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": 0.9000989119683481,
+    "accuracy": 0.9090009891196835,
     "epoch": 20.0,
     "eval_accuracy": 0.9022556390977443,
-    "eval_f1": 0.884617951284618,
-    "eval_loss": 0.2810901701450348,
-    "eval_precision": 0.8772893772893773,
-    "eval_recall": 0.8933442444080741,
-    "eval_runtime": 5.7274,
+    "eval_f1": 0.8811928811928812,
+    "eval_loss": 0.29284632205963135,
+    "eval_precision": 0.8842105263157894,
+    "eval_recall": 0.878341516639389,
+    "eval_runtime": 5.5622,
     "eval_samples": 399,
-    "eval_samples_per_second": 69.665,
-    "eval_steps_per_second": 8.73,
-    "f1": 0.881994210133999,
-    "precision": 0.875823871126101,
-    "recall": 0.8891323173658895,
-    "train_loss": 0.21111928674041247,
-    "train_runtime": 2283.5364,
+    "eval_samples_per_second": 71.734,
+    "eval_steps_per_second": 8.989,
+    "f1": 0.8907735522904062,
+    "precision": 0.8900210970464135,
+    "recall": 0.8915373175070833,
+    "train_loss": 0.2130153269064231,
+    "train_runtime": 2280.4037,
     "train_samples": 3638,
-    "train_samples_per_second": 31.863,
-    "train_steps_per_second": 1.069
+    "train_samples_per_second": 31.907,
+    "train_steps_per_second": 1.07
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 20.0,
     "eval_accuracy": 0.9022556390977443,
-    "eval_f1": 0.884617951284618,
-    "eval_loss": 0.2810901701450348,
-    "eval_precision": 0.8772893772893773,
-    "eval_recall": 0.8933442444080741,
-    "eval_runtime": 5.7274,
+    "eval_f1": 0.8811928811928812,
+    "eval_loss": 0.29284632205963135,
+    "eval_precision": 0.8842105263157894,
+    "eval_recall": 0.878341516639389,
+    "eval_runtime": 5.5622,
     "eval_samples": 399,
-    "eval_samples_per_second": 69.665,
-    "eval_steps_per_second": 8.73
+    "eval_samples_per_second": 71.734,
+    "eval_steps_per_second": 8.989
 }

predict_results.txt

@@ -1,10 +1,10 @@
 index	prediction
 0	1
-1	0
+1	1
 2	1
 3	1
-4	0
-5	1
+4	1
+5	0
 6	1
 7	1
 8	0
@@ -14,7 +14,7 @@ index	prediction
 12	1
 13	1
 14	1
-15	0
+15	1
 16	1
 17	1
 18	1
@@ -24,49 +24,49 @@ index	prediction
 22	0
 23	1
 24	1
-25	1
-26	1
+25	0
+26	0
 27	1
 28	1
 29	1
 30	1
 31	1
-32	1
+32	0
 33	1
-34	0
+34	1
 35	1
 36	1
-37	0
+37	1
 38	1
-39	0
+39	1
 40	1
-41	1
+41	0
 42	1
-43	0
-44	0
+43	1
+44	1
 45	0
-46	1
+46	0
 47	1
 48	1
-49	0
+49	1
 50	1
-51	1
-52	0
+51	0
+52	1
 53	1
 54	1
 55	1
 56	1
-57	0
+57	1
 58	1
 59	1
-60	1
+60	0
 61	1
 62	1
 63	1
-64	1
+64	0
 65	1
 66	1
-67	1
+67	0
 68	1
 69	1
 70	1
@@ -74,37 +74,37 @@ index	prediction
 72	1
 73	1
 74	1
-75	1
-76	1
+75	0
+76	0
 77	1
 78	1
 79	1
 80	1
-81	0
-82	1
-83	1
+81	1
+82	0
+83	0
 84	1
-85	0
+85	1
 86	1
 87	1
 88	1
 89	1
-90	1
+90	0
 91	1
 92	1
 93	1
 94	1
 95	1
 96	1
-97	0
+97	1
 98	1
-99	0
+99	1
 100	1
-101	0
-102	1
+101	1
+102	0
 103	1
 104	1
-105	1
+105	0
 106	1
 107	1
 108	1
@@ -114,28 +114,28 @@ index	prediction
 112	1
 113	1
 114	1
-115	1
+115	0
 116	1
 117	1
-118	0
+118	1
 119	1
-120	1
-121	1
+120	0
+121	0
 122	1
 123	1
-124	1
+124	0
 125	1
 126	1
-127	1
+127	0
 128	1
 129	1
-130	1
-131	0
+130	0
+131	1
 132	1
 133	1
 134	1
 135	1
-136	0
+136	1
 137	1
 138	1
 139	1
@@ -150,11 +150,11 @@ index	prediction
 148	1
 149	1
 150	1
-151	1
+151	0
 152	1
 153	1
 154	1
-155	0
+155	1
 156	1
 157	1
 158	1
@@ -164,23 +164,23 @@ index	prediction
 162	1
 163	1
 164	1
-165	0
+165	1
 166	1
-167	1
-168	0
+167	0
+168	1
 169	1
-170	1
+170	0
 171	1
 172	1
-173	0
-174	1
+173	1
+174	0
 175	1
 176	1
-177	0
+177	1
 178	1
-179	1
+179	0
 180	1
-181	1
+181	0
 182	1
 183	1
 184	1
@@ -191,20 +191,20 @@ index	prediction
 189	1
 190	1
 191	1
-192	1
+192	0
 193	1
 194	1
 195	1
 196	1
 197	1
 198	1
-199	0
+199	1
 200	1
 201	1
 202	1
 203	1
 204	1
-205	0
+205	1
 206	1
 207	1
 208	1
@@ -213,20 +213,20 @@ index	prediction
 211	1
 212	1
 213	1
-214	0
-215	1
-216	0
+214	1
+215	0
+216	1
 217	1
-218	0
+218	1
 219	1
-220	0
+220	1
 221	1
 222	1
 223	1
 224	0
 225	1
-226	0
-227	0
+226	1
+227	1
 228	1
 229	0
 230	1
@@ -234,9 +234,9 @@ index	prediction
 232	1
 233	1
 234	1
-235	1
+235	0
 236	1
-237	1
+237	0
 238	1
 239	1
 240	1
@@ -245,14 +245,14 @@ index	prediction
 243	1
 244	1
 245	1
-246	0
+246	1
 247	1
-248	1
+248	0
 249	1
-250	0
+250	1
 251	1
 252	1
-253	1
+253	0
 254	1
 255	1
 256	1
@@ -267,20 +267,20 @@ index	prediction
 265	1
 266	1
 267	1
-268	1
+268	0
 269	1
 270	1
 271	1
-272	1
+272	0
 273	1
 274	1
-275	1
-276	1
+275	0
+276	0
 277	1
 278	1
 279	1
-280	0
-281	1
+280	1
+281	0
 282	1
 283	1
 284	1
@@ -288,7 +288,7 @@ index	prediction
 286	1
 287	1
 288	1
-289	0
+289	1
 290	1
 291	1
 292	1
@@ -301,33 +301,33 @@ index	prediction
 299	0
 300	0
 301	0
-302	1
+302	0
 303	0
 304	0
-305	1
+305	0
 306	0
 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
+323	1
+324	1
 325	0
 326	0
 327	0
-328	1
+328	0
 329	0
 330	0
 331	0
@@ -337,11 +337,11 @@ index	prediction
 335	0
 336	0
 337	0
-338	0
+338	1
 339	0
-340	0
+340	1
 341	0
-342	0
+342	1
 343	0
 344	0
 345	0
@@ -350,7 +350,7 @@ index	prediction
 348	0
 349	0
 350	0
-351	1
+351	0
 352	0
 353	0
 354	0
@@ -365,7 +365,7 @@ index	prediction
 363	0
 364	0
 365	0
-366	1
+366	0
 367	0
 368	0
 369	0
@@ -381,7 +381,7 @@ index	prediction
 379	0
 380	0
 381	0
-382	0
+382	1
 383	0
 384	0
 385	0
@@ -400,8 +400,8 @@ index	prediction
 398	1
 399	0
 400	0
-401	1
-402	1
+401	0
+402	0
 403	0
 404	0
 405	0
@@ -419,26 +419,26 @@ index	prediction
 417	0
 418	0
 419	0
-420	1
+420	0
 421	0
 422	0
 423	0
 424	0
-425	1
+425	0
 426	0
 427	0
 428	0
-429	0
+429	1
 430	0
 431	0
 432	0
 433	0
-434	0
-435	0
+434	1
+435	1
 436	0
 437	0
 438	0
-439	1
+439	0
 440	0
 441	0
 442	0
@@ -446,7 +446,7 @@ index	prediction
 444	0
 445	0
 446	0
-447	1
+447	0
 448	0
 449	0
 450	0
@@ -454,15 +454,15 @@ index	prediction
 452	0
 453	0
 454	0
-455	0
+455	1
 456	0
-457	1
+457	0
 458	0
 459	0
 460	0
 461	0
 462	0
-463	0
+463	1
 464	0
 465	0
 466	0
@@ -486,18 +486,18 @@ index	prediction
 484	0
 485	0
 486	0
-487	0
+487	1
 488	0
 489	0
 490	0
-491	0
+491	1
 492	0
 493	0
 494	0
 495	0
 496	0
 497	0
-498	0
+498	1
 499	0
 500	0
 501	0
@@ -510,7 +510,7 @@ index	prediction
 508	0
 509	0
 510	0
-511	1
+511	0
 512	0
 513	0
 514	0
@@ -521,14 +521,14 @@ index	prediction
 519	0
 520	0
 521	0
-522	0
-523	0
+522	1
+523	1
 524	0
 525	0
 526	0
 527	0
 528	0
-529	1
+529	0
 530	0
 531	0
 532	0
@@ -559,7 +559,7 @@ index	prediction
 557	0
 558	0
 559	0
-560	1
+560	0
 561	0
 562	0
 563	0
@@ -578,10 +578,10 @@ index	prediction
 576	0
 577	0
 578	0
-579	0
+579	1
 580	0
-581	0
-582	0
+581	1
+582	1
 583	0
 584	0
 585	0
@@ -590,12 +590,12 @@ index	prediction
 588	0
 589	0
 590	0
-591	0
+591	1
 592	0
 593	0
 594	0
 595	0
-596	1
+596	0
 597	0
 598	0
 599	0
@@ -607,10 +607,10 @@ index	prediction
 605	0
 606	0
 607	0
-608	1
+608	0
 609	0
-610	1
-611	1
+610	0
+611	0
 612	0
 613	0
 614	0
@@ -620,7 +620,7 @@ index	prediction
 618	0
 619	0
 620	0
-621	1
+621	0
 622	0
 623	0
 624	0
@@ -632,13 +632,13 @@ index	prediction
 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
@@ -651,12 +651,12 @@ index	prediction
 649	0
 650	0
 651	0
-652	1
+652	0
 653	0
 654	0
 655	0
 656	0
-657	1
+657	0
 658	0
 659	0
 660	0
@@ -664,15 +664,15 @@ index	prediction
 662	0
 663	0
 664	0
-665	0
+665	1
 666	0
-667	0
+667	1
 668	0
-669	1
+669	0
 670	0
 671	0
 672	0
-673	0
+673	1
 674	0
 675	0
 676	0
@@ -687,7 +687,7 @@ index	prediction
 685	0
 686	0
 687	0
-688	0
+688	1
 689	0
 690	0
 691	0
@@ -709,12 +709,12 @@ index	prediction
 707	0
 708	0
 709	0
-710	0
+710	1
 711	0
-712	0
+712	1
 713	0
 714	0
-715	0
+715	1
 716	0
 717	0
 718	0
@@ -726,24 +726,24 @@ 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
+733	0
+734	1
 735	0
 736	0
-737	0
+737	1
 738	0
 739	0
 740	0
 741	0
 742	0
 743	0
-744	0
+744	1
 745	0
 746	0
 747	0
@@ -755,28 +755,28 @@ index	prediction
 753	0
 754	0
 755	0
-756	1
+756	0
 757	0
 758	0
 759	0
 760	0
 761	0
-762	0
+762	1
 763	0
 764	0
-765	1
+765	0
 766	0
 767	0
 768	0
 769	0
-770	1
+770	0
 771	0
 772	0
 773	0
-774	0
+774	1
 775	0
 776	0
-777	1
+777	0
 778	0
 779	0
 780	0
@@ -785,7 +785,7 @@ index	prediction
 783	0
 784	0
 785	0
-786	0
+786	1
 787	0
 788	0
 789	0
@@ -813,12 +813,12 @@ index	prediction
 811	0
 812	0
 813	0
-814	1
+814	0
 815	0
 816	0
 817	0
 818	0
-819	1
+819	0
 820	0
 821	0
 822	0
@@ -831,8 +831,8 @@ index	prediction
 829	0
 830	0
 831	0
-832	1
-833	1
+832	0
+833	0
 834	0
 835	0
 836	0
@@ -848,15 +848,15 @@ index	prediction
 846	0
 847	0
 848	0
-849	1
+849	0
 850	0
-851	0
+851	1
 852	0
 853	0
-854	0
+854	1
 855	0
 856	0
-857	0
+857	1
 858	0
 859	0
 860	0
@@ -864,10 +864,10 @@ index	prediction
 862	0
 863	0
 864	0
-865	0
+865	1
 866	0
 867	0
-868	1
+868	0
 869	0
 870	0
 871	0
@@ -882,7 +882,7 @@ index	prediction
 880	0
 881	0
 882	0
-883	1
+883	0
 884	0
 885	0
 886	0
@@ -890,13 +890,13 @@ index	prediction
 888	0
 889	0
 890	0
-891	1
+891	0
 892	0
-893	0
+893	1
 894	0
 895	0
-896	0
-897	1
+896	1
+897	0
 898	0
 899	0
 900	0
@@ -905,8 +905,8 @@ index	prediction
 903	0
 904	0
 905	0
-906	1
-907	1
+906	0
+907	0
 908	0
 909	0
 910	0
@@ -915,7 +915,7 @@ index	prediction
 913	0
 914	0
 915	0
-916	1
+916	0
 917	0
 918	0
 919	0
@@ -927,36 +927,36 @@ index	prediction
 925	0
 926	0
 927	0
-928	1
+928	0
 929	0
 930	0
 931	0
 932	0
 933	0
 934	0
-935	0
-936	0
+935	1
+936	1
 937	0
 938	0
 939	0
 940	0
 941	0
 942	0
-943	1
+943	0
 944	0
 945	0
 946	0
 947	0
 948	0
 949	0
-950	1
+950	0
 951	0
 952	0
 953	0
 954	0
 955	0
 956	0
-957	1
+957	0
 958	0
 959	0
 960	0
@@ -968,7 +968,7 @@ index	prediction
 966	0
 967	0
 968	0
-969	1
+969	0
 970	0
 971	0
 972	0
@@ -979,26 +979,26 @@ index	prediction
 977	0
 978	0
 979	0
-980	1
+980	0
 981	0
 982	0
 983	0
 984	0
 985	0
-986	1
+986	0
 987	0
 988	0
 989	0
 990	0
-991	1
+991	0
 992	0
-993	0
+993	1
 994	0
-995	0
+995	1
 996	0
 997	0
 998	0
-999	1
+999	0
 1000	0
 1001	0
 1002	0

runs/May20_05-56-39_indolem-petl-vm/events.out.tfevents.1716186904.indolem-petl-vm.2737008.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9636c835e603941ce911ab7e6300870d7602cc9d7dbe5130e7d4590b71f43a6a
+size 560

test_results.json

@@ -1,6 +1,6 @@
 {
-    "accuracy": 0.9000989119683481,
-    "f1": 0.881994210133999,
-    "precision": 0.875823871126101,
-    "recall": 0.8891323173658895
+    "accuracy": 0.9090009891196835,
+    "f1": 0.8907735522904062,
+    "precision": 0.8900210970464135,
+    "recall": 0.8915373175070833
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 20.0,
-    "train_loss": 0.21111928674041247,
-    "train_runtime": 2283.5364,
+    "train_loss": 0.2130153269064231,
+    "train_runtime": 2280.4037,
     "train_samples": 3638,
-    "train_samples_per_second": 31.863,
-    "train_steps_per_second": 1.069
+    "train_samples_per_second": 31.907,
+    "train_steps_per_second": 1.07
 }

trainer_state.json

@@ -10,392 +10,392 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 4.3501811027526855,
+      "grad_norm": 4.303664207458496,
       "learning_rate": 4.75e-05,
-      "loss": 0.5459,
+      "loss": 0.5535,
       "step": 122
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7468671679197995,
-      "eval_f1": 0.6572777139941319,
-      "eval_loss": 0.46394461393356323,
-      "eval_precision": 0.6922477833692786,
-      "eval_recall": 0.6458901618476087,
-      "eval_runtime": 5.3143,
-      "eval_samples_per_second": 75.081,
-      "eval_steps_per_second": 9.409,
+      "eval_accuracy": 0.7293233082706767,
+      "eval_f1": 0.6372727272727272,
+      "eval_loss": 0.49923330545425415,
+      "eval_precision": 0.6645702306079665,
+      "eval_recall": 0.6284779050736498,
+      "eval_runtime": 5.2819,
+      "eval_samples_per_second": 75.541,
+      "eval_steps_per_second": 9.466,
       "step": 122
     },
     {
       "epoch": 2.0,
-      "grad_norm": 3.848093271255493,
+      "grad_norm": 4.080423831939697,
       "learning_rate": 4.5e-05,
-      "loss": 0.4335,
+      "loss": 0.444,
       "step": 244
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7844611528822055,
-      "eval_f1": 0.7634169884169884,
-      "eval_loss": 0.41080254316329956,
-      "eval_precision": 0.7551731309140064,
-      "eval_recall": 0.7975086379341698,
-      "eval_runtime": 5.5615,
-      "eval_samples_per_second": 71.743,
-      "eval_steps_per_second": 8.99,
+      "eval_accuracy": 0.8170426065162907,
+      "eval_f1": 0.7960536910871955,
+      "eval_loss": 0.4052737355232239,
+      "eval_precision": 0.7846938775510204,
+      "eval_recall": 0.8255591925804692,
+      "eval_runtime": 5.5544,
+      "eval_samples_per_second": 71.835,
+      "eval_steps_per_second": 9.002,
       "step": 244
     },
     {
       "epoch": 3.0,
-      "grad_norm": 4.800747394561768,
+      "grad_norm": 4.110426425933838,
       "learning_rate": 4.25e-05,
-      "loss": 0.3375,
+      "loss": 0.3464,
       "step": 366
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8596491228070176,
-      "eval_f1": 0.8271551457392166,
-      "eval_loss": 0.3282613754272461,
-      "eval_precision": 0.8347358430876305,
-      "eval_recall": 0.8206946717585015,
-      "eval_runtime": 5.5806,
-      "eval_samples_per_second": 71.498,
-      "eval_steps_per_second": 8.96,
+      "eval_accuracy": 0.8421052631578947,
+      "eval_f1": 0.7905197629940748,
+      "eval_loss": 0.3424628674983978,
+      "eval_precision": 0.8345238095238094,
+      "eval_recall": 0.7682760501909438,
+      "eval_runtime": 5.6127,
+      "eval_samples_per_second": 71.089,
+      "eval_steps_per_second": 8.908,
       "step": 366
     },
     {
       "epoch": 4.0,
-      "grad_norm": 2.052788019180298,
+      "grad_norm": 1.6437464952468872,
       "learning_rate": 4e-05,
-      "loss": 0.2801,
+      "loss": 0.2852,
       "step": 488
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8596491228070176,
-      "eval_f1": 0.8347043853938569,
-      "eval_loss": 0.32024893164634705,
-      "eval_precision": 0.8277993283927745,
-      "eval_recall": 0.8431987634115294,
-      "eval_runtime": 5.6891,
-      "eval_samples_per_second": 70.134,
-      "eval_steps_per_second": 8.789,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8469505178365937,
+      "eval_loss": 0.3135569393634796,
+      "eval_precision": 0.844489247311828,
+      "eval_recall": 0.8495635570103655,
+      "eval_runtime": 5.5998,
+      "eval_samples_per_second": 71.253,
+      "eval_steps_per_second": 8.929,
       "step": 488
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.35927698016166687,
+      "grad_norm": 3.6121034622192383,
       "learning_rate": 3.7500000000000003e-05,
-      "loss": 0.2572,
+      "loss": 0.2608,
       "step": 610
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.87468671679198,
-      "eval_f1": 0.8550061050061051,
-      "eval_loss": 0.31085968017578125,
-      "eval_precision": 0.8437710437710437,
-      "eval_recall": 0.8713402436806692,
-      "eval_runtime": 5.6502,
-      "eval_samples_per_second": 70.617,
-      "eval_steps_per_second": 8.849,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8469505178365937,
+      "eval_loss": 0.3060314953327179,
+      "eval_precision": 0.844489247311828,
+      "eval_recall": 0.8495635570103655,
+      "eval_runtime": 5.6686,
+      "eval_samples_per_second": 70.388,
+      "eval_steps_per_second": 8.821,
       "step": 610
     },
     {
       "epoch": 6.0,
-      "grad_norm": 1.9262036085128784,
+      "grad_norm": 2.0154571533203125,
       "learning_rate": 3.5e-05,
-      "loss": 0.2339,
+      "loss": 0.2415,
       "step": 732
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8671679197994987,
-      "eval_f1": 0.8472754847795472,
-      "eval_loss": 0.3074397146701813,
-      "eval_precision": 0.8352906879893387,
-      "eval_recall": 0.8660210947444991,
-      "eval_runtime": 5.5676,
-      "eval_samples_per_second": 71.664,
-      "eval_steps_per_second": 8.98,
+      "eval_accuracy": 0.8646616541353384,
+      "eval_f1": 0.8447157518450185,
+      "eval_loss": 0.3100413978099823,
+      "eval_precision": 0.8325401217487549,
+      "eval_recall": 0.864248045099109,
+      "eval_runtime": 5.5541,
+      "eval_samples_per_second": 71.838,
+      "eval_steps_per_second": 9.002,
       "step": 732
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.7879945635795593,
+      "grad_norm": 0.5025161504745483,
       "learning_rate": 3.2500000000000004e-05,
-      "loss": 0.2249,
+      "loss": 0.2329,
       "step": 854
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.8671679197994987,
-      "eval_f1": 0.8472754847795472,
-      "eval_loss": 0.2915370464324951,
-      "eval_precision": 0.8352906879893387,
-      "eval_recall": 0.8660210947444991,
-      "eval_runtime": 5.5784,
-      "eval_samples_per_second": 71.526,
-      "eval_steps_per_second": 8.963,
+      "eval_accuracy": 0.8847117794486216,
+      "eval_f1": 0.8642214594306682,
+      "eval_loss": 0.28597915172576904,
+      "eval_precision": 0.8566755442334414,
+      "eval_recall": 0.8734315330060011,
+      "eval_runtime": 5.5629,
+      "eval_samples_per_second": 71.725,
+      "eval_steps_per_second": 8.988,
       "step": 854
     },
     {
       "epoch": 8.0,
-      "grad_norm": 2.2202210426330566,
+      "grad_norm": 2.4278862476348877,
       "learning_rate": 3e-05,
-      "loss": 0.193,
+      "loss": 0.199,
       "step": 976
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8972431077694235,
-      "eval_f1": 0.8751002084335417,
-      "eval_loss": 0.25404733419418335,
-      "eval_precision": 0.8780701754385964,
-      "eval_recall": 0.8722949627204946,
-      "eval_runtime": 5.5919,
-      "eval_samples_per_second": 71.353,
-      "eval_steps_per_second": 8.942,
+      "eval_accuracy": 0.8872180451127819,
+      "eval_f1": 0.8622036668943447,
+      "eval_loss": 0.2878971993923187,
+      "eval_precision": 0.8671602787456446,
+      "eval_recall": 0.8577014002545917,
+      "eval_runtime": 5.6077,
+      "eval_samples_per_second": 71.152,
+      "eval_steps_per_second": 8.916,
       "step": 976
     },
     {
       "epoch": 9.0,
-      "grad_norm": 8.847825050354004,
+      "grad_norm": 8.504670143127441,
       "learning_rate": 2.7500000000000004e-05,
-      "loss": 0.1899,
+      "loss": 0.1939,
       "step": 1098
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.8822055137844611,
-      "eval_f1": 0.8628173897776901,
-      "eval_loss": 0.26359453797340393,
-      "eval_precision": 0.8526132107592781,
-      "eval_recall": 0.8766593926168395,
-      "eval_runtime": 5.5857,
-      "eval_samples_per_second": 71.432,
-      "eval_steps_per_second": 8.951,
+      "eval_accuracy": 0.8897243107769424,
+      "eval_f1": 0.8676337535436396,
+      "eval_loss": 0.28258949518203735,
+      "eval_precision": 0.8658613445378152,
+      "eval_recall": 0.8694762684124386,
+      "eval_runtime": 5.5938,
+      "eval_samples_per_second": 71.329,
+      "eval_steps_per_second": 8.939,
       "step": 1098
     },
     {
       "epoch": 10.0,
-      "grad_norm": 1.7180150747299194,
+      "grad_norm": 2.462061882019043,
       "learning_rate": 2.5e-05,
-      "loss": 0.1801,
+      "loss": 0.1806,
       "step": 1220
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.9072681704260651,
-      "eval_f1": 0.8900228699985846,
-      "eval_loss": 0.23711469769477844,
-      "eval_precision": 0.8840175953079179,
-      "eval_recall": 0.8968903436988543,
-      "eval_runtime": 5.6079,
-      "eval_samples_per_second": 71.15,
-      "eval_steps_per_second": 8.916,
+      "eval_accuracy": 0.8796992481203008,
+      "eval_f1": 0.8439374185136896,
+      "eval_loss": 0.2981988787651062,
+      "eval_precision": 0.8794955044955045,
+      "eval_recall": 0.822376795781051,
+      "eval_runtime": 5.5576,
+      "eval_samples_per_second": 71.793,
+      "eval_steps_per_second": 8.997,
       "step": 1220
     },
     {
       "epoch": 11.0,
-      "grad_norm": 0.6990593671798706,
+      "grad_norm": 1.0077548027038574,
       "learning_rate": 2.25e-05,
-      "loss": 0.157,
+      "loss": 0.1674,
       "step": 1342
     },
     {
       "epoch": 11.0,
-      "eval_accuracy": 0.899749373433584,
-      "eval_f1": 0.882467302933899,
-      "eval_loss": 0.2566535174846649,
-      "eval_precision": 0.8732988802756245,
-      "eval_recall": 0.8940716493907983,
-      "eval_runtime": 5.5787,
-      "eval_samples_per_second": 71.522,
-      "eval_steps_per_second": 8.963,
+      "eval_accuracy": 0.8947368421052632,
+      "eval_f1": 0.8730223677032187,
+      "eval_loss": 0.2734816372394562,
+      "eval_precision": 0.8730223677032187,
+      "eval_recall": 0.8730223677032187,
+      "eval_runtime": 5.5924,
+      "eval_samples_per_second": 71.346,
+      "eval_steps_per_second": 8.941,
       "step": 1342
     },
     {
       "epoch": 12.0,
-      "grad_norm": 3.7353861331939697,
+      "grad_norm": 3.9673709869384766,
       "learning_rate": 2e-05,
       "loss": 0.1553,
       "step": 1464
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.8972431077694235,
-      "eval_f1": 0.8792560061999484,
-      "eval_loss": 0.25933051109313965,
-      "eval_precision": 0.8707622232472325,
-      "eval_recall": 0.889798145117294,
-      "eval_runtime": 5.6004,
-      "eval_samples_per_second": 71.245,
-      "eval_steps_per_second": 8.928,
+      "eval_accuracy": 0.8947368421052632,
+      "eval_f1": 0.8717238211879976,
+      "eval_loss": 0.2753015458583832,
+      "eval_precision": 0.8757194133300328,
+      "eval_recall": 0.8680214584469903,
+      "eval_runtime": 5.5661,
+      "eval_samples_per_second": 71.684,
+      "eval_steps_per_second": 8.983,
       "step": 1464
     },
     {
       "epoch": 13.0,
-      "grad_norm": 1.2111871242523193,
+      "grad_norm": 3.968949794769287,
       "learning_rate": 1.75e-05,
-      "loss": 0.1381,
+      "loss": 0.1431,
       "step": 1586
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.9172932330827067,
-      "eval_f1": 0.8999810095332144,
-      "eval_loss": 0.24901245534420013,
-      "eval_precision": 0.9009991470695747,
-      "eval_recall": 0.8989816330241862,
-      "eval_runtime": 5.6194,
-      "eval_samples_per_second": 71.004,
-      "eval_steps_per_second": 8.898,
+      "eval_accuracy": 0.8922305764411027,
+      "eval_f1": 0.8661961395983623,
+      "eval_loss": 0.2937251627445221,
+      "eval_precision": 0.8784532165625604,
+      "eval_recall": 0.8562465902891435,
+      "eval_runtime": 5.5699,
+      "eval_samples_per_second": 71.635,
+      "eval_steps_per_second": 8.977,
       "step": 1586
     },
     {
       "epoch": 14.0,
-      "grad_norm": 9.943241119384766,
+      "grad_norm": 8.566404342651367,
       "learning_rate": 1.5e-05,
-      "loss": 0.1476,
+      "loss": 0.1417,
       "step": 1708
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.899749373433584,
-      "eval_f1": 0.881931703852755,
-      "eval_loss": 0.27014100551605225,
-      "eval_precision": 0.8740012737378415,
-      "eval_recall": 0.8915711947626841,
-      "eval_runtime": 5.611,
-      "eval_samples_per_second": 71.11,
-      "eval_steps_per_second": 8.911,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8910359080340997,
+      "eval_loss": 0.29110613465309143,
+      "eval_precision": 0.8822647601476015,
+      "eval_recall": 0.9018912529550827,
+      "eval_runtime": 5.5858,
+      "eval_samples_per_second": 71.432,
+      "eval_steps_per_second": 8.951,
       "step": 1708
     },
     {
       "epoch": 15.0,
-      "grad_norm": 0.20924903452396393,
+      "grad_norm": 0.1758796125650406,
       "learning_rate": 1.25e-05,
-      "loss": 0.1447,
+      "loss": 0.1236,
       "step": 1830
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.9122807017543859,
-      "eval_f1": 0.8959675797283908,
-      "eval_loss": 0.2611282765865326,
-      "eval_precision": 0.8898680351906159,
-      "eval_recall": 0.9029368976177486,
-      "eval_runtime": 5.6134,
-      "eval_samples_per_second": 71.08,
-      "eval_steps_per_second": 8.907,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8817957385392532,
+      "eval_loss": 0.2955999970436096,
+      "eval_precision": 0.8827677592299257,
+      "eval_recall": 0.8808419712675032,
+      "eval_runtime": 5.6052,
+      "eval_samples_per_second": 71.184,
+      "eval_steps_per_second": 8.92,
       "step": 1830
     },
     {
       "epoch": 16.0,
-      "grad_norm": 0.40175938606262207,
+      "grad_norm": 0.7015694975852966,
       "learning_rate": 1e-05,
-      "loss": 0.1336,
+      "loss": 0.1304,
       "step": 1952
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.899749373433584,
-      "eval_f1": 0.884004884004884,
-      "eval_loss": 0.31003570556640625,
-      "eval_precision": 0.8717592592592593,
-      "eval_recall": 0.9015730132751409,
-      "eval_runtime": 5.6634,
-      "eval_samples_per_second": 70.453,
-      "eval_steps_per_second": 8.829,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.884617951284618,
+      "eval_loss": 0.3010990023612976,
+      "eval_precision": 0.8772893772893773,
+      "eval_recall": 0.8933442444080741,
+      "eval_runtime": 5.6368,
+      "eval_samples_per_second": 70.785,
+      "eval_steps_per_second": 8.87,
       "step": 1952
     },
     {
       "epoch": 17.0,
-      "grad_norm": 7.287301540374756,
+      "grad_norm": 0.19915825128555298,
       "learning_rate": 7.5e-06,
-      "loss": 0.1192,
+      "loss": 0.1164,
       "step": 2074
     },
     {
       "epoch": 17.0,
-      "eval_accuracy": 0.8972431077694235,
-      "eval_f1": 0.8803300634230913,
-      "eval_loss": 0.29346275329589844,
-      "eval_precision": 0.8695948246510044,
-      "eval_recall": 0.8947990543735225,
-      "eval_runtime": 5.5767,
-      "eval_samples_per_second": 71.548,
-      "eval_steps_per_second": 8.966,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.879667048676036,
+      "eval_loss": 0.29428762197494507,
+      "eval_precision": 0.8778361344537815,
+      "eval_recall": 0.8815693762502272,
+      "eval_runtime": 5.5793,
+      "eval_samples_per_second": 71.514,
+      "eval_steps_per_second": 8.962,
       "step": 2074
     },
     {
       "epoch": 18.0,
-      "grad_norm": 6.602230072021484,
+      "grad_norm": 9.03445816040039,
       "learning_rate": 5e-06,
-      "loss": 0.1247,
+      "loss": 0.1144,
       "step": 2196
     },
     {
       "epoch": 18.0,
-      "eval_accuracy": 0.9022556390977443,
-      "eval_f1": 0.885145957117024,
-      "eval_loss": 0.28685662150382996,
-      "eval_precision": 0.876513491697417,
-      "eval_recall": 0.8958446990361884,
-      "eval_runtime": 5.5755,
-      "eval_samples_per_second": 71.563,
-      "eval_steps_per_second": 8.968,
+      "eval_accuracy": 0.8972431077694235,
+      "eval_f1": 0.8775533117267087,
+      "eval_loss": 0.2937219738960266,
+      "eval_precision": 0.873246730188791,
+      "eval_recall": 0.8822967812329514,
+      "eval_runtime": 5.5648,
+      "eval_samples_per_second": 71.7,
+      "eval_steps_per_second": 8.985,
       "step": 2196
     },
     {
       "epoch": 19.0,
-      "grad_norm": 7.744582653045654,
+      "grad_norm": 5.45957612991333,
       "learning_rate": 2.5e-06,
-      "loss": 0.117,
+      "loss": 0.1198,
       "step": 2318
     },
     {
       "epoch": 19.0,
-      "eval_accuracy": 0.9022556390977443,
-      "eval_f1": 0.884617951284618,
-      "eval_loss": 0.2761416733264923,
-      "eval_precision": 0.8772893772893773,
-      "eval_recall": 0.8933442444080741,
-      "eval_runtime": 5.5884,
-      "eval_samples_per_second": 71.398,
-      "eval_steps_per_second": 8.947,
+      "eval_accuracy": 0.8972431077694235,
+      "eval_f1": 0.8737897035111135,
+      "eval_loss": 0.29848915338516235,
+      "eval_precision": 0.8812047813777917,
+      "eval_recall": 0.8672940534642661,
+      "eval_runtime": 5.5642,
+      "eval_samples_per_second": 71.709,
+      "eval_steps_per_second": 8.986,
       "step": 2318
     },
     {
       "epoch": 20.0,
-      "grad_norm": 0.1699504405260086,
+      "grad_norm": 3.5000033378601074,
       "learning_rate": 0.0,
-      "loss": 0.1092,
+      "loss": 0.1104,
       "step": 2440
     },
     {
       "epoch": 20.0,
       "eval_accuracy": 0.9022556390977443,
-      "eval_f1": 0.884617951284618,
-      "eval_loss": 0.2810901701450348,
-      "eval_precision": 0.8772893772893773,
-      "eval_recall": 0.8933442444080741,
-      "eval_runtime": 5.588,
-      "eval_samples_per_second": 71.403,
-      "eval_steps_per_second": 8.948,
+      "eval_f1": 0.8811928811928812,
+      "eval_loss": 0.29284632205963135,
+      "eval_precision": 0.8842105263157894,
+      "eval_recall": 0.878341516639389,
+      "eval_runtime": 5.5868,
+      "eval_samples_per_second": 71.418,
+      "eval_steps_per_second": 8.95,
       "step": 2440
     },
     {
       "epoch": 20.0,
       "step": 2440,
       "total_flos": 8551203605328000.0,
-      "train_loss": 0.21111928674041247,
-      "train_runtime": 2283.5364,
-      "train_samples_per_second": 31.863,
-      "train_steps_per_second": 1.069
+      "train_loss": 0.2130153269064231,
+      "train_runtime": 2280.4037,
+      "train_samples_per_second": 31.907,
+      "train_steps_per_second": 1.07
     }
   ],
   "logging_steps": 500,