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 +1,22 @@
+{
+    "accuracy": 0.9090009891196835,
+    "epoch": 20.0,
+    "eval_accuracy": 0.9022556390977443,
+    "eval_f1": 0.8817957385392532,
+    "eval_loss": 0.2682853937149048,
+    "eval_precision": 0.8827677592299257,
+    "eval_recall": 0.8808419712675032,
+    "eval_runtime": 1.7941,
+    "eval_samples": 399,
+    "eval_samples_per_second": 222.401,
+    "eval_steps_per_second": 27.87,
+    "f1": 0.8926077478709058,
+    "precision": 0.8859756595605652,
+    "recall": 0.9003266281992149,
+    "total_flos": 8444128359504000.0,
+    "train_loss": 0.22609603365913766,
+    "train_runtime": 618.465,
+    "train_samples": 3638,
+    "train_samples_per_second": 117.646,
+    "train_steps_per_second": 3.945
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.9022556390977443,
+    "eval_f1": 0.8817957385392532,
+    "eval_loss": 0.2682853937149048,
+    "eval_precision": 0.8827677592299257,
+    "eval_recall": 0.8808419712675032,
+    "eval_runtime": 1.7941,
+    "eval_samples": 399,
+    "eval_samples_per_second": 222.401,
+    "eval_steps_per_second": 27.87
+}

predict_results.json

@@ -0,0 +1,6 @@
+{
+    "accuracy": 0.9090009891196835,
+    "f1": 0.8926077478709058,
+    "precision": 0.8859756595605652,
+    "recall": 0.9003266281992149
+}

predict_results.txt

@@ -0,0 +1,1012 @@
+index	prediction
+0	1
+1	1
+2	1
+3	1
+4	1
+5	1
+6	1
+7	1
+8	0
+9	1
+10	1
+11	1
+12	1
+13	0
+14	1
+15	1
+16	1
+17	1
+18	1
+19	1
+20	1
+21	0
+22	1
+23	1
+24	1
+25	1
+26	1
+27	1
+28	1
+29	1
+30	1
+31	0
+32	1
+33	1
+34	1
+35	1
+36	1
+37	0
+38	1
+39	1
+40	1
+41	1
+42	1
+43	1
+44	1
+45	1
+46	1
+47	0
+48	1
+49	1
+50	1
+51	1
+52	0
+53	0
+54	1
+55	1
+56	1
+57	1
+58	1
+59	1
+60	1
+61	1
+62	0
+63	1
+64	1
+65	0
+66	1
+67	1
+68	1
+69	1
+70	1
+71	1
+72	1
+73	1
+74	1
+75	1
+76	0
+77	1
+78	0
+79	1
+80	1
+81	1
+82	1
+83	1
+84	1
+85	1
+86	1
+87	1
+88	1
+89	1
+90	1
+91	1
+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	1
+105	0
+106	1
+107	1
+108	1
+109	0
+110	1
+111	1
+112	1
+113	1
+114	1
+115	1
+116	1
+117	0
+118	1
+119	1
+120	1
+121	1
+122	1
+123	1
+124	1
+125	1
+126	1
+127	1
+128	1
+129	1
+130	1
+131	1
+132	1
+133	1
+134	1
+135	1
+136	1
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	1
+144	1
+145	1
+146	1
+147	1
+148	1
+149	1
+150	1
+151	1
+152	1
+153	1
+154	1
+155	1
+156	0
+157	1
+158	1
+159	1
+160	1
+161	0
+162	1
+163	0
+164	1
+165	1
+166	1
+167	0
+168	1
+169	1
+170	1
+171	1
+172	1
+173	1
+174	1
+175	1
+176	1
+177	1
+178	1
+179	1
+180	0
+181	1
+182	0
+183	1
+184	1
+185	1
+186	1
+187	1
+188	1
+189	0
+190	0
+191	1
+192	1
+193	1
+194	1
+195	1
+196	1
+197	0
+198	1
+199	1
+200	1
+201	1
+202	1
+203	1
+204	1
+205	1
+206	0
+207	1
+208	1
+209	1
+210	1
+211	1
+212	0
+213	1
+214	0
+215	0
+216	1
+217	0
+218	0
+219	1
+220	1
+221	1
+222	1
+223	0
+224	1
+225	1
+226	1
+227	0
+228	1
+229	1
+230	1
+231	1
+232	1
+233	1
+234	1
+235	1
+236	1
+237	1
+238	1
+239	1
+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	0
+253	1
+254	1
+255	1
+256	1
+257	1
+258	1
+259	1
+260	1
+261	1
+262	1
+263	1
+264	1
+265	1
+266	1
+267	1
+268	1
+269	1
+270	1
+271	0
+272	1
+273	1
+274	1
+275	1
+276	1
+277	1
+278	1
+279	1
+280	1
+281	1
+282	0
+283	1
+284	0
+285	1
+286	1
+287	1
+288	1
+289	1
+290	1
+291	1
+292	1
+293	1
+294	1
+295	1
+296	1
+297	1
+298	0
+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	1
+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	1
+340	0
+341	0
+342	0
+343	0
+344	0
+345	0
+346	1
+347	0
+348	0
+349	0
+350	0
+351	0
+352	0
+353	0
+354	0
+355	0
+356	0
+357	1
+358	0
+359	0
+360	0
+361	0
+362	0
+363	0
+364	0
+365	0
+366	0
+367	0
+368	1
+369	0
+370	0
+371	0
+372	1
+373	0
+374	0
+375	0
+376	0
+377	0
+378	1
+379	0
+380	0
+381	0
+382	0
+383	0
+384	1
+385	0
+386	0
+387	0
+388	0
+389	0
+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	0
+410	0
+411	0
+412	0
+413	0
+414	0
+415	0
+416	0
+417	0
+418	0
+419	0
+420	0
+421	0
+422	0
+423	0
+424	0
+425	0
+426	0
+427	0
+428	0
+429	0
+430	0
+431	0
+432	0
+433	0
+434	0
+435	1
+436	0
+437	0
+438	0
+439	0
+440	0
+441	0
+442	1
+443	0
+444	0
+445	0
+446	0
+447	0
+448	0
+449	0
+450	0
+451	0
+452	0
+453	0
+454	0
+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	1
+474	1
+475	0
+476	1
+477	0
+478	0
+479	1
+480	1
+481	0
+482	0
+483	0
+484	0
+485	0
+486	1
+487	0
+488	0
+489	0
+490	1
+491	0
+492	0
+493	0
+494	0
+495	0
+496	0
+497	0
+498	0
+499	0
+500	0
+501	0
+502	0
+503	0
+504	0
+505	0
+506	1
+507	0
+508	0
+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	0
+527	0
+528	0
+529	0
+530	0
+531	0
+532	0
+533	0
+534	1
+535	0
+536	0
+537	0
+538	0
+539	1
+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	0
+553	0
+554	0
+555	0
+556	0
+557	0
+558	0
+559	0
+560	0
+561	0
+562	0
+563	0
+564	0
+565	1
+566	0
+567	1
+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	1
+598	0
+599	0
+600	0
+601	0
+602	1
+603	0
+604	0
+605	1
+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	1
+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	0
+664	0
+665	0
+666	0
+667	0
+668	0
+669	0
+670	0
+671	0
+672	0
+673	0
+674	1
+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	1
+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	0
+707	0
+708	0
+709	0
+710	0
+711	0
+712	0
+713	0
+714	1
+715	0
+716	0
+717	0
+718	0
+719	0
+720	0
+721	0
+722	0
+723	0
+724	0
+725	0
+726	0
+727	0
+728	1
+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	1
+748	0
+749	0
+750	0
+751	0
+752	0
+753	0
+754	0
+755	0
+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	0
+781	0
+782	0
+783	0
+784	0
+785	1
+786	0
+787	0
+788	0
+789	0
+790	0
+791	0
+792	0
+793	0
+794	0
+795	1
+796	0
+797	0
+798	1
+799	0
+800	0
+801	0
+802	1
+803	0
+804	0
+805	0
+806	0
+807	0
+808	0
+809	1
+810	1
+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	1
+829	0
+830	0
+831	1
+832	1
+833	0
+834	0
+835	0
+836	0
+837	0
+838	1
+839	0
+840	0
+841	0
+842	0
+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	1
+861	0
+862	0
+863	0
+864	0
+865	0
+866	1
+867	0
+868	0
+869	0
+870	0
+871	0
+872	0
+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	0
+891	1
+892	0
+893	0
+894	0
+895	0
+896	0
+897	0
+898	0
+899	0
+900	0
+901	0
+902	0
+903	0
+904	0
+905	0
+906	0
+907	0
+908	0
+909	0
+910	0
+911	0
+912	1
+913	1
+914	0
+915	0
+916	0
+917	0
+918	0
+919	0
+920	0
+921	1
+922	0
+923	0
+924	0
+925	0
+926	1
+927	0
+928	0
+929	1
+930	0
+931	0
+932	0
+933	0
+934	0
+935	0
+936	0
+937	0
+938	0
+939	0
+940	0
+941	0
+942	0
+943	0
+944	0
+945	1
+946	0
+947	1
+948	0
+949	0
+950	0
+951	0
+952	0
+953	0
+954	0
+955	0
+956	0
+957	0
+958	0
+959	0
+960	0
+961	1
+962	0
+963	0
+964	0
+965	0
+966	0
+967	1
+968	0
+969	0
+970	0
+971	0
+972	0
+973	0
+974	1
+975	0
+976	0
+977	1
+978	0
+979	0
+980	0
+981	0
+982	0
+983	0
+984	0
+985	0
+986	0
+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	1
+1000	0
+1001	0
+1002	0
+1003	0
+1004	0
+1005	0
+1006	0
+1007	0
+1008	0
+1009	0
+1010	0

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "total_flos": 8444128359504000.0,
+    "train_loss": 0.22609603365913766,
+    "train_runtime": 618.465,
+    "train_samples": 3638,
+    "train_samples_per_second": 117.646,
+    "train_steps_per_second": 3.945
+}

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": 4.800751686096191,
+      "learning_rate": 4.75e-05,
+      "loss": 0.5455,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7543859649122807,
+      "eval_f1": 0.6639335808580858,
+      "eval_loss": 0.48765844106674194,
+      "eval_precision": 0.7053086419753087,
+      "eval_recall": 0.6512093107837789,
+      "eval_runtime": 1.7695,
+      "eval_samples_per_second": 225.487,
+      "eval_steps_per_second": 28.257,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.828364849090576,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4356,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8446115288220551,
+      "eval_f1": 0.8209674617878647,
+      "eval_loss": 0.35374370217323303,
+      "eval_precision": 0.810288627625787,
+      "eval_recall": 0.8375613747954174,
+      "eval_runtime": 1.7671,
+      "eval_samples_per_second": 225.791,
+      "eval_steps_per_second": 28.295,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.537293910980225,
+      "learning_rate": 4.25e-05,
+      "loss": 0.3468,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.849624060150376,
+      "eval_f1": 0.8072960267885891,
+      "eval_loss": 0.3415985107421875,
+      "eval_precision": 0.8325657894736842,
+      "eval_recall": 0.7910983815239134,
+      "eval_runtime": 1.7644,
+      "eval_samples_per_second": 226.134,
+      "eval_steps_per_second": 28.338,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.427431106567383,
+      "learning_rate": 4e-05,
+      "loss": 0.3049,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8546365914786967,
+      "eval_f1": 0.8180088078011953,
+      "eval_loss": 0.3125925660133362,
+      "eval_precision": 0.8323930726843348,
+      "eval_recall": 0.8071467539552646,
+      "eval_runtime": 1.7656,
+      "eval_samples_per_second": 225.985,
+      "eval_steps_per_second": 28.319,
+      "step": 488
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.060295820236206,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.2673,
+      "step": 610
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8596491228070176,
+      "eval_f1": 0.8315338681464504,
+      "eval_loss": 0.29185813665390015,
+      "eval_precision": 0.8299369747899159,
+      "eval_recall": 0.8331969448990726,
+      "eval_runtime": 1.7632,
+      "eval_samples_per_second": 226.299,
+      "eval_steps_per_second": 28.358,
+      "step": 610
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.6104700565338135,
+      "learning_rate": 3.5e-05,
+      "loss": 0.2516,
+      "step": 732
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8646616541353384,
+      "eval_f1": 0.8350734843845683,
+      "eval_loss": 0.2822675108909607,
+      "eval_precision": 0.8386812302741506,
+      "eval_recall": 0.8317421349336243,
+      "eval_runtime": 1.761,
+      "eval_samples_per_second": 226.577,
+      "eval_steps_per_second": 28.393,
+      "step": 732
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.407837837934494,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.2243,
+      "step": 854
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8822055137844611,
+      "eval_f1": 0.8622085718274466,
+      "eval_loss": 0.26883605122566223,
+      "eval_precision": 0.8530168716042322,
+      "eval_recall": 0.8741589379887251,
+      "eval_runtime": 1.7626,
+      "eval_samples_per_second": 226.37,
+      "eval_steps_per_second": 28.367,
+      "step": 854
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.6773055791854858,
+      "learning_rate": 3e-05,
+      "loss": 0.2157,
+      "step": 976
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8947368421052632,
+      "eval_f1": 0.8696646341463414,
+      "eval_loss": 0.2641172409057617,
+      "eval_precision": 0.8807130969146075,
+      "eval_recall": 0.8605200945626478,
+      "eval_runtime": 1.7614,
+      "eval_samples_per_second": 226.526,
+      "eval_steps_per_second": 28.387,
+      "step": 976
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.9705936908721924,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.2052,
+      "step": 1098
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8847117794486216,
+      "eval_f1": 0.8572517421602788,
+      "eval_loss": 0.26267343759536743,
+      "eval_precision": 0.8679426449878376,
+      "eval_recall": 0.8484269867248591,
+      "eval_runtime": 1.7598,
+      "eval_samples_per_second": 226.73,
+      "eval_steps_per_second": 28.412,
+      "step": 1098
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 13.646815299987793,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1864,
+      "step": 1220
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8847117794486216,
+      "eval_f1": 0.8548402404302435,
+      "eval_loss": 0.288084477186203,
+      "eval_precision": 0.8737291514386338,
+      "eval_recall": 0.8409256228405164,
+      "eval_runtime": 1.7593,
+      "eval_samples_per_second": 226.79,
+      "eval_steps_per_second": 28.42,
+      "step": 1220
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 4.454102039337158,
+      "learning_rate": 2.25e-05,
+      "loss": 0.1928,
+      "step": 1342
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8872180451127819,
+      "eval_f1": 0.867476104365797,
+      "eval_loss": 0.2784619927406311,
+      "eval_precision": 0.8592596863468634,
+      "eval_recall": 0.8777050372795053,
+      "eval_runtime": 1.7608,
+      "eval_samples_per_second": 226.608,
+      "eval_steps_per_second": 28.397,
+      "step": 1342
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 4.11415958404541,
+      "learning_rate": 2e-05,
+      "loss": 0.1804,
+      "step": 1464
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8758710801393728,
+      "eval_loss": 0.2506408393383026,
+      "eval_precision": 0.8870983228779925,
+      "eval_recall": 0.8665666484815421,
+      "eval_runtime": 1.7598,
+      "eval_samples_per_second": 226.734,
+      "eval_steps_per_second": 28.413,
+      "step": 1464
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 1.9822263717651367,
+      "learning_rate": 1.75e-05,
+      "loss": 0.1654,
+      "step": 1586
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8790689216221131,
+      "eval_loss": 0.26640743017196655,
+      "eval_precision": 0.8790689216221131,
+      "eval_recall": 0.8790689216221131,
+      "eval_runtime": 1.7621,
+      "eval_samples_per_second": 226.429,
+      "eval_steps_per_second": 28.375,
+      "step": 1586
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 4.247542381286621,
+      "learning_rate": 1.5e-05,
+      "loss": 0.1567,
+      "step": 1708
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8878351186601172,
+      "eval_loss": 0.2660583257675171,
+      "eval_precision": 0.879776516905975,
+      "eval_recall": 0.8976177486815784,
+      "eval_runtime": 1.7643,
+      "eval_samples_per_second": 226.146,
+      "eval_steps_per_second": 28.339,
+      "step": 1708
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.1535786390304565,
+      "learning_rate": 1.25e-05,
+      "loss": 0.1438,
+      "step": 1830
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9097744360902256,
+      "eval_f1": 0.8917003438084323,
+      "eval_loss": 0.2614538073539734,
+      "eval_precision": 0.8898109243697478,
+      "eval_recall": 0.893662484088016,
+      "eval_runtime": 1.7625,
+      "eval_samples_per_second": 226.385,
+      "eval_steps_per_second": 28.369,
+      "step": 1830
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.5205868482589722,
+      "learning_rate": 1e-05,
+      "loss": 0.1472,
+      "step": 1952
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8856836962422341,
+      "eval_loss": 0.25552284717559814,
+      "eval_precision": 0.8838235294117647,
+      "eval_recall": 0.8876159301691217,
+      "eval_runtime": 1.7611,
+      "eval_samples_per_second": 226.564,
+      "eval_steps_per_second": 28.392,
+      "step": 1952
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 6.205023288726807,
+      "learning_rate": 7.5e-06,
+      "loss": 0.1394,
+      "step": 2074
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8790689216221131,
+      "eval_loss": 0.2647987902164459,
+      "eval_precision": 0.8790689216221131,
+      "eval_recall": 0.8790689216221131,
+      "eval_runtime": 1.7605,
+      "eval_samples_per_second": 226.638,
+      "eval_steps_per_second": 28.401,
+      "step": 2074
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.5985056161880493,
+      "learning_rate": 5e-06,
+      "loss": 0.1387,
+      "step": 2196
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8862394957983193,
+      "eval_loss": 0.26299694180488586,
+      "eval_precision": 0.8826476009275225,
+      "eval_recall": 0.8901163847972358,
+      "eval_runtime": 1.7607,
+      "eval_samples_per_second": 226.62,
+      "eval_steps_per_second": 28.399,
+      "step": 2196
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 1.7635153532028198,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1378,
+      "step": 2318
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8845345436822225,
+      "eval_loss": 0.26893848180770874,
+      "eval_precision": 0.8865278628291489,
+      "eval_recall": 0.8826150209128933,
+      "eval_runtime": 1.7631,
+      "eval_samples_per_second": 226.305,
+      "eval_steps_per_second": 28.359,
+      "step": 2318
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 3.3988428115844727,
+      "learning_rate": 0.0,
+      "loss": 0.1365,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8817957385392532,
+      "eval_loss": 0.2682853937149048,
+      "eval_precision": 0.8827677592299257,
+      "eval_recall": 0.8808419712675032,
+      "eval_runtime": 1.7608,
+      "eval_samples_per_second": 226.596,
+      "eval_steps_per_second": 28.396,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "step": 2440,
+      "total_flos": 8444128359504000.0,
+      "train_loss": 0.22609603365913766,
+      "train_runtime": 618.465,
+      "train_samples_per_second": 117.646,
+      "train_steps_per_second": 3.945
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 8444128359504000.0,
+  "train_batch_size": 30,
+  "trial_name": null,
+  "trial_params": null
+}