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": 0.9233067729083665,
+    "epoch": 20.0,
+    "eval_accuracy": 0.9223057644110275,
+    "eval_f1": 0.9035367518034705,
+    "eval_loss": 0.717867374420166,
+    "eval_precision": 0.9169940112048426,
+    "eval_recall": 0.8925259138025095,
+    "eval_runtime": 4.7405,
+    "eval_samples": 399,
+    "eval_samples_per_second": 84.169,
+    "eval_steps_per_second": 10.547,
+    "f1": 0.9051778803991193,
+    "precision": 0.9160780898395615,
+    "recall": 0.8959519018875156,
+    "train_loss": 0.05354873166098947,
+    "train_runtime": 2701.55,
+    "train_samples": 3645,
+    "train_samples_per_second": 26.985,
+    "train_steps_per_second": 0.903
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.9223057644110275,
+    "eval_f1": 0.9035367518034705,
+    "eval_loss": 0.717867374420166,
+    "eval_precision": 0.9169940112048426,
+    "eval_recall": 0.8925259138025095,
+    "eval_runtime": 4.7405,
+    "eval_samples": 399,
+    "eval_samples_per_second": 84.169,
+    "eval_steps_per_second": 10.547
+}

predict_results.json

@@ -0,0 +1,6 @@
+{
+    "accuracy": 0.9233067729083665,
+    "f1": 0.9051778803991193,
+    "precision": 0.9160780898395615,
+    "recall": 0.8959519018875156
+}

predict_results.txt

@@ -0,0 +1,1005 @@
+index	prediction
+0	1
+1	0
+2	1
+3	1
+4	1
+5	1
+6	0
+7	1
+8	1
+9	1
+10	1
+11	1
+12	0
+13	1
+14	1
+15	1
+16	0
+17	1
+18	0
+19	1
+20	1
+21	0
+22	1
+23	1
+24	1
+25	1
+26	1
+27	1
+28	1
+29	0
+30	0
+31	1
+32	1
+33	1
+34	1
+35	1
+36	1
+37	1
+38	1
+39	0
+40	0
+41	1
+42	1
+43	1
+44	1
+45	1
+46	1
+47	1
+48	0
+49	1
+50	1
+51	1
+52	1
+53	1
+54	0
+55	1
+56	1
+57	1
+58	0
+59	0
+60	1
+61	1
+62	1
+63	1
+64	1
+65	1
+66	1
+67	1
+68	0
+69	1
+70	1
+71	0
+72	1
+73	1
+74	1
+75	0
+76	1
+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	0
+93	1
+94	0
+95	1
+96	0
+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	1
+110	1
+111	1
+112	1
+113	1
+114	0
+115	1
+116	1
+117	1
+118	1
+119	1
+120	1
+121	0
+122	1
+123	1
+124	1
+125	0
+126	1
+127	1
+128	0
+129	1
+130	1
+131	1
+132	1
+133	1
+134	0
+135	1
+136	1
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	0
+144	1
+145	1
+146	1
+147	1
+148	1
+149	1
+150	1
+151	1
+152	1
+153	0
+154	1
+155	1
+156	1
+157	0
+158	1
+159	1
+160	1
+161	1
+162	1
+163	1
+164	1
+165	1
+166	1
+167	1
+168	1
+169	1
+170	0
+171	1
+172	1
+173	1
+174	1
+175	1
+176	1
+177	1
+178	1
+179	1
+180	1
+181	1
+182	1
+183	1
+184	1
+185	1
+186	1
+187	0
+188	1
+189	1
+190	0
+191	1
+192	1
+193	0
+194	1
+195	1
+196	1
+197	1
+198	1
+199	1
+200	1
+201	1
+202	0
+203	1
+204	1
+205	1
+206	1
+207	0
+208	1
+209	1
+210	1
+211	1
+212	1
+213	1
+214	1
+215	1
+216	1
+217	1
+218	1
+219	1
+220	1
+221	0
+222	1
+223	1
+224	1
+225	0
+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	0
+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	0
+255	1
+256	1
+257	1
+258	1
+259	1
+260	0
+261	1
+262	1
+263	0
+264	1
+265	1
+266	1
+267	1
+268	1
+269	0
+270	1
+271	1
+272	0
+273	1
+274	1
+275	1
+276	1
+277	1
+278	1
+279	1
+280	0
+281	0
+282	0
+283	1
+284	1
+285	1
+286	1
+287	0
+288	0
+289	1
+290	1
+291	1
+292	1
+293	1
+294	0
+295	0
+296	0
+297	0
+298	0
+299	0
+300	0
+301	0
+302	0
+303	1
+304	0
+305	0
+306	0
+307	0
+308	0
+309	0
+310	0
+311	0
+312	1
+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	0
+343	0
+344	0
+345	0
+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	0
+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	0
+380	0
+381	0
+382	0
+383	0
+384	0
+385	0
+386	0
+387	0
+388	0
+389	0
+390	0
+391	0
+392	0
+393	0
+394	0
+395	0
+396	1
+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	1
+431	0
+432	0
+433	0
+434	0
+435	0
+436	0
+437	0
+438	0
+439	0
+440	0
+441	0
+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	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	0
+474	0
+475	0
+476	0
+477	0
+478	0
+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	0
+499	0
+500	1
+501	0
+502	0
+503	0
+504	0
+505	0
+506	0
+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	1
+533	0
+534	0
+535	0
+536	0
+537	1
+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	0
+553	0
+554	0
+555	0
+556	0
+557	0
+558	0
+559	1
+560	0
+561	0
+562	0
+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	1
+576	0
+577	0
+578	0
+579	0
+580	0
+581	0
+582	0
+583	0
+584	0
+585	0
+586	1
+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	1
+650	0
+651	0
+652	0
+653	0
+654	0
+655	0
+656	0
+657	1
+658	1
+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	1
+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	0
+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	0
+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	0
+756	0
+757	0
+758	0
+759	0
+760	0
+761	0
+762	0
+763	0
+764	0
+765	0
+766	0
+767	1
+768	0
+769	0
+770	0
+771	0
+772	0
+773	0
+774	1
+775	0
+776	0
+777	0
+778	0
+779	0
+780	0
+781	0
+782	0
+783	0
+784	0
+785	0
+786	0
+787	0
+788	0
+789	0
+790	0
+791	0
+792	0
+793	1
+794	0
+795	0
+796	0
+797	0
+798	1
+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	1
+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	1
+830	0
+831	0
+832	0
+833	0
+834	0
+835	1
+836	0
+837	0
+838	0
+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	0
+861	0
+862	0
+863	0
+864	0
+865	0
+866	0
+867	0
+868	0
+869	0
+870	0
+871	1
+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	0
+892	0
+893	0
+894	1
+895	0
+896	0
+897	0
+898	0
+899	0
+900	0
+901	0
+902	0
+903	0
+904	0
+905	0
+906	1
+907	0
+908	0
+909	0
+910	0
+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	0
+926	0
+927	0
+928	0
+929	0
+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	0
+946	0
+947	0
+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	0
+962	0
+963	0
+964	0
+965	0
+966	0
+967	0
+968	0
+969	0
+970	0
+971	0
+972	0
+973	0
+974	0
+975	0
+976	0
+977	0
+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	0
+1000	0
+1001	1
+1002	0
+1003	0

runs/May25_15-30-47_indolem-petl-vm/events.out.tfevents.1716653793.indolem-petl-vm.2276655.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c0b520e9b847e5ee96ae0da93762aa744d24e0a8d963dc6b0c253940a8adab
+size 560

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.05354873166098947,
+    "train_runtime": 2701.55,
+    "train_samples": 3645,
+    "train_samples_per_second": 26.985,
+    "train_steps_per_second": 0.903
+}

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": 24.956905364990234,
+      "learning_rate": 4.75e-05,
+      "loss": 0.3833,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8696741854636592,
+      "eval_f1": 0.8395012067578439,
+      "eval_loss": 0.31313076615333557,
+      "eval_precision": 0.8473584308763049,
+      "eval_recall": 0.8327877795962902,
+      "eval_runtime": 5.0044,
+      "eval_samples_per_second": 79.73,
+      "eval_steps_per_second": 9.991,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.629110813140869,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2232,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8872180451127819,
+      "eval_f1": 0.8629148629148629,
+      "eval_loss": 0.26969170570373535,
+      "eval_precision": 0.8657894736842104,
+      "eval_recall": 0.860201854882706,
+      "eval_runtime": 4.9679,
+      "eval_samples_per_second": 80.315,
+      "eval_steps_per_second": 10.065,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 20.295835494995117,
+      "learning_rate": 4.25e-05,
+      "loss": 0.1574,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8596491228070176,
+      "eval_f1": 0.8079620462046204,
+      "eval_loss": 0.5306064486503601,
+      "eval_precision": 0.8777160493827161,
+      "eval_recall": 0.7781869430805601,
+      "eval_runtime": 4.8971,
+      "eval_samples_per_second": 81.477,
+      "eval_steps_per_second": 10.21,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.211064100265503,
+      "learning_rate": 4e-05,
+      "loss": 0.0861,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9147869674185464,
+      "eval_f1": 0.8991765265473572,
+      "eval_loss": 0.39748647809028625,
+      "eval_precision": 0.8922773722627737,
+      "eval_recall": 0.9072104018912529,
+      "eval_runtime": 4.9778,
+      "eval_samples_per_second": 80.157,
+      "eval_steps_per_second": 10.045,
+      "step": 488
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.07590118050575256,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0444,
+      "step": 610
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8972431077694235,
+      "eval_f1": 0.8757339815412664,
+      "eval_loss": 0.4915539622306824,
+      "eval_precision": 0.8766906299500427,
+      "eval_recall": 0.8747954173486088,
+      "eval_runtime": 4.9432,
+      "eval_samples_per_second": 80.717,
+      "eval_steps_per_second": 10.115,
+      "step": 610
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.3078179359436035,
+      "learning_rate": 3.5e-05,
+      "loss": 0.0323,
+      "step": 732
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8851154755410074,
+      "eval_loss": 0.4762665033340454,
+      "eval_precision": 0.8851154755410074,
+      "eval_recall": 0.8851154755410074,
+      "eval_runtime": 4.9518,
+      "eval_samples_per_second": 80.576,
+      "eval_steps_per_second": 10.097,
+      "step": 732
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 12.544130325317383,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.0343,
+      "step": 854
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.87468671679198,
+      "eval_f1": 0.8353634383046148,
+      "eval_loss": 0.850492000579834,
+      "eval_precision": 0.8784261715296198,
+      "eval_recall": 0.8113293326059283,
+      "eval_runtime": 4.9345,
+      "eval_samples_per_second": 80.859,
+      "eval_steps_per_second": 10.133,
+      "step": 854
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.023242522031068802,
+      "learning_rate": 3e-05,
+      "loss": 0.021,
+      "step": 976
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8878574955372402,
+      "eval_loss": 0.5842882990837097,
+      "eval_precision": 0.8888448885098087,
+      "eval_recall": 0.8868885251863976,
+      "eval_runtime": 4.9396,
+      "eval_samples_per_second": 80.775,
+      "eval_steps_per_second": 10.122,
+      "step": 976
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.315354824066162,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.0171,
+      "step": 1098
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8972431077694235,
+      "eval_f1": 0.8694882125334078,
+      "eval_loss": 0.7051700353622437,
+      "eval_precision": 0.8940436639772188,
+      "eval_recall": 0.8522913256955811,
+      "eval_runtime": 4.9356,
+      "eval_samples_per_second": 80.841,
+      "eval_steps_per_second": 10.13,
+      "step": 1098
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.0030266689136624336,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0125,
+      "step": 1220
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8820775261324042,
+      "eval_loss": 0.7267709970474243,
+      "eval_precision": 0.8934835488413775,
+      "eval_recall": 0.8726132024004365,
+      "eval_runtime": 4.9522,
+      "eval_samples_per_second": 80.57,
+      "eval_steps_per_second": 10.096,
+      "step": 1220
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.10744116455316544,
+      "learning_rate": 2.25e-05,
+      "loss": 0.0106,
+      "step": 1342
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9122807017543859,
+      "eval_f1": 0.8904851902099328,
+      "eval_loss": 0.7197956442832947,
+      "eval_precision": 0.9064374185136896,
+      "eval_recall": 0.8779323513366066,
+      "eval_runtime": 4.9857,
+      "eval_samples_per_second": 80.028,
+      "eval_steps_per_second": 10.029,
+      "step": 1342
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.00939513836055994,
+      "learning_rate": 2e-05,
+      "loss": 0.0153,
+      "step": 1464
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9097744360902256,
+      "eval_f1": 0.8917003438084323,
+      "eval_loss": 0.6022568941116333,
+      "eval_precision": 0.8898109243697478,
+      "eval_recall": 0.893662484088016,
+      "eval_runtime": 4.9277,
+      "eval_samples_per_second": 80.97,
+      "eval_steps_per_second": 10.147,
+      "step": 1464
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.0019507030956447124,
+      "learning_rate": 1.75e-05,
+      "loss": 0.0047,
+      "step": 1586
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.9147869674185464,
+      "eval_f1": 0.892708003796267,
+      "eval_loss": 0.7098793387413025,
+      "eval_precision": 0.9134992358296232,
+      "eval_recall": 0.8772049463538825,
+      "eval_runtime": 4.9409,
+      "eval_samples_per_second": 80.755,
+      "eval_steps_per_second": 10.12,
+      "step": 1586
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.0021610422991216183,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0109,
+      "step": 1708
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9097744360902256,
+      "eval_f1": 0.8882839721254355,
+      "eval_loss": 0.6721974611282349,
+      "eval_precision": 0.8998687748047625,
+      "eval_recall": 0.8786597563193308,
+      "eval_runtime": 4.9095,
+      "eval_samples_per_second": 81.271,
+      "eval_steps_per_second": 10.184,
+      "step": 1708
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.0025670749600976706,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0044,
+      "step": 1830
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9197994987468672,
+      "eval_f1": 0.8995910663730733,
+      "eval_loss": 0.7060150504112244,
+      "eval_precision": 0.9174593282602992,
+      "eval_recall": 0.8857519549008911,
+      "eval_runtime": 4.9454,
+      "eval_samples_per_second": 80.681,
+      "eval_steps_per_second": 10.11,
+      "step": 1830
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.0015903374878689647,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 1952
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9223057644110275,
+      "eval_f1": 0.9030011684716548,
+      "eval_loss": 0.7098459005355835,
+      "eval_precision": 0.9194426336375489,
+      "eval_recall": 0.8900254591743954,
+      "eval_runtime": 4.9282,
+      "eval_samples_per_second": 80.962,
+      "eval_steps_per_second": 10.146,
+      "step": 1952
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.0019439965253695846,
+      "learning_rate": 7.5e-06,
+      "loss": 0.005,
+      "step": 2074
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.9197994987468672,
+      "eval_f1": 0.9012315118509808,
+      "eval_loss": 0.7069065570831299,
+      "eval_precision": 0.9104713698196774,
+      "eval_recall": 0.8932533187852337,
+      "eval_runtime": 5.0714,
+      "eval_samples_per_second": 78.676,
+      "eval_steps_per_second": 9.859,
+      "step": 2074
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.001250488217920065,
+      "learning_rate": 5e-06,
+      "loss": 0.0005,
+      "step": 2196
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.9172932330827067,
+      "eval_f1": 0.8961601249201505,
+      "eval_loss": 0.758560061454773,
+      "eval_precision": 0.9154783125371361,
+      "eval_recall": 0.8814784506273867,
+      "eval_runtime": 4.9396,
+      "eval_samples_per_second": 80.776,
+      "eval_steps_per_second": 10.122,
+      "step": 2196
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.0011430870508775115,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0017,
+      "step": 2318
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.9223057644110275,
+      "eval_f1": 0.9035367518034705,
+      "eval_loss": 0.7198145985603333,
+      "eval_precision": 0.9169940112048426,
+      "eval_recall": 0.8925259138025095,
+      "eval_runtime": 4.9455,
+      "eval_samples_per_second": 80.68,
+      "eval_steps_per_second": 10.11,
+      "step": 2318
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0008615191909484565,
+      "learning_rate": 0.0,
+      "loss": 0.0009,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9223057644110275,
+      "eval_f1": 0.9035367518034705,
+      "eval_loss": 0.717867374420166,
+      "eval_precision": 0.9169940112048426,
+      "eval_recall": 0.8925259138025095,
+      "eval_runtime": 4.9346,
+      "eval_samples_per_second": 80.858,
+      "eval_steps_per_second": 10.133,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "step": 2440,
+      "total_flos": 7598755382040000.0,
+      "train_loss": 0.05354873166098947,
+      "train_runtime": 2701.55,
+      "train_samples_per_second": 26.985,
+      "train_steps_per_second": 0.903
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 7598755382040000.0,
+  "train_batch_size": 30,
+  "trial_name": null,
+  "trial_params": null
+}