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": 0.8615232443125618,
+    "accuracy": 0.9109792284866469,
     "epoch": 20.0,
-    "eval_accuracy": 0.8546365914786967,
-    "eval_f1": 0.8263655462184873,
-    "eval_loss": 0.35401326417922974,
-    "eval_precision": 0.8233396753671443,
-    "eval_recall": 0.8296508456082925,
-    "eval_runtime": 5.0488,
+    "eval_accuracy": 0.9022556390977443,
+    "eval_f1": 0.8817957385392532,
+    "eval_loss": 0.8104944229125977,
+    "eval_precision": 0.8827677592299257,
+    "eval_recall": 0.8808419712675032,
+    "eval_runtime": 4.7231,
     "eval_samples": 399,
-    "eval_samples_per_second": 79.029,
-    "eval_steps_per_second": 9.903,
-    "f1": 0.8344251555846709,
-    "precision": 0.8325509007667684,
-    "recall": 0.8363917467548971,
-    "train_loss": 0.35800845193081215,
-    "train_runtime": 2113.1391,
+    "eval_samples_per_second": 84.478,
+    "eval_steps_per_second": 10.586,
+    "f1": 0.8920886346170267,
+    "precision": 0.8953297623033144,
+    "recall": 0.8890334817436486,
+    "train_loss": 0.05662053943168922,
+    "train_runtime": 2712.8409,
     "train_samples": 3638,
-    "train_samples_per_second": 34.432,
-    "train_steps_per_second": 1.155
+    "train_samples_per_second": 26.821,
+    "train_steps_per_second": 0.899
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 20.0,
-    "eval_accuracy": 0.8546365914786967,
-    "eval_f1": 0.8263655462184873,
-    "eval_loss": 0.35401326417922974,
-    "eval_precision": 0.8233396753671443,
-    "eval_recall": 0.8296508456082925,
-    "eval_runtime": 5.0488,
+    "eval_accuracy": 0.9022556390977443,
+    "eval_f1": 0.8817957385392532,
+    "eval_loss": 0.8104944229125977,
+    "eval_precision": 0.8827677592299257,
+    "eval_recall": 0.8808419712675032,
+    "eval_runtime": 4.7231,
     "eval_samples": 399,
-    "eval_samples_per_second": 79.029,
-    "eval_steps_per_second": 9.903
+    "eval_samples_per_second": 84.478,
+    "eval_steps_per_second": 10.586
 }

predict_results.txt

@@ -1,6 +1,6 @@
 index	prediction
 0	1
-1	0
+1	1
 2	1
 3	1
 4	0
@@ -8,62 +8,62 @@ index	prediction
 6	1
 7	1
 8	0
-9	1
+9	0
 10	1
 11	1
 12	1
 13	1
 14	1
-15	1
+15	0
 16	1
 17	1
 18	1
 19	1
 20	1
 21	1
-22	0
+22	1
 23	1
-24	1
-25	1
+24	0
+25	0
 26	1
 27	1
 28	1
-29	0
+29	1
 30	1
 31	1
 32	1
 33	1
-34	0
+34	1
 35	1
 36	1
 37	1
 38	1
 39	0
 40	1
-41	0
-42	0
-43	0
-44	0
+41	1
+42	1
+43	1
+44	1
 45	0
 46	1
 47	1
 48	1
 49	0
-50	1
+50	0
 51	1
 52	0
 53	1
 54	1
 55	1
-56	0
+56	1
 57	0
-58	1
-59	1
-60	0
+58	0
+59	0
+60	1
 61	1
 62	1
 63	1
-64	0
+64	1
 65	1
 66	1
 67	1
@@ -79,31 +79,31 @@ index	prediction
 77	0
 78	1
 79	1
-80	0
+80	1
 81	1
 82	1
 83	1
 84	1
 85	0
-86	0
+86	1
 87	1
 88	1
 89	1
 90	1
-91	0
+91	1
 92	0
-93	0
+93	1
 94	1
 95	1
 96	1
 97	0
-98	0
-99	0
-100	0
+98	1
+99	1
+100	1
 101	0
 102	1
 103	1
-104	0
+104	1
 105	1
 106	1
 107	1
@@ -112,12 +112,12 @@ index	prediction
 110	1
 111	1
 112	1
-113	1
+113	0
 114	1
 115	1
 116	1
 117	1
-118	1
+118	0
 119	1
 120	1
 121	1
@@ -133,23 +133,23 @@ index	prediction
 131	0
 132	1
 133	1
-134	1
-135	0
+134	0
+135	1
 136	0
 137	1
 138	1
 139	1
 140	1
 141	1
-142	1
+142	0
 143	1
 144	1
 145	1
 146	1
-147	0
+147	1
 148	1
 149	1
-150	1
+150	0
 151	1
 152	1
 153	1
@@ -163,24 +163,24 @@ index	prediction
 161	1
 162	1
 163	1
-164	0
+164	1
 165	0
 166	1
 167	1
-168	0
-169	0
+168	1
+169	1
 170	1
 171	1
 172	0
 173	0
-174	0
+174	1
 175	1
-176	0
+176	1
 177	0
 178	1
 179	1
 180	1
-181	1
+181	0
 182	1
 183	1
 184	1
@@ -189,7 +189,7 @@ index	prediction
 187	1
 188	1
 189	1
-190	0
+190	1
 191	1
 192	1
 193	1
@@ -206,7 +206,7 @@ index	prediction
 204	1
 205	0
 206	1
-207	1
+207	0
 208	1
 209	1
 210	1
@@ -217,22 +217,22 @@ index	prediction
 215	1
 216	0
 217	0
-218	0
+218	1
 219	1
 220	0
 221	1
 222	1
 223	1
-224	1
+224	0
 225	1
 226	0
 227	0
-228	0
-229	0
+228	1
+229	1
 230	1
 231	1
-232	0
-233	0
+232	1
+233	1
 234	1
 235	1
 236	1
@@ -260,7 +260,7 @@ index	prediction
 258	1
 259	1
 260	1
-261	0
+261	1
 262	1
 263	1
 264	1
@@ -292,16 +292,16 @@ index	prediction
 290	1
 291	1
 292	1
-293	0
+293	1
 294	1
 295	1
 296	1
-297	1
+297	0
 298	0
 299	0
 300	0
 301	0
-302	1
+302	0
 303	0
 304	0
 305	1
@@ -313,9 +313,9 @@ index	prediction
 311	0
 312	0
 313	0
-314	1
+314	0
 315	0
-316	1
+316	0
 317	0
 318	1
 319	0
@@ -327,7 +327,7 @@ index	prediction
 325	0
 326	0
 327	0
-328	0
+328	1
 329	0
 330	0
 331	0
@@ -343,14 +343,14 @@ index	prediction
 341	0
 342	0
 343	0
-344	1
+344	0
 345	0
-346	0
+346	1
 347	0
 348	0
 349	0
 350	0
-351	1
+351	0
 352	0
 353	0
 354	0
@@ -363,9 +363,9 @@ index	prediction
 361	0
 362	0
 363	0
-364	1
+364	0
 365	0
-366	1
+366	0
 367	0
 368	0
 369	0
@@ -375,7 +375,7 @@ index	prediction
 373	0
 374	0
 375	0
-376	1
+376	0
 377	0
 378	0
 379	0
@@ -391,16 +391,16 @@ index	prediction
 389	0
 390	0
 391	0
-392	0
+392	1
 393	0
 394	0
 395	0
 396	0
 397	0
-398	0
+398	1
 399	0
 400	0
-401	1
+401	0
 402	0
 403	0
 404	0
@@ -419,12 +419,12 @@ index	prediction
 417	0
 418	0
 419	0
-420	0
+420	1
 421	1
 422	0
 423	0
 424	0
-425	1
+425	0
 426	0
 427	0
 428	0
@@ -438,7 +438,7 @@ index	prediction
 436	0
 437	0
 438	0
-439	1
+439	0
 440	0
 441	0
 442	0
@@ -446,17 +446,17 @@ index	prediction
 444	0
 445	0
 446	0
-447	0
+447	1
 448	0
 449	0
 450	0
 451	0
-452	0
+452	1
 453	0
 454	0
-455	1
+455	0
 456	0
-457	0
+457	1
 458	0
 459	0
 460	0
@@ -465,12 +465,12 @@ index	prediction
 463	0
 464	0
 465	0
-466	1
+466	0
 467	0
 468	0
 469	0
 470	0
-471	0
+471	1
 472	0
 473	0
 474	0
@@ -486,12 +486,12 @@ index	prediction
 484	0
 485	0
 486	0
-487	1
+487	0
 488	0
 489	0
 490	0
 491	0
-492	1
+492	0
 493	0
 494	0
 495	0
@@ -502,7 +502,7 @@ index	prediction
 500	0
 501	0
 502	0
-503	1
+503	0
 504	0
 505	0
 506	0
@@ -510,7 +510,7 @@ index	prediction
 508	0
 509	0
 510	0
-511	0
+511	1
 512	0
 513	0
 514	0
@@ -521,9 +521,9 @@ index	prediction
 519	0
 520	0
 521	0
-522	1
+522	0
 523	0
-524	1
+524	0
 525	0
 526	0
 527	0
@@ -533,11 +533,11 @@ index	prediction
 531	0
 532	0
 533	0
-534	1
+534	0
 535	0
 536	0
 537	0
-538	0
+538	1
 539	0
 540	0
 541	0
@@ -559,7 +559,7 @@ index	prediction
 557	0
 558	0
 559	0
-560	0
+560	1
 561	0
 562	0
 563	0
@@ -587,27 +587,27 @@ index	prediction
 585	0
 586	0
 587	0
-588	1
+588	0
 589	0
 590	0
 591	0
 592	0
 593	0
 594	0
-595	1
-596	1
+595	0
+596	0
 597	0
 598	0
 599	0
 600	0
-601	1
+601	0
 602	0
 603	0
 604	0
 605	0
 606	0
 607	0
-608	1
+608	0
 609	0
 610	1
 611	0
@@ -623,22 +623,22 @@ index	prediction
 621	1
 622	0
 623	0
-624	1
+624	0
 625	0
 626	0
 627	0
-628	1
+628	0
 629	0
 630	0
 631	0
 632	0
-633	1
+633	0
 634	0
-635	1
+635	0
 636	0
 637	0
 638	0
-639	1
+639	0
 640	0
 641	0
 642	0
@@ -653,7 +653,7 @@ index	prediction
 651	0
 652	1
 653	0
-654	1
+654	0
 655	0
 656	0
 657	1
@@ -668,7 +668,7 @@ index	prediction
 666	0
 667	0
 668	0
-669	1
+669	0
 670	0
 671	0
 672	0
@@ -726,7 +726,7 @@ index	prediction
 724	0
 725	0
 726	0
-727	1
+727	0
 728	1
 729	0
 730	0
@@ -755,7 +755,7 @@ index	prediction
 753	0
 754	0
 755	0
-756	1
+756	0
 757	0
 758	0
 759	0
@@ -764,14 +764,14 @@ index	prediction
 762	0
 763	0
 764	0
-765	1
+765	0
 766	0
 767	0
 768	0
 769	0
-770	1
+770	0
 771	0
-772	1
+772	0
 773	0
 774	0
 775	0
@@ -808,12 +808,12 @@ index	prediction
 806	0
 807	0
 808	0
-809	1
+809	0
 810	0
 811	0
 812	0
 813	0
-814	1
+814	0
 815	0
 816	0
 817	0
@@ -837,10 +837,10 @@ index	prediction
 835	0
 836	0
 837	0
-838	0
+838	1
 839	0
 840	0
-841	0
+841	1
 842	0
 843	0
 844	0
@@ -867,7 +867,7 @@ index	prediction
 865	0
 866	0
 867	0
-868	0
+868	1
 869	0
 870	0
 871	0
@@ -883,7 +883,7 @@ index	prediction
 881	0
 882	0
 883	0
-884	1
+884	0
 885	0
 886	0
 887	0
@@ -893,10 +893,10 @@ index	prediction
 891	1
 892	0
 893	0
-894	1
+894	0
 895	0
 896	0
-897	1
+897	0
 898	0
 899	0
 900	0
@@ -905,13 +905,13 @@ index	prediction
 903	0
 904	0
 905	0
-906	1
+906	0
 907	1
 908	0
 909	0
 910	0
 911	0
-912	1
+912	0
 913	0
 914	0
 915	0
@@ -933,7 +933,7 @@ index	prediction
 931	0
 932	0
 933	0
-934	0
+934	1
 935	0
 936	0
 937	0
@@ -949,14 +949,14 @@ index	prediction
 947	0
 948	0
 949	0
-950	1
+950	0
 951	0
 952	0
 953	0
 954	0
-955	0
+955	1
 956	0
-957	1
+957	0
 958	0
 959	0
 960	0
@@ -991,18 +991,18 @@ index	prediction
 989	0
 990	0
 991	1
-992	1
+992	0
 993	0
 994	0
-995	1
+995	0
 996	0
 997	0
-998	1
+998	0
 999	1
 1000	0
 1001	0
 1002	0
-1003	1
+1003	0
 1004	0
 1005	0
 1006	0

runs/May16_05-22-17_indolem-petl-vm/events.out.tfevents.1715839711.indolem-petl-vm.755698.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc15e198501063b589387ed23d37f34dcd5b85d6a545bd80fa0ff8c476b4cff
+size 560

test_results.json

@@ -1,6 +1,6 @@
 {
-    "accuracy": 0.8615232443125618,
-    "f1": 0.8344251555846709,
-    "precision": 0.8325509007667684,
-    "recall": 0.8363917467548971
+    "accuracy": 0.9109792284866469,
+    "f1": 0.8920886346170267,
+    "precision": 0.8953297623033144,
+    "recall": 0.8890334817436486
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.35800845193081215,
-    "train_runtime": 2113.1391,
+    "train_loss": 0.05662053943168922,
+    "train_runtime": 2712.8409,
     "train_samples": 3638,
-    "train_samples_per_second": 34.432,
-    "train_steps_per_second": 1.155
+    "train_samples_per_second": 26.821,
+    "train_steps_per_second": 0.899
 }

trainer_state.json

@@ -10,392 +10,392 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 3.0131800174713135,
+      "grad_norm": 21.900392532348633,
       "learning_rate": 4.75e-05,
-      "loss": 0.5623,
+      "loss": 0.4267,
       "step": 122
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7167919799498746,
-      "eval_f1": 0.5794790005316321,
-      "eval_loss": 0.5053456425666809,
-      "eval_precision": 0.6409822866344606,
-      "eval_recall": 0.5796053827968721,
-      "eval_runtime": 5.6071,
-      "eval_samples_per_second": 71.159,
-      "eval_steps_per_second": 8.917,
+      "eval_accuracy": 0.8796992481203008,
+      "eval_f1": 0.8409196624360422,
+      "eval_loss": 0.35864609479904175,
+      "eval_precision": 0.8892469089546646,
+      "eval_recall": 0.8148754318967084,
+      "eval_runtime": 4.9024,
+      "eval_samples_per_second": 81.389,
+      "eval_steps_per_second": 10.199,
       "step": 122
     },
     {
       "epoch": 2.0,
-      "grad_norm": 5.634490966796875,
+      "grad_norm": 23.599449157714844,
       "learning_rate": 4.5e-05,
-      "loss": 0.518,
+      "loss": 0.2234,
       "step": 244
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7293233082706767,
-      "eval_f1": 0.599784530797236,
-      "eval_loss": 0.4860531687736511,
-      "eval_precision": 0.6673625792811839,
-      "eval_recall": 0.5959719949081652,
-      "eval_runtime": 5.7755,
-      "eval_samples_per_second": 69.085,
-      "eval_steps_per_second": 8.657,
+      "eval_accuracy": 0.8696741854636592,
+      "eval_f1": 0.8539284708532808,
+      "eval_loss": 0.36683306097984314,
+      "eval_precision": 0.8394707327494125,
+      "eval_recall": 0.8852973267866885,
+      "eval_runtime": 4.9237,
+      "eval_samples_per_second": 81.037,
+      "eval_steps_per_second": 10.155,
       "step": 244
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.959808111190796,
+      "grad_norm": 8.989884376525879,
       "learning_rate": 4.25e-05,
-      "loss": 0.4835,
+      "loss": 0.126,
       "step": 366
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7694235588972431,
-      "eval_f1": 0.7145034843205575,
-      "eval_loss": 0.45518842339515686,
-      "eval_precision": 0.7210824478299833,
-      "eval_recall": 0.7093562465902892,
-      "eval_runtime": 5.2584,
-      "eval_samples_per_second": 75.878,
-      "eval_steps_per_second": 9.509,
+      "eval_accuracy": 0.8922305764411027,
+      "eval_f1": 0.8755702215614461,
+      "eval_loss": 0.4554330110549927,
+      "eval_precision": 0.8632157235517781,
+      "eval_recall": 0.8937534097108566,
+      "eval_runtime": 4.9271,
+      "eval_samples_per_second": 80.981,
+      "eval_steps_per_second": 10.148,
       "step": 366
     },
     {
       "epoch": 4.0,
-      "grad_norm": 4.635169506072998,
+      "grad_norm": 15.863175392150879,
       "learning_rate": 4e-05,
-      "loss": 0.4497,
+      "loss": 0.0886,
       "step": 488
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7944862155388471,
-      "eval_f1": 0.7520912893253319,
-      "eval_loss": 0.4223441481590271,
-      "eval_precision": 0.7520912893253319,
-      "eval_recall": 0.7520912893253319,
-      "eval_runtime": 5.0487,
-      "eval_samples_per_second": 79.03,
-      "eval_steps_per_second": 9.903,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8854915648632926,
+      "eval_loss": 0.44412538409233093,
+      "eval_precision": 0.8956662848415425,
+      "eval_recall": 0.8768867066739408,
+      "eval_runtime": 4.9398,
+      "eval_samples_per_second": 80.773,
+      "eval_steps_per_second": 10.122,
       "step": 488
     },
     {
       "epoch": 5.0,
-      "grad_norm": 8.219679832458496,
+      "grad_norm": 0.03718271106481552,
       "learning_rate": 3.7500000000000003e-05,
-      "loss": 0.4266,
+      "loss": 0.0611,
       "step": 610
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8170426065162907,
-      "eval_f1": 0.7740779522978476,
-      "eval_loss": 0.399569034576416,
-      "eval_precision": 0.7814051164566629,
-      "eval_recall": 0.7680487361338425,
-      "eval_runtime": 5.0767,
-      "eval_samples_per_second": 78.595,
-      "eval_steps_per_second": 9.849,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8839406001224739,
+      "eval_loss": 0.4922772943973541,
+      "eval_precision": 0.8880654743486602,
+      "eval_recall": 0.880114566284779,
+      "eval_runtime": 4.9142,
+      "eval_samples_per_second": 81.193,
+      "eval_steps_per_second": 10.175,
       "step": 610
     },
     {
       "epoch": 6.0,
-      "grad_norm": 4.150725841522217,
+      "grad_norm": 0.006236851681023836,
       "learning_rate": 3.5e-05,
-      "loss": 0.3907,
+      "loss": 0.0366,
       "step": 732
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8195488721804511,
-      "eval_f1": 0.784453781512605,
-      "eval_loss": 0.3830115497112274,
-      "eval_precision": 0.7818241274748796,
-      "eval_recall": 0.787324968176032,
-      "eval_runtime": 5.0718,
-      "eval_samples_per_second": 78.67,
-      "eval_steps_per_second": 9.858,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8813841488792438,
+      "eval_loss": 0.6796092391014099,
+      "eval_precision": 0.8748029197080291,
+      "eval_recall": 0.8890707401345699,
+      "eval_runtime": 4.9691,
+      "eval_samples_per_second": 80.296,
+      "eval_steps_per_second": 10.062,
       "step": 732
     },
     {
       "epoch": 7.0,
-      "grad_norm": 3.297985076904297,
+      "grad_norm": 0.006574722938239574,
       "learning_rate": 3.2500000000000004e-05,
-      "loss": 0.3742,
+      "loss": 0.0358,
       "step": 854
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.8345864661654135,
-      "eval_f1": 0.798423147581139,
-      "eval_loss": 0.3684135675430298,
-      "eval_precision": 0.8016430472182685,
-      "eval_recall": 0.7954628114202582,
-      "eval_runtime": 5.0743,
-      "eval_samples_per_second": 78.632,
-      "eval_steps_per_second": 9.854,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8820775261324042,
+      "eval_loss": 0.5746134519577026,
+      "eval_precision": 0.8934835488413775,
+      "eval_recall": 0.8726132024004365,
+      "eval_runtime": 4.9771,
+      "eval_samples_per_second": 80.167,
+      "eval_steps_per_second": 10.046,
       "step": 854
     },
     {
       "epoch": 8.0,
-      "grad_norm": 8.395323753356934,
+      "grad_norm": 0.0049128723330795765,
       "learning_rate": 3e-05,
-      "loss": 0.3616,
+      "loss": 0.0272,
       "step": 976
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8270676691729323,
-      "eval_f1": 0.7967966933608887,
-      "eval_loss": 0.3719731867313385,
-      "eval_precision": 0.7902444649446494,
-      "eval_recall": 0.8051463902527732,
-      "eval_runtime": 5.0484,
-      "eval_samples_per_second": 79.035,
-      "eval_steps_per_second": 9.904,
+      "eval_accuracy": 0.8947368421052632,
+      "eval_f1": 0.8736504011098378,
+      "eval_loss": 0.5952700972557068,
+      "eval_precision": 0.8718487394957983,
+      "eval_recall": 0.8755228223313329,
+      "eval_runtime": 4.9556,
+      "eval_samples_per_second": 80.515,
+      "eval_steps_per_second": 10.09,
       "step": 976
     },
     {
       "epoch": 9.0,
-      "grad_norm": 3.748974561691284,
+      "grad_norm": 0.006197785492986441,
       "learning_rate": 2.7500000000000004e-05,
-      "loss": 0.3294,
+      "loss": 0.0231,
       "step": 1098
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.8370927318295739,
-      "eval_f1": 0.8076965854743632,
-      "eval_loss": 0.36888691782951355,
-      "eval_precision": 0.8018925518925519,
-      "eval_recall": 0.8147390434624477,
-      "eval_runtime": 5.0543,
-      "eval_samples_per_second": 78.943,
-      "eval_steps_per_second": 9.893,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8751876876876876,
+      "eval_loss": 0.6506014466285706,
+      "eval_precision": 0.8891156462585035,
+      "eval_recall": 0.864066193853428,
+      "eval_runtime": 4.9505,
+      "eval_samples_per_second": 80.598,
+      "eval_steps_per_second": 10.1,
       "step": 1098
     },
     {
       "epoch": 10.0,
-      "grad_norm": 9.309541702270508,
+      "grad_norm": 0.009196682833135128,
       "learning_rate": 2.5e-05,
-      "loss": 0.3207,
+      "loss": 0.0141,
       "step": 1220
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.8395989974937343,
-      "eval_f1": 0.8110907261644079,
-      "eval_loss": 0.36315786838531494,
-      "eval_precision": 0.8046983557202408,
-      "eval_recall": 0.819012547735952,
-      "eval_runtime": 5.0709,
-      "eval_samples_per_second": 78.684,
-      "eval_steps_per_second": 9.86,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8823853973772722,
+      "eval_loss": 0.6854431629180908,
+      "eval_precision": 0.8814464081066409,
+      "eval_recall": 0.8833424258956174,
+      "eval_runtime": 4.9291,
+      "eval_samples_per_second": 80.948,
+      "eval_steps_per_second": 10.144,
       "step": 1220
     },
     {
       "epoch": 11.0,
-      "grad_norm": 1.2568168640136719,
+      "grad_norm": 0.01001653354614973,
       "learning_rate": 2.25e-05,
-      "loss": 0.3214,
+      "loss": 0.023,
       "step": 1342
     },
     {
       "epoch": 11.0,
-      "eval_accuracy": 0.8370927318295739,
-      "eval_f1": 0.8085765951950401,
-      "eval_loss": 0.3577338457107544,
-      "eval_precision": 0.8017470018450185,
-      "eval_recall": 0.817239498090562,
-      "eval_runtime": 5.1071,
-      "eval_samples_per_second": 78.126,
-      "eval_steps_per_second": 9.79,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8823853973772722,
+      "eval_loss": 0.7218220829963684,
+      "eval_precision": 0.8814464081066409,
+      "eval_recall": 0.8833424258956174,
+      "eval_runtime": 4.9437,
+      "eval_samples_per_second": 80.709,
+      "eval_steps_per_second": 10.114,
       "step": 1342
     },
     {
       "epoch": 12.0,
-      "grad_norm": 1.915198802947998,
+      "grad_norm": 0.0031623237300664186,
       "learning_rate": 2e-05,
-      "loss": 0.3167,
+      "loss": 0.0067,
       "step": 1464
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.8395989974937343,
-      "eval_f1": 0.8119476846942383,
-      "eval_loss": 0.36069995164871216,
-      "eval_precision": 0.8045650301464256,
-      "eval_recall": 0.8215130023640662,
-      "eval_runtime": 5.0598,
-      "eval_samples_per_second": 78.857,
-      "eval_steps_per_second": 9.882,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8823853973772722,
+      "eval_loss": 0.7694610357284546,
+      "eval_precision": 0.8814464081066409,
+      "eval_recall": 0.8833424258956174,
+      "eval_runtime": 4.9712,
+      "eval_samples_per_second": 80.263,
+      "eval_steps_per_second": 10.058,
       "step": 1464
     },
     {
       "epoch": 13.0,
-      "grad_norm": 1.9545631408691406,
+      "grad_norm": 0.002341507002711296,
       "learning_rate": 1.75e-05,
-      "loss": 0.289,
+      "loss": 0.0064,
       "step": 1586
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.8345864661654135,
-      "eval_f1": 0.8060710498409331,
-      "eval_loss": 0.3684280812740326,
-      "eval_precision": 0.7988372093023256,
-      "eval_recall": 0.8154664484451719,
-      "eval_runtime": 5.1019,
-      "eval_samples_per_second": 78.206,
-      "eval_steps_per_second": 9.8,
+      "eval_accuracy": 0.8796992481203008,
+      "eval_f1": 0.8602043795620438,
+      "eval_loss": 0.9004446268081665,
+      "eval_precision": 0.849624060150376,
+      "eval_recall": 0.8748863429714493,
+      "eval_runtime": 4.9523,
+      "eval_samples_per_second": 80.569,
+      "eval_steps_per_second": 10.096,
       "step": 1586
     },
     {
       "epoch": 14.0,
-      "grad_norm": 5.748187065124512,
+      "grad_norm": 0.0026841196231544018,
       "learning_rate": 1.5e-05,
-      "loss": 0.2997,
+      "loss": 0.0103,
       "step": 1708
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.849624060150376,
-      "eval_f1": 0.8176861216035092,
-      "eval_loss": 0.3479882776737213,
-      "eval_precision": 0.8193355786895284,
-      "eval_recall": 0.8161029278050556,
-      "eval_runtime": 5.0557,
-      "eval_samples_per_second": 78.92,
-      "eval_steps_per_second": 9.89,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8835263209107715,
+      "eval_loss": 0.7978267073631287,
+      "eval_precision": 0.8791501449961532,
+      "eval_recall": 0.8883433351518457,
+      "eval_runtime": 4.9622,
+      "eval_samples_per_second": 80.407,
+      "eval_steps_per_second": 10.076,
       "step": 1708
     },
     {
       "epoch": 15.0,
-      "grad_norm": 4.010083198547363,
+      "grad_norm": 0.0031805976759642363,
       "learning_rate": 1.25e-05,
-      "loss": 0.2986,
+      "loss": 0.0072,
       "step": 1830
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.849624060150376,
-      "eval_f1": 0.821236559139785,
-      "eval_loss": 0.35758015513420105,
-      "eval_precision": 0.8169406150583245,
-      "eval_recall": 0.8261047463175123,
-      "eval_runtime": 5.0955,
-      "eval_samples_per_second": 78.304,
-      "eval_steps_per_second": 9.813,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8790689216221131,
+      "eval_loss": 0.8251467943191528,
+      "eval_precision": 0.8790689216221131,
+      "eval_recall": 0.8790689216221131,
+      "eval_runtime": 4.9558,
+      "eval_samples_per_second": 80.512,
+      "eval_steps_per_second": 10.089,
       "step": 1830
     },
     {
       "epoch": 16.0,
-      "grad_norm": 0.9220337271690369,
+      "grad_norm": 0.0014117677928879857,
       "learning_rate": 1e-05,
-      "loss": 0.2914,
+      "loss": 0.0054,
       "step": 1952
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.849624060150376,
-      "eval_f1": 0.8195005730140539,
-      "eval_loss": 0.34965991973876953,
-      "eval_precision": 0.8179621848739496,
-      "eval_recall": 0.8211038370612839,
-      "eval_runtime": 5.0617,
-      "eval_samples_per_second": 78.827,
-      "eval_steps_per_second": 9.878,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8823853973772722,
+      "eval_loss": 0.7715300917625427,
+      "eval_precision": 0.8814464081066409,
+      "eval_recall": 0.8833424258956174,
+      "eval_runtime": 4.96,
+      "eval_samples_per_second": 80.444,
+      "eval_steps_per_second": 10.081,
       "step": 1952
     },
     {
       "epoch": 17.0,
-      "grad_norm": 1.7026562690734863,
+      "grad_norm": 0.0014807094121351838,
       "learning_rate": 7.5e-06,
-      "loss": 0.278,
+      "loss": 0.0038,
       "step": 2074
     },
     {
       "epoch": 17.0,
-      "eval_accuracy": 0.8521303258145363,
-      "eval_f1": 0.8229427559286084,
-      "eval_loss": 0.3539772927761078,
-      "eval_precision": 0.8206541218637993,
-      "eval_recall": 0.8253773413347881,
-      "eval_runtime": 5.1199,
-      "eval_samples_per_second": 77.931,
-      "eval_steps_per_second": 9.766,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8867007927797945,
+      "eval_loss": 0.7821339964866638,
+      "eval_precision": 0.89198606271777,
+      "eval_recall": 0.8818876159301692,
+      "eval_runtime": 4.9491,
+      "eval_samples_per_second": 80.62,
+      "eval_steps_per_second": 10.103,
       "step": 2074
     },
     {
       "epoch": 18.0,
-      "grad_norm": 5.839470863342285,
+      "grad_norm": 0.0014356797328218818,
       "learning_rate": 5e-06,
-      "loss": 0.2887,
+      "loss": 0.0021,
       "step": 2196
     },
     {
       "epoch": 18.0,
-      "eval_accuracy": 0.8521303258145363,
-      "eval_f1": 0.8229427559286084,
-      "eval_loss": 0.35161107778549194,
-      "eval_precision": 0.8206541218637993,
-      "eval_recall": 0.8253773413347881,
-      "eval_runtime": 5.1154,
-      "eval_samples_per_second": 77.999,
-      "eval_steps_per_second": 9.774,
+      "eval_accuracy": 0.8972431077694235,
+      "eval_f1": 0.8763538792940554,
+      "eval_loss": 0.8211472630500793,
+      "eval_precision": 0.8754297605404427,
+      "eval_recall": 0.877295871976723,
+      "eval_runtime": 4.9631,
+      "eval_samples_per_second": 80.393,
+      "eval_steps_per_second": 10.074,
       "step": 2196
     },
     {
       "epoch": 19.0,
-      "grad_norm": 7.782900810241699,
+      "grad_norm": 0.0011136590037494898,
       "learning_rate": 2.5e-06,
-      "loss": 0.2829,
+      "loss": 0.0022,
       "step": 2318
     },
     {
       "epoch": 19.0,
-      "eval_accuracy": 0.8521303258145363,
-      "eval_f1": 0.8229427559286084,
-      "eval_loss": 0.35369938611984253,
-      "eval_precision": 0.8206541218637993,
-      "eval_recall": 0.8253773413347881,
-      "eval_runtime": 5.0565,
-      "eval_samples_per_second": 78.908,
-      "eval_steps_per_second": 9.888,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8790689216221131,
+      "eval_loss": 0.8161725401878357,
+      "eval_precision": 0.8790689216221131,
+      "eval_recall": 0.8790689216221131,
+      "eval_runtime": 4.9339,
+      "eval_samples_per_second": 80.869,
+      "eval_steps_per_second": 10.134,
       "step": 2318
     },
     {
       "epoch": 20.0,
-      "grad_norm": 5.059621334075928,
+      "grad_norm": 0.0013613783521577716,
       "learning_rate": 0.0,
-      "loss": 0.2771,
+      "loss": 0.0027,
       "step": 2440
     },
     {
       "epoch": 20.0,
-      "eval_accuracy": 0.8546365914786967,
-      "eval_f1": 0.8263655462184873,
-      "eval_loss": 0.35401326417922974,
-      "eval_precision": 0.8233396753671443,
-      "eval_recall": 0.8296508456082925,
-      "eval_runtime": 5.0854,
-      "eval_samples_per_second": 78.459,
-      "eval_steps_per_second": 9.832,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8817957385392532,
+      "eval_loss": 0.8104944229125977,
+      "eval_precision": 0.8827677592299257,
+      "eval_recall": 0.8808419712675032,
+      "eval_runtime": 4.9425,
+      "eval_samples_per_second": 80.729,
+      "eval_steps_per_second": 10.116,
       "step": 2440
     },
     {
       "epoch": 20.0,
       "step": 2440,
-      "total_flos": 7597037114448000.0,
-      "train_loss": 0.35800845193081215,
-      "train_runtime": 2113.1391,
-      "train_samples_per_second": 34.432,
-      "train_steps_per_second": 1.155
+      "total_flos": 7584162436176000.0,
+      "train_loss": 0.05662053943168922,
+      "train_runtime": 2712.8409,
+      "train_samples_per_second": 26.821,
+      "train_steps_per_second": 0.899
     }
   ],
   "logging_steps": 500,
@@ -403,7 +403,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 7597037114448000.0,
+  "total_flos": 7584162436176000.0,
   "train_batch_size": 30,
   "trial_name": null,
   "trial_params": null