End of training

README.md

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

all_results.json

@@ -0,0 +1,21 @@
+{
+    "accuracy": 0.8911968348170128,
+    "epoch": 20.0,
+    "eval_accuracy": 0.87468671679198,
+    "eval_f1": 0.8456742372671576,
+    "eval_loss": 0.2945931851863861,
+    "eval_precision": 0.8536697247706422,
+    "eval_recall": 0.8388343335151845,
+    "eval_runtime": 1.7572,
+    "eval_samples": 399,
+    "eval_samples_per_second": 227.061,
+    "eval_steps_per_second": 28.454,
+    "f1": 0.8670309436127983,
+    "precision": 0.8734567901234568,
+    "recall": 0.8613359752252041,
+    "train_loss": 0.3118248751906098,
+    "train_runtime": 625.8688,
+    "train_samples": 3638,
+    "train_samples_per_second": 116.254,
+    "train_steps_per_second": 3.899
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.87468671679198,
+    "eval_f1": 0.8456742372671576,
+    "eval_loss": 0.2945931851863861,
+    "eval_precision": 0.8536697247706422,
+    "eval_recall": 0.8388343335151845,
+    "eval_runtime": 1.7572,
+    "eval_samples": 399,
+    "eval_samples_per_second": 227.061,
+    "eval_steps_per_second": 28.454
+}

predict_results.json

@@ -0,0 +1,6 @@
+{
+    "accuracy": 0.8911968348170128,
+    "f1": 0.8670309436127983,
+    "precision": 0.8734567901234568,
+    "recall": 0.8613359752252041
+}

predict_results.txt

@@ -0,0 +1,1012 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	1
+5	0
+6	0
+7	1
+8	1
+9	1
+10	1
+11	1
+12	1
+13	1
+14	1
+15	1
+16	0
+17	1
+18	0
+19	0
+20	1
+21	1
+22	1
+23	1
+24	1
+25	1
+26	1
+27	1
+28	1
+29	1
+30	0
+31	0
+32	1
+33	1
+34	1
+35	1
+36	0
+37	1
+38	1
+39	0
+40	0
+41	1
+42	1
+43	1
+44	0
+45	1
+46	0
+47	1
+48	1
+49	1
+50	1
+51	1
+52	1
+53	1
+54	1
+55	1
+56	1
+57	0
+58	1
+59	1
+60	1
+61	1
+62	1
+63	1
+64	1
+65	1
+66	1
+67	1
+68	1
+69	0
+70	1
+71	0
+72	1
+73	0
+74	1
+75	1
+76	1
+77	0
+78	1
+79	1
+80	1
+81	1
+82	1
+83	1
+84	0
+85	1
+86	1
+87	0
+88	1
+89	1
+90	1
+91	0
+92	1
+93	1
+94	1
+95	1
+96	1
+97	1
+98	1
+99	1
+100	1
+101	1
+102	1
+103	1
+104	0
+105	0
+106	1
+107	0
+108	1
+109	1
+110	0
+111	1
+112	0
+113	0
+114	0
+115	1
+116	1
+117	0
+118	1
+119	1
+120	1
+121	0
+122	1
+123	0
+124	1
+125	0
+126	1
+127	1
+128	0
+129	1
+130	1
+131	1
+132	1
+133	1
+134	1
+135	1
+136	0
+137	1
+138	1
+139	1
+140	1
+141	1
+142	0
+143	1
+144	1
+145	1
+146	1
+147	1
+148	1
+149	1
+150	1
+151	0
+152	0
+153	1
+154	1
+155	1
+156	1
+157	1
+158	1
+159	1
+160	1
+161	1
+162	1
+163	1
+164	0
+165	1
+166	1
+167	1
+168	1
+169	1
+170	0
+171	1
+172	1
+173	0
+174	0
+175	1
+176	0
+177	0
+178	1
+179	1
+180	0
+181	0
+182	1
+183	1
+184	1
+185	1
+186	1
+187	1
+188	1
+189	1
+190	1
+191	1
+192	1
+193	1
+194	1
+195	1
+196	1
+197	0
+198	1
+199	1
+200	0
+201	1
+202	1
+203	0
+204	0
+205	1
+206	1
+207	1
+208	1
+209	1
+210	1
+211	1
+212	1
+213	1
+214	0
+215	0
+216	1
+217	0
+218	0
+219	0
+220	1
+221	1
+222	1
+223	1
+224	1
+225	1
+226	1
+227	1
+228	1
+229	1
+230	1
+231	1
+232	1
+233	1
+234	0
+235	0
+236	0
+237	1
+238	0
+239	0
+240	1
+241	1
+242	1
+243	1
+244	1
+245	1
+246	1
+247	1
+248	1
+249	1
+250	1
+251	1
+252	1
+253	1
+254	1
+255	1
+256	1
+257	1
+258	1
+259	1
+260	0
+261	1
+262	1
+263	1
+264	1
+265	0
+266	0
+267	1
+268	1
+269	1
+270	1
+271	1
+272	1
+273	1
+274	1
+275	0
+276	1
+277	1
+278	1
+279	1
+280	1
+281	1
+282	1
+283	1
+284	1
+285	1
+286	0
+287	1
+288	1
+289	1
+290	1
+291	1
+292	1
+293	1
+294	1
+295	1
+296	1
+297	1
+298	1
+299	0
+300	0
+301	0
+302	0
+303	0
+304	0
+305	0
+306	0
+307	0
+308	0
+309	0
+310	0
+311	0
+312	0
+313	0
+314	0
+315	0
+316	0
+317	0
+318	0
+319	0
+320	0
+321	0
+322	0
+323	0
+324	0
+325	0
+326	0
+327	0
+328	0
+329	0
+330	0
+331	0
+332	0
+333	0
+334	0
+335	0
+336	0
+337	0
+338	0
+339	0
+340	0
+341	0
+342	1
+343	0
+344	0
+345	1
+346	0
+347	0
+348	0
+349	0
+350	0
+351	0
+352	0
+353	0
+354	0
+355	0
+356	0
+357	0
+358	0
+359	0
+360	0
+361	0
+362	0
+363	0
+364	0
+365	0
+366	1
+367	0
+368	0
+369	0
+370	0
+371	0
+372	0
+373	0
+374	0
+375	0
+376	0
+377	0
+378	0
+379	1
+380	0
+381	0
+382	0
+383	0
+384	0
+385	0
+386	0
+387	0
+388	0
+389	1
+390	0
+391	0
+392	0
+393	0
+394	0
+395	0
+396	0
+397	0
+398	0
+399	0
+400	0
+401	0
+402	0
+403	0
+404	0
+405	0
+406	0
+407	0
+408	0
+409	1
+410	0
+411	0
+412	0
+413	1
+414	0
+415	0
+416	0
+417	1
+418	0
+419	0
+420	0
+421	0
+422	0
+423	1
+424	0
+425	0
+426	0
+427	0
+428	0
+429	0
+430	0
+431	0
+432	0
+433	0
+434	0
+435	0
+436	0
+437	0
+438	0
+439	0
+440	0
+441	1
+442	0
+443	0
+444	0
+445	0
+446	0
+447	0
+448	0
+449	0
+450	0
+451	0
+452	1
+453	0
+454	1
+455	0
+456	0
+457	0
+458	0
+459	0
+460	0
+461	0
+462	0
+463	0
+464	0
+465	0
+466	0
+467	0
+468	0
+469	0
+470	0
+471	0
+472	0
+473	0
+474	0
+475	0
+476	0
+477	0
+478	1
+479	0
+480	0
+481	0
+482	0
+483	0
+484	0
+485	0
+486	0
+487	0
+488	0
+489	0
+490	0
+491	0
+492	0
+493	0
+494	0
+495	0
+496	0
+497	0
+498	1
+499	0
+500	0
+501	1
+502	0
+503	0
+504	0
+505	0
+506	0
+507	0
+508	1
+509	0
+510	0
+511	0
+512	0
+513	0
+514	0
+515	0
+516	0
+517	0
+518	0
+519	0
+520	0
+521	0
+522	0
+523	0
+524	0
+525	0
+526	1
+527	0
+528	0
+529	0
+530	0
+531	0
+532	0
+533	1
+534	0
+535	0
+536	0
+537	0
+538	0
+539	0
+540	0
+541	0
+542	0
+543	0
+544	0
+545	0
+546	0
+547	0
+548	0
+549	0
+550	0
+551	0
+552	1
+553	0
+554	0
+555	0
+556	0
+557	0
+558	0
+559	0
+560	0
+561	0
+562	1
+563	0
+564	0
+565	0
+566	0
+567	0
+568	0
+569	0
+570	0
+571	0
+572	0
+573	0
+574	0
+575	0
+576	0
+577	0
+578	0
+579	0
+580	0
+581	0
+582	0
+583	0
+584	0
+585	0
+586	0
+587	0
+588	0
+589	0
+590	0
+591	0
+592	0
+593	0
+594	0
+595	0
+596	0
+597	0
+598	0
+599	0
+600	0
+601	0
+602	0
+603	1
+604	0
+605	0
+606	0
+607	0
+608	0
+609	0
+610	0
+611	0
+612	0
+613	0
+614	0
+615	0
+616	0
+617	0
+618	0
+619	0
+620	0
+621	0
+622	0
+623	0
+624	0
+625	0
+626	0
+627	0
+628	0
+629	0
+630	0
+631	0
+632	0
+633	0
+634	0
+635	0
+636	0
+637	0
+638	0
+639	0
+640	0
+641	0
+642	0
+643	0
+644	0
+645	0
+646	0
+647	0
+648	0
+649	0
+650	0
+651	0
+652	0
+653	0
+654	0
+655	0
+656	0
+657	0
+658	0
+659	0
+660	0
+661	0
+662	0
+663	1
+664	0
+665	0
+666	0
+667	0
+668	0
+669	0
+670	0
+671	0
+672	0
+673	0
+674	0
+675	0
+676	0
+677	0
+678	0
+679	0
+680	0
+681	0
+682	0
+683	0
+684	0
+685	0
+686	0
+687	0
+688	0
+689	0
+690	0
+691	0
+692	0
+693	0
+694	0
+695	0
+696	0
+697	0
+698	0
+699	0
+700	0
+701	0
+702	0
+703	0
+704	0
+705	0
+706	1
+707	0
+708	0
+709	0
+710	0
+711	0
+712	0
+713	0
+714	0
+715	0
+716	0
+717	0
+718	0
+719	0
+720	0
+721	1
+722	0
+723	0
+724	0
+725	0
+726	0
+727	0
+728	0
+729	0
+730	0
+731	0
+732	0
+733	0
+734	0
+735	0
+736	0
+737	0
+738	0
+739	0
+740	0
+741	0
+742	0
+743	0
+744	0
+745	0
+746	0
+747	0
+748	0
+749	0
+750	0
+751	0
+752	0
+753	0
+754	0
+755	1
+756	0
+757	0
+758	0
+759	0
+760	0
+761	0
+762	0
+763	0
+764	0
+765	0
+766	0
+767	0
+768	0
+769	0
+770	0
+771	0
+772	0
+773	0
+774	0
+775	0
+776	0
+777	0
+778	0
+779	0
+780	1
+781	0
+782	0
+783	1
+784	0
+785	0
+786	0
+787	0
+788	0
+789	0
+790	0
+791	0
+792	0
+793	0
+794	0
+795	0
+796	0
+797	0
+798	0
+799	0
+800	0
+801	0
+802	0
+803	0
+804	0
+805	0
+806	0
+807	0
+808	0
+809	0
+810	0
+811	0
+812	0
+813	0
+814	0
+815	0
+816	0
+817	0
+818	0
+819	0
+820	0
+821	0
+822	0
+823	0
+824	0
+825	0
+826	0
+827	0
+828	0
+829	0
+830	0
+831	0
+832	0
+833	0
+834	0
+835	0
+836	0
+837	0
+838	0
+839	0
+840	0
+841	0
+842	1
+843	0
+844	0
+845	0
+846	0
+847	0
+848	0
+849	0
+850	0
+851	0
+852	0
+853	0
+854	0
+855	0
+856	0
+857	0
+858	0
+859	0
+860	0
+861	0
+862	0
+863	0
+864	0
+865	0
+866	0
+867	1
+868	0
+869	0
+870	0
+871	0
+872	1
+873	0
+874	0
+875	0
+876	0
+877	0
+878	0
+879	0
+880	0
+881	0
+882	0
+883	0
+884	0
+885	0
+886	0
+887	0
+888	0
+889	0
+890	1
+891	0
+892	0
+893	0
+894	0
+895	0
+896	0
+897	0
+898	0
+899	1
+900	0
+901	0
+902	0
+903	0
+904	0
+905	0
+906	0
+907	0
+908	0
+909	0
+910	1
+911	0
+912	0
+913	0
+914	0
+915	0
+916	0
+917	0
+918	0
+919	0
+920	0
+921	0
+922	0
+923	0
+924	0
+925	1
+926	0
+927	0
+928	0
+929	0
+930	0
+931	0
+932	0
+933	1
+934	0
+935	0
+936	0
+937	1
+938	0
+939	0
+940	1
+941	0
+942	0
+943	0
+944	0
+945	0
+946	0
+947	0
+948	0
+949	0
+950	0
+951	0
+952	1
+953	1
+954	0
+955	0
+956	0
+957	0
+958	0
+959	0
+960	0
+961	0
+962	1
+963	0
+964	0
+965	0
+966	1
+967	0
+968	0
+969	1
+970	0
+971	0
+972	0
+973	0
+974	0
+975	0
+976	1
+977	0
+978	0
+979	0
+980	1
+981	0
+982	0
+983	0
+984	0
+985	1
+986	1
+987	0
+988	0
+989	0
+990	0
+991	0
+992	0
+993	0
+994	0
+995	0
+996	0
+997	0
+998	0
+999	0
+1000	0
+1001	0
+1002	0
+1003	0
+1004	0
+1005	0
+1006	0
+1007	0
+1008	0
+1009	0
+1010	0

runs/Jun03_11-53-56_a358b85c7679/events.out.tfevents.1717416279.a358b85c7679.62335.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518e7f65c430be25cf3d6590d0d7247c82caa39a6235ae8e3094635315c805cd
+size 560

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.3118248751906098,
+    "train_runtime": 625.8688,
+    "train_samples": 3638,
+    "train_samples_per_second": 116.254,
+    "train_steps_per_second": 3.899
+}

trainer_state.json

@@ -0,0 +1,410 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 2440,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.055661201477051,
+      "learning_rate": 4.75e-05,
+      "loss": 0.5556,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7268170426065163,
+      "eval_f1": 0.6351456783080679,
+      "eval_loss": 0.5150498151779175,
+      "eval_precision": 0.660825575132723,
+      "eval_recall": 0.6267048554282597,
+      "eval_runtime": 1.7164,
+      "eval_samples_per_second": 232.466,
+      "eval_steps_per_second": 29.131,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.175451755523682,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4868,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7844611528822055,
+      "eval_f1": 0.7495328467153285,
+      "eval_loss": 0.47025182843208313,
+      "eval_precision": 0.7424812030075187,
+      "eval_recall": 0.7600018185124569,
+      "eval_runtime": 1.7481,
+      "eval_samples_per_second": 228.245,
+      "eval_steps_per_second": 28.602,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.4971930980682373,
+      "learning_rate": 4.25e-05,
+      "loss": 0.4308,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8195488721804511,
+      "eval_f1": 0.7893841642228739,
+      "eval_loss": 0.4005482494831085,
+      "eval_precision": 0.7817733849834796,
+      "eval_recall": 0.799827241316603,
+      "eval_runtime": 1.7244,
+      "eval_samples_per_second": 231.38,
+      "eval_steps_per_second": 28.995,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.280220031738281,
+      "learning_rate": 4e-05,
+      "loss": 0.3892,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8220551378446115,
+      "eval_f1": 0.7927666951960849,
+      "eval_loss": 0.38431689143180847,
+      "eval_precision": 0.7846867551923731,
+      "eval_recall": 0.8041007455901072,
+      "eval_runtime": 1.728,
+      "eval_samples_per_second": 230.903,
+      "eval_steps_per_second": 28.935,
+      "step": 488
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.974445819854736,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.3615,
+      "step": 610
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8521303258145363,
+      "eval_f1": 0.8254476698921143,
+      "eval_loss": 0.35448285937309265,
+      "eval_precision": 0.8192918192918193,
+      "eval_recall": 0.8328787052191308,
+      "eval_runtime": 1.7302,
+      "eval_samples_per_second": 230.604,
+      "eval_steps_per_second": 28.898,
+      "step": 610
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.594826698303223,
+      "learning_rate": 3.5e-05,
+      "loss": 0.3255,
+      "step": 732
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8596491228070176,
+      "eval_f1": 0.8323529411764705,
+      "eval_loss": 0.3457643389701843,
+      "eval_precision": 0.8292704679231822,
+      "eval_recall": 0.8356973995271868,
+      "eval_runtime": 1.7308,
+      "eval_samples_per_second": 230.527,
+      "eval_steps_per_second": 28.888,
+      "step": 732
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.2065014839172363,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.3142,
+      "step": 854
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8596491228070176,
+      "eval_f1": 0.8289650949173301,
+      "eval_loss": 0.3296651840209961,
+      "eval_precision": 0.8325081997648369,
+      "eval_recall": 0.82569558101473,
+      "eval_runtime": 1.7337,
+      "eval_samples_per_second": 230.143,
+      "eval_steps_per_second": 28.84,
+      "step": 854
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.79945707321167,
+      "learning_rate": 3e-05,
+      "loss": 0.3002,
+      "step": 976
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8646616541353384,
+      "eval_f1": 0.8315033783783784,
+      "eval_loss": 0.32283803820610046,
+      "eval_precision": 0.8438775510204082,
+      "eval_recall": 0.8217403164211674,
+      "eval_runtime": 1.7335,
+      "eval_samples_per_second": 230.167,
+      "eval_steps_per_second": 28.843,
+      "step": 976
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 7.0031962394714355,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.2872,
+      "step": 1098
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8696741854636592,
+      "eval_f1": 0.842789598108747,
+      "eval_loss": 0.3236847221851349,
+      "eval_precision": 0.842789598108747,
+      "eval_recall": 0.842789598108747,
+      "eval_runtime": 1.7323,
+      "eval_samples_per_second": 230.33,
+      "eval_steps_per_second": 28.863,
+      "step": 1098
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 8.21018123626709,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2794,
+      "step": 1220
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8461962888779714,
+      "eval_loss": 0.3075161576271057,
+      "eval_precision": 0.8453465227094517,
+      "eval_recall": 0.8470631023822512,
+      "eval_runtime": 1.7347,
+      "eval_samples_per_second": 230.013,
+      "eval_steps_per_second": 28.824,
+      "step": 1220
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 11.819586753845215,
+      "learning_rate": 2.25e-05,
+      "loss": 0.2698,
+      "step": 1342
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8464912280701754,
+      "eval_loss": 0.305667906999588,
+      "eval_precision": 0.8522897897897899,
+      "eval_recall": 0.8413347881432988,
+      "eval_runtime": 1.7337,
+      "eval_samples_per_second": 230.142,
+      "eval_steps_per_second": 28.84,
+      "step": 1342
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 17.956451416015625,
+      "learning_rate": 2e-05,
+      "loss": 0.2685,
+      "step": 1464
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8456742372671576,
+      "eval_loss": 0.3076314628124237,
+      "eval_precision": 0.8536697247706422,
+      "eval_recall": 0.8388343335151845,
+      "eval_runtime": 1.7313,
+      "eval_samples_per_second": 230.463,
+      "eval_steps_per_second": 28.88,
+      "step": 1464
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 2.3994736671447754,
+      "learning_rate": 1.75e-05,
+      "loss": 0.2585,
+      "step": 1586
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8430067043674827,
+      "eval_loss": 0.30824607610702515,
+      "eval_precision": 0.8498269896193772,
+      "eval_recall": 0.8370612838697945,
+      "eval_runtime": 1.7388,
+      "eval_samples_per_second": 229.463,
+      "eval_steps_per_second": 28.755,
+      "step": 1586
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 12.113729476928711,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2548,
+      "step": 1708
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8822055137844611,
+      "eval_f1": 0.8589543987905864,
+      "eval_loss": 0.2982984185218811,
+      "eval_precision": 0.8564068100358423,
+      "eval_recall": 0.8616566648481543,
+      "eval_runtime": 1.7324,
+      "eval_samples_per_second": 230.317,
+      "eval_steps_per_second": 28.862,
+      "step": 1708
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 4.383078575134277,
+      "learning_rate": 1.25e-05,
+      "loss": 0.2391,
+      "step": 1830
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.8721804511278195,
+      "eval_f1": 0.8430067043674827,
+      "eval_loss": 0.29739707708358765,
+      "eval_precision": 0.8498269896193772,
+      "eval_recall": 0.8370612838697945,
+      "eval_runtime": 1.7343,
+      "eval_samples_per_second": 230.06,
+      "eval_steps_per_second": 28.83,
+      "step": 1830
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 3.95792818069458,
+      "learning_rate": 1e-05,
+      "loss": 0.2476,
+      "step": 1952
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8495838108450449,
+      "eval_loss": 0.2973519563674927,
+      "eval_precision": 0.8478991596638655,
+      "eval_recall": 0.8513366066557555,
+      "eval_runtime": 1.7333,
+      "eval_samples_per_second": 230.195,
+      "eval_steps_per_second": 28.846,
+      "step": 1952
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 2.338597059249878,
+      "learning_rate": 7.5e-06,
+      "loss": 0.243,
+      "step": 2074
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8448388501742161,
+      "eval_loss": 0.2962024509906769,
+      "eval_precision": 0.8551721930610677,
+      "eval_recall": 0.8363338788870704,
+      "eval_runtime": 1.7332,
+      "eval_samples_per_second": 230.215,
+      "eval_steps_per_second": 28.849,
+      "step": 2074
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 5.178797721862793,
+      "learning_rate": 5e-06,
+      "loss": 0.242,
+      "step": 2196
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8796992481203008,
+      "eval_f1": 0.8541488972828073,
+      "eval_loss": 0.2951340973377228,
+      "eval_precision": 0.8559859154929578,
+      "eval_recall": 0.8523822513184216,
+      "eval_runtime": 1.7361,
+      "eval_samples_per_second": 229.826,
+      "eval_steps_per_second": 28.8,
+      "step": 2196
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 3.4869022369384766,
+      "learning_rate": 2.5e-06,
+      "loss": 0.2425,
+      "step": 2318
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8456742372671576,
+      "eval_loss": 0.2940848469734192,
+      "eval_precision": 0.8536697247706422,
+      "eval_recall": 0.8388343335151845,
+      "eval_runtime": 1.7338,
+      "eval_samples_per_second": 230.127,
+      "eval_steps_per_second": 28.838,
+      "step": 2318
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 3.7974979877471924,
+      "learning_rate": 0.0,
+      "loss": 0.2403,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8456742372671576,
+      "eval_loss": 0.2945931851863861,
+      "eval_precision": 0.8536697247706422,
+      "eval_recall": 0.8388343335151845,
+      "eval_runtime": 1.7317,
+      "eval_samples_per_second": 230.406,
+      "eval_steps_per_second": 28.873,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "step": 2440,
+      "total_flos": 7635661149264000.0,
+      "train_loss": 0.3118248751906098,
+      "train_runtime": 625.8688,
+      "train_samples_per_second": 116.254,
+      "train_steps_per_second": 3.899
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 7635661149264000.0,
+  "train_batch_size": 30,
+  "trial_name": null,
+  "trial_params": null
+}