0.0875	74	2.2010	0.6429	0.0494	0.6425
10.4375	0.0899	76	2.1544	0.7411	0.0681	0.7459
10.4375	0.0922	78	2.1061	0.7189	0.0784	0.7294
9.8219	0.0946	80	2.0634	0.7750	0.0760	0.7598
9.8219	0.0970	82	2.0236	0.7750	0.0760	0.7623
9.8219	0.0993	84	1.9868	0.7392	0.0878	0.7403
9.3656	0.1017	86	1.9535	0.7644	0.0925	0.7510
9.3656	0.1040	88	1.9262	0.7739	0.1223	0.7634
9.3219	0.1064	90	1.8991	0.6875	0.1424	0.6897
9.3219	0.1088	92	1.8768	0.7263	0.0901	0.6871
9.3219	0.1111	94	1.8530	0.7523	0.1107	0.7597
9.0906	0.1135	96	1.8351	0.7397	0.0838	0.7469
9.0906	0.1159	98	1.8159	0.7583	0.0708	0.7547
8.6734	0.1182	100	1.7986	0.7562	0.0756	0.7542
8.6734	0.1206	102	1.7803	0.6245	0.1143	0.6239
8.6734	0.1230	104	1.7648	0.8005	0.1242	0.7925
8.6797	0.1253	106	1.7515	0.7797	0.1012	0.7647
8.6797	0.1277	108	1.7404	0.7362	0.1294	0.7552
8.3234	0.1301	110	1.7295	0.7997	0.1424	0.7996
8.3234	0.1324	112	1.7170	0.7510	0.1221	0.7269
8.3234	0.1348	114	1.7078	0.8098	0.1255	0.8037
8.2719	0.1372	116	1.6992	0.7767	0.1221	0.7854
8.2719	0.1395	118	1.6841	0.8123	0.1073	0.8102
8.1047	0.1419	120	1.6742	0.7983	0.0901	0.7967
8.1047	0.1443	122	1.6654	0.7767	0.0962	0.7926
8.1047	0.1466	124	1.6552	0.7209	0.1019	0.7741
8.0344	0.1490	126	1.6490	0.7143	0.1070	0.7729
8.0344	0.1513	128	1.6420	0.7666	0.1185	0.8004
8.0188	0.1537	130	1.6311	0.8292	0.1607	0.8299
8.0188	0.1561	132	1.6261	0.8413	0.1690	0.8462
8.0188	0.1584	134	1.6114	0.8404	0.1559	0.8454
7.8234	0.1608	136	1.6067	0.8476	0.1582	0.8511
7.8234	0.1632	138	1.5963	0.8407	0.1110	0.8378
8.1344	0.1655	140	1.5954	0.8511	0.1448	0.8594
8.1344	0.1679	142	1.5874	0.8202	0.1396	0.8386
8.1344	0.1703	144	1.5777	0.8314	0.1138	0.8446
7.6031	0.1726	146	1.5738	0.8317	0.1057	0.8200
7.6031	0.1750	148	1.5675	0.8418	0.2091	0.8424
7.8359	0.1774	150	1.5653	0.8711	0.1863	0.8738
7.8359	0.1797	152	1.5550	0.8664	0.1844	0.8722
7.8359	0.1821	154	1.5463	0.8621	0.1838	0.8691
7.6719	0.1845	156	1.5415	0.8574	0.2000	0.8629
7.6719	0.1868	158	1.5353	0.8648	0.2456	0.8722
7.3688	0.1892	160	1.5314	0.8632	0.2680	0.8733
7.3688	0.1915	162	1.5249	0.8766	0.1953	0.8784
7.3688	0.1939	164	1.5191	0.8790	0.2130	0.8789
7.4938	0.1963	166	1.5135	0.8602	0.2704	0.8644
7.4938	0.1986	168	1.5090	0.8766	0.2119	0.8757
7.4047	0.2010	170	1.5034	0.8643	0.2073	0.8621
7.4047	0.2034	172	1.4997	0.8706	0.2253	0.8798
7.4047	0.2057	174	1.4930	0.8766	0.2371	0.8831
7.3922	0.2081	176	1.4902	0.8654	0.2019	0.8662
7.3922	0.2105	178	1.4856	0.8812	0.2140	0.8868
7.3547	0.2128	180	1.4813	0.8528	0.2151	0.8583
7.3547	0.2152	182	1.4735	0.8807	0.2103	0.8790
7.3547	0.2176	184	1.4698	0.8848	0.2140	0.8834
7.3906	0.2199	186	1.4667	0.8845	0.2049	0.8829
7.3906	0.2223	188	1.4666	0.8842	0.2183	0.8881
7.2547	0.2247	190	1.4623	0.8810	0.2093	0.8858
7.2547	0.2270	192	1.4597	0.8768	0.1998	0.8804
7.2547	0.2294	194	1.4535	0.8788	0.2515	0.8844
7.1766	0.2317	196	1.4491	0.8703	0.2557	0.8782
7.1766	0.2341	198	1.4433	0.8719	0.2204	0.8774
7.0969	0.2365	200	1.4407	0.8790	0.2183	0.8867
7.0969	0.2388	202	1.4364	0.8602	0.2403	0.8739
7.0969	0.2412	204	1.4333	0.8651	0.1945	0.8683
7.2828	0.2436	206	1.4289	0.8955	0.2498	0.8999
7.2828	0.2459	208	1.4265	0.8435	0.2328	0.8498
7.0344	0.2483	210	1.4221	0.8845	0.2119	0.8897
7.0344	0.2507	212	1.4149	0.8848	0.1704	0.8820
7.0344	0.2530	214	1.4149	0.8911	0.1977	0.8884
7.1422	0.2554	216	1.4098	0.8738	0.1858	0.8752
7.1422	0.2578	218	1.4096	0.8957	0.2088	0.8930
7.0281	0.2601	220	1.4042	0.8944	0.1912	0.8912
7.0281	0.2625	222	1.4002	0.8793	0.1500	0.8831
7.0281	0.2649	224	1.3970	0.8755	0.1601	0.8838
6.6609	0.2672	226	1.3937	0.8752	0.1968	0.8865
6.6609	0.2696	228	1.3921	0.8563	0.2183	0.8695
7.0062	0.2719	230	1.3917	0.8842	0.2151	0.8922
7.0062	0.2743	232	1.3866	0.8552	0.1486	0.8444
7.0062	0.2767	234	1.3839	0.8848	0.2038	0.8869
6.7625	0.2790	236	1.3792	0.8725	0.2551	0.8801
6.7625	0.2814	238	1.3770	0.8823	0.2575	0.8864
7.2453	0.2838	240	1.3737	0.8889	0.1576	0.8859
7.2453	0.2861	242	1.3732	0.8558	0.1314	0.8521
7.2453	0.2885	244	1.3730	0.8974	0.2087	0.9021
7.0719	0.2909	246	1.3689	0.8522	0.2364	0.8628
7.0719	0.2932	248	1.3637	0.8763	0.2290	0.8841
6.8812	0.2956	250	1.3613	0.8976	0.2259	0.9005
6.8812	0.2980	252	1.3599	0.8648	0.1699	0.8623
6.8812	0.3003	254	1.3552	0.8960	0.2237	0.8975
6.6547	0.3027	256	1.3545	0.8897	0.2867	0.8936
6.6547	0.3051	258	1.3509	0.8648	0.2929	0.8694
7.0234	0.3074	260	1.3482	0.8933	0.2817	0.8961
7.0234	0.3098	262	1.3467	0.8963	0.2215	0.8937
7.0234	0.3121	264	1.3424	0.8812	0.2069	0.8787
6.4594	0.3145	266	1.3398	0.9056	0.2640	0.9093
6.4594	0.3169	268	1.3397	0.8971	0.2782	0.9023
6.7359	0.3192	270	1.3382	0.9018	0.2822	0.9066
6.7359	0.3216	272	1.3347	0.9034	0.2676	0.9074
6.7359	0.3240	274	1.3331	0.9026	0.2654	0.9067
6.7359	0.3263	276	1.3301	0.9034	0.2733	0.9078
6.7359	0.3287	278	1.3292	0.9089	0.2617	0.9105
6.5094	0.3311	280	1.3285	0.9053	0.1904	0.9068
6.5094	0.3334	282	1.3261	0.9083	0.2220	0.9081
6.5094	0.3358	284	1.3199	0.9059	0.2390	0.9076
6.6656	0.3382	286	1.3148	0.9078	0.2267	0.9113
6.6656	0.3405	288	1.3143	0.9061	0.2535	0.9118
6.5469	0.3429	290	1.3136	0.9053	0.2679	0.9122
6.5469	0.3453	292	1.3124	0.9067	0.2905	0.9125
6.5469	0.3476	294	1.3091	0.9086	0.2796	0.9123
6.5547	0.3500	296	1.3063	0.9078	0.2909	0.9112
6.5547	0.3523	298	1.3051	0.9116	0.2932	0.9144
6.4188	0.3547	300	1.3024	0.9067	0.2553	0.9086
6.4188	0.3571	302	1.2986	0.9105	0.2398	0.9124
6.4188	0.3594	304	1.2971	0.9097	0.2259	0.9126
6.3484	0.3618	306	1.2954	0.9105	0.2522	0.9136
6.3484	0.3642	308	1.2922	0.9113	0.2467	0.9146
6.6437	0.3665	310	1.2922	0.9037	0.2212	0.9064
6.6437	0.3689	312	1.2887	0.9048	0.2568	0.9059
6.6437	0.3713	314	1.2839	0.9034	0.2261	0.9053
6.2656	0.3736	316	1.2831	0.9034	0.2288	0.9067
6.2656	0.3760	318	1.2823	0.9097	0.2839	0.9141
6.4328	0.3784	320	1.2765	0.9080	0.2731	0.9136
6.4328	0.3807	322	1.2748	0.9028	0.2716	0.9090
6.4328	0.3831	324	1.2753	0.9007	0.2557	0.9070
6.3063	0.3855	326	1.2703	0.8941	0.2013	0.9016
6.3063	0.3878	328	1.2690	0.8952	0.1966	0.9033
6.4047	0.3902	330	1.2650	0.8987	0.1938	0.9097
6.4047	0.3926	332	1.2632	0.8960	0.1712	0.9096
6.4047	0.3949	334	1.2621	0.8886	0.1968	0.9030
6.3391	0.3973	336	1.2606	0.8966	0.1540	0.9051
6.3391	0.3996	338	1.2592	0.8974	0.1451	0.9030
6.4703	0.4020	340	1.2570	0.8894	0.1568	0.8998
6.4703	0.4044	342	1.2547	0.8955	0.1609	0.9050
6.4703	0.4067	344	1.2554	0.9031	0.2165	0.9099
6.2844	0.4091	346	1.2553	0.9097	0.2525	0.9153
6.2844	0.4115	348	1.2496	0.9111	0.2352	0.9165
6.2203	0.4138	350	1.2487	0.9135	0.2480	0.9186
6.2203	0.4162	352	1.2473	0.9089	0.2598	0.9145
6.2203	0.4186	354	1.2438	0.9108	0.2776	0.9171
6.4078	0.4209	356	1.2412	0.9042	0.2689	0.9107
6.4078	0.4233	358	1.2383	0.9045	0.2635	0.9107
6.3766	0.4257	360	1.2381	0.9124	0.2504	0.9171
6.3766	0.4280	362	1.2367	0.9086	0.2552	0.9124
6.3766	0.4304	364	1.2333	0.9138	0.2427	0.9167
6.0359	0.4328	366	1.2322	0.9187	0.2685	0.9213
6.0359	0.4351	368	1.2305	0.9138	0.2544	0.9167
6.3109	0.4375	370	1.2284	0.9100	0.2824	0.9125
6.3109	0.4398	372	1.2258	0.9127	0.3026	0.9145
6.3109	0.4422	374	1.2243	0.9163	0.2611	0.9162
6.1813	0.4446	376	1.2218	0.9004	0.2495	0.8992
6.1813	0.4469	378	1.2197	0.9059	0.2153	0.9055
6.1328	0.4493	380	1.2186	0.9132	0.2453	0.9141
6.1328	0.4517	382	1.2181	0.9012	0.2453	0.9038
6.1328	0.4540	384	1.2162	0.9102	0.2412	0.9115
6.0844	0.4564	386	1.2134	0.9146	0.2529	0.9150
6.0844	0.4588	388	1.2119	0.9138	0.2465	0.9145
6.3187	0.4611	390	1.2111	0.9160	0.2406	0.9166
6.3187	0.4635	392	1.2112	0.9182	0.3112	0.9185
6.3187	0.4659	394	1.2092	0.9206	0.2829	0.9212
6.3172	0.4682	396	1.2097	0.9193	0.2300	0.9202
6.3172	0.4706	398	1.2047	0.9212	0.2570	0.9233
5.8797	0.4730	400	1.2055	0.9190	0.2640	0.9214
5.8797	0.4753	402	1.2004	0.9215	0.2402	0.9249
5.8797	0.4777	404	1.1995	0.9204	0.2362	0.9247
6.1266	0.4800	406	1.1991	0.9143	0.2353	0.9199
6.1266	0.4824	408	1.1960	0.9059	0.2763	0.9125
5.8875	0.4848	410	1.1953	0.9094	0.2781	0.9160
5.8875	0.4871	412	1.1950	0.9132	0.2681	0.9182
5.8875	0.4895	414	1.1941	0.9113	0.2185	0.9156
6.0625	0.4919	416	1.1923	0.9138	0.2327	0.9174
6.0625	0.4942	418	1.1902	0.9215	0.2426	0.9252
6.0219	0.4966	420	1.1891	0.9220	0.2419	0.9252
6.0219	0.4990	422	1.1888	0.9228	0.2462	0.9247
6.0219	0.5013	424	1.1867	0.9168	0.2271	0.9179
5.9344	0.5037	426	1.1839	0.9198	0.2377	0.9218
5.9344	0.5061	428	1.1827	0.9215	0.2489	0.9243
5.775	0.5084	430	1.1798	0.9168	0.2473	0.9200
5.775	0.5108	432	1.1797	0.9184	0.2314	0.9212
5.775	0.5132	434	1.1781	0.9195	0.2114	0.9220
5.9062	0.5155	436	1.1758	0.9187	0.2170	0.9217
5.9062	0.5179	438	1.1754	0.9168	0.2193	0.9207
6.1375	0.5202	440	1.1738	0.9212	0.2087	0.9240
6.1375	0.5226	442	1.1700	0.9193	0.2084	0.9224
6.1375	0.5250	444	1.1677	0.9160	0.2742	0.9211
5.6359	0.5273	446	1.1673	0.9143	0.2738	0.9213
5.6359	0.5297	448	1.1676	0.9165	0.2831	0.9234
5.9031	0.5321	450	1.1661	0.9204	0.3040	0.9264
5.9031	0.5344	452	1.1662	0.9204	0.3062	0.9255
5.9031	0.5368	454	1.1637	0.9204	0.2760	0.9260
5.6781	0.5392	456	1.1635	0.9204	0.2920	0.9258
5.6781	0.5415	458	1.1620	0.9193	0.2938	0.9253
6.2328	0.5439	460	1.1598	0.9223	0.2835	0.9276
6.2328	0.5463	462	1.1571	0.9239	0.2822	0.9291
6.2328	0.5486	464	1.1552	0.9212	0.2687	0.9261
5.7578	0.5510	466	1.1537	0.9250	0.2950	0.9296
5.7578	0.5534	468	1.1519	0.9220	0.3059	0.9270
5.8141	0.5557	470	1.1519	0.9223	0.3021	0.9275
5.8141	0.5581	472	1.1498	0.9245	0.3121	0.9293
5.8141	0.5604	474	1.1483	0.9236	0.2967	0.9290
5.7406	0.5628	476	1.1475	0.9204	0.2970	0.9260
5.7406	0.5652	478	1.1476	0.9165	0.3022	0.9220
5.8781	0.5675	480	1.1464	0.9154	0.2938	0.9217
5.8781	0.5699	482	1.1441	0.9174	0.3234	0.9241
5.8781	0.5723	484	1.1435	0.9168	0.3015	0.9241
5.7891	0.5746	486	1.1428	0.9113	0.3794	0.9192
5.7891	0.5770	488	1.1414	0.9174	0.3970	0.9247
5.4078	0.5794	490	1.1404	0.9171	0.3626	0.9241
5.4078	0.5817	492	1.1393	0.9242	0.3815	0.9302
5.4078	0.5841	494	1.1394	0.9258	0.3714	0.9306
6.0516	0.5865	496	1.1381	0.9223	0.3579	0.9271
6.0516	0.5888	498	1.1374	0.9231	0.3577	0.9279
5.7656	0.5912	500	1.1342	0.9242	0.3692	0.9288
5.7656	0.5936	502	1.1331	0.9234	0.3633	0.9284
5.7656	0.5959	504	1.1332	0.9212	0.3894	0.9265
5.6219	0.5983	506	1.1319	0.9245	0.3705	0.9290
5.6219	0.6007	508	1.1298	0.9253	0.3442	0.9289
5.8469	0.6030	510	1.1292	0.9212	0.3214	0.9251
5.8469	0.6054	512	1.1284	0.9234	0.3372	0.9270
5.8469	0.6077	514	1.1249	0.9223	0.3197	0.9266
5.575	0.6101	516	1.1232	0.9236	0.3445	0.9278
5.575	0.6125	518	1.1234	0.9223	0.3138	0.9267
5.6484	0.6148	520	1.1234	0.9217	0.2873	0.9259
5.6484	0.6172	522	1.1228	0.9245	0.2895	0.9286
5.6484	0.6196	524	1.1211	0.9258	0.2753	0.9296
5.6516	0.6219	526	1.1193	0.9226	0.2822	0.9267
5.6516	0.6243	528	1.1188	0.9220	0.2395	0.9254
5.5922	0.6267	530	1.1176	0.9215	0.2243	0.9236
5.5922	0.6290	532	1.1172	0.9176	0.2193	0.9196
5.5922	0.6314	534	1.1161	0.9201	0.2263	0.9217
5.4531	0.6338	536	1.1154	0.9228	0.2125	0.9238
5.4531	0.6361	538	1.1134	0.9231	0.2349	0.9244
5.6422	0.6385	540	1.1123	0.9253	0.2664	0.9276
5.6422	0.6409	542	1.1111	0.9226	0.2952	0.9260
5.6422	0.6432	544	1.1113	0.9228	0.3361	0.9272
5.8234	0.6456	546	1.1100	0.9234	0.2897	0.9275
5.8234	0.6479	548	1.1091	0.9239	0.2969	0.9270
5.418	0.6503	550	1.1084	0.9226	0.2773	0.9259
5.418	0.6527	552	1.1082	0.9234	0.2737	0.9272
5.418	0.6550	554	1.1086	0.9223	0.3022	0.9253
5.4859	0.6574	556	1.1065	0.9253	0.3165	0.9288
5.4859	0.6598	558	1.1050	0.9247	0.3182	0.9288
5.5062	0.6621	560	1.1039	0.9256	0.3581	0.9301
5.5062	0.6645	562	1.1034	0.9261	0.3875	0.9309
5.5062	0.6669	564	1.1025	0.9242	0.4122	0.9296
5.7141	0.6692	566	1.1016	0.9247	0.3108	0.9298
5.7141	0.6716	568	1.1001	0.9267	0.2566	0.9313
5.5719	0.6740	570	1.0992	0.9236	0.2697	0.9281
5.5719	0.6763	572	1.0985	0.9250	0.2551	0.9286
5.5719	0.6787	574	1.0977	0.9278	0.2610	0.9302
5.6437	0.6811	576	1.0968	0.9261	0.2709	0.9283
5.6437	0.6834	578	1.0966	0.9250	0.2693	0.9265
5.5625	0.6858	580	1.0950	0.9242	0.2610	0.9261
5.5625	0.6881	582	1.0938	0.9231	0.2588	0.9251
5.5625	0.6905	584	1.0932	0.9264	0.2642	0.9282
5.7266	0.6929	586	1.0924	0.9267	0.2659	0.9288
5.7266	0.6952	588	1.0921	0.9250	0.3042	0.9271
5.5547	0.6976	590	1.0917	0.9272	0.3022	0.9298
5.5547	0.7000	592	1.0900	0.9272	0.3136	0.9299
5.5547	0.7023	594	1.0887	0.9250	0.3092	0.9284
5.4437	0.7047	596	1.0879	0.9247	0.3619	0.9295
5.4437	0.7071	598	1.0869	0.9242	0.3665	0.9292
5.3328	0.7094	600	1.0859	0.9236	0.3337	0.9284
5.3328	0.7118	602	1.0862	0.9267	0.3658	0.9313
5.3328	0.7142	604	1.0847	0.9250	0.3114	0.9294
5.2984	0.7165	606	1.0845	0.9242	0.3033	0.9280
5.2984	0.7189	608	1.0825	0.9247	0.2967	0.9283
5.3266	0.7213	610	1.0824	0.9247	0.2647	0.9285
5.3266	0.7236	612	1.0836	0.9239	0.2930	0.9283
5.3266	0.7260	614	1.0800	0.9236	0.3276	0.9283
5.475	0.7283	616	1.0800	0.9261	0.3422	0.9304
5.475	0.7307	618	1.0790	0.9258	0.3682	0.9301
5.55	0.7331	620	1.0781	0.9242	0.3501	0.9287
5.55	0.7354	622	1.0775	0.9236	0.3451	0.9282
5.55	0.7378	624	1.0762	0.9253	0.3143	0.9295
5.3891	0.7402	626	1.0758	0.9261	0.3188	0.9308
5.3891	0.7425	628	1.0744	0.9258	0.3076	0.9302
5.5125	0.7449	630	1.0748	0.9253	0.3456	0.9300
5.5125	0.7473	632	1.0740	0.9256	0.3405	0.9300
5.5125	0.7496	634	1.0721	0.9253	0.3145	0.9298
5.4875	0.7520	636	1.0718	0.9253	0.3060	0.9297
5.4875	0.7544	638	1.0711	0.9245	0.2939	0.9288
5.2375	0.7567	640	1.0702	0.9269	0.2882	0.9312
5.2375	0.7591	642	1.0700	0.9272	0.3050	0.9318
5.2375	0.7615	644	1.0702	0.9283	0.3088	0.9325
5.1937	0.7638	646	1.0690	0.9264	0.2994	0.9312
5.1937	0.7662	648	1.0684	0.9280	0.3252	0.9326
5.4797	0.7685	650	1.0673	0.9278	0.3202	0.9323
5.4797	0.7709	652	1.0669	0.9267	0.3055	0.9314
5.4797	0.7733	654	1.0665	0.9267	0.3054	0.9309
5.3906	0.7756	656	1.0663	0.9264	0.2932	0.9305
5.3906	0.7780	658	1.0657	0.9261	0.2936	0.9308
5.2055	0.7804	660	1.0653	0.9267	0.3238	0.9310
5.2055	0.7827	662	1.0646	0.9278	0.3545	0.9321
5.2055	0.7851	664	1.0640	0.9275	0.3456	0.9313
5.2891	0.7875	666	1.0633	0.9267	0.3212	0.9308
5.2891	0.7898	668	1.0622	0.9288	0.3126	0.9327
5.3875	0.7922	670	1.0616	0.9264	0.3169	0.9305
5.3875	0.7946	672	1.0619	0.9272	0.3387	0.9304
5.3875	0.7969	674	1.0612	0.9283	0.3380	0.9314
5.2844	0.7993	676	1.0605	0.9291	0.3233	0.9321
5.2844	0.8017	678	1.0600	0.9302	0.3236	0.9329
5.1945	0.8040	680	1.0595	0.9280	0.3300	0.9310
5.1945	0.8064	682	1.0591	0.9294	0.3056	0.9321
5.1945	0.8087	684	1.0585	0.9291	0.3490	0.9318
5.4734	0.8111	686	1.0581	0.9275	0.3121	0.9304
5.4734	0.8135	688	1.0579	0.9294	0.3132	0.9318
5.5187	0.8158	690	1.0575	0.9299	0.3204	0.9320
5.5187	0.8182	692	1.0568	0.9280	0.3386	0.9304
5.5187	0.8206	694	1.0568	0.9258	0.3029	0.9283
5.2359	0.8229	696	1.0564	0.9291	0.3152	0.9316
5.2359	0.8253	698	1.0559	0.9272	0.3297	0.9300
5.1219	0.8277	700	1.0552	0.9302	0.3882	0.9333
5.1219	0.8300	702	1.0544	0.9302	0.3883	0.9335
5.1219	0.8324	704	1.0541	0.9297	0.3922	0.9334
5.3203	0.8348	706	1.0541	0.9297	0.3675	0.9337
5.3203	0.8371	708	1.0537	0.9286	0.3749	0.9331
5.6063	0.8395	710	1.0535	0.9305	0.3822	0.9346
5.6063	0.8419	712	1.0529	0.9291	0.3667	0.9331
5.6063	0.8442	714	1.0527	0.9283	0.3612	0.9322
5.15	0.8466	716	1.0527	0.9280	0.3614	0.9320
5.15	0.8490	718	1.0524	0.9288	0.3536	0.9326
5.2953	0.8513	720	1.0519	0.9283	0.3303	0.9321
5.2953	0.8537	722	1.0514	0.9278	0.3541	0.9313
5.2953	0.8560	724	1.0511	0.9272	0.3317	0.9311
5.4141	0.8584	726	1.0505	0.9272	0.3533	0.9311
5.4141	0.8608	728	1.0503	0.9278	0.3415	0.9317
5.0766	0.8631	730	1.0500	0.9291	0.3578	0.9330
5.0766	0.8655	732	1.0497	0.9278	0.3390	0.9320
5.0766	0.8679	734	1.0496	0.9280	0.3549	0.9322
5.3359	0.8702	736	1.0498	0.9264	0.3541	0.9307
5.3359	0.8726	738	1.0490	0.9288	0.3732	0.9330
5.4547	0.8750	740	1.0489	0.9275	0.3634	0.9320
5.4547	0.8773	742	1.0492	0.9275	0.3578	0.9315
5.4547	0.8797	744	1.0489	0.9299	0.3566	0.9337
5.1813	0.8821	746	1.0486	0.9280	0.3320	0.9322
5.1813	0.8844	748	1.0486	0.9297	0.3211	0.9337
5.1922	0.8868	750	1.0484	0.9280	0.3729	0.9321
5.1922	0.8892	752	1.0479	0.9286	0.3405	0.9324
5.1922	0.8915	754	1.0474	0.9294	0.3886	0.9329
5.0906	0.8939	756	1.0471	0.9294	0.3578	0.9332
5.0906	0.8962	758	1.0471	0.9283	0.3472	0.9322
5.3172	0.8986	760	1.0466	0.9283	0.3412	0.9325
5.3172	0.9010	762	1.0468	0.9278	0.3831	0.9321
5.3172	0.9033	764	1.0469	0.9286	0.3685	0.9327
5.3344	0.9057	766	1.0460	0.9267	0.3268	0.9306
5.3344	0.9081	768	1.0461	0.9280	0.3752	0.9326
5.2531	0.9104	770	1.0461	0.9278	0.3596	0.9319
5.2531	0.9128	772	1.0459	0.9278	0.3375	0.9318
5.2531	0.9152	774	1.0455	0.9275	0.3621	0.9318
5.0031	0.9175	776	1.0455	0.9267	0.3523	0.9309
5.0031	0.9199	778	1.0455	0.9294	0.3968	0.9337
5.3563	0.9223	780	1.0457	0.9297	0.3727	0.9343
5.3563	0.9246	782	1.0453	0.9280	0.3887	0.9324
5.3563	0.9270	784	1.0453	0.9286	0.3796	0.9330
5.2578	0.9294	786	1.0453	0.9286	0.3816	0.9330
5.2578	0.9317	788	1.0452	0.9275	0.3682	0.9320
5.0609	0.9341	790	1.0449	0.9308	0.3636	0.9347
5.0609	0.9364	792	1.0448	0.9272	0.3826	0.9316
5.0609	0.9388	794	1.0447	0.9280	0.3752	0.9321
5.193	0.9412	796	1.0446	0.9275	0.3441	0.9319
5.193	0.9435	798	1.0445	0.9294	0.3675	0.9334
5.2656	0.9459	800	1.0445	0.9286	0.3815	0.9329
5.2656	0.9483	802	1.0444	0.9283	0.3657	0.9325
5.2656	0.9506	804	1.0444	0.9291	0.3623	0.9332
5.0609	0.9530	806	1.0445	0.9280	0.3485	0.9320
5.0609	0.9554	808	1.0443	0.9288	0.3791	0.9331
5.4359	0.9577	810	1.0442	0.9283	0.3551	0.9326
5.4359	0.9601	812	1.0442	0.9291	0.3744	0.9330
5.4359	0.9625	814	1.0443	0.9272	0.3333	0.9310
5.2797	0.9648	816	1.0444	0.9291	0.3603	0.9330
5.2797	0.9672	818	1.0442	0.9283	0.3637	0.9323
5.3758	0.9696	820	1.0440	0.9280	0.3421	0.9326
5.3758	0.9719	822	1.0443	0.9297	0.3473	0.9335
5.3758	0.9743	824	1.0442	0.9294	0.3789	0.9332
4.9203	0.9766	826	1.0442	0.9278	0.3393	0.9316
4.9203	0.9790	828	1.0440	0.9308	0.3778	0.9344
5.1516	0.9814	830	1.0442	0.9286	0.3832	0.9326
5.1516	0.9837	832	1.0440	0.9278	0.3954	0.9323
5.1516	0.9861	834	1.0440	0.9294	0.3795	0.9337
5.15	0.9885	836	1.0441	0.9291	0.3735	0.9332
5.15	0.9908	838	1.0440	0.9280	0.3689	0.9318
5.3875	0.9932	840	1.0441	0.9297	0.3615	0.9336
5.3875	0.9956	842	1.0442	0.9278	0.3445	0.9322
5.3875	0.9979	844	1.0442	0.9286	0.3499	0.9322

Framework versions

—PEFT 0.18.1
—Transformers 4.51.0
—Pytorch 2.8.0+cu128
—Datasets 3.6.0
—Tokenizers 0.21.0