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": 0.8941641938674579,
+    "accuracy": 0.9023904382470119,
     "epoch": 20.0,
-    "eval_accuracy": 0.8847117794486216,
-    "eval_f1": 0.8587719298245614,
-    "eval_loss": 0.2786270081996918,
-    "eval_precision": 0.864771021021021,
-    "eval_recall": 0.8534278959810875,
-    "eval_runtime": 5.0263,
+    "eval_accuracy": 0.8771929824561403,
+    "eval_f1": 0.850729517396184,
+    "eval_loss": 0.29076284170150757,
+    "eval_precision": 0.8535087719298247,
+    "eval_recall": 0.8481087470449173,
+    "eval_runtime": 5.0376,
     "eval_samples": 399,
-    "eval_samples_per_second": 79.383,
-    "eval_steps_per_second": 9.948,
-    "f1": 0.872841399982368,
-    "precision": 0.8724798955319228,
-    "recall": 0.8732056628105085,
-    "train_loss": 0.30967485005738304,
-    "train_runtime": 1934.4038,
-    "train_samples": 3638,
-    "train_samples_per_second": 37.614,
-    "train_steps_per_second": 1.261
+    "eval_samples_per_second": 79.205,
+    "eval_steps_per_second": 9.925,
+    "f1": 0.8812035158891143,
+    "precision": 0.8844205933342424,
+    "recall": 0.8781738047331609,
+    "train_loss": 0.32445813476062213,
+    "train_runtime": 1939.7236,
+    "train_samples": 3645,
+    "train_samples_per_second": 37.583,
+    "train_steps_per_second": 1.258
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 20.0,
-    "eval_accuracy": 0.8847117794486216,
-    "eval_f1": 0.8587719298245614,
-    "eval_loss": 0.2786270081996918,
-    "eval_precision": 0.864771021021021,
-    "eval_recall": 0.8534278959810875,
-    "eval_runtime": 5.0263,
+    "eval_accuracy": 0.8771929824561403,
+    "eval_f1": 0.850729517396184,
+    "eval_loss": 0.29076284170150757,
+    "eval_precision": 0.8535087719298247,
+    "eval_recall": 0.8481087470449173,
+    "eval_runtime": 5.0376,
     "eval_samples": 399,
-    "eval_samples_per_second": 79.383,
-    "eval_steps_per_second": 9.948
+    "eval_samples_per_second": 79.205,
+    "eval_steps_per_second": 9.925
 }

predict_results.json

@@ -1,6 +1,6 @@
 {
-    "accuracy": 0.8941641938674579,
-    "f1": 0.872841399982368,
-    "precision": 0.8724798955319228,
-    "recall": 0.8732056628105085
+    "accuracy": 0.9023904382470119,
+    "f1": 0.8812035158891143,
+    "precision": 0.8844205933342424,
+    "recall": 0.8781738047331609
 }

predict_results.txt

@@ -2,60 +2,60 @@ index	prediction
 0	1
 1	1
 2	1
-3	0
+3	1
 4	1
-5	1
+5	0
 6	0
 7	1
-8	0
+8	1
 9	1
 10	1
 11	1
-12	1
-13	0
-14	0
+12	0
+13	1
+14	1
 15	1
 16	1
-17	1
+17	0
 18	1
 19	1
 20	1
-21	1
+21	0
 22	1
 23	1
 24	1
-25	0
+25	1
 26	1
 27	1
 28	1
-29	1
-30	1
-31	0
+29	0
+30	0
+31	1
 32	1
 33	1
 34	1
 35	1
 36	1
 37	1
-38	1
-39	1
+38	0
+39	0
 40	1
 41	1
-42	1
+42	0
 43	1
 44	1
 45	1
-46	0
+46	1
 47	0
-48	1
+48	0
 49	1
 50	1
-51	1
-52	0
-53	0
+51	0
+52	1
+53	1
 54	1
 55	1
-56	1
+56	0
 57	1
 58	1
 59	1
@@ -64,41 +64,41 @@ index	prediction
 62	1
 63	1
 64	1
-65	0
+65	1
 66	1
 67	1
-68	1
+68	0
 69	1
 70	1
 71	1
 72	1
 73	1
 74	1
-75	0
-76	0
+75	1
+76	1
 77	1
-78	1
-79	0
+78	0
+79	1
 80	1
-81	1
+81	0
 82	1
-83	0
+83	1
 84	1
 85	1
 86	1
 87	1
-88	0
+88	1
 89	1
-90	0
+90	1
 91	1
-92	1
+92	0
 93	1
 94	1
-95	0
+95	1
 96	1
 97	1
 98	1
-99	1
+99	0
 100	1
 101	1
 102	1
@@ -108,7 +108,7 @@ index	prediction
 106	1
 107	1
 108	1
-109	0
+109	1
 110	1
 111	1
 112	1
@@ -127,49 +127,49 @@ index	prediction
 125	1
 126	1
 127	1
-128	1
-129	0
+128	0
+129	1
 130	1
 131	1
-132	1
+132	0
 133	1
-134	1
+134	0
 135	1
 136	1
 137	1
 138	1
 139	1
-140	0
+140	1
 141	1
 142	1
-143	1
+143	0
 144	1
-145	0
+145	1
 146	1
 147	1
-148	0
+148	1
 149	1
 150	1
 151	1
 152	1
-153	1
-154	0
+153	0
+154	1
 155	1
-156	0
+156	1
 157	1
-158	0
-159	0
+158	1
+159	1
 160	1
-161	0
+161	1
 162	1
 163	1
 164	1
 165	1
-166	0
-167	0
+166	1
+167	1
 168	1
 169	0
-170	1
+170	0
 171	1
 172	1
 173	1
@@ -179,65 +179,65 @@ index	prediction
 177	1
 178	1
 179	1
-180	0
+180	1
 181	1
 182	1
 183	1
-184	1
-185	1
+184	0
+185	0
 186	1
 187	0
 188	1
-189	0
-190	0
+189	1
+190	1
 191	1
 192	1
 193	1
 194	1
 195	1
 196	1
-197	1
+197	0
 198	1
 199	1
 200	1
 201	1
 202	1
-203	1
+203	0
 204	1
 205	1
-206	0
-207	1
-208	1
+206	1
+207	0
+208	0
 209	1
 210	1
 211	1
-212	0
-213	1
-214	0
-215	0
-216	1
-217	0
+212	1
+213	0
+214	1
+215	1
+216	0
+217	1
 218	1
 219	1
 220	1
-221	1
+221	0
 222	1
 223	1
-224	1
-225	1
+224	0
+225	0
 226	1
 227	0
 228	1
 229	1
-230	0
+230	1
 231	1
 232	1
-233	0
+233	1
 234	1
 235	1
 236	1
 237	1
-238	1
+238	0
 239	1
 240	1
 241	0
@@ -245,64 +245,64 @@ index	prediction
 243	1
 244	1
 245	1
-246	1
+246	0
 247	1
 248	1
 249	1
 250	1
 251	1
-252	0
+252	1
 253	1
-254	1
+254	0
 255	1
 256	1
 257	1
 258	1
 259	1
-260	1
+260	0
 261	1
-262	1
-263	1
+262	0
+263	0
 264	1
 265	1
 266	1
 267	1
-268	1
-269	1
+268	0
+269	0
 270	1
-271	0
+271	1
 272	1
 273	1
 274	1
 275	1
 276	1
-277	1
+277	0
 278	1
-279	1
+279	0
 280	1
 281	0
-282	0
+282	1
 283	1
 284	1
 285	1
 286	1
-287	0
+287	1
 288	1
-289	0
+289	1
 290	1
-291	1
+291	0
 292	1
 293	1
-294	1
-295	1
-296	1
+294	0
+295	0
+296	0
 297	0
 298	0
 299	0
 300	0
 301	0
 302	0
-303	1
+303	0
 304	0
 305	0
 306	0
@@ -312,7 +312,7 @@ index	prediction
 310	0
 311	0
 312	1
-313	1
+313	0
 314	0
 315	0
 316	0
@@ -325,27 +325,27 @@ index	prediction
 323	0
 324	0
 325	0
-326	1
+326	0
 327	0
 328	0
 329	0
 330	0
 331	0
-332	1
+332	0
 333	0
 334	0
 335	0
 336	0
 337	0
 338	0
-339	1
+339	0
 340	0
 341	0
 342	0
 343	0
 344	0
 345	0
-346	1
+346	0
 347	0
 348	0
 349	0
@@ -359,19 +359,19 @@ index	prediction
 357	0
 358	0
 359	0
-360	0
+360	1
 361	0
 362	0
 363	0
 364	0
-365	0
+365	1
 366	0
 367	0
 368	0
 369	0
 370	0
 371	0
-372	1
+372	0
 373	0
 374	0
 375	0
@@ -383,9 +383,9 @@ index	prediction
 381	0
 382	0
 383	0
-384	1
-385	0
-386	1
+384	0
+385	1
+386	0
 387	0
 388	0
 389	0
@@ -395,8 +395,8 @@ index	prediction
 393	0
 394	0
 395	0
-396	0
-397	0
+396	1
+397	1
 398	0
 399	0
 400	0
@@ -423,23 +423,23 @@ index	prediction
 421	0
 422	0
 423	0
-424	0
+424	1
 425	0
 426	0
 427	0
 428	0
 429	0
-430	0
+430	1
 431	0
 432	0
 433	0
 434	0
-435	1
+435	0
 436	0
 437	0
 438	0
 439	0
-440	1
+440	0
 441	0
 442	0
 443	0
@@ -451,7 +451,7 @@ index	prediction
 449	0
 450	0
 451	0
-452	0
+452	1
 453	0
 454	0
 455	0
@@ -467,19 +467,19 @@ index	prediction
 465	0
 466	0
 467	0
-468	0
+468	1
 469	0
 470	0
 471	0
-472	1
+472	0
 473	0
-474	1
+474	0
 475	0
-476	1
+476	0
 477	0
 478	0
 479	0
-480	1
+480	0
 481	0
 482	0
 483	0
@@ -489,7 +489,7 @@ index	prediction
 487	0
 488	0
 489	0
-490	1
+490	0
 491	0
 492	0
 493	0
@@ -498,11 +498,11 @@ index	prediction
 496	0
 497	0
 498	0
-499	0
-500	0
+499	1
+500	1
 501	0
 502	0
-503	0
+503	1
 504	0
 505	0
 506	0
@@ -522,7 +522,7 @@ index	prediction
 520	0
 521	0
 522	0
-523	1
+523	0
 524	0
 525	0
 526	0
@@ -531,14 +531,14 @@ index	prediction
 529	0
 530	0
 531	0
-532	0
+532	1
 533	0
-534	1
+534	0
 535	0
 536	0
 537	0
 538	0
-539	1
+539	0
 540	0
 541	0
 542	0
@@ -546,7 +546,7 @@ index	prediction
 544	0
 545	0
 546	0
-547	0
+547	1
 548	0
 549	0
 550	0
@@ -564,9 +564,9 @@ index	prediction
 562	0
 563	0
 564	0
-565	1
+565	0
 566	0
-567	1
+567	0
 568	0
 569	0
 570	0
@@ -574,18 +574,18 @@ index	prediction
 572	0
 573	0
 574	0
-575	0
+575	1
 576	0
 577	0
 578	0
 579	0
 580	0
 581	0
-582	0
+582	1
 583	0
 584	0
 585	0
-586	0
+586	1
 587	0
 588	0
 589	0
@@ -596,7 +596,7 @@ index	prediction
 594	0
 595	0
 596	0
-597	1
+597	0
 598	0
 599	0
 600	0
@@ -604,13 +604,13 @@ index	prediction
 602	0
 603	0
 604	0
-605	1
+605	0
 606	0
 607	0
 608	0
 609	0
 610	0
-611	0
+611	1
 612	0
 613	0
 614	0
@@ -656,12 +656,12 @@ index	prediction
 654	0
 655	0
 656	0
-657	0
-658	0
+657	1
+658	1
 659	0
 660	0
 661	0
-662	0
+662	1
 663	0
 664	0
 665	0
@@ -672,7 +672,7 @@ index	prediction
 670	0
 671	0
 672	0
-673	1
+673	0
 674	0
 675	0
 676	0
@@ -681,18 +681,18 @@ index	prediction
 679	0
 680	0
 681	0
-682	0
+682	1
 683	0
 684	0
 685	0
 686	0
 687	0
 688	0
-689	1
+689	0
 690	0
 691	0
 692	0
-693	1
+693	0
 694	0
 695	0
 696	0
@@ -700,7 +700,7 @@ index	prediction
 698	0
 699	0
 700	0
-701	1
+701	0
 702	0
 703	0
 704	0
@@ -727,9 +727,9 @@ index	prediction
 725	0
 726	0
 727	0
-728	1
-729	0
-730	0
+728	0
+729	1
+730	1
 731	0
 732	0
 733	0
@@ -746,7 +746,7 @@ index	prediction
 744	0
 745	0
 746	0
-747	1
+747	0
 748	0
 749	0
 750	0
@@ -766,7 +766,7 @@ index	prediction
 764	0
 765	0
 766	0
-767	0
+767	1
 768	0
 769	0
 770	0
@@ -790,33 +790,33 @@ index	prediction
 788	0
 789	0
 790	0
-791	0
+791	1
 792	0
-793	0
+793	1
 794	0
 795	0
 796	0
-797	0
+797	1
 798	1
-799	1
+799	0
 800	0
 801	0
-802	1
+802	0
 803	0
 804	0
 805	0
 806	0
 807	0
 808	0
-809	1
-810	1
+809	0
+810	0
 811	0
 812	0
 813	0
 814	0
 815	0
 816	0
-817	0
+817	1
 818	0
 819	0
 820	0
@@ -825,19 +825,19 @@ index	prediction
 823	0
 824	0
 825	0
-826	1
+826	0
 827	0
 828	0
-829	0
+829	1
 830	0
-831	1
-832	1
+831	0
+832	0
 833	0
 834	0
-835	0
+835	1
 836	0
 837	0
-838	1
+838	0
 839	0
 840	0
 841	0
@@ -893,7 +893,7 @@ index	prediction
 891	0
 892	0
 893	0
-894	0
+894	1
 895	0
 896	0
 897	0
@@ -905,13 +905,13 @@ index	prediction
 903	0
 904	0
 905	0
-906	0
+906	1
 907	0
 908	0
 909	0
 910	0
 911	0
-912	1
+912	0
 913	0
 914	0
 915	0
@@ -920,15 +920,15 @@ index	prediction
 918	0
 919	0
 920	0
-921	1
-922	0
+921	0
+922	1
 923	0
-924	1
+924	0
 925	0
-926	1
-927	1
+926	0
+927	0
 928	0
-929	1
+929	0
 930	0
 931	0
 932	0
@@ -938,13 +938,13 @@ index	prediction
 936	0
 937	0
 938	0
-939	0
+939	1
 940	0
-941	1
+941	0
 942	0
 943	0
 944	0
-945	1
+945	0
 946	0
 947	0
 948	0
@@ -956,11 +956,11 @@ index	prediction
 954	0
 955	0
 956	0
-957	0
+957	1
 958	0
 959	0
 960	0
-961	1
+961	0
 962	0
 963	0
 964	0
@@ -973,12 +973,12 @@ index	prediction
 971	0
 972	0
 973	0
-974	1
+974	0
 975	0
 976	0
-977	1
+977	0
 978	0
-979	0
+979	1
 980	0
 981	0
 982	0
@@ -988,25 +988,18 @@ index	prediction
 986	0
 987	0
 988	0
-989	0
+989	1
 990	0
 991	0
-992	0
+992	1
 993	0
 994	0
 995	0
 996	0
 997	0
 998	0
-999	1
+999	0
 1000	0
-1001	0
+1001	1
 1002	0
-1003	0
-1004	0
-1005	0
-1006	0
-1007	0
-1008	0
-1009	1
-1010	0
+1003	1

runs/May27_00-11-16_indolem-petl-vm/events.out.tfevents.1716770635.indolem-petl-vm.3191687.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c7640c7371cf49078cfb32411c7e83a09df491ca05ec168b44f41968494294
+size 560

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.30967485005738304,
-    "train_runtime": 1934.4038,
-    "train_samples": 3638,
-    "train_samples_per_second": 37.614,
-    "train_steps_per_second": 1.261
+    "train_loss": 0.32445813476062213,
+    "train_runtime": 1939.7236,
+    "train_samples": 3645,
+    "train_samples_per_second": 37.583,
+    "train_steps_per_second": 1.258
 }

trainer_state.json

@@ -10,392 +10,392 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 5.93964147567749,
+      "grad_norm": 3.6051695346832275,
       "learning_rate": 4.75e-05,
-      "loss": 0.5623,
+      "loss": 0.556,
       "step": 122
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7268170426065163,
-      "eval_f1": 0.6301313943104988,
-      "eval_loss": 0.5216777324676514,
-      "eval_precision": 0.6603762281332375,
-      "eval_recall": 0.6217039461720313,
-      "eval_runtime": 5.0877,
-      "eval_samples_per_second": 78.424,
-      "eval_steps_per_second": 9.828,
+      "eval_accuracy": 0.7167919799498746,
+      "eval_f1": 0.6641239002659476,
+      "eval_loss": 0.5324748158454895,
+      "eval_precision": 0.6617008797653958,
+      "eval_recall": 0.6671212947808693,
+      "eval_runtime": 5.0818,
+      "eval_samples_per_second": 78.516,
+      "eval_steps_per_second": 9.839,
       "step": 122
     },
     {
       "epoch": 2.0,
-      "grad_norm": 3.8485560417175293,
+      "grad_norm": 3.362328290939331,
       "learning_rate": 4.5e-05,
-      "loss": 0.5061,
+      "loss": 0.5103,
       "step": 244
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7568922305764411,
-      "eval_f1": 0.7089058868656783,
-      "eval_loss": 0.48978015780448914,
-      "eval_precision": 0.7074372759856631,
-      "eval_recall": 0.7104928168757956,
-      "eval_runtime": 5.0629,
-      "eval_samples_per_second": 78.809,
-      "eval_steps_per_second": 9.876,
+      "eval_accuracy": 0.7719298245614035,
+      "eval_f1": 0.6523624874335775,
+      "eval_loss": 0.4822019934654236,
+      "eval_precision": 0.7714565527065527,
+      "eval_recall": 0.6386161120203673,
+      "eval_runtime": 5.0545,
+      "eval_samples_per_second": 78.94,
+      "eval_steps_per_second": 9.892,
       "step": 244
     },
     {
       "epoch": 3.0,
-      "grad_norm": 5.005080699920654,
+      "grad_norm": 4.656192779541016,
       "learning_rate": 4.25e-05,
-      "loss": 0.4443,
+      "loss": 0.4637,
       "step": 366
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8120300751879699,
-      "eval_f1": 0.7678883071553229,
-      "eval_loss": 0.40850991010665894,
-      "eval_precision": 0.7750572737686139,
-      "eval_recall": 0.7620021822149482,
-      "eval_runtime": 5.144,
-      "eval_samples_per_second": 77.566,
-      "eval_steps_per_second": 9.72,
+      "eval_accuracy": 0.8045112781954887,
+      "eval_f1": 0.7479591836734694,
+      "eval_loss": 0.42453086376190186,
+      "eval_precision": 0.771505376344086,
+      "eval_recall": 0.7341789416257501,
+      "eval_runtime": 5.075,
+      "eval_samples_per_second": 78.62,
+      "eval_steps_per_second": 9.852,
       "step": 366
     },
     {
       "epoch": 4.0,
-      "grad_norm": 2.8029582500457764,
+      "grad_norm": 1.4060696363449097,
       "learning_rate": 4e-05,
-      "loss": 0.3805,
+      "loss": 0.4173,
       "step": 488
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.8245614035087719,
-      "eval_f1": 0.7751786979200206,
-      "eval_loss": 0.3672122061252594,
-      "eval_precision": 0.7980263157894737,
-      "eval_recall": 0.7608656119294417,
-      "eval_runtime": 5.0838,
-      "eval_samples_per_second": 78.485,
-      "eval_steps_per_second": 9.835,
+      "eval_f1": 0.7873004752040941,
+      "eval_loss": 0.38980478048324585,
+      "eval_precision": 0.7887936313533375,
+      "eval_recall": 0.7858701582105838,
+      "eval_runtime": 5.064,
+      "eval_samples_per_second": 78.791,
+      "eval_steps_per_second": 9.874,
       "step": 488
     },
     {
       "epoch": 5.0,
-      "grad_norm": 3.751908540725708,
+      "grad_norm": 3.650151491165161,
       "learning_rate": 3.7500000000000003e-05,
-      "loss": 0.3488,
+      "loss": 0.3674,
       "step": 610
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8521303258145363,
-      "eval_f1": 0.8229427559286084,
-      "eval_loss": 0.35348454117774963,
-      "eval_precision": 0.8206541218637993,
-      "eval_recall": 0.8253773413347881,
-      "eval_runtime": 5.0536,
-      "eval_samples_per_second": 78.953,
-      "eval_steps_per_second": 9.894,
+      "eval_accuracy": 0.8370927318295739,
+      "eval_f1": 0.7999105055663995,
+      "eval_loss": 0.3571353554725647,
+      "eval_precision": 0.8058980811575966,
+      "eval_recall": 0.794735406437534,
+      "eval_runtime": 5.0507,
+      "eval_samples_per_second": 78.999,
+      "eval_steps_per_second": 9.9,
       "step": 610
     },
     {
       "epoch": 6.0,
-      "grad_norm": 4.316796779632568,
+      "grad_norm": 2.5915608406066895,
       "learning_rate": 3.5e-05,
-      "loss": 0.3156,
+      "loss": 0.3484,
       "step": 732
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8571428571428571,
-      "eval_f1": 0.8254579780661698,
-      "eval_loss": 0.33368828892707825,
-      "eval_precision": 0.8299216027874565,
-      "eval_recall": 0.8214220767412257,
-      "eval_runtime": 5.0533,
-      "eval_samples_per_second": 78.959,
-      "eval_steps_per_second": 9.895,
+      "eval_accuracy": 0.8370927318295739,
+      "eval_f1": 0.8029928975654221,
+      "eval_loss": 0.3431943356990814,
+      "eval_precision": 0.8037650785914463,
+      "eval_recall": 0.8022367703218767,
+      "eval_runtime": 5.135,
+      "eval_samples_per_second": 77.703,
+      "eval_steps_per_second": 9.737,
       "step": 732
     },
     {
       "epoch": 7.0,
-      "grad_norm": 18.979951858520508,
+      "grad_norm": 0.9446077346801758,
       "learning_rate": 3.2500000000000004e-05,
-      "loss": 0.3055,
+      "loss": 0.3247,
       "step": 854
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.8621553884711779,
-      "eval_f1": 0.8297847585805701,
-      "eval_loss": 0.3217175304889679,
-      "eval_precision": 0.8385357006491028,
-      "eval_recall": 0.8224677214038916,
-      "eval_runtime": 5.0744,
-      "eval_samples_per_second": 78.63,
-      "eval_steps_per_second": 9.853,
+      "eval_accuracy": 0.8521303258145363,
+      "eval_f1": 0.816408656658218,
+      "eval_loss": 0.3298611342906952,
+      "eval_precision": 0.8270654903728508,
+      "eval_recall": 0.8078741589379888,
+      "eval_runtime": 5.0753,
+      "eval_samples_per_second": 78.617,
+      "eval_steps_per_second": 9.852,
       "step": 854
     },
     {
       "epoch": 8.0,
-      "grad_norm": 5.143575191497803,
+      "grad_norm": 9.143532752990723,
       "learning_rate": 3e-05,
-      "loss": 0.2995,
+      "loss": 0.3102,
       "step": 976
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8596491228070176,
-      "eval_f1": 0.8271551457392166,
-      "eval_loss": 0.31452828645706177,
-      "eval_precision": 0.8347358430876305,
-      "eval_recall": 0.8206946717585015,
-      "eval_runtime": 5.0883,
-      "eval_samples_per_second": 78.414,
-      "eval_steps_per_second": 9.826,
+      "eval_accuracy": 0.8621553884711779,
+      "eval_f1": 0.8228198648441347,
+      "eval_loss": 0.3259894549846649,
+      "eval_precision": 0.8509591907917684,
+      "eval_recall": 0.8049645390070922,
+      "eval_runtime": 5.087,
+      "eval_samples_per_second": 78.435,
+      "eval_steps_per_second": 9.829,
       "step": 976
     },
     {
       "epoch": 9.0,
-      "grad_norm": 6.147844314575195,
+      "grad_norm": 4.818455696105957,
       "learning_rate": 2.7500000000000004e-05,
-      "loss": 0.2825,
+      "loss": 0.2991,
       "step": 1098
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.8671679197994987,
-      "eval_f1": 0.8393634395533442,
-      "eval_loss": 0.3090471923351288,
-      "eval_precision": 0.8402278542707444,
-      "eval_recall": 0.8385160938352427,
-      "eval_runtime": 5.0782,
-      "eval_samples_per_second": 78.572,
-      "eval_steps_per_second": 9.846,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_f1": 0.821647309770462,
+      "eval_loss": 0.31378358602523804,
+      "eval_precision": 0.8349087353324641,
+      "eval_recall": 0.8114202582287688,
+      "eval_runtime": 5.0565,
+      "eval_samples_per_second": 78.909,
+      "eval_steps_per_second": 9.888,
       "step": 1098
     },
     {
       "epoch": 10.0,
-      "grad_norm": 5.50480842590332,
+      "grad_norm": 3.8728206157684326,
       "learning_rate": 2.5e-05,
-      "loss": 0.272,
+      "loss": 0.29,
       "step": 1220
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.8721804511278195,
-      "eval_f1": 0.8461962888779714,
-      "eval_loss": 0.29923897981643677,
-      "eval_precision": 0.8453465227094517,
-      "eval_recall": 0.8470631023822512,
-      "eval_runtime": 5.0745,
-      "eval_samples_per_second": 78.629,
-      "eval_steps_per_second": 9.853,
+      "eval_accuracy": 0.8546365914786967,
+      "eval_f1": 0.8180088078011953,
+      "eval_loss": 0.31225934624671936,
+      "eval_precision": 0.8323930726843348,
+      "eval_recall": 0.8071467539552646,
+      "eval_runtime": 5.0562,
+      "eval_samples_per_second": 78.913,
+      "eval_steps_per_second": 9.889,
       "step": 1220
     },
     {
       "epoch": 11.0,
-      "grad_norm": 6.085771083831787,
+      "grad_norm": 2.6045541763305664,
       "learning_rate": 2.25e-05,
-      "loss": 0.2626,
+      "loss": 0.2778,
       "step": 1342
     },
     {
       "epoch": 11.0,
-      "eval_accuracy": 0.87468671679198,
-      "eval_f1": 0.8439846096096095,
-      "eval_loss": 0.30075788497924805,
-      "eval_precision": 0.8568027210884354,
-      "eval_recall": 0.8338334242589562,
-      "eval_runtime": 5.0607,
-      "eval_samples_per_second": 78.843,
-      "eval_steps_per_second": 9.88,
+      "eval_accuracy": 0.8671679197994987,
+      "eval_f1": 0.8377065410088949,
+      "eval_loss": 0.30650559067726135,
+      "eval_precision": 0.8423344947735192,
+      "eval_recall": 0.8335151845790143,
+      "eval_runtime": 5.0839,
+      "eval_samples_per_second": 78.483,
+      "eval_steps_per_second": 9.835,
       "step": 1342
     },
     {
       "epoch": 12.0,
-      "grad_norm": 10.957924842834473,
+      "grad_norm": 1.5327140092849731,
       "learning_rate": 2e-05,
-      "loss": 0.2641,
+      "loss": 0.2702,
       "step": 1464
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.87468671679198,
-      "eval_f1": 0.8488361520276414,
-      "eval_loss": 0.2949255406856537,
-      "eval_precision": 0.8488361520276414,
-      "eval_recall": 0.8488361520276414,
-      "eval_runtime": 5.0742,
-      "eval_samples_per_second": 78.634,
-      "eval_steps_per_second": 9.854,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_f1": 0.821647309770462,
+      "eval_loss": 0.3005804717540741,
+      "eval_precision": 0.8349087353324641,
+      "eval_recall": 0.8114202582287688,
+      "eval_runtime": 5.0646,
+      "eval_samples_per_second": 78.782,
+      "eval_steps_per_second": 9.872,
       "step": 1464
     },
     {
       "epoch": 13.0,
-      "grad_norm": 3.114020347595215,
+      "grad_norm": 5.446022987365723,
       "learning_rate": 1.75e-05,
-      "loss": 0.257,
+      "loss": 0.2664,
       "step": 1586
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.8771929824561403,
-      "eval_f1": 0.8475258334958082,
-      "eval_loss": 0.28850188851356506,
-      "eval_precision": 0.8591828192414193,
-      "eval_recall": 0.8381069285324605,
-      "eval_runtime": 5.0549,
-      "eval_samples_per_second": 78.934,
-      "eval_steps_per_second": 9.891,
+      "eval_accuracy": 0.8596491228070176,
+      "eval_f1": 0.8298403801632752,
+      "eval_loss": 0.29961732029914856,
+      "eval_precision": 0.8315523576240049,
+      "eval_recall": 0.8281960356428442,
+      "eval_runtime": 5.0899,
+      "eval_samples_per_second": 78.39,
+      "eval_steps_per_second": 9.823,
       "step": 1586
     },
     {
       "epoch": 14.0,
-      "grad_norm": 4.347434043884277,
+      "grad_norm": 2.8527348041534424,
       "learning_rate": 1.5e-05,
-      "loss": 0.2473,
+      "loss": 0.264,
       "step": 1708
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.8822055137844611,
-      "eval_f1": 0.8568221901555235,
-      "eval_loss": 0.2826312482357025,
-      "eval_precision": 0.8596491228070176,
-      "eval_recall": 0.8541553009638116,
-      "eval_runtime": 5.0506,
-      "eval_samples_per_second": 79.001,
-      "eval_steps_per_second": 9.9,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8476882658063937,
+      "eval_loss": 0.2987360656261444,
+      "eval_precision": 0.8437296561519796,
+      "eval_recall": 0.8520640116384797,
+      "eval_runtime": 5.0668,
+      "eval_samples_per_second": 78.748,
+      "eval_steps_per_second": 9.868,
       "step": 1708
     },
     {
       "epoch": 15.0,
-      "grad_norm": 1.6674721240997314,
+      "grad_norm": 2.7352912425994873,
       "learning_rate": 1.25e-05,
-      "loss": 0.2456,
+      "loss": 0.254,
       "step": 1830
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.8847117794486216,
-      "eval_f1": 0.8609292598654301,
-      "eval_loss": 0.2825632393360138,
-      "eval_precision": 0.8609292598654301,
-      "eval_recall": 0.8609292598654301,
-      "eval_runtime": 5.071,
-      "eval_samples_per_second": 78.683,
-      "eval_steps_per_second": 9.86,
+      "eval_accuracy": 0.8771929824561403,
+      "eval_f1": 0.8522278069611882,
+      "eval_loss": 0.2951277792453766,
+      "eval_precision": 0.8513631702756499,
+      "eval_recall": 0.8531096563011457,
+      "eval_runtime": 5.222,
+      "eval_samples_per_second": 76.408,
+      "eval_steps_per_second": 9.575,
       "step": 1830
     },
     {
       "epoch": 16.0,
-      "grad_norm": 5.605799674987793,
+      "grad_norm": 2.442108154296875,
       "learning_rate": 1e-05,
-      "loss": 0.2477,
+      "loss": 0.2571,
       "step": 1952
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.8847117794486216,
-      "eval_f1": 0.8602260265626904,
-      "eval_loss": 0.2795054018497467,
-      "eval_precision": 0.8620943049601959,
-      "eval_recall": 0.8584288052373159,
-      "eval_runtime": 5.063,
-      "eval_samples_per_second": 78.807,
-      "eval_steps_per_second": 9.876,
+      "eval_accuracy": 0.8671679197994987,
+      "eval_f1": 0.8350789627607721,
+      "eval_loss": 0.2944652736186981,
+      "eval_precision": 0.8463358876939919,
+      "eval_recall": 0.8260138206946717,
+      "eval_runtime": 5.0611,
+      "eval_samples_per_second": 78.837,
+      "eval_steps_per_second": 9.879,
       "step": 1952
     },
     {
       "epoch": 17.0,
-      "grad_norm": 1.4996304512023926,
+      "grad_norm": 3.852628231048584,
       "learning_rate": 7.5e-06,
-      "loss": 0.2426,
+      "loss": 0.2511,
       "step": 2074
     },
     {
       "epoch": 17.0,
-      "eval_accuracy": 0.8796992481203008,
-      "eval_f1": 0.8526315789473684,
-      "eval_loss": 0.2793760895729065,
-      "eval_precision": 0.8585304054054055,
-      "eval_recall": 0.8473813420621932,
-      "eval_runtime": 5.0574,
-      "eval_samples_per_second": 78.894,
-      "eval_steps_per_second": 9.886,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8454251965513313,
+      "eval_loss": 0.2917979061603546,
+      "eval_precision": 0.8463049835506276,
+      "eval_recall": 0.8445626477541371,
+      "eval_runtime": 5.0682,
+      "eval_samples_per_second": 78.727,
+      "eval_steps_per_second": 9.866,
       "step": 2074
     },
     {
       "epoch": 18.0,
-      "grad_norm": 3.353811264038086,
+      "grad_norm": 5.464624881744385,
       "learning_rate": 5e-06,
-      "loss": 0.2359,
+      "loss": 0.2574,
       "step": 2196
     },
     {
       "epoch": 18.0,
-      "eval_accuracy": 0.8872180451127819,
-      "eval_f1": 0.8629148629148629,
-      "eval_loss": 0.27959930896759033,
-      "eval_precision": 0.8657894736842104,
-      "eval_recall": 0.860201854882706,
-      "eval_runtime": 5.0719,
-      "eval_samples_per_second": 78.668,
-      "eval_steps_per_second": 9.858,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8472902633190447,
+      "eval_loss": 0.29094478487968445,
+      "eval_precision": 0.8510272912927781,
+      "eval_recall": 0.8438352427714131,
+      "eval_runtime": 5.1003,
+      "eval_samples_per_second": 78.231,
+      "eval_steps_per_second": 9.803,
       "step": 2196
     },
     {
       "epoch": 19.0,
-      "grad_norm": 6.069816589355469,
+      "grad_norm": 2.1257989406585693,
       "learning_rate": 2.5e-06,
-      "loss": 0.2417,
+      "loss": 0.2508,
       "step": 2318
     },
     {
       "epoch": 19.0,
-      "eval_accuracy": 0.8847117794486216,
-      "eval_f1": 0.8587719298245614,
-      "eval_loss": 0.27870801091194153,
-      "eval_precision": 0.864771021021021,
-      "eval_recall": 0.8534278959810875,
-      "eval_runtime": 5.0523,
-      "eval_samples_per_second": 78.973,
-      "eval_steps_per_second": 9.896,
+      "eval_accuracy": 0.8771929824561403,
+      "eval_f1": 0.850729517396184,
+      "eval_loss": 0.29074448347091675,
+      "eval_precision": 0.8535087719298247,
+      "eval_recall": 0.8481087470449173,
+      "eval_runtime": 5.1136,
+      "eval_samples_per_second": 78.027,
+      "eval_steps_per_second": 9.778,
       "step": 2318
     },
     {
       "epoch": 20.0,
-      "grad_norm": 4.868233680725098,
+      "grad_norm": 3.8716917037963867,
       "learning_rate": 0.0,
-      "loss": 0.2319,
+      "loss": 0.2536,
       "step": 2440
     },
     {
       "epoch": 20.0,
-      "eval_accuracy": 0.8847117794486216,
-      "eval_f1": 0.8587719298245614,
-      "eval_loss": 0.2786270081996918,
-      "eval_precision": 0.864771021021021,
-      "eval_recall": 0.8534278959810875,
-      "eval_runtime": 5.0608,
-      "eval_samples_per_second": 78.841,
-      "eval_steps_per_second": 9.88,
+      "eval_accuracy": 0.8771929824561403,
+      "eval_f1": 0.850729517396184,
+      "eval_loss": 0.29076284170150757,
+      "eval_precision": 0.8535087719298247,
+      "eval_recall": 0.8481087470449173,
+      "eval_runtime": 5.0627,
+      "eval_samples_per_second": 78.811,
+      "eval_steps_per_second": 9.876,
       "step": 2440
     },
     {
       "epoch": 20.0,
       "step": 2440,
-      "total_flos": 7609911792720000.0,
-      "train_loss": 0.30967485005738304,
-      "train_runtime": 1934.4038,
-      "train_samples_per_second": 37.614,
-      "train_steps_per_second": 1.261
+      "total_flos": 7624554283800000.0,
+      "train_loss": 0.32445813476062213,
+      "train_runtime": 1939.7236,
+      "train_samples_per_second": 37.583,
+      "train_steps_per_second": 1.258
     }
   ],
   "logging_steps": 500,
@@ -403,7 +403,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 7609911792720000.0,
+  "total_flos": 7624554283800000.0,
   "train_batch_size": 30,
   "trial_name": null,
   "trial_params": null