text_shortening_model_v52

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5235
• Rouge1: 0.4999
• Rouge2: 0.2774
• Rougel: 0.4503
• Rougelsum: 0.4506
• Bert precision: 0.8767
• Bert recall: 0.8725
• Average word count: 8.1138
• Max word count: 16
• Min word count: 3
• Average token count: 12.5
• % shortened texts with length > 12: 5.8201

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 250

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bert precision	Bert recall	Average word count	Max word count	Min word count	Average token count	% shortened texts with length > 12
2.1707	1.0	83	1.8170	0.4878	0.2747	0.4466	0.445	0.8688	0.8685	8.6667	17	3	13.0767	12.963
1.7733	2.0	166	1.6790	0.4915	0.2767	0.4462	0.4458	0.8665	0.8724	9.1825	17	4	13.7778	14.8148
1.6346	3.0	249	1.6275	0.5003	0.2755	0.4523	0.4517	0.8706	0.8723	8.8148	17	4	13.4206	12.963
1.5193	4.0	332	1.5648	0.5179	0.2984	0.4686	0.4674	0.8717	0.8795	9.373	17	4	13.8995	15.6085
1.414	5.0	415	1.5338	0.512	0.2843	0.4591	0.4585	0.8721	0.8747	8.8598	17	4	13.3122	13.7566
1.3401	6.0	498	1.4932	0.5067	0.2814	0.4543	0.4539	0.8712	0.874	8.9074	17	4	13.3942	14.0212
1.2739	7.0	581	1.4780	0.5015	0.2726	0.4498	0.4496	0.8717	0.8715	8.5714	16	4	13.0	10.8466
1.2165	8.0	664	1.4522	0.5188	0.2933	0.469	0.469	0.8746	0.8776	8.9021	16	4	13.3519	14.5503
1.1494	9.0	747	1.4381	0.5105	0.2825	0.4587	0.4584	0.8734	0.8746	8.6878	16	4	13.119	12.963
1.0923	10.0	830	1.4354	0.513	0.2855	0.462	0.4618	0.8725	0.8753	9.0053	17	4	13.3624	14.2857
1.0625	11.0	913	1.4224	0.5132	0.2841	0.4645	0.4643	0.8736	0.8766	8.9497	16	4	13.3704	15.3439
1.0264	12.0	996	1.4196	0.4984	0.2716	0.4458	0.4456	0.8701	0.8712	8.8148	16	4	13.172	14.8148
0.9701	13.0	1079	1.4137	0.5065	0.2765	0.4541	0.4537	0.8753	0.8737	8.545	16	4	12.7434	11.1111
0.9328	14.0	1162	1.4155	0.5073	0.2786	0.4543	0.4541	0.8727	0.873	8.6349	16	4	12.9868	11.6402
0.8992	15.0	1245	1.4097	0.5116	0.28	0.4602	0.4604	0.8758	0.875	8.6402	16	4	12.8598	11.6402
0.8526	16.0	1328	1.4446	0.5055	0.276	0.4526	0.4523	0.8721	0.8732	8.746	16	4	13.0741	11.9048
0.8119	17.0	1411	1.4334	0.5084	0.2772	0.4557	0.4552	0.8744	0.8722	8.5212	16	4	12.8333	9.7884
0.8129	18.0	1494	1.4401	0.5039	0.2719	0.4526	0.4518	0.8743	0.8727	8.5238	17	4	12.7222	10.3175
0.7636	19.0	1577	1.4418	0.5037	0.269	0.4493	0.4492	0.8721	0.8726	8.6455	17	4	13.0159	10.0529
0.7277	20.0	1660	1.4461	0.5064	0.2769	0.452	0.452	0.8733	0.8736	8.5423	17	4	12.9788	10.0529
0.7254	21.0	1743	1.4375	0.5059	0.2761	0.4534	0.453	0.8759	0.8732	8.373	17	3	12.7884	8.9947
0.6898	22.0	1826	1.4799	0.5096	0.2825	0.4594	0.4594	0.876	0.8751	8.5026	17	4	12.9841	9.5238
0.6712	23.0	1909	1.4885	0.5164	0.2874	0.4599	0.4602	0.8743	0.8768	8.8624	17	4	13.3175	13.2275
0.6456	24.0	1992	1.4956	0.5168	0.2876	0.4653	0.465	0.8784	0.8763	8.4788	17	4	12.7381	9.2593
0.619	25.0	2075	1.5044	0.5054	0.2762	0.4569	0.4568	0.8765	0.8728	8.2804	17	4	12.6825	8.7302
0.6044	26.0	2158	1.5089	0.511	0.2902	0.4624	0.463	0.8767	0.8737	8.3915	16	4	12.7275	10.0529
0.58	27.0	2241	1.5231	0.511	0.2814	0.4567	0.4574	0.8756	0.8754	8.6984	17	4	12.9868	11.3757
0.5671	28.0	2324	1.5270	0.5095	0.2766	0.4524	0.4529	0.8745	0.8746	8.672	17	4	13.0291	12.1693
0.5547	29.0	2407	1.5530	0.5019	0.27	0.4482	0.4485	0.8737	0.8719	8.4233	17	4	12.8042	8.2011
0.5371	30.0	2490	1.5537	0.5021	0.2693	0.4491	0.4488	0.8737	0.8711	8.3995	16	4	12.7884	9.5238
0.526	31.0	2573	1.5595	0.5024	0.273	0.4481	0.4482	0.8737	0.8722	8.4868	17	4	12.8836	10.0529
0.5067	32.0	2656	1.5753	0.5048	0.2745	0.4535	0.4537	0.8752	0.8717	8.3413	16	4	12.7513	9.2593
0.4954	33.0	2739	1.5977	0.5011	0.2713	0.4523	0.4523	0.8738	0.8721	8.4815	16	4	12.8545	12.1693
0.4766	34.0	2822	1.6143	0.5083	0.2764	0.4528	0.453	0.8744	0.874	8.6085	17	4	12.955	10.8466
0.4603	35.0	2905	1.6225	0.5058	0.2768	0.4541	0.4541	0.8743	0.8724	8.5397	16	4	12.8624	10.0529
0.449	36.0	2988	1.6171	0.5004	0.2704	0.4484	0.4485	0.8758	0.8717	8.3042	16	4	12.6005	6.8783
0.4299	37.0	3071	1.6431	0.5016	0.2757	0.4508	0.4504	0.8763	0.8705	8.1455	16	4	12.5053	6.8783
0.4177	38.0	3154	1.6731	0.5	0.2695	0.4434	0.4437	0.8736	0.8707	8.2698	16	3	12.664	8.2011
0.4092	39.0	3237	1.6705	0.5041	0.2726	0.4512	0.4506	0.8742	0.8735	8.5106	16	4	12.9524	8.4656
0.3996	40.0	3320	1.6956	0.5066	0.277	0.4538	0.4538	0.876	0.8733	8.2566	16	4	12.6534	7.9365
0.3949	41.0	3403	1.6975	0.5089	0.2773	0.4573	0.4576	0.8759	0.8753	8.4577	16	4	12.9339	8.2011
0.3802	42.0	3486	1.7115	0.4986	0.2676	0.4458	0.4459	0.8739	0.8711	8.3466	17	4	12.8651	8.9947
0.3734	43.0	3569	1.7011	0.5055	0.2793	0.4541	0.454	0.8756	0.8746	8.4127	16	4	12.8413	9.2593
0.356	44.0	3652	1.7285	0.5015	0.2728	0.4469	0.4474	0.8741	0.8727	8.3862	17	4	12.8836	7.9365
0.3438	45.0	3735	1.7326	0.4989	0.2731	0.4426	0.4432	0.8744	0.8709	8.2566	17	4	12.6667	7.9365
0.3412	46.0	3818	1.7328	0.5051	0.2777	0.4519	0.4523	0.8753	0.8731	8.3254	16	4	12.7963	6.6138
0.3404	47.0	3901	1.7651	0.5135	0.2825	0.4584	0.459	0.8746	0.8749	8.6032	16	4	13.0582	10.0529
0.3283	48.0	3984	1.7700	0.5052	0.2763	0.4519	0.453	0.8749	0.873	8.3704	17	4	12.8254	6.8783
0.3206	49.0	4067	1.7754	0.5028	0.2741	0.4481	0.4489	0.8744	0.8728	8.3836	17	4	12.8122	6.0847
0.3116	50.0	4150	1.7851	0.5027	0.2769	0.4491	0.4494	0.8747	0.8727	8.3439	17	4	12.754	6.0847
0.3081	51.0	4233	1.8009	0.4975	0.2673	0.4392	0.4394	0.8727	0.8699	8.3175	17	4	12.746	7.4074
0.2999	52.0	4316	1.8090	0.502	0.2706	0.4464	0.4468	0.8741	0.8716	8.3122	17	4	12.7487	6.3492
0.2925	53.0	4399	1.8183	0.5082	0.2794	0.4535	0.4543	0.8762	0.8734	8.2725	16	4	12.672	7.672
0.2837	54.0	4482	1.8324	0.5101	0.28	0.4525	0.4538	0.8763	0.8741	8.3201	17	4	12.7857	6.6138
0.2763	55.0	4565	1.8444	0.4984	0.2688	0.4437	0.4446	0.8745	0.8703	8.2169	16	4	12.6825	6.0847
0.2663	56.0	4648	1.8723	0.4998	0.2715	0.4451	0.4451	0.874	0.8712	8.3175	16	4	12.7672	7.9365
0.2659	57.0	4731	1.8871	0.5043	0.2818	0.4513	0.4513	0.8754	0.8726	8.2751	16	4	12.7646	6.6138
0.2532	58.0	4814	1.8827	0.5084	0.2848	0.4542	0.4547	0.8769	0.8748	8.254	16	4	12.7672	5.8201
0.2528	59.0	4897	1.8852	0.4997	0.2749	0.4467	0.4472	0.8752	0.8709	8.2037	16	4	12.6376	7.4074
0.2408	60.0	4980	1.9075	0.5026	0.2833	0.452	0.4531	0.8755	0.8726	8.2434	16	4	12.7328	6.8783
0.2405	61.0	5063	1.9030	0.5028	0.2798	0.4508	0.4512	0.8759	0.8725	8.2037	16	4	12.6349	8.4656
0.233	62.0	5146	1.8968	0.5018	0.2775	0.4484	0.4487	0.874	0.8723	8.3598	16	4	12.7989	7.1429
0.2272	63.0	5229	1.9150	0.4976	0.2737	0.4432	0.4437	0.8745	0.8702	8.1243	16	4	12.4788	4.7619
0.2204	64.0	5312	1.9315	0.4971	0.2731	0.443	0.4438	0.8745	0.8698	8.1111	16	4	12.5053	6.8783
0.2222	65.0	5395	1.9321	0.5043	0.2778	0.4455	0.4457	0.8746	0.8719	8.2222	16	4	12.7672	5.8201
0.2179	66.0	5478	1.9581	0.4965	0.2712	0.4403	0.4412	0.8738	0.8691	8.1217	16	4	12.5397	6.6138
0.2083	67.0	5561	1.9525	0.5056	0.2783	0.452	0.4526	0.8755	0.8727	8.2857	16	4	12.7249	6.8783
0.2064	68.0	5644	1.9598	0.5025	0.2715	0.4453	0.4462	0.8746	0.8711	8.2249	16	4	12.5899	7.1429
0.1988	69.0	5727	2.0058	0.5017	0.2793	0.4493	0.4502	0.8757	0.8736	8.2487	16	4	12.8862	6.8783
0.202	70.0	5810	1.9937	0.4954	0.2668	0.4418	0.443	0.8743	0.8697	8.1111	16	4	12.5265	7.9365
0.1886	71.0	5893	2.0146	0.5008	0.2757	0.4477	0.4491	0.8754	0.871	8.1587	16	4	12.5582	7.1429
0.1911	72.0	5976	2.0179	0.4938	0.2703	0.4424	0.4436	0.8741	0.8692	8.119	16	4	12.4603	6.3492
0.1842	73.0	6059	2.0298	0.5016	0.2783	0.4517	0.4523	0.8766	0.8718	8.1058	16	4	12.5397	6.0847
0.1879	74.0	6142	2.0286	0.4974	0.2728	0.4445	0.4446	0.8754	0.8707	8.1958	16	4	12.5529	5.291
0.1848	75.0	6225	2.0334	0.4983	0.2742	0.4447	0.4453	0.875	0.8705	8.1111	16	4	12.5026	5.8201
0.1739	76.0	6308	2.0553	0.4928	0.2695	0.4402	0.4403	0.8749	0.869	8.0026	16	4	12.3836	5.5556
0.1755	77.0	6391	2.0758	0.4987	0.2723	0.4447	0.4449	0.8745	0.8715	8.1852	16	4	12.6693	5.8201
0.1718	78.0	6474	2.0837	0.4978	0.2746	0.4467	0.4473	0.8759	0.8708	8.0503	16	4	12.4101	6.3492
0.1627	79.0	6557	2.0698	0.5026	0.2797	0.4523	0.4522	0.8758	0.8739	8.3016	16	4	12.7143	8.4656
0.173	80.0	6640	2.0829	0.5042	0.2825	0.4542	0.4544	0.876	0.8736	8.2857	16	4	12.7487	7.4074
0.1644	81.0	6723	2.0771	0.4957	0.2718	0.443	0.4438	0.8757	0.871	8.1243	16	4	12.4815	6.0847
0.1613	82.0	6806	2.0779	0.4972	0.2741	0.4486	0.4495	0.876	0.8725	8.2487	16	4	12.6243	6.6138
0.155	83.0	6889	2.1022	0.4997	0.2781	0.4475	0.4481	0.8751	0.8718	8.2884	16	4	12.6958	6.8783
0.1506	84.0	6972	2.1198	0.503	0.2782	0.4495	0.4504	0.8759	0.8728	8.3677	16	4	12.7831	8.4656
0.1526	85.0	7055	2.1269	0.4977	0.2738	0.4472	0.4475	0.8748	0.8721	8.3016	16	4	12.709	7.1429
0.149	86.0	7138	2.1286	0.4966	0.2699	0.4454	0.4458	0.8764	0.8698	8.0053	16	4	12.2751	5.291
0.1472	87.0	7221	2.1412	0.5	0.2788	0.4473	0.4474	0.8758	0.8713	8.1005	16	4	12.4524	6.3492
0.1491	88.0	7304	2.1345	0.4969	0.2782	0.4451	0.4451	0.8753	0.8709	8.119	16	4	12.4947	6.8783
0.1381	89.0	7387	2.1461	0.4964	0.2742	0.4443	0.4442	0.8756	0.8705	8.1296	16	4	12.5053	6.0847
0.1437	90.0	7470	2.1432	0.4992	0.279	0.4451	0.4459	0.8755	0.8712	8.2566	16	4	12.5979	6.3492
0.1404	91.0	7553	2.1540	0.5004	0.2789	0.4486	0.4489	0.8765	0.8719	8.1138	16	4	12.5582	5.291
0.1329	92.0	7636	2.1649	0.5012	0.2804	0.4476	0.4488	0.8765	0.8724	8.1587	16	4	12.5503	5.8201
0.1351	93.0	7719	2.1639	0.4965	0.2757	0.4449	0.4459	0.8752	0.8715	8.1693	15	4	12.4894	7.4074
0.129	94.0	7802	2.1781	0.5063	0.2807	0.4545	0.4552	0.8771	0.8738	8.2646	16	4	12.5688	7.9365
0.1368	95.0	7885	2.1866	0.5007	0.2778	0.4455	0.4456	0.8772	0.8713	8.1058	16	4	12.3704	6.8783
0.1303	96.0	7968	2.1857	0.5038	0.2829	0.4494	0.4496	0.8768	0.8731	8.172	16	3	12.4788	6.8783
0.1258	97.0	8051	2.2108	0.5002	0.2765	0.4461	0.4465	0.8765	0.8724	8.1693	15	4	12.5423	5.8201
0.123	98.0	8134	2.2159	0.5033	0.2838	0.4487	0.4491	0.8771	0.8734	8.2698	16	4	12.6402	7.9365
0.117	99.0	8217	2.2073	0.5101	0.2881	0.4586	0.4584	0.8785	0.875	8.2275	16	4	12.5952	6.8783
0.1231	100.0	8300	2.2047	0.498	0.2775	0.4474	0.4469	0.8756	0.8722	8.328	17	4	12.6905	7.9365
0.12	101.0	8383	2.2128	0.4948	0.2709	0.4437	0.4441	0.8758	0.8714	8.1508	16	4	12.4683	6.6138
0.1135	102.0	8466	2.2282	0.5016	0.2806	0.4505	0.4509	0.8762	0.874	8.3757	17	4	12.7672	8.2011
0.122	103.0	8549	2.2265	0.493	0.2713	0.4437	0.4433	0.8744	0.8697	8.127	17	4	12.5079	5.8201
0.1156	104.0	8632	2.2346	0.4909	0.2684	0.4391	0.439	0.8731	0.8703	8.3519	17	4	12.6931	9.5238
0.1084	105.0	8715	2.2580	0.4891	0.2646	0.437	0.4369	0.8729	0.8697	8.3122	17	4	12.6931	8.2011
0.1122	106.0	8798	2.2623	0.4969	0.2755	0.4443	0.4446	0.8749	0.8719	8.3466	16	4	12.7487	7.4074
0.1131	107.0	8881	2.2554	0.4989	0.2751	0.4481	0.448	0.8758	0.8725	8.2646	16	4	12.7143	6.6138
0.1102	108.0	8964	2.2697	0.5023	0.2787	0.4514	0.4519	0.8768	0.8729	8.2196	16	4	12.6376	7.1429
0.1088	109.0	9047	2.2657	0.4979	0.2778	0.4501	0.4499	0.8746	0.8727	8.4286	16	4	12.8413	8.7302
0.1098	110.0	9130	2.2708	0.4911	0.2698	0.4376	0.4379	0.8749	0.8696	8.0767	16	4	12.4312	6.3492
0.1045	111.0	9213	2.2643	0.5014	0.2778	0.4508	0.4511	0.8758	0.8722	8.1931	16	4	12.5952	6.8783
0.0976	112.0	9296	2.2865	0.5012	0.2802	0.4475	0.4478	0.8761	0.8721	8.1534	16	4	12.5265	7.1429
0.1043	113.0	9379	2.2988	0.5025	0.2858	0.4497	0.4499	0.8767	0.8727	8.2037	16	4	12.5635	7.9365
0.1058	114.0	9462	2.3022	0.5027	0.2833	0.453	0.4535	0.877	0.8734	8.246	16	4	12.6693	8.2011
0.1024	115.0	9545	2.3016	0.498	0.2773	0.4477	0.448	0.8759	0.8721	8.2354	16	4	12.6905	7.9365
0.1049	116.0	9628	2.2934	0.4973	0.2779	0.448	0.4478	0.8758	0.8721	8.1931	16	2	12.6587	7.9365
0.0995	117.0	9711	2.3201	0.4987	0.2766	0.4489	0.4489	0.8766	0.8718	8.1138	16	4	12.5238	6.3492
0.0968	118.0	9794	2.3141	0.492	0.2703	0.4407	0.4403	0.8746	0.8699	8.1138	16	4	12.5079	6.8783
0.095	119.0	9877	2.3291	0.4952	0.2735	0.4456	0.4454	0.8752	0.8703	8.1217	16	2	12.537	6.6138
0.0981	120.0	9960	2.3340	0.4959	0.2765	0.4464	0.446	0.8753	0.8705	8.1429	16	2	12.5556	7.1429
0.0966	121.0	10043	2.3176	0.4953	0.276	0.4464	0.4461	0.875	0.8713	8.1667	16	2	12.5529	6.0847
0.086	122.0	10126	2.3323	0.4999	0.2835	0.4513	0.4516	0.8772	0.8719	8.0688	16	3	12.4577	5.8201
0.092	123.0	10209	2.3340	0.5001	0.2806	0.4512	0.4519	0.8758	0.873	8.2778	16	2	12.7222	7.1429
0.09	124.0	10292	2.3530	0.5054	0.2831	0.4542	0.454	0.8767	0.8743	8.2963	16	2	12.7698	7.1429
0.0935	125.0	10375	2.3389	0.5025	0.2849	0.4526	0.4523	0.8779	0.874	8.1561	16	2	12.5397	7.1429
0.092	126.0	10458	2.3580	0.5057	0.2826	0.4512	0.451	0.8776	0.874	8.2434	16	2	12.5979	7.4074
0.0881	127.0	10541	2.3666	0.5069	0.2839	0.4563	0.4557	0.8775	0.8741	8.2831	16	3	12.6878	7.672
0.0857	128.0	10624	2.3517	0.5041	0.2823	0.4528	0.4526	0.8775	0.8734	8.1746	16	2	12.5661	6.8783
0.0869	129.0	10707	2.3571	0.5009	0.2796	0.4502	0.4502	0.8769	0.8725	8.1217	16	2	12.5	6.3492
0.0818	130.0	10790	2.3604	0.5076	0.2872	0.4591	0.459	0.8792	0.8743	8.0952	16	2	12.4735	6.0847
0.0876	131.0	10873	2.3589	0.4996	0.2815	0.4498	0.4502	0.8766	0.8722	8.1243	16	2	12.5582	5.291
0.0871	132.0	10956	2.3850	0.5	0.2845	0.4512	0.4513	0.877	0.8726	8.1508	16	4	12.5661	6.3492
0.0854	133.0	11039	2.3704	0.4958	0.2757	0.4441	0.4445	0.8766	0.8706	8.0423	15	2	12.4815	5.5556
0.0856	134.0	11122	2.3682	0.4973	0.2754	0.4426	0.4423	0.8746	0.8725	8.2937	16	2	12.7963	7.672
0.0839	135.0	11205	2.3730	0.4978	0.2762	0.4457	0.4455	0.8749	0.8719	8.2566	16	3	12.7196	6.3492
0.0855	136.0	11288	2.3803	0.4942	0.2725	0.4399	0.4401	0.8743	0.8712	8.2381	16	2	12.6878	5.8201
0.0829	137.0	11371	2.3822	0.4959	0.2723	0.4447	0.4445	0.8753	0.8721	8.2566	16	2	12.6587	7.672
0.0832	138.0	11454	2.3868	0.4957	0.2713	0.4438	0.4437	0.8749	0.8714	8.1878	16	3	12.6243	6.3492
0.086	139.0	11537	2.3940	0.4979	0.2744	0.4429	0.4428	0.8754	0.8717	8.1825	16	3	12.582	6.8783
0.0789	140.0	11620	2.3893	0.5057	0.2811	0.4507	0.4511	0.8767	0.8739	8.209	16	3	12.672	6.3492
0.0841	141.0	11703	2.3948	0.5021	0.275	0.4477	0.4476	0.875	0.8725	8.2698	16	3	12.7354	7.1429
0.0784	142.0	11786	2.3889	0.4999	0.2737	0.4464	0.4466	0.8756	0.8727	8.2566	16	2	12.7566	6.3492
0.0752	143.0	11869	2.4188	0.5032	0.2759	0.4477	0.4479	0.8765	0.8729	8.1693	16	2	12.6217	5.291
0.0769	144.0	11952	2.4022	0.4994	0.2743	0.4438	0.4438	0.8753	0.8715	8.2063	16	2	12.6746	6.8783
0.0773	145.0	12035	2.4139	0.5042	0.2819	0.4518	0.4519	0.8772	0.8736	8.209	16	2	12.6243	6.0847
0.0751	146.0	12118	2.4150	0.4909	0.2655	0.4387	0.4386	0.875	0.8694	8.0079	16	2	12.455	3.9683
0.0816	147.0	12201	2.4090	0.4968	0.2711	0.443	0.4437	0.8752	0.8715	8.1667	17	2	12.6058	5.5556
0.0775	148.0	12284	2.4251	0.5002	0.2752	0.4459	0.4463	0.8764	0.8727	8.1878	16	2	12.6693	5.8201
0.0761	149.0	12367	2.4093	0.5032	0.2805	0.4516	0.4512	0.8767	0.8741	8.2011	15	3	12.6243	4.7619
0.078	150.0	12450	2.4119	0.4981	0.2737	0.4484	0.4488	0.8767	0.8726	8.127	16	2	12.5688	5.5556
0.0791	151.0	12533	2.4017	0.4959	0.2723	0.4462	0.4463	0.8756	0.8715	8.1561	16	2	12.5503	5.291
0.0762	152.0	12616	2.4192	0.4995	0.2736	0.4507	0.4503	0.8758	0.8711	8.1243	15	2	12.5688	5.5556
0.0761	153.0	12699	2.4085	0.5022	0.2781	0.4529	0.4524	0.8759	0.8728	8.2804	16	3	12.6667	6.3492
0.0738	154.0	12782	2.4299	0.5019	0.2785	0.452	0.4523	0.8771	0.872	8.0952	16	3	12.4894	5.8201
0.0735	155.0	12865	2.4236	0.5002	0.2792	0.4514	0.4515	0.8771	0.872	8.0767	16	3	12.4947	5.291
0.0722	156.0	12948	2.4271	0.5035	0.279	0.4528	0.4527	0.8765	0.8739	8.3413	16	3	12.7011	7.4074
0.069	157.0	13031	2.4337	0.4978	0.2731	0.4473	0.4475	0.8748	0.8714	8.2937	16	3	12.6402	6.8783
0.0737	158.0	13114	2.4321	0.4962	0.2722	0.4441	0.4444	0.8762	0.8714	8.0926	16	3	12.4815	5.8201
0.0673	159.0	13197	2.4347	0.4967	0.2748	0.4446	0.4438	0.8748	0.8718	8.1905	16	3	12.6111	5.5556
0.0713	160.0	13280	2.4431	0.5017	0.2771	0.4508	0.4509	0.8764	0.8729	8.2011	16	3	12.6058	6.0847
0.0757	161.0	13363	2.4656	0.4969	0.2737	0.4458	0.4459	0.8759	0.8711	8.119	16	3	12.5582	5.5556
0.0756	162.0	13446	2.4435	0.4978	0.2747	0.4454	0.445	0.8749	0.8718	8.2619	16	3	12.6746	6.6138
0.0738	163.0	13529	2.4417	0.5045	0.2824	0.4522	0.4523	0.8765	0.8736	8.2302	16	3	12.6508	5.8201
0.0656	164.0	13612	2.4491	0.5009	0.2757	0.4494	0.4497	0.8763	0.8725	8.164	16	3	12.6032	5.5556
0.0726	165.0	13695	2.4493	0.4994	0.2773	0.4475	0.4478	0.8759	0.8728	8.2407	16	3	12.6508	6.6138
0.0704	166.0	13778	2.4400	0.4982	0.2766	0.4479	0.4478	0.8761	0.8717	8.0952	16	3	12.5344	4.7619
0.0681	167.0	13861	2.4468	0.499	0.2753	0.4469	0.4469	0.8762	0.8717	8.1455	16	3	12.5952	5.0265
0.0646	168.0	13944	2.4546	0.497	0.2754	0.445	0.4447	0.8746	0.8717	8.2116	16	3	12.6878	5.0265
0.0712	169.0	14027	2.4622	0.4959	0.2714	0.442	0.4424	0.8748	0.8713	8.2116	16	3	12.6138	5.5556
0.0724	170.0	14110	2.4731	0.4998	0.2729	0.4445	0.4443	0.8754	0.8715	8.1746	16	3	12.5635	5.0265
0.0689	171.0	14193	2.4743	0.4977	0.273	0.4452	0.4451	0.8749	0.8712	8.2037	16	3	12.6032	5.5556
0.0684	172.0	14276	2.4612	0.5047	0.2798	0.4489	0.4492	0.8761	0.874	8.3333	16	3	12.7857	6.6138
0.069	173.0	14359	2.4644	0.4997	0.2778	0.4492	0.4499	0.8757	0.8726	8.2275	16	3	12.6905	6.0847
0.0703	174.0	14442	2.4594	0.498	0.2722	0.4442	0.4442	0.8748	0.8726	8.2407	16	3	12.6931	5.5556
0.0685	175.0	14525	2.4617	0.4988	0.2762	0.448	0.4484	0.8761	0.8725	8.164	16	3	12.5873	5.8201
0.0647	176.0	14608	2.4674	0.4998	0.2777	0.4481	0.4482	0.8764	0.872	8.1243	16	3	12.5397	5.0265
0.065	177.0	14691	2.4695	0.4998	0.2751	0.4466	0.4467	0.8761	0.8723	8.1746	16	3	12.6005	5.291
0.0622	178.0	14774	2.4708	0.5043	0.283	0.4527	0.4529	0.8773	0.8739	8.1878	16	3	12.5926	5.8201
0.0639	179.0	14857	2.4797	0.4996	0.2745	0.4486	0.4482	0.8756	0.8726	8.164	16	3	12.5952	5.291
0.0646	180.0	14940	2.4685	0.497	0.2757	0.449	0.4486	0.8763	0.8721	8.119	16	3	12.5794	4.4974
0.0625	181.0	15023	2.4856	0.4996	0.2746	0.4486	0.4484	0.8764	0.8723	8.1481	16	3	12.5503	5.0265
0.0653	182.0	15106	2.4901	0.4987	0.2715	0.4473	0.4477	0.8756	0.8723	8.1931	16	3	12.6402	5.8201
0.065	183.0	15189	2.4897	0.5016	0.275	0.4497	0.4494	0.8766	0.8722	8.119	16	2	12.5053	5.291
0.0614	184.0	15272	2.4936	0.4984	0.2738	0.4459	0.4461	0.8758	0.8719	8.1667	16	3	12.5582	5.8201
0.0649	185.0	15355	2.4916	0.4983	0.2731	0.4435	0.4438	0.876	0.8723	8.1931	16	3	12.5926	5.8201
0.0618	186.0	15438	2.4926	0.4992	0.2742	0.4456	0.4456	0.8758	0.8719	8.1958	16	3	12.5899	6.0847
0.0624	187.0	15521	2.4986	0.499	0.2732	0.4452	0.4452	0.8758	0.8722	8.1693	16	3	12.6005	5.291
0.0641	188.0	15604	2.4982	0.5059	0.2806	0.4503	0.4508	0.877	0.8737	8.2063	16	3	12.6005	4.7619
0.0663	189.0	15687	2.4938	0.5031	0.2761	0.4483	0.4488	0.8763	0.8731	8.1614	16	3	12.5847	5.8201
0.0633	190.0	15770	2.4823	0.499	0.278	0.446	0.4457	0.8763	0.8727	8.1481	16	3	12.5608	5.0265
0.0653	191.0	15853	2.4956	0.4983	0.2744	0.4445	0.4446	0.8762	0.8722	8.1217	16	3	12.5741	5.0265
0.0657	192.0	15936	2.4920	0.5034	0.2804	0.4482	0.4476	0.8762	0.8735	8.2566	16	2	12.6693	6.0847
0.0625	193.0	16019	2.4892	0.504	0.2815	0.4499	0.4496	0.8767	0.8735	8.2381	16	2	12.6958	5.8201
0.0621	194.0	16102	2.4890	0.503	0.28	0.45	0.45	0.8765	0.8726	8.1614	16	3	12.5873	5.8201
0.063	195.0	16185	2.4954	0.5013	0.2773	0.4493	0.4487	0.8763	0.8724	8.1984	16	2	12.6323	5.8201
0.0626	196.0	16268	2.4961	0.5001	0.2769	0.4489	0.4493	0.8762	0.872	8.1746	16	2	12.5556	5.8201
0.0623	197.0	16351	2.5007	0.4954	0.271	0.4415	0.4416	0.8749	0.8708	8.2011	16	2	12.537	6.0847
0.0607	198.0	16434	2.5061	0.5023	0.2764	0.4498	0.4497	0.876	0.872	8.1852	16	2	12.5926	6.0847
0.0621	199.0	16517	2.5001	0.4951	0.2746	0.4449	0.4447	0.875	0.8712	8.172	16	2	12.5582	6.0847
0.0581	200.0	16600	2.5074	0.497	0.2725	0.4455	0.4459	0.8757	0.8719	8.2011	15	2	12.5794	5.8201
0.06	201.0	16683	2.5067	0.4948	0.2734	0.4444	0.4445	0.8749	0.8713	8.1958	16	2	12.5661	5.8201
0.0614	202.0	16766	2.5133	0.4941	0.2742	0.445	0.445	0.8752	0.8715	8.1667	16	2	12.5476	6.0847
0.0637	203.0	16849	2.5173	0.4957	0.2739	0.446	0.446	0.8756	0.8717	8.1852	15	2	12.5767	5.291
0.0592	204.0	16932	2.5142	0.4909	0.2726	0.4435	0.4434	0.875	0.871	8.1481	16	2	12.5238	5.5556
0.0594	205.0	17015	2.5157	0.4936	0.2727	0.4458	0.4453	0.8756	0.8715	8.1349	16	2	12.5317	5.5556
0.0584	206.0	17098	2.5139	0.4929	0.2724	0.4439	0.4441	0.8753	0.871	8.172	15	3	12.5688	5.8201
0.0602	207.0	17181	2.5148	0.5	0.2784	0.4503	0.4507	0.8763	0.8726	8.1746	15	3	12.5714	5.5556
0.0623	208.0	17264	2.5022	0.5021	0.2811	0.4545	0.4546	0.8773	0.8733	8.1534	15	3	12.5582	5.291
0.0599	209.0	17347	2.5013	0.4986	0.2768	0.45	0.4502	0.8763	0.8725	8.1825	16	3	12.6032	5.5556
0.0564	210.0	17430	2.5135	0.501	0.2793	0.4518	0.4523	0.8764	0.8728	8.2063	16	3	12.672	5.8201
0.0576	211.0	17513	2.5129	0.4994	0.2762	0.4501	0.4497	0.8754	0.8723	8.2063	15	3	12.6852	5.5556
0.0624	212.0	17596	2.5019	0.4988	0.2755	0.4497	0.4496	0.8753	0.8719	8.1852	15	4	12.619	5.5556
0.0549	213.0	17679	2.5068	0.4993	0.2775	0.4499	0.45	0.8758	0.8724	8.1958	16	4	12.672	6.3492
0.0599	214.0	17762	2.5078	0.4965	0.2741	0.4464	0.4463	0.8753	0.8719	8.1746	17	2	12.582	6.0847
0.0595	215.0	17845	2.5134	0.5021	0.281	0.4527	0.453	0.8766	0.8732	8.1667	16	4	12.6138	5.8201
0.0606	216.0	17928	2.5134	0.5025	0.2804	0.4548	0.4553	0.8768	0.873	8.1376	16	4	12.582	5.5556
0.0593	217.0	18011	2.5090	0.5043	0.2818	0.4547	0.4551	0.8769	0.8734	8.1614	16	4	12.582	5.8201
0.0617	218.0	18094	2.5083	0.4994	0.2755	0.449	0.4491	0.8762	0.8728	8.1852	16	3	12.582	5.8201
0.059	219.0	18177	2.5082	0.4971	0.2731	0.4467	0.4472	0.8759	0.8721	8.1296	16	2	12.5132	5.5556
0.0592	220.0	18260	2.5075	0.4973	0.2754	0.4463	0.4467	0.8761	0.8729	8.1852	16	2	12.5661	5.8201
0.0595	221.0	18343	2.5078	0.4964	0.2738	0.4462	0.4463	0.8758	0.8727	8.1746	16	2	12.537	5.8201
0.0573	222.0	18426	2.5065	0.4929	0.2705	0.4424	0.4425	0.8757	0.8716	8.1323	16	3	12.4709	5.5556
0.0541	223.0	18509	2.5154	0.4937	0.2705	0.443	0.4431	0.8755	0.8715	8.1243	16	3	12.463	5.8201
0.0589	224.0	18592	2.5163	0.4946	0.2718	0.4437	0.4438	0.8755	0.8718	8.164	16	2	12.5185	5.8201
0.0566	225.0	18675	2.5151	0.4922	0.2703	0.4418	0.4423	0.8754	0.8715	8.1508	16	2	12.5053	5.8201
0.0557	226.0	18758	2.5158	0.4926	0.2687	0.4411	0.4415	0.8752	0.8712	8.1481	16	2	12.5185	5.5556
0.053	227.0	18841	2.5210	0.4928	0.2696	0.4418	0.4425	0.8748	0.8712	8.1614	16	2	12.537	6.0847
0.0583	228.0	18924	2.5222	0.4942	0.2702	0.4446	0.4452	0.8751	0.8712	8.1508	16	3	12.5397	5.291
0.0615	229.0	19007	2.5243	0.4927	0.2697	0.4409	0.4413	0.875	0.871	8.1534	16	2	12.5344	5.291
0.0585	230.0	19090	2.5194	0.4916	0.27	0.4404	0.4407	0.875	0.8706	8.1164	16	3	12.4868	5.291
0.0563	231.0	19173	2.5186	0.4901	0.2673	0.4381	0.4389	0.8741	0.8704	8.1614	16	2	12.5794	5.5556
0.0523	232.0	19256	2.5209	0.4913	0.2681	0.4395	0.4402	0.875	0.8703	8.0979	16	2	12.463	5.291
0.0543	233.0	19339	2.5230	0.4932	0.2715	0.4428	0.444	0.8756	0.8707	8.0688	16	2	12.4471	5.291
0.0561	234.0	19422	2.5236	0.4961	0.274	0.4455	0.4459	0.8762	0.8718	8.1005	16	2	12.4868	5.291
0.0551	235.0	19505	2.5214	0.4959	0.2739	0.4456	0.4462	0.876	0.8717	8.1243	16	2	12.4921	5.291
0.0575	236.0	19588	2.5205	0.4984	0.2751	0.4478	0.4485	0.8763	0.8724	8.1349	16	2	12.5159	5.5556
0.0596	237.0	19671	2.5214	0.4957	0.2726	0.4447	0.4455	0.876	0.8716	8.119	16	2	12.4841	5.5556
0.0546	238.0	19754	2.5209	0.4948	0.2733	0.445	0.4455	0.8761	0.8717	8.0926	16	3	12.4868	5.5556
0.0577	239.0	19837	2.5189	0.4962	0.2724	0.446	0.4463	0.8762	0.8717	8.0661	16	3	12.4497	5.5556
0.0577	240.0	19920	2.5190	0.4969	0.2738	0.4465	0.4467	0.8761	0.8722	8.1349	16	3	12.5423	5.8201
0.0547	241.0	20003	2.5187	0.4961	0.2729	0.4459	0.446	0.8759	0.872	8.1217	16	3	12.5265	5.8201
0.0506	242.0	20086	2.5190	0.4965	0.2735	0.4465	0.4469	0.8761	0.8721	8.1217	16	3	12.5132	5.8201
0.0539	243.0	20169	2.5192	0.4968	0.2743	0.4466	0.4469	0.8762	0.8721	8.1164	16	3	12.4974	6.0847
0.0529	244.0	20252	2.5203	0.496	0.2734	0.4461	0.4464	0.8762	0.8718	8.0899	16	3	12.4683	5.5556
0.0567	245.0	20335	2.5208	0.4971	0.2741	0.4476	0.4472	0.8763	0.8723	8.127	16	3	12.5212	5.5556
0.0563	246.0	20418	2.5219	0.4976	0.2749	0.4476	0.4477	0.8764	0.8722	8.1243	16	3	12.5079	6.0847
0.0542	247.0	20501	2.5230	0.4997	0.2766	0.4495	0.4495	0.8766	0.8724	8.119	16	3	12.5079	5.8201
0.0537	248.0	20584	2.5234	0.5001	0.278	0.4505	0.4509	0.8768	0.8725	8.1138	16	3	12.5	5.8201
0.0573	249.0	20667	2.5236	0.4999	0.2774	0.4503	0.4506	0.8767	0.8725	8.1138	16	3	12.5	5.8201
0.0562	250.0	20750	2.5235	0.4999	0.2774	0.4503	0.4506	0.8767	0.8725	8.1138	16	3	12.5	5.8201

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3