End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- id
 license: mit
 base_model: indolem/indobert-base-uncased
 tags:

all_results.json

@@ -1,21 +1,21 @@
 {
-    "accuracy": 0.8100890207715133,
+    "accuracy": 0.8308605341246291,
     "epoch": 20.0,
-    "eval_accuracy": 0.8145363408521303,
-    "eval_f1": 0.7762775050009092,
-    "eval_loss": 0.40420523285865784,
-    "eval_precision": 0.7762775050009092,
-    "eval_recall": 0.7762775050009092,
-    "eval_runtime": 4.9659,
+    "eval_accuracy": 0.7869674185463659,
+    "eval_f1": 0.7325336550973572,
+    "eval_loss": 0.445127934217453,
+    "eval_precision": 0.7442562883739354,
+    "eval_recall": 0.7242680487361338,
+    "eval_runtime": 4.9605,
     "eval_samples": 399,
-    "eval_samples_per_second": 80.349,
-    "eval_steps_per_second": 10.069,
-    "f1": 0.7742127596218269,
-    "precision": 0.7712898624085408,
-    "recall": 0.7774645368374483,
-    "train_loss": 0.45743675075593543,
-    "train_runtime": 1951.2471,
+    "eval_samples_per_second": 80.435,
+    "eval_steps_per_second": 10.08,
+    "f1": 0.7908926081061303,
+    "precision": 0.800266779694824,
+    "recall": 0.7834017338592016,
+    "train_loss": 0.4626342241881324,
+    "train_runtime": 1944.0727,
     "train_samples": 3638,
-    "train_samples_per_second": 37.289,
-    "train_steps_per_second": 1.25
+    "train_samples_per_second": 37.427,
+    "train_steps_per_second": 1.255
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 20.0,
-    "eval_accuracy": 0.8145363408521303,
-    "eval_f1": 0.7762775050009092,
-    "eval_loss": 0.40420523285865784,
-    "eval_precision": 0.7762775050009092,
-    "eval_recall": 0.7762775050009092,
-    "eval_runtime": 4.9659,
+    "eval_accuracy": 0.7869674185463659,
+    "eval_f1": 0.7325336550973572,
+    "eval_loss": 0.445127934217453,
+    "eval_precision": 0.7442562883739354,
+    "eval_recall": 0.7242680487361338,
+    "eval_runtime": 4.9605,
     "eval_samples": 399,
-    "eval_samples_per_second": 80.349,
-    "eval_steps_per_second": 10.069
+    "eval_samples_per_second": 80.435,
+    "eval_steps_per_second": 10.08
 }

predict_results.txt

@@ -1,352 +1,352 @@
 index	prediction
-0	1
-1	0
-2	1
+0	0
+1	1
+2	0
 3	1
 4	0
-5	0
+5	1
 6	1
 7	1
-8	0
+8	1
 9	1
-10	1
+10	0
 11	1
-12	0
+12	1
 13	1
 14	1
-15	0
-16	1
+15	1
+16	0
 17	1
 18	1
-19	0
-20	1
+19	1
+20	0
 21	1
-22	0
+22	1
 23	1
 24	1
-25	1
-26	1
+25	0
+26	0
 27	1
 28	1
-29	0
+29	1
 30	1
-31	1
-32	0
-33	1
+31	0
+32	1
+33	0
 34	0
 35	1
-36	1
-37	0
+36	0
+37	1
 38	1
 39	0
 40	1
 41	0
-42	0
-43	0
-44	0
+42	1
+43	1
+44	1
 45	0
-46	0
+46	1
 47	1
 48	1
-49	0
-50	1
-51	0
-52	1
+49	1
+50	0
+51	1
+52	0
 53	1
 54	0
-55	1
+55	0
 56	1
 57	0
-58	0
-59	0
-60	1
+58	1
+59	1
+60	0
 61	1
 62	1
 63	1
 64	0
 65	1
-66	1
-67	1
+66	0
+67	0
 68	1
-69	0
+69	1
 70	1
 71	1
-72	0
+72	1
 73	1
 74	1
-75	0
-76	1
-77	0
+75	1
+76	0
+77	1
 78	1
-79	1
-80	0
-81	1
-82	1
-83	1
-84	0
-85	0
-86	0
-87	1
-88	0
+79	0
+80	1
+81	0
+82	0
+83	0
+84	1
+85	1
+86	1
+87	0
+88	1
 89	1
-90	1
+90	0
 91	0
-92	0
-93	0
-94	1
+92	1
+93	1
+94	0
 95	1
 96	1
-97	0
-98	0
-99	1
+97	1
+98	1
+99	0
 100	0
-101	0
-102	1
+101	1
+102	0
 103	1
-104	0
-105	0
+104	1
+105	1
 106	0
-107	1
+107	0
 108	1
 109	1
-110	1
+110	0
 111	1
 112	1
-113	0
+113	1
 114	1
-115	1
+115	0
 116	1
 117	1
-118	0
+118	1
 119	1
 120	1
 121	1
 122	0
 123	1
-124	1
+124	0
 125	1
-126	1
-127	1
-128	1
+126	0
+127	0
+128	0
 129	1
-130	1
-131	0
+130	0
+131	1
 132	1
 133	1
 134	1
-135	0
-136	0
-137	0
+135	1
+136	1
+137	1
 138	1
 139	1
-140	1
+140	0
 141	1
 142	1
 143	1
 144	1
-145	1
+145	0
 146	1
 147	0
-148	1
-149	1
+148	0
+149	0
 150	1
 151	1
 152	1
 153	1
 154	1
-155	0
+155	1
 156	0
 157	1
-158	0
-159	1
-160	1
+158	1
+159	0
+160	0
 161	1
 162	1
 163	1
-164	0
-165	0
-166	0
+164	1
+165	1
+166	1
 167	1
-168	0
-169	0
-170	1
-171	1
+168	1
+169	1
+170	0
+171	0
 172	1
 173	1
 174	0
 175	1
-176	0
-177	1
+176	1
+177	0
 178	1
-179	1
+179	0
 180	1
-181	1
+181	0
 182	1
 183	1
 184	1
-185	1
-186	0
-187	1
+185	0
+186	1
+187	0
 188	1
-189	1
-190	0
-191	0
+189	0
+190	1
+191	1
 192	1
 193	1
 194	1
 195	1
-196	1
+196	0
 197	1
 198	1
 199	1
-200	0
+200	1
 201	1
 202	1
 203	1
 204	1
-205	0
-206	1
-207	1
+205	1
+206	0
+207	0
 208	1
 209	1
-210	0
+210	1
 211	1
 212	1
 213	1
-214	1
-215	1
+214	0
+215	0
 216	0
-217	0
+217	1
 218	0
 219	1
 220	0
 221	1
-222	1
+222	0
 223	1
-224	1
+224	0
 225	1
-226	0
+226	1
 227	0
 228	0
-229	0
+229	1
 230	1
 231	1
-232	0
+232	1
 233	1
 234	1
-235	0
+235	1
 236	1
 237	1
 238	1
-239	1
-240	1
-241	1
+239	0
+240	0
+241	0
 242	1
 243	1
 244	1
 245	1
 246	1
 247	1
-248	1
+248	0
 249	1
 250	0
 251	1
 252	1
-253	1
+253	0
 254	1
-255	0
+255	1
 256	1
-257	0
-258	1
+257	1
+258	0
 259	1
-260	1
+260	0
 261	0
 262	1
-263	1
-264	1
-265	0
+263	0
+264	0
+265	1
 266	1
-267	1
+267	0
 268	1
-269	0
+269	1
 270	1
 271	1
-272	1
-273	1
+272	0
+273	0
 274	0
-275	1
-276	1
+275	0
+276	0
 277	1
 278	1
 279	1
 280	0
 281	1
-282	1
-283	1
-284	1
+282	0
+283	0
+284	0
 285	1
-286	1
-287	1
+286	0
+287	0
 288	1
-289	0
+289	1
 290	1
 291	1
 292	1
-293	0
-294	0
+293	1
+294	1
 295	1
 296	1
-297	1
+297	0
 298	0
 299	0
-300	0
+300	1
 301	0
-302	1
+302	0
 303	0
 304	0
-305	1
+305	0
 306	0
-307	1
+307	0
 308	0
-309	0
+309	1
 310	0
 311	0
 312	0
 313	0
-314	1
+314	0
 315	0
-316	1
+316	0
 317	0
-318	1
+318	0
 319	0
 320	0
 321	0
 322	0
 323	0
-324	0
+324	1
 325	0
-326	1
+326	0
 327	0
 328	0
-329	0
+329	1
 330	0
-331	1
-332	0
+331	0
+332	1
 333	0
-334	1
+334	0
 335	0
 336	1
 337	0
 338	1
-339	0
+339	1
 340	0
 341	0
 342	0
 343	0
-344	1
+344	0
 345	0
-346	1
-347	0
+346	0
+347	1
 348	0
 349	0
 350	0
@@ -355,52 +355,52 @@ index	prediction
 353	0
 354	0
 355	0
-356	1
+356	0
 357	0
 358	0
 359	0
-360	1
+360	0
 361	0
 362	0
-363	1
+363	0
 364	0
 365	0
-366	1
+366	0
 367	0
 368	0
 369	0
-370	1
+370	0
 371	0
 372	0
-373	0
+373	1
 374	0
 375	0
-376	1
+376	0
 377	0
 378	0
 379	0
 380	0
-381	1
+381	0
 382	0
 383	0
 384	0
-385	0
+385	1
 386	0
 387	0
 388	0
 389	0
 390	0
 391	0
-392	0
+392	1
 393	0
 394	0
 395	0
 396	0
 397	0
-398	1
+398	0
 399	0
 400	0
-401	1
+401	0
 402	0
 403	0
 404	0
@@ -417,18 +417,18 @@ index	prediction
 415	0
 416	0
 417	0
-418	1
+418	0
 419	0
 420	0
 421	0
 422	0
 423	0
 424	0
-425	1
-426	0
+425	0
+426	1
 427	0
 428	0
-429	0
+429	1
 430	0
 431	0
 432	0
@@ -438,10 +438,10 @@ index	prediction
 436	0
 437	0
 438	0
-439	1
+439	0
 440	0
 441	0
-442	0
+442	1
 443	0
 444	0
 445	0
@@ -449,24 +449,24 @@ index	prediction
 447	0
 448	0
 449	0
-450	1
+450	0
 451	0
 452	0
 453	0
 454	0
 455	1
 456	0
-457	0
+457	1
 458	0
 459	0
 460	0
 461	0
 462	0
-463	0
+463	1
 464	0
-465	0
+465	1
 466	0
-467	1
+467	0
 468	0
 469	0
 470	0
@@ -479,25 +479,25 @@ index	prediction
 477	0
 478	0
 479	0
-480	0
+480	1
 481	0
 482	0
 483	0
 484	0
 485	0
-486	1
+486	0
 487	0
 488	0
 489	0
-490	1
-491	0
+490	0
+491	1
 492	0
 493	0
 494	0
 495	0
-496	1
+496	0
 497	0
-498	0
+498	1
 499	0
 500	0
 501	0
@@ -511,9 +511,9 @@ index	prediction
 509	0
 510	0
 511	0
-512	0
+512	1
 513	0
-514	1
+514	0
 515	1
 516	0
 517	0
@@ -522,18 +522,18 @@ index	prediction
 520	0
 521	0
 522	1
-523	0
+523	1
 524	0
 525	0
 526	0
 527	0
-528	1
+528	0
 529	1
 530	0
 531	0
 532	0
 533	0
-534	1
+534	0
 535	0
 536	0
 537	0
@@ -542,13 +542,13 @@ index	prediction
 540	0
 541	0
 542	0
-543	1
+543	0
 544	0
 545	0
 546	0
 547	0
 548	0
-549	0
+549	1
 550	0
 551	0
 552	0
@@ -556,26 +556,26 @@ index	prediction
 554	0
 555	0
 556	0
-557	1
+557	0
 558	0
 559	0
 560	0
 561	0
-562	0
+562	1
 563	0
 564	0
 565	0
 566	0
-567	0
+567	1
 568	0
 569	0
 570	0
-571	0
+571	1
 572	0
 573	0
 574	0
 575	0
-576	0
+576	1
 577	0
 578	0
 579	0
@@ -587,47 +587,47 @@ index	prediction
 585	0
 586	0
 587	0
-588	0
+588	1
 589	0
 590	0
-591	0
-592	0
+591	1
+592	1
 593	0
 594	0
-595	1
-596	1
+595	0
+596	0
 597	0
 598	0
-599	0
+599	1
 600	0
 601	0
-602	0
+602	1
 603	0
 604	0
 605	0
 606	0
-607	1
+607	0
 608	0
 609	0
 610	0
 611	0
 612	0
 613	0
-614	1
+614	0
 615	0
 616	0
 617	0
 618	0
 619	0
 620	0
-621	1
+621	0
 622	0
 623	0
-624	1
+624	0
 625	0
 626	0
 627	0
-628	1
+628	0
 629	0
 630	0
 631	0
@@ -638,25 +638,25 @@ index	prediction
 636	0
 637	0
 638	0
-639	1
-640	1
+639	0
+640	0
 641	0
-642	1
-643	0
+642	0
+643	1
 644	0
 645	0
 646	0
-647	1
-648	1
+647	0
+648	0
 649	0
-650	1
-651	0
-652	1
+650	0
+651	1
+652	0
 653	0
 654	0
 655	0
 656	0
-657	1
+657	0
 658	0
 659	0
 660	0
@@ -667,14 +667,14 @@ index	prediction
 665	0
 666	0
 667	0
-668	0
+668	1
 669	0
 670	0
 671	0
 672	0
-673	0
+673	1
 674	0
-675	1
+675	0
 676	0
 677	0
 678	0
@@ -684,7 +684,7 @@ index	prediction
 682	0
 683	0
 684	0
-685	0
+685	1
 686	0
 687	0
 688	0
@@ -698,9 +698,9 @@ index	prediction
 696	0
 697	0
 698	0
-699	0
+699	1
 700	0
-701	1
+701	0
 702	0
 703	0
 704	0
@@ -711,13 +711,13 @@ index	prediction
 709	0
 710	0
 711	0
-712	0
-713	1
+712	1
+713	0
 714	0
 715	0
 716	0
 717	0
-718	0
+718	1
 719	0
 720	0
 721	0
@@ -726,22 +726,22 @@ index	prediction
 724	0
 725	0
 726	0
-727	1
-728	1
+727	0
+728	0
 729	0
 730	0
 731	0
-732	0
-733	1
-734	0
+732	1
+733	0
+734	1
 735	0
 736	0
 737	0
 738	0
 739	0
-740	1
+740	0
 741	0
-742	0
+742	1
 743	0
 744	0
 745	0
@@ -751,13 +751,13 @@ index	prediction
 749	0
 750	0
 751	0
-752	0
-753	1
+752	1
+753	0
 754	0
 755	0
 756	0
 757	0
-758	1
+758	0
 759	0
 760	0
 761	0
@@ -769,20 +769,20 @@ index	prediction
 767	0
 768	0
 769	0
-770	1
+770	0
 771	0
-772	1
+772	0
 773	0
 774	0
 775	0
-776	1
-777	1
+776	0
+777	0
 778	0
 779	0
 780	0
 781	0
 782	0
-783	0
+783	1
 784	0
 785	0
 786	0
@@ -794,13 +794,13 @@ index	prediction
 792	0
 793	0
 794	0
-795	1
+795	0
 796	0
 797	0
 798	0
 799	0
 800	0
-801	1
+801	0
 802	0
 803	0
 804	0
@@ -808,7 +808,7 @@ index	prediction
 806	0
 807	0
 808	0
-809	1
+809	0
 810	0
 811	0
 812	0
@@ -822,38 +822,38 @@ index	prediction
 820	0
 821	0
 822	0
-823	1
+823	0
 824	0
 825	0
-826	1
+826	0
 827	0
 828	0
 829	0
 830	0
 831	0
-832	1
-833	1
+832	0
+833	0
 834	0
 835	0
-836	0
+836	1
 837	0
 838	0
 839	0
 840	0
 841	1
-842	1
+842	0
 843	0
-844	0
+844	1
 845	0
-846	1
+846	0
 847	0
-848	1
-849	1
-850	0
+848	0
+849	0
+850	1
 851	0
 852	0
 853	0
-854	0
+854	1
 855	0
 856	0
 857	0
@@ -863,8 +863,8 @@ index	prediction
 861	0
 862	0
 863	0
-864	0
-865	0
+864	1
+865	1
 866	0
 867	0
 868	0
@@ -877,35 +877,35 @@ index	prediction
 875	0
 876	0
 877	0
-878	0
+878	1
 879	0
 880	0
 881	0
 882	0
 883	0
-884	1
+884	0
 885	0
 886	0
 887	0
 888	0
 889	0
 890	0
-891	1
+891	0
 892	0
-893	0
+893	1
 894	1
 895	0
 896	0
-897	0
+897	1
 898	0
 899	0
 900	0
-901	1
+901	0
 902	0
 903	0
 904	0
 905	0
-906	1
+906	0
 907	0
 908	0
 909	0
@@ -915,7 +915,7 @@ index	prediction
 913	0
 914	0
 915	0
-916	1
+916	0
 917	0
 918	0
 919	0
@@ -927,18 +927,18 @@ index	prediction
 925	0
 926	0
 927	0
-928	1
+928	0
 929	0
-930	0
+930	1
 931	0
 932	0
 933	0
 934	0
-935	0
-936	0
+935	1
+936	1
 937	0
 938	0
-939	0
+939	1
 940	0
 941	0
 942	0
@@ -947,31 +947,31 @@ index	prediction
 945	0
 946	0
 947	0
-948	0
-949	1
-950	1
+948	1
+949	0
+950	0
 951	0
 952	0
 953	0
 954	0
 955	0
-956	1
-957	1
+956	0
+957	0
 958	0
 959	0
 960	0
 961	0
-962	0
+962	1
 963	0
 964	0
 965	0
-966	1
+966	0
 967	0
 968	0
 969	0
 970	0
 971	0
-972	1
+972	0
 973	0
 974	0
 975	0
@@ -983,22 +983,22 @@ index	prediction
 981	0
 982	0
 983	0
-984	1
+984	0
 985	0
-986	1
+986	0
 987	0
 988	0
 989	0
 990	0
-991	1
-992	1
+991	0
+992	0
 993	0
 994	0
 995	1
-996	0
+996	1
 997	0
 998	0
-999	1
+999	0
 1000	0
 1001	0
 1002	0
@@ -1009,4 +1009,4 @@ index	prediction
 1007	0
 1008	0
 1009	0
-1010	1
+1010	0

runs/May20_05-06-29_indolem-petl-vm/events.out.tfevents.1716183553.indolem-petl-vm.2721960.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74626c29b311ab2f7febd8de0e13fa74e4a103a1080886bc8397ab30398e6574
+size 560

test_results.json

@@ -1,6 +1,6 @@
 {
-    "accuracy": 0.8100890207715133,
-    "f1": 0.7742127596218269,
-    "precision": 0.7712898624085408,
-    "recall": 0.7774645368374483
+    "accuracy": 0.8308605341246291,
+    "f1": 0.7908926081061303,
+    "precision": 0.800266779694824,
+    "recall": 0.7834017338592016
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.45743675075593543,
-    "train_runtime": 1951.2471,
+    "train_loss": 0.4626342241881324,
+    "train_runtime": 1944.0727,
     "train_samples": 3638,
-    "train_samples_per_second": 37.289,
-    "train_steps_per_second": 1.25
+    "train_samples_per_second": 37.427,
+    "train_steps_per_second": 1.255
 }

trainer_state.json

@@ -10,392 +10,392 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 5.584501266479492,
+      "grad_norm": 5.431522846221924,
       "learning_rate": 4.75e-05,
-      "loss": 0.5636,
+      "loss": 0.5653,
       "step": 122
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7243107769423559,
-      "eval_f1": 0.6354408930825969,
-      "eval_loss": 0.507041335105896,
-      "eval_precision": 0.6575309104533533,
-      "eval_recall": 0.6274322604109838,
-      "eval_runtime": 4.6793,
-      "eval_samples_per_second": 85.269,
-      "eval_steps_per_second": 10.685,
+      "eval_accuracy": 0.7218045112781954,
+      "eval_f1": 0.6333236742973052,
+      "eval_loss": 0.5245500802993774,
+      "eval_precision": 0.6540233301136786,
+      "eval_recall": 0.6256592107655937,
+      "eval_runtime": 4.6575,
+      "eval_samples_per_second": 85.668,
+      "eval_steps_per_second": 10.735,
       "step": 122
     },
     {
       "epoch": 2.0,
-      "grad_norm": 4.185054302215576,
+      "grad_norm": 3.8715531826019287,
       "learning_rate": 4.5e-05,
-      "loss": 0.5128,
+      "loss": 0.5167,
       "step": 244
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7343358395989975,
-      "eval_f1": 0.6976408350014298,
-      "eval_loss": 0.501506507396698,
-      "eval_precision": 0.6911057692307692,
-      "eval_recall": 0.7120385524640844,
-      "eval_runtime": 5.0462,
-      "eval_samples_per_second": 79.069,
-      "eval_steps_per_second": 9.908,
+      "eval_accuracy": 0.7293233082706767,
+      "eval_f1": 0.6854598540145985,
+      "eval_loss": 0.521543025970459,
+      "eval_precision": 0.6804511278195489,
+      "eval_recall": 0.6934897254046191,
+      "eval_runtime": 5.0566,
+      "eval_samples_per_second": 78.907,
+      "eval_steps_per_second": 9.888,
       "step": 244
     },
     {
       "epoch": 3.0,
-      "grad_norm": 4.350452423095703,
+      "grad_norm": 4.720804691314697,
       "learning_rate": 4.25e-05,
-      "loss": 0.4941,
+      "loss": 0.4984,
       "step": 366
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7468671679197995,
-      "eval_f1": 0.6969020059116857,
-      "eval_loss": 0.470926433801651,
-      "eval_precision": 0.6955197132616487,
-      "eval_recall": 0.698399709038007,
-      "eval_runtime": 5.0701,
-      "eval_samples_per_second": 78.696,
-      "eval_steps_per_second": 9.862,
+      "eval_accuracy": 0.7443609022556391,
+      "eval_f1": 0.6916257501363885,
+      "eval_loss": 0.49747392535209656,
+      "eval_precision": 0.6916257501363885,
+      "eval_recall": 0.6916257501363885,
+      "eval_runtime": 5.0553,
+      "eval_samples_per_second": 78.927,
+      "eval_steps_per_second": 9.891,
       "step": 366
     },
     {
       "epoch": 4.0,
-      "grad_norm": 3.6379525661468506,
+      "grad_norm": 3.2620692253112793,
       "learning_rate": 4e-05,
-      "loss": 0.4702,
+      "loss": 0.4765,
       "step": 488
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7744360902255639,
-      "eval_f1": 0.7207099303135889,
-      "eval_loss": 0.4496114253997803,
-      "eval_precision": 0.7274676737933683,
-      "eval_recall": 0.7154028005091835,
-      "eval_runtime": 5.0568,
-      "eval_samples_per_second": 78.904,
-      "eval_steps_per_second": 9.888,
+      "eval_accuracy": 0.7418546365914787,
+      "eval_f1": 0.6619339448031918,
+      "eval_loss": 0.4854496121406555,
+      "eval_precision": 0.6836634025138848,
+      "eval_recall": 0.6523458810692853,
+      "eval_runtime": 5.0451,
+      "eval_samples_per_second": 79.087,
+      "eval_steps_per_second": 9.911,
       "step": 488
     },
     {
       "epoch": 5.0,
-      "grad_norm": 2.561305046081543,
+      "grad_norm": 4.330729007720947,
       "learning_rate": 3.7500000000000003e-05,
-      "loss": 0.4704,
+      "loss": 0.4797,
       "step": 610
     },
     {
       "epoch": 5.0,
       "eval_accuracy": 0.7719298245614035,
       "eval_f1": 0.7320072332730561,
-      "eval_loss": 0.45210200548171997,
+      "eval_loss": 0.485201358795166,
       "eval_precision": 0.7269805119926199,
       "eval_recall": 0.7386342971449354,
-      "eval_runtime": 5.0475,
-      "eval_samples_per_second": 79.049,
-      "eval_steps_per_second": 9.906,
+      "eval_runtime": 5.0467,
+      "eval_samples_per_second": 79.062,
+      "eval_steps_per_second": 9.907,
       "step": 610
     },
     {
       "epoch": 6.0,
-      "grad_norm": 3.5164988040924072,
+      "grad_norm": 2.9019949436187744,
       "learning_rate": 3.5e-05,
-      "loss": 0.4616,
+      "loss": 0.4668,
       "step": 732
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.7644110275689223,
-      "eval_f1": 0.7212527498662227,
-      "eval_loss": 0.4490063786506653,
-      "eval_precision": 0.7175328467153285,
-      "eval_recall": 0.7258137843244226,
-      "eval_runtime": 5.059,
-      "eval_samples_per_second": 78.869,
-      "eval_steps_per_second": 9.883,
+      "eval_accuracy": 0.7669172932330827,
+      "eval_f1": 0.7195344091304183,
+      "eval_loss": 0.47377943992614746,
+      "eval_precision": 0.7189969238192895,
+      "eval_recall": 0.7200854700854701,
+      "eval_runtime": 5.0582,
+      "eval_samples_per_second": 78.882,
+      "eval_steps_per_second": 9.885,
       "step": 732
     },
     {
       "epoch": 7.0,
-      "grad_norm": 2.614987373352051,
+      "grad_norm": 14.114830017089844,
       "learning_rate": 3.2500000000000004e-05,
-      "loss": 0.4543,
+      "loss": 0.4622,
       "step": 854
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.7819548872180451,
-      "eval_f1": 0.7449392712550607,
-      "eval_loss": 0.4381465017795563,
-      "eval_precision": 0.7389190734915643,
-      "eval_recall": 0.7532278596108384,
-      "eval_runtime": 5.0493,
-      "eval_samples_per_second": 79.021,
-      "eval_steps_per_second": 9.902,
+      "eval_accuracy": 0.7719298245614035,
+      "eval_f1": 0.7295157072938161,
+      "eval_loss": 0.47686928510665894,
+      "eval_precision": 0.7260557184750733,
+      "eval_recall": 0.7336333878887071,
+      "eval_runtime": 5.045,
+      "eval_samples_per_second": 79.088,
+      "eval_steps_per_second": 9.911,
       "step": 854
     },
     {
       "epoch": 8.0,
-      "grad_norm": 4.577010631561279,
+      "grad_norm": 4.223310947418213,
       "learning_rate": 3e-05,
-      "loss": 0.4532,
+      "loss": 0.4621,
       "step": 976
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8070175438596491,
-      "eval_f1": 0.7519478107817887,
-      "eval_loss": 0.41970905661582947,
-      "eval_precision": 0.7744157656086501,
-      "eval_recall": 0.7384524458992544,
-      "eval_runtime": 5.0679,
-      "eval_samples_per_second": 78.731,
-      "eval_steps_per_second": 9.866,
+      "eval_accuracy": 0.7493734335839599,
+      "eval_f1": 0.6685826300750881,
+      "eval_loss": 0.46253928542137146,
+      "eval_precision": 0.6949044585987261,
+      "eval_recall": 0.6576650300054556,
+      "eval_runtime": 5.052,
+      "eval_samples_per_second": 78.979,
+      "eval_steps_per_second": 9.897,
       "step": 976
     },
     {
       "epoch": 9.0,
-      "grad_norm": 3.4122800827026367,
+      "grad_norm": 4.2552032470703125,
       "learning_rate": 2.7500000000000004e-05,
-      "loss": 0.4517,
+      "loss": 0.4561,
       "step": 1098
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.7969924812030075,
-      "eval_f1": 0.7544988415815261,
-      "eval_loss": 0.4194534420967102,
-      "eval_precision": 0.7551480443523821,
-      "eval_recall": 0.753864338970722,
-      "eval_runtime": 5.0418,
-      "eval_samples_per_second": 79.138,
-      "eval_steps_per_second": 9.917,
+      "eval_accuracy": 0.7769423558897243,
+      "eval_f1": 0.7199470035725271,
+      "eval_loss": 0.4609311521053314,
+      "eval_precision": 0.7310853634383045,
+      "eval_recall": 0.7121749408983451,
+      "eval_runtime": 5.0567,
+      "eval_samples_per_second": 78.905,
+      "eval_steps_per_second": 9.888,
       "step": 1098
     },
     {
       "epoch": 10.0,
-      "grad_norm": 3.07973575592041,
+      "grad_norm": 3.524580240249634,
       "learning_rate": 2.5e-05,
-      "loss": 0.4438,
+      "loss": 0.4519,
       "step": 1220
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.8170426065162907,
-      "eval_f1": 0.7539886990379824,
-      "eval_loss": 0.41020727157592773,
-      "eval_precision": 0.8012931034482759,
-      "eval_recall": 0.7330423713402436,
-      "eval_runtime": 5.0907,
-      "eval_samples_per_second": 78.378,
-      "eval_steps_per_second": 9.822,
+      "eval_accuracy": 0.7669172932330827,
+      "eval_f1": 0.6822078533807219,
+      "eval_loss": 0.4608353078365326,
+      "eval_precision": 0.7252321981424149,
+      "eval_recall": 0.6675759228950718,
+      "eval_runtime": 5.0558,
+      "eval_samples_per_second": 78.919,
+      "eval_steps_per_second": 9.89,
       "step": 1220
     },
     {
       "epoch": 11.0,
-      "grad_norm": 3.512185573577881,
+      "grad_norm": 3.3073718547821045,
       "learning_rate": 2.25e-05,
-      "loss": 0.4389,
+      "loss": 0.4413,
       "step": 1342
     },
     {
       "epoch": 11.0,
-      "eval_accuracy": 0.8270676691729323,
-      "eval_f1": 0.7875973059089472,
-      "eval_loss": 0.41120436787605286,
-      "eval_precision": 0.7933469644542308,
-      "eval_recall": 0.7826422985997454,
-      "eval_runtime": 5.0564,
-      "eval_samples_per_second": 78.909,
-      "eval_steps_per_second": 9.888,
+      "eval_accuracy": 0.7694235588972431,
+      "eval_f1": 0.7079992363497518,
+      "eval_loss": 0.4543740451335907,
+      "eval_precision": 0.7214646464646465,
+      "eval_recall": 0.6993544280778323,
+      "eval_runtime": 5.0512,
+      "eval_samples_per_second": 78.992,
+      "eval_steps_per_second": 9.899,
       "step": 1342
     },
     {
       "epoch": 12.0,
-      "grad_norm": 6.24143123626709,
+      "grad_norm": 6.039628982543945,
       "learning_rate": 2e-05,
-      "loss": 0.4428,
+      "loss": 0.4449,
       "step": 1464
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.7969924812030075,
-      "eval_f1": 0.7603603603603604,
-      "eval_loss": 0.417868971824646,
-      "eval_precision": 0.7554945054945055,
-      "eval_recall": 0.766366612111293,
-      "eval_runtime": 5.0497,
-      "eval_samples_per_second": 79.014,
-      "eval_steps_per_second": 9.901,
+      "eval_accuracy": 0.7844611528822055,
+      "eval_f1": 0.7412841546534773,
+      "eval_loss": 0.4569094777107239,
+      "eval_precision": 0.7401260504201681,
+      "eval_recall": 0.7424986361156574,
+      "eval_runtime": 5.0491,
+      "eval_samples_per_second": 79.023,
+      "eval_steps_per_second": 9.903,
       "step": 1464
     },
     {
       "epoch": 13.0,
-      "grad_norm": 1.4772980213165283,
+      "grad_norm": 1.8723957538604736,
       "learning_rate": 1.75e-05,
-      "loss": 0.4421,
+      "loss": 0.4506,
       "step": 1586
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.8320802005012531,
-      "eval_f1": 0.7828368575397437,
-      "eval_loss": 0.4030059576034546,
-      "eval_precision": 0.810950998442147,
-      "eval_recall": 0.7661847608656118,
-      "eval_runtime": 5.0599,
-      "eval_samples_per_second": 78.855,
-      "eval_steps_per_second": 9.882,
+      "eval_accuracy": 0.7644110275689223,
+      "eval_f1": 0.6821309919316564,
+      "eval_loss": 0.4527250826358795,
+      "eval_precision": 0.7196598101265823,
+      "eval_recall": 0.6683033278777959,
+      "eval_runtime": 5.0532,
+      "eval_samples_per_second": 78.959,
+      "eval_steps_per_second": 9.895,
       "step": 1586
     },
     {
       "epoch": 14.0,
-      "grad_norm": 4.054733753204346,
+      "grad_norm": 2.8429393768310547,
       "learning_rate": 1.5e-05,
-      "loss": 0.4403,
+      "loss": 0.4446,
       "step": 1708
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.8320802005012531,
-      "eval_f1": 0.7915149151881459,
-      "eval_loss": 0.4036868214607239,
-      "eval_precision": 0.801371627277996,
-      "eval_recall": 0.7836879432624113,
-      "eval_runtime": 5.0499,
-      "eval_samples_per_second": 79.012,
-      "eval_steps_per_second": 9.901,
+      "eval_accuracy": 0.7794486215538847,
+      "eval_f1": 0.7120834426659669,
+      "eval_loss": 0.4487856924533844,
+      "eval_precision": 0.7379122870605291,
+      "eval_recall": 0.69894526277505,
+      "eval_runtime": 5.0594,
+      "eval_samples_per_second": 78.864,
+      "eval_steps_per_second": 9.883,
       "step": 1708
     },
     {
       "epoch": 15.0,
-      "grad_norm": 2.8372957706451416,
+      "grad_norm": 2.688943386077881,
       "learning_rate": 1.25e-05,
-      "loss": 0.4392,
+      "loss": 0.4426,
       "step": 1830
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.8220551378446115,
-      "eval_f1": 0.7858811080458032,
-      "eval_loss": 0.4077085256576538,
-      "eval_precision": 0.7851800470474697,
-      "eval_recall": 0.7865975631933079,
-      "eval_runtime": 5.0546,
-      "eval_samples_per_second": 78.938,
-      "eval_steps_per_second": 9.892,
+      "eval_accuracy": 0.7869674185463659,
+      "eval_f1": 0.7355039968804835,
+      "eval_loss": 0.44907739758491516,
+      "eval_precision": 0.7435604353145727,
+      "eval_recall": 0.7292689579923622,
+      "eval_runtime": 5.0481,
+      "eval_samples_per_second": 79.039,
+      "eval_steps_per_second": 9.905,
       "step": 1830
     },
     {
       "epoch": 16.0,
-      "grad_norm": 3.2562994956970215,
+      "grad_norm": 2.842677593231201,
       "learning_rate": 1e-05,
-      "loss": 0.4329,
+      "loss": 0.4409,
       "step": 1952
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.8195488721804511,
-      "eval_f1": 0.7834006876168647,
-      "eval_loss": 0.40617087483406067,
-      "eval_precision": 0.7820378151260504,
-      "eval_recall": 0.7848245135479177,
-      "eval_runtime": 5.0513,
-      "eval_samples_per_second": 78.99,
-      "eval_steps_per_second": 9.898,
+      "eval_accuracy": 0.7719298245614035,
+      "eval_f1": 0.7068474127421138,
+      "eval_loss": 0.44651278853416443,
+      "eval_precision": 0.725706313219393,
+      "eval_recall": 0.696126568466994,
+      "eval_runtime": 5.0391,
+      "eval_samples_per_second": 79.18,
+      "eval_steps_per_second": 9.922,
       "step": 1952
     },
     {
       "epoch": 17.0,
-      "grad_norm": 3.811532497406006,
+      "grad_norm": 3.7264163494110107,
       "learning_rate": 7.5e-06,
-      "loss": 0.4338,
+      "loss": 0.4348,
       "step": 2074
     },
     {
       "epoch": 17.0,
-      "eval_accuracy": 0.8145363408521303,
-      "eval_f1": 0.7773840400506664,
-      "eval_loss": 0.4058062434196472,
-      "eval_precision": 0.7760504201680672,
-      "eval_recall": 0.7787779596290234,
-      "eval_runtime": 5.0681,
-      "eval_samples_per_second": 78.728,
-      "eval_steps_per_second": 9.866,
+      "eval_accuracy": 0.7869674185463659,
+      "eval_f1": 0.7355039968804835,
+      "eval_loss": 0.4473975598812103,
+      "eval_precision": 0.7435604353145727,
+      "eval_recall": 0.7292689579923622,
+      "eval_runtime": 5.0762,
+      "eval_samples_per_second": 78.602,
+      "eval_steps_per_second": 9.85,
       "step": 2074
     },
     {
       "epoch": 18.0,
-      "grad_norm": 3.1403231620788574,
+      "grad_norm": 3.3701038360595703,
       "learning_rate": 5e-06,
-      "loss": 0.4407,
+      "loss": 0.4478,
       "step": 2196
     },
     {
       "epoch": 18.0,
-      "eval_accuracy": 0.8145363408521303,
-      "eval_f1": 0.7762775050009092,
-      "eval_loss": 0.40417465567588806,
-      "eval_precision": 0.7762775050009092,
-      "eval_recall": 0.7762775050009092,
-      "eval_runtime": 5.0621,
-      "eval_samples_per_second": 78.821,
-      "eval_steps_per_second": 9.877,
+      "eval_accuracy": 0.7844611528822055,
+      "eval_f1": 0.7301509908776345,
+      "eval_loss": 0.4460136294364929,
+      "eval_precision": 0.7407832589871425,
+      "eval_recall": 0.7224949990907438,
+      "eval_runtime": 5.1002,
+      "eval_samples_per_second": 78.233,
+      "eval_steps_per_second": 9.804,
       "step": 2196
     },
     {
       "epoch": 19.0,
-      "grad_norm": 2.9727184772491455,
+      "grad_norm": 3.103198289871216,
       "learning_rate": 2.5e-06,
-      "loss": 0.4329,
+      "loss": 0.4382,
       "step": 2318
     },
     {
       "epoch": 19.0,
-      "eval_accuracy": 0.8195488721804511,
-      "eval_f1": 0.781223345924211,
-      "eval_loss": 0.4033084809780121,
-      "eval_precision": 0.7826852418860992,
-      "eval_recall": 0.7798236042916894,
-      "eval_runtime": 5.0559,
-      "eval_samples_per_second": 78.918,
-      "eval_steps_per_second": 9.889,
+      "eval_accuracy": 0.7869674185463659,
+      "eval_f1": 0.7309977236133474,
+      "eval_loss": 0.44484180212020874,
+      "eval_precision": 0.7447157190635452,
+      "eval_recall": 0.7217675941080197,
+      "eval_runtime": 5.061,
+      "eval_samples_per_second": 78.838,
+      "eval_steps_per_second": 9.879,
       "step": 2318
     },
     {
       "epoch": 20.0,
-      "grad_norm": 5.092881202697754,
+      "grad_norm": 6.061123847961426,
       "learning_rate": 0.0,
-      "loss": 0.4292,
+      "loss": 0.4313,
       "step": 2440
     },
     {
       "epoch": 20.0,
-      "eval_accuracy": 0.8145363408521303,
-      "eval_f1": 0.7762775050009092,
-      "eval_loss": 0.40420523285865784,
-      "eval_precision": 0.7762775050009092,
-      "eval_recall": 0.7762775050009092,
-      "eval_runtime": 5.0503,
-      "eval_samples_per_second": 79.006,
-      "eval_steps_per_second": 9.9,
+      "eval_accuracy": 0.7869674185463659,
+      "eval_f1": 0.7325336550973572,
+      "eval_loss": 0.445127934217453,
+      "eval_precision": 0.7442562883739354,
+      "eval_recall": 0.7242680487361338,
+      "eval_runtime": 5.049,
+      "eval_samples_per_second": 79.025,
+      "eval_steps_per_second": 9.903,
       "step": 2440
     },
     {
       "epoch": 20.0,
       "step": 2440,
       "total_flos": 7588990440528000.0,
-      "train_loss": 0.45743675075593543,
-      "train_runtime": 1951.2471,
-      "train_samples_per_second": 37.289,
-      "train_steps_per_second": 1.25
+      "train_loss": 0.4626342241881324,
+      "train_runtime": 1944.0727,
+      "train_samples_per_second": 37.427,
+      "train_steps_per_second": 1.255
     }
   ],
   "logging_steps": 500,