crfTask-Llama-3.1-8B-Instruct-60k

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5117
• F1 Micro: 0.9269
• F1 Macro: 0.4307
• F1 Weighted: 0.9361

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
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	F1 Weighted
15.0938	0.0024	2	4.3000	0.0	0.0	0.0
15.0938	0.0047	4	4.2937	0.0	0.0	0.0
15.5781	0.0071	6	4.2562	0.0	0.0	0.0
15.5781	0.0095	8	4.1687	0.0	0.0	0.0
15.5281	0.0118	10	4.0156	0.0	0.0	0.0
15.5281	0.0142	12	3.8719	0.0	0.0	0.0
15.5281	0.0165	14	3.7062	0.0	0.0	0.0
14.2406	0.0189	16	3.5187	0.0033	0.0001	0.0066
14.2406	0.0213	18	3.3063	0.0	0.0	0.0
12.9437	0.0236	20	3.1406	0.0166	0.0066	0.0253
12.9437	0.0260	22	2.9625	0.0764	0.0101	0.1133
12.9437	0.0284	24	2.7687	0.3223	0.1498	0.2605
11.5406	0.0307	26	2.6219	0.4950	0.4156	0.4387
11.5406	0.0331	28	2.5156	0.0332	0.0715	0.0515
10.5375	0.0355	30	2.4094	0.0033	0.0111	0.0059
10.5375	0.0378	32	2.3187	0.5349	0.0708	0.5234
10.5375	0.0402	34	2.2344	0.6977	0.1242	0.7145
9.6656	0.0426	36	2.1562	0.7608	0.1312	0.7611
9.6656	0.0449	38	2.0844	0.8372	0.1939	0.8335
9.0844	0.0473	40	2.0047	0.8239	0.2121	0.8162
9.0844	0.0496	42	1.9469	0.8239	0.2986	0.8171
9.0844	0.0520	44	1.8828	0.8605	0.4560	0.8571
8.5531	0.0544	46	1.8297	0.8904	0.4696	0.8863
8.5531	0.0567	48	1.7844	0.9169	0.4803	0.9187
8.2031	0.0591	50	1.7359	0.9169	0.5268	0.9197
8.2031	0.0615	52	1.6938	0.9070	0.4108	0.9090
8.2031	0.0638	54	1.6641	0.9037	0.4187	0.9036
7.5344	0.0662	56	1.6266	0.9203	0.4257	0.9192
7.5344	0.0686	58	1.6000	0.9203	0.4578	0.9266
7.4406	0.0709	60	1.5688	0.9236	0.4656	0.9296
7.4406	0.0733	62	1.5422	0.9302	0.4664	0.9357
7.4406	0.0757	64	1.5187	0.9203	0.4183	0.9197
7.2234	0.0780	66	1.4969	0.9336	0.4015	0.9367
7.2234	0.0804	68	1.4719	0.9336	0.4697	0.9387
7.0	0.0827	70	1.4562	0.9269	0.4351	0.9342
7.0	0.0851	72	1.4375	0.9269	0.4337	0.9348
7.0	0.0875	74	1.4219	0.9336	0.4419	0.9389
6.75	0.0898	76	1.4078	0.9302	0.3779	0.9336
6.75	0.0922	78	1.3984	0.9369	0.4092	0.9385
6.6063	0.0946	80	1.3828	0.9336	0.3783	0.9381
6.6063	0.0969	82	1.3703	0.9336	0.3821	0.9381
6.6063	0.0993	84	1.3625	0.9369	0.4733	0.9417
6.4922	0.1017	86	1.3438	0.9369	0.5060	0.9405
6.4922	0.1040	88	1.3375	0.9402	0.5104	0.9424
6.4141	0.1064	90	1.3359	0.9369	0.4367	0.9370
6.4141	0.1087	92	1.3203	0.9336	0.4277	0.9362
6.4141	0.1111	94	1.3109	0.9369	0.4328	0.9384
6.2406	0.1135	96	1.3047	0.9402	0.5122	0.9429
6.2406	0.1158	98	1.2953	0.9369	0.5062	0.9416
6.0641	0.1182	100	1.2859	0.9236	0.5123	0.9279
6.0641	0.1206	102	1.2828	0.9169	0.4644	0.9212
6.0641	0.1229	104	1.2687	0.9169	0.4547	0.9208
6.2062	0.1253	106	1.2656	0.9169	0.4718	0.9220
6.2062	0.1277	108	1.2641	0.9369	0.4764	0.9410
6.1484	0.1300	110	1.2547	0.9468	0.4890	0.9482
6.1484	0.1324	112	1.25	0.9435	0.5112	0.9459
6.1484	0.1348	114	1.2391	0.9468	0.5149	0.9487
6.1344	0.1371	116	1.2391	0.9402	0.4355	0.9399
6.1344	0.1395	118	1.2313	0.9336	0.3979	0.9343
5.8484	0.1418	120	1.2234	0.9402	0.4014	0.9418
5.8484	0.1442	122	1.2203	0.9402	0.4098	0.9419
5.8484	0.1466	124	1.2141	0.9435	0.4814	0.9468
5.9578	0.1489	126	1.2047	0.9468	0.4397	0.9474
5.9578	0.1513	128	1.2000	0.9402	0.4779	0.9448
5.8469	0.1537	130	1.1875	0.9302	0.4763	0.9350
5.8469	0.1560	132	1.1891	0.9369	0.5694	0.9433
5.8469	0.1584	134	1.1828	0.9336	0.4931	0.9370
5.9031	0.1608	136	1.1781	0.9502	0.5096	0.9501
5.9031	0.1631	138	1.1672	0.9435	0.4522	0.9444
5.6594	0.1655	140	1.1656	0.9435	0.4820	0.9455
5.6594	0.1678	142	1.1609	0.9402	0.4469	0.9441
5.6594	0.1702	144	1.1531	0.9369	0.5115	0.9396
5.5328	0.1726	146	1.1516	0.9435	0.5157	0.9458
5.5328	0.1749	148	1.1469	0.9336	0.4706	0.9378
5.6453	0.1773	150	1.1437	0.9336	0.4706	0.9378
5.6453	0.1797	152	1.1375	0.9402	0.5532	0.9438
5.6453	0.1820	154	1.1344	0.9468	0.5670	0.9502
5.5812	0.1844	156	1.1344	0.9402	0.5162	0.9418
5.5812	0.1868	158	1.1281	0.9336	0.5074	0.9356
5.3953	0.1891	160	1.1234	0.9336	0.5074	0.9356
5.3953	0.1915	162	1.1203	0.9369	0.5150	0.9369
5.3953	0.1939	164	1.1141	0.9468	0.5209	0.9465
5.4313	0.1962	166	1.1078	0.9468	0.5208	0.9467
5.4313	0.1986	168	1.1063	0.9269	0.5035	0.9270
5.4297	0.2009	170	1.1047	0.9302	0.5128	0.9335
5.4297	0.2033	172	1.0984	0.9369	0.6294	0.9382
5.4297	0.2057	174	1.0953	0.9402	0.5428	0.9409
5.3328	0.2080	176	1.0906	0.9402	0.5291	0.9441
5.3328	0.2104	178	1.0859	0.9369	0.6114	0.9425
5.2062	0.2128	180	1.0828	0.9336	0.6133	0.9394
5.2062	0.2151	182	1.0812	0.9269	0.6179	0.9318
5.2062	0.2175	184	1.0812	0.9302	0.5070	0.9321
5.3281	0.2199	186	1.0781	0.9336	0.5076	0.9354
5.3281	0.2222	188	1.0781	0.9502	0.5191	0.9505
5.275	0.2246	190	1.0719	0.9468	0.4457	0.9452
5.275	0.2270	192	1.0672	0.9369	0.4322	0.9345
5.275	0.2293	194	1.0656	0.9468	0.5132	0.9469
5.2313	0.2317	196	1.0609	0.9502	0.5191	0.9505
5.2313	0.2340	198	1.0609	0.9402	0.5114	0.9415
5.3219	0.2364	200	1.0578	0.9468	0.5186	0.9473
5.3219	0.2388	202	1.0547	0.9435	0.5652	0.9466
5.3219	0.2411	204	1.0453	0.9435	0.4499	0.9463
5.2438	0.2435	206	1.0438	0.9435	0.4973	0.9452
5.2438	0.2459	208	1.0359	0.9336	0.4847	0.9367
5.0625	0.2482	210	1.0328	0.9435	0.5016	0.9441
5.0625	0.2506	212	1.0281	0.9468	0.5236	0.9495
5.0625	0.2530	214	1.0266	0.9402	0.5192	0.9431
5.0266	0.2553	216	1.0234	0.9435	0.5248	0.9466
5.0266	0.2577	218	1.0187	0.9435	0.4415	0.9436
4.9516	0.2600	220	1.0187	0.9468	0.4105	0.9469
4.9516	0.2624	222	1.0195	0.9502	0.4822	0.9518
4.9516	0.2648	224	1.0164	0.9502	0.5193	0.9518
5.0484	0.2671	226	1.0148	0.9535	0.5235	0.9536
5.0484	0.2695	228	1.0148	0.9535	0.5235	0.9536
4.8859	0.2719	230	1.0070	0.9468	0.6380	0.9481
4.8859	0.2742	232	1.0055	0.9568	0.6464	0.9572
4.8859	0.2766	234	1.0070	0.9568	0.5282	0.9568
4.9	0.2790	236	1.0008	0.9601	0.5795	0.9613
4.9	0.2813	238	0.9977	0.9568	0.5282	0.9568
4.9266	0.2837	240	0.9961	0.9568	0.5282	0.9568
4.9266	0.2861	242	0.9898	0.9568	0.5282	0.9568
4.9266	0.2884	244	0.9883	0.9568	0.5282	0.9568
4.8063	0.2908	246	0.9844	0.9535	0.5333	0.9563
4.8063	0.2931	248	0.9828	0.9468	0.4917	0.9518
4.9109	0.2955	250	0.9828	0.9468	0.5421	0.9521
4.9109	0.2979	252	0.9797	0.9336	0.5194	0.9416
4.9109	0.3002	254	0.9750	0.9402	0.5322	0.9475
4.825	0.3026	256	0.9703	0.9435	0.5409	0.9512
4.825	0.3050	258	0.9680	0.9402	0.5491	0.9501
4.7984	0.3073	260	0.9680	0.9402	0.4904	0.9496
4.7984	0.3097	262	0.9625	0.9502	0.5262	0.9536
4.7984	0.3121	264	0.9609	0.9502	0.5262	0.9536
4.7766	0.3144	266	0.9609	0.9435	0.5223	0.9474
4.7766	0.3168	268	0.9570	0.9402	0.4747	0.9429
4.5906	0.3191	270	0.9555	0.9369	0.4717	0.9402
4.5906	0.3215	272	0.9539	0.9435	0.5144	0.9441
4.5906	0.3239	274	0.9484	0.9468	0.5150	0.9475
4.5891	0.3262	276	0.9469	0.9535	0.5196	0.9538
4.5891	0.3286	278	0.9438	0.9535	0.5276	0.9536
4.6125	0.3310	280	0.9414	0.9535	0.5276	0.9536
4.6125	0.3333	282	0.9398	0.9568	0.5789	0.9581
4.6125	0.3357	284	0.9406	0.9601	0.6011	0.9618
4.6047	0.3381	286	0.9336	0.9601	0.5956	0.9614
4.6047	0.3404	288	0.9305	0.9601	0.5917	0.9627
4.6172	0.3428	290	0.9281	0.9535	0.5874	0.9576
4.6172	0.3452	292	0.9273	0.9568	0.5926	0.9587
4.6172	0.3475	294	0.9266	0.9535	0.5902	0.9562
4.4078	0.3499	296	0.9234	0.9435	0.5620	0.9471
4.4078	0.3522	298	0.9203	0.9468	0.5625	0.9504
4.4211	0.3546	300	0.9203	0.9435	0.5597	0.9478
4.4211	0.3570	302	0.9187	0.9502	0.5654	0.9530
4.4211	0.3593	304	0.9164	0.9502	0.5654	0.9530
4.4398	0.3617	306	0.9180	0.9468	0.6921	0.9504
4.4398	0.3641	308	0.9164	0.9468	0.7133	0.9503
4.2398	0.3664	310	0.9125	0.9502	0.5883	0.9525
4.2398	0.3688	312	0.9102	0.9568	0.5964	0.9585
4.2398	0.3712	314	0.9086	0.9568	0.5966	0.9599
4.4773	0.3735	316	0.9055	0.9402	0.5675	0.9460
4.4773	0.3759	318	0.9062	0.9369	0.5590	0.9424
4.4156	0.3783	320	0.9023	0.9369	0.5576	0.9420
4.4156	0.3806	322	0.9008	0.9336	0.5571	0.9387
4.4156	0.3830	324	0.9016	0.9369	0.5669	0.9428
4.1977	0.3853	326	0.8961	0.9435	0.5667	0.9489
4.1977	0.3877	328	0.8930	0.9535	0.5810	0.9581
4.1523	0.3901	330	0.8875	0.9601	0.5956	0.9614
4.1523	0.3924	332	0.8820	0.9601	0.5956	0.9614
4.1523	0.3948	334	0.8789	0.9601	0.5956	0.9614
4.1945	0.3972	336	0.8789	0.9635	0.6016	0.9650
4.1945	0.3995	338	0.8727	0.9568	0.5950	0.9581
4.0773	0.4019	340	0.8742	0.9635	0.6017	0.9651
4.0773	0.4043	342	0.8656	0.9635	0.6017	0.9651
4.0773	0.4066	344	0.8664	0.9635	0.6017	0.9651
4.075	0.4090	346	0.8633	0.9535	0.5889	0.9558
4.075	0.4113	348	0.8609	0.9502	0.5495	0.9537
4.1719	0.4137	350	0.8586	0.9535	0.5944	0.9549
4.1719	0.4161	352	0.8570	0.9535	0.5944	0.9549
4.1719	0.4184	354	0.8539	0.9601	0.5956	0.9614
4.0867	0.4208	356	0.8500	0.9601	0.5956	0.9614
4.0867	0.4232	358	0.8492	0.9502	0.5389	0.9531
4.2211	0.4255	360	0.8453	0.9468	0.4716	0.9529
4.2211	0.4279	362	0.8438	0.9502	0.5033	0.9546
4.2211	0.4303	364	0.8422	0.9502	0.4627	0.9558
3.9312	0.4326	366	0.8375	0.9535	0.5287	0.9559
3.9312	0.4350	368	0.8359	0.9535	0.5248	0.9560
4.0234	0.4374	370	0.8336	0.9568	0.5692	0.9577
4.0234	0.4397	372	0.8313	0.9535	0.5650	0.9547
4.0234	0.4421	374	0.8313	0.9535	0.5650	0.9547
3.9758	0.4444	376	0.8297	0.9502	0.5644	0.9514
3.9758	0.4468	378	0.8305	0.9535	0.5703	0.9550
3.975	0.4492	380	0.8266	0.9502	0.5259	0.9532
3.975	0.4515	382	0.8273	0.9568	0.5926	0.9587
3.975	0.4539	384	0.8227	0.9601	0.5968	0.9618
3.8	0.4563	386	0.8211	0.9601	0.5968	0.9618
3.8	0.4586	388	0.8195	0.9601	0.5968	0.9618
3.8922	0.4610	390	0.8188	0.9601	0.5968	0.9618
3.8922	0.4634	392	0.8172	0.9502	0.5456	0.9535
3.8922	0.4657	394	0.8156	0.9502	0.5457	0.9535
4.0117	0.4681	396	0.8133	0.9502	0.5086	0.9544
4.0117	0.4704	398	0.8125	0.9535	0.5083	0.9585
3.7359	0.4728	400	0.8070	0.9601	0.5545	0.9631
3.7359	0.4752	402	0.8086	0.9502	0.5491	0.9533
3.7359	0.4775	404	0.8055	0.9502	0.5456	0.9535
3.7016	0.4799	406	0.8047	0.9502	0.5456	0.9535
3.7016	0.4823	408	0.8039	0.9502	0.5259	0.9532
3.7719	0.4846	410	0.7984	0.9502	0.5259	0.9532
3.7719	0.4870	412	0.7937	0.9535	0.5298	0.9563
3.7719	0.4894	414	0.7914	0.9601	0.5800	0.9613
3.6156	0.4917	416	0.7875	0.9502	0.5698	0.9516
3.6156	0.4941	418	0.7836	0.9535	0.5704	0.9550
3.6367	0.4965	420	0.7812	0.9535	0.5704	0.9550
3.6367	0.4988	422	0.7805	0.9535	0.5704	0.9550
3.6367	0.5012	424	0.7766	0.9535	0.5704	0.9550
3.5805	0.5035	426	0.7750	0.9568	0.5710	0.9583
3.5805	0.5059	428	0.7711	0.9535	0.5704	0.9550
3.5859	0.5083	430	0.7664	0.9535	0.5920	0.9555
3.5859	0.5106	432	0.7625	0.9568	0.5974	0.9588
3.5859	0.5130	434	0.7578	0.9568	0.5974	0.9588
3.5578	0.5154	436	0.7547	0.9601	0.6017	0.9619
3.5578	0.5177	438	0.7523	0.9601	0.6017	0.9619
3.2711	0.5201	440	0.7508	0.9601	0.6016	0.9618
3.2711	0.5225	442	0.7492	0.9568	0.5963	0.9584
3.2711	0.5248	444	0.7461	0.9635	0.6022	0.9651
3.3477	0.5272	446	0.7414	0.9601	0.6016	0.9618
3.3477	0.5296	448	0.7391	0.9568	0.6010	0.9585
3.6391	0.5319	450	0.7352	0.9568	0.6010	0.9585
3.6391	0.5343	452	0.7344	0.9535	0.5956	0.9553
3.6391	0.5366	454	0.7336	0.9502	0.5911	0.9533
3.5383	0.5390	456	0.7281	0.9502	0.5857	0.9529
3.5383	0.5414	458	0.7250	0.9502	0.5857	0.9529
3.393	0.5437	460	0.7242	0.9502	0.5857	0.9529
3.393	0.5461	462	0.7219	0.9535	0.5902	0.9548
3.393	0.5485	464	0.7211	0.9535	0.5902	0.9548
3.3102	0.5508	466	0.7195	0.9601	0.6011	0.9618
3.3102	0.5532	468	0.7188	0.9535	0.5958	0.9553
3.0887	0.5556	470	0.7156	0.9535	0.6453	0.9539
3.0887	0.5579	472	0.7141	0.9468	0.5663	0.9487
3.0887	0.5603	474	0.7141	0.9502	0.5700	0.9517
3.3156	0.5626	476	0.7125	0.9468	0.5255	0.9499
3.3156	0.5650	478	0.7102	0.9468	0.5224	0.9503
3.0727	0.5674	480	0.7078	0.9535	0.5920	0.9555
3.0727	0.5697	482	0.7055	0.9635	0.6509	0.9636
3.0727	0.5721	484	0.7039	0.9535	0.5920	0.9554
3.2828	0.5745	486	0.7016	0.9568	0.5908	0.9581
3.2828	0.5768	488	0.6992	0.9568	0.5908	0.9581
3.2781	0.5792	490	0.6977	0.9568	0.5908	0.9581
3.2781	0.5816	492	0.6938	0.9502	0.5896	0.9516
3.2781	0.5839	494	0.6906	0.9535	0.5956	0.9552
3.2195	0.5863	496	0.6891	0.9535	0.5494	0.9566
3.2195	0.5887	498	0.6875	0.9535	0.5920	0.9555
3.1945	0.5910	500	0.6852	0.9502	0.5456	0.9535
3.1945	0.5934	502	0.6812	0.9535	0.5453	0.9577
3.1945	0.5957	504	0.6773	0.9535	0.5461	0.9568
2.9336	0.5981	506	0.6758	0.9502	0.5414	0.9546
2.9336	0.6005	508	0.6750	0.9468	0.5362	0.9522
2.9797	0.6028	510	0.6703	0.9502	0.5414	0.9546
2.9797	0.6052	512	0.6687	0.9502	0.5414	0.9546
2.9797	0.6076	514	0.6680	0.9568	0.5962	0.9585
3.032	0.6099	516	0.6672	0.9568	0.5962	0.9585
3.032	0.6123	518	0.6656	0.9568	0.5926	0.9587
3.1461	0.6147	520	0.6625	0.9601	0.6464	0.9605
3.1461	0.6170	522	0.6609	0.9601	0.6481	0.9608
3.1461	0.6194	524	0.6594	0.9535	0.6437	0.9547
3.243	0.6217	526	0.6547	0.9502	0.5685	0.9524
3.243	0.6241	528	0.6516	0.9468	0.5652	0.9497
2.9344	0.6265	530	0.6500	0.9502	0.5685	0.9524
2.9344	0.6288	532	0.6453	0.9502	0.5685	0.9524
2.9344	0.6312	534	0.6453	0.9502	0.5685	0.9524
2.9969	0.6336	536	0.6422	0.9502	0.5685	0.9524
2.9969	0.6359	538	0.6406	0.9535	0.5671	0.9553
2.8379	0.6383	540	0.6391	0.9568	0.5710	0.9582
2.8379	0.6407	542	0.6375	0.9568	0.6400	0.9568
2.8379	0.6430	544	0.6375	0.9535	0.6394	0.9536
2.9375	0.6454	546	0.6352	0.9568	0.6439	0.9566
2.9375	0.6478	548	0.6320	0.9468	0.5392	0.9508
2.9531	0.6501	550	0.6297	0.9502	0.5439	0.9530
2.9531	0.6525	552	0.6281	0.9468	0.4672	0.9534
2.9531	0.6548	554	0.6273	0.9502	0.4713	0.9556
2.9539	0.6572	556	0.6258	0.9402	0.4866	0.9468
2.9539	0.6596	558	0.6219	0.9435	0.4915	0.9492
2.7633	0.6619	560	0.6203	0.9502	0.5024	0.9540
2.7633	0.6643	562	0.6203	0.9568	0.5501	0.9599
2.7633	0.6667	564	0.6180	0.9568	0.5963	0.9585
2.9102	0.6690	566	0.6156	0.9568	0.5501	0.9599
2.9102	0.6714	568	0.6141	0.9502	0.5089	0.9560
2.7398	0.6738	570	0.6109	0.9535	0.5496	0.9566
2.7398	0.6761	572	0.6078	0.9435	0.5035	0.9502
2.7398	0.6785	574	0.6047	0.9468	0.5084	0.9527
2.7898	0.6809	576	0.6008	0.9502	0.5128	0.9549
2.7898	0.6832	578	0.5992	0.9535	0.5133	0.9581
2.9055	0.6856	580	0.5984	0.9435	0.4999	0.9494
2.9055	0.6879	582	0.5969	0.9468	0.5046	0.9531
2.9055	0.6903	584	0.5969	0.9468	0.5007	0.9538
2.5855	0.6927	586	0.5945	0.9535	0.5464	0.9584
2.5855	0.6950	588	0.5938	0.9568	0.5964	0.9585
2.6891	0.6974	590	0.5938	0.9568	0.5964	0.9585
2.6891	0.6998	592	0.5922	0.9568	0.5964	0.9585
2.6891	0.7021	594	0.5898	0.9535	0.5496	0.9566
2.8	0.7045	596	0.5875	0.9502	0.5089	0.9560
2.8	0.7069	598	0.5844	0.9468	0.4724	0.9540
2.5113	0.7092	600	0.5836	0.9435	0.4984	0.9508
2.5113	0.7116	602	0.5836	0.9402	0.4626	0.9488
2.5113	0.7139	604	0.5828	0.9468	0.5040	0.9535
2.5523	0.7163	606	0.5813	0.9402	0.4626	0.9488
2.5523	0.7187	608	0.5797	0.9402	0.4626	0.9487
2.6152	0.7210	610	0.5773	0.9468	0.5040	0.9535
2.6152	0.7234	612	0.5766	0.9468	0.4683	0.9548
2.6152	0.7258	614	0.5758	0.9568	0.5138	0.9614
2.7	0.7281	616	0.5742	0.9535	0.5094	0.9592
2.7	0.7305	618	0.5734	0.9535	0.5094	0.9592
2.5863	0.7329	620	0.5719	0.9435	0.4926	0.9509
2.5863	0.7352	622	0.5703	0.9402	0.4571	0.9489
2.5863	0.7376	624	0.5695	0.9502	0.5000	0.9581
2.5766	0.7400	626	0.5680	0.9402	0.4882	0.9498
2.5766	0.7423	628	0.5672	0.9435	0.4938	0.9525
2.4121	0.7447	630	0.5672	0.9402	0.4882	0.9498
2.4121	0.7470	632	0.5656	0.9468	0.4943	0.9559
2.4121	0.7494	634	0.5641	0.9435	0.4888	0.9531
2.7289	0.7518	636	0.5633	0.9502	0.5000	0.9581
2.7289	0.7541	638	0.5633	0.9435	0.4908	0.9529
2.4738	0.7565	640	0.5625	0.9402	0.4903	0.9496
2.4738	0.7589	642	0.5625	0.9402	0.4596	0.9490
2.4738	0.7612	644	0.5602	0.9468	0.4653	0.9551
2.5812	0.7636	646	0.5586	0.9435	0.4629	0.9526
2.5812	0.7660	648	0.5586	0.9468	0.4675	0.9550
2.1652	0.7683	650	0.5570	0.9435	0.4582	0.9531
2.1652	0.7707	652	0.5570	0.9402	0.4577	0.9498
2.1652	0.7730	654	0.5555	0.9402	0.4577	0.9498
2.4156	0.7754	656	0.5539	0.9369	0.4518	0.9466
2.4156	0.7778	658	0.5531	0.9468	0.4634	0.9559
2.3066	0.7801	660	0.5531	0.9402	0.4523	0.9499
2.3066	0.7825	662	0.5500	0.9369	0.4518	0.9466
2.3066	0.7849	664	0.5500	0.9402	0.4523	0.9499
2.473	0.7872	666	0.5484	0.9336	0.4513	0.9433
2.473	0.7896	668	0.5477	0.9302	0.4444	0.9397
2.3289	0.7920	670	0.5469	0.9369	0.4454	0.9463
2.3289	0.7943	672	0.5461	0.9369	0.4518	0.9466
2.3289	0.7967	674	0.5461	0.9369	0.4454	0.9463
2.5141	0.7991	676	0.5437	0.9336	0.4449	0.9430
2.5141	0.8014	678	0.5430	0.9369	0.4518	0.9466
2.3312	0.8038	680	0.5414	0.9369	0.4461	0.9473
2.3312	0.8061	682	0.5406	0.9369	0.4454	0.9463
2.3312	0.8085	684	0.5398	0.9402	0.4523	0.9499
2.4254	0.8109	686	0.5391	0.9402	0.4523	0.9499
2.4254	0.8132	688	0.5375	0.9402	0.4824	0.9499
2.2059	0.8156	690	0.5359	0.9336	0.4449	0.9430
2.2059	0.8180	692	0.5352	0.9402	0.4523	0.9499
2.2059	0.8203	694	0.5344	0.9302	0.4444	0.9397
2.3016	0.8227	696	0.5328	0.9336	0.4449	0.9430
2.3016	0.8251	698	0.5328	0.9302	0.4369	0.9387
2.241	0.8274	700	0.5320	0.9302	0.4369	0.9387
2.241	0.8298	702	0.5297	0.9302	0.4369	0.9387
2.241	0.8322	704	0.5297	0.9336	0.4746	0.9430
2.3813	0.8345	706	0.5289	0.9302	0.4312	0.9394
2.3813	0.8369	708	0.5281	0.9336	0.4665	0.9420
2.2258	0.8392	710	0.5273	0.9302	0.4599	0.9394
2.2258	0.8416	712	0.5273	0.9336	0.4665	0.9420
2.2258	0.8440	714	0.5266	0.9302	0.4312	0.9394
2.3098	0.8463	716	0.5250	0.9302	0.4599	0.9394
2.3098	0.8487	718	0.5242	0.9302	0.4312	0.9394
2.182	0.8511	720	0.5238	0.9336	0.4392	0.9436
2.182	0.8534	722	0.5238	0.9336	0.4374	0.9420
2.182	0.8558	724	0.5230	0.9336	0.4374	0.9420
2.3766	0.8582	726	0.5230	0.9336	0.4374	0.9420
2.3766	0.8605	728	0.5230	0.9302	0.4387	0.9403
2.2934	0.8629	730	0.5230	0.9302	0.4599	0.9394
2.2934	0.8652	732	0.5207	0.9236	0.4493	0.9311
2.2934	0.8676	734	0.5207	0.9302	0.4369	0.9387
2.1684	0.8700	736	0.5199	0.9269	0.4240	0.9363
2.1684	0.8723	738	0.5176	0.9336	0.4374	0.9420
2.2758	0.8747	740	0.5176	0.9302	0.4369	0.9387
2.2758	0.8771	742	0.5176	0.9336	0.4665	0.9420
2.2758	0.8794	744	0.5176	0.9302	0.4660	0.9387
2.1699	0.8818	746	0.5168	0.9336	0.4374	0.9420
2.1699	0.8842	748	0.5160	0.9302	0.4369	0.9387
2.2426	0.8865	750	0.5160	0.9336	0.4374	0.9420
2.2426	0.8889	752	0.5160	0.9269	0.4594	0.9361
2.2426	0.8913	754	0.5152	0.9336	0.4374	0.9420
2.1137	0.8936	756	0.5145	0.9269	0.4594	0.9361
2.1137	0.8960	758	0.5145	0.9269	0.4594	0.9361
2.2496	0.8983	760	0.5137	0.9236	0.4493	0.9311
2.2496	0.9007	762	0.5137	0.9302	0.4599	0.9394
2.2496	0.9031	764	0.5137	0.9302	0.4279	0.9370
2.298	0.9054	766	0.5137	0.9302	0.4369	0.9387
2.298	0.9078	768	0.5137	0.9336	0.4665	0.9420
2.1523	0.9102	770	0.5129	0.9336	0.4449	0.9430
2.1523	0.9125	772	0.5129	0.9336	0.4665	0.9420
2.1523	0.9149	774	0.5121	0.9302	0.4660	0.9387
2.173	0.9173	776	0.5129	0.9269	0.4274	0.9337
2.173	0.9196	778	0.5129	0.9302	0.4369	0.9387
2.2578	0.9220	780	0.5121	0.9302	0.4660	0.9387
2.2578	0.9243	782	0.5121	0.9302	0.4599	0.9394
2.2578	0.9267	784	0.5121	0.9269	0.4594	0.9361
2.0625	0.9291	786	0.5117	0.9302	0.4369	0.9387
2.0625	0.9314	788	0.5117	0.9336	0.4665	0.9420
2.273	0.9338	790	0.5117	0.9336	0.4665	0.9420
2.273	0.9362	792	0.5117	0.9336	0.4374	0.9420
2.273	0.9385	794	0.5117	0.9302	0.4279	0.9370
2.3676	0.9409	796	0.5117	0.9302	0.4369	0.9387
2.3676	0.9433	798	0.5117	0.9236	0.4212	0.9311
2.3828	0.9456	800	0.5117	0.9302	0.4312	0.9394
2.3828	0.9480	802	0.5117	0.9269	0.4307	0.9361
2.3828	0.9504	804	0.5117	0.9369	0.4751	0.9463
2.3293	0.9527	806	0.5117	0.9269	0.4594	0.9361
2.3293	0.9551	808	0.5117	0.9336	0.4746	0.9430
2.3215	0.9574	810	0.5117	0.9336	0.4374	0.9420
2.3215	0.9598	812	0.5117	0.9336	0.4392	0.9436
2.3215	0.9622	814	0.5117	0.9336	0.4746	0.9430
2.277	0.9645	816	0.5117	0.9302	0.4369	0.9387
2.277	0.9669	818	0.5117	0.9336	0.4374	0.9420
2.2863	0.9693	820	0.5117	0.9269	0.4307	0.9361
2.2863	0.9716	822	0.5117	0.9269	0.4307	0.9361
2.2863	0.9740	824	0.5117	0.9302	0.4312	0.9394
2.1504	0.9764	826	0.5117	0.9336	0.4665	0.9420
2.1504	0.9787	828	0.5117	0.9336	0.4685	0.9436
2.2391	0.9811	830	0.5109	0.9269	0.4594	0.9361
2.2391	0.9835	832	0.5117	0.9336	0.4374	0.9420
2.2391	0.9858	834	0.5117	0.9336	0.4374	0.9420
2.1863	0.9882	836	0.5109	0.9336	0.4374	0.9420
2.1863	0.9905	838	0.5117	0.9369	0.4454	0.9463
2.4371	0.9929	840	0.5117	0.9336	0.4374	0.9420
2.4371	0.9953	842	0.5109	0.9336	0.4374	0.9420
2.4371	0.9976	844	0.5109	0.9336	0.4449	0.9430
2.2313	1.0	846	0.5117	0.9269	0.4307	0.9361

Framework versions

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