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": 0.857566765578635,
+    "epoch": 20.0,
+    "eval_accuracy": 0.8471177944862155,
+    "eval_f1": 0.8186863532409097,
+    "eval_loss": 0.3607771396636963,
+    "eval_precision": 0.8138123167155425,
+    "eval_recall": 0.8243316966721222,
+    "eval_runtime": 5.0236,
+    "eval_samples": 399,
+    "eval_samples_per_second": 79.425,
+    "eval_steps_per_second": 9.953,
+    "f1": 0.829367088607595,
+    "precision": 0.8281181404646036,
+    "recall": 0.8306569274358274,
+    "train_loss": 0.39638843536376955,
+    "train_runtime": 1955.7644,
+    "train_samples": 3638,
+    "train_samples_per_second": 37.203,
+    "train_steps_per_second": 1.248
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.8471177944862155,
+    "eval_f1": 0.8186863532409097,
+    "eval_loss": 0.3607771396636963,
+    "eval_precision": 0.8138123167155425,
+    "eval_recall": 0.8243316966721222,
+    "eval_runtime": 5.0236,
+    "eval_samples": 399,
+    "eval_samples_per_second": 79.425,
+    "eval_steps_per_second": 9.953
+}

predict_results.txt

@@ -0,0 +1,1012 @@
+index	prediction
+0	1
+1	0
+2	1
+3	1
+4	0
+5	1
+6	1
+7	1
+8	0
+9	1
+10	1
+11	1
+12	0
+13	1
+14	1
+15	1
+16	1
+17	1
+18	1
+19	1
+20	1
+21	1
+22	0
+23	1
+24	1
+25	1
+26	1
+27	1
+28	1
+29	0
+30	1
+31	1
+32	1
+33	1
+34	0
+35	1
+36	1
+37	1
+38	1
+39	0
+40	1
+41	0
+42	0
+43	0
+44	0
+45	0
+46	1
+47	1
+48	1
+49	0
+50	1
+51	1
+52	0
+53	1
+54	1
+55	1
+56	0
+57	0
+58	1
+59	0
+60	1
+61	1
+62	1
+63	1
+64	0
+65	0
+66	1
+67	1
+68	1
+69	0
+70	1
+71	1
+72	1
+73	1
+74	1
+75	1
+76	1
+77	0
+78	1
+79	1
+80	0
+81	0
+82	1
+83	0
+84	1
+85	0
+86	1
+87	1
+88	0
+89	1
+90	1
+91	0
+92	1
+93	0
+94	1
+95	1
+96	1
+97	0
+98	0
+99	0
+100	1
+101	0
+102	1
+103	1
+104	0
+105	1
+106	1
+107	1
+108	1
+109	1
+110	1
+111	1
+112	1
+113	1
+114	1
+115	1
+116	1
+117	1
+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	0
+132	1
+133	1
+134	1
+135	0
+136	0
+137	1
+138	1
+139	1
+140	1
+141	1
+142	1
+143	1
+144	1
+145	1
+146	1
+147	0
+148	1
+149	0
+150	1
+151	1
+152	1
+153	1
+154	1
+155	0
+156	1
+157	1
+158	1
+159	1
+160	1
+161	1
+162	1
+163	1
+164	0
+165	0
+166	1
+167	1
+168	0
+169	0
+170	1
+171	1
+172	0
+173	1
+174	1
+175	1
+176	0
+177	0
+178	1
+179	1
+180	1
+181	1
+182	1
+183	1
+184	1
+185	1
+186	1
+187	1
+188	1
+189	1
+190	0
+191	0
+192	1
+193	1
+194	1
+195	1
+196	1
+197	1
+198	1
+199	1
+200	1
+201	1
+202	1
+203	1
+204	1
+205	0
+206	1
+207	1
+208	1
+209	1
+210	0
+211	1
+212	1
+213	1
+214	0
+215	1
+216	0
+217	0
+218	0
+219	1
+220	0
+221	1
+222	1
+223	1
+224	1
+225	1
+226	0
+227	0
+228	0
+229	0
+230	1
+231	1
+232	0
+233	0
+234	1
+235	0
+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	0
+251	1
+252	1
+253	1
+254	1
+255	0
+256	1
+257	1
+258	1
+259	1
+260	1
+261	0
+262	1
+263	1
+264	1
+265	1
+266	1
+267	1
+268	1
+269	1
+270	1
+271	1
+272	1
+273	0
+274	1
+275	1
+276	1
+277	1
+278	1
+279	1
+280	0
+281	1
+282	1
+283	1
+284	1
+285	1
+286	1
+287	1
+288	1
+289	0
+290	1
+291	1
+292	1
+293	0
+294	1
+295	1
+296	1
+297	1
+298	0
+299	0
+300	0
+301	0
+302	0
+303	0
+304	0
+305	1
+306	0
+307	0
+308	0
+309	0
+310	0
+311	0
+312	0
+313	0
+314	1
+315	0
+316	1
+317	0
+318	1
+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	1
+345	0
+346	1
+347	0
+348	0
+349	0
+350	0
+351	1
+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	1
+365	0
+366	1
+367	0
+368	0
+369	0
+370	0
+371	0
+372	0
+373	0
+374	0
+375	0
+376	1
+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	0
+397	0
+398	1
+399	0
+400	0
+401	1
+402	1
+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	1
+422	0
+423	0
+424	0
+425	1
+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	1
+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	0
+453	0
+454	0
+455	1
+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	1
+488	0
+489	0
+490	0
+491	0
+492	1
+493	0
+494	0
+495	0
+496	1
+497	0
+498	0
+499	0
+500	0
+501	0
+502	0
+503	1
+504	0
+505	0
+506	0
+507	0
+508	0
+509	0
+510	0
+511	1
+512	0
+513	0
+514	0
+515	0
+516	0
+517	0
+518	0
+519	0
+520	0
+521	0
+522	1
+523	0
+524	0
+525	0
+526	0
+527	0
+528	0
+529	1
+530	0
+531	0
+532	0
+533	0
+534	1
+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	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	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	1
+589	0
+590	0
+591	0
+592	0
+593	0
+594	0
+595	1
+596	1
+597	0
+598	0
+599	0
+600	0
+601	1
+602	0
+603	0
+604	0
+605	0
+606	0
+607	0
+608	0
+609	0
+610	1
+611	0
+612	0
+613	0
+614	0
+615	0
+616	0
+617	0
+618	0
+619	0
+620	0
+621	1
+622	0
+623	0
+624	1
+625	0
+626	0
+627	0
+628	1
+629	0
+630	0
+631	0
+632	0
+633	0
+634	0
+635	1
+636	0
+637	0
+638	0
+639	1
+640	0
+641	0
+642	0
+643	0
+644	0
+645	0
+646	0
+647	0
+648	1
+649	0
+650	1
+651	0
+652	1
+653	0
+654	1
+655	0
+656	0
+657	1
+658	0
+659	0
+660	0
+661	0
+662	0
+663	0
+664	0
+665	0
+666	0
+667	0
+668	0
+669	1
+670	0
+671	0
+672	0
+673	0
+674	0
+675	1
+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	1
+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	1
+728	1
+729	0
+730	0
+731	0
+732	0
+733	1
+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	1
+753	0
+754	0
+755	0
+756	1
+757	0
+758	1
+759	0
+760	0
+761	0
+762	0
+763	0
+764	0
+765	0
+766	0
+767	0
+768	0
+769	0
+770	1
+771	0
+772	0
+773	0
+774	0
+775	0
+776	0
+777	1
+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	0
+794	0
+795	1
+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	1
+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	1
+833	1
+834	0
+835	0
+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	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	1
+885	0
+886	0
+887	0
+888	0
+889	0
+890	0
+891	1
+892	0
+893	0
+894	1
+895	0
+896	0
+897	1
+898	0
+899	0
+900	0
+901	0
+902	0
+903	0
+904	0
+905	0
+906	1
+907	1
+908	0
+909	0
+910	0
+911	0
+912	0
+913	0
+914	0
+915	0
+916	1
+917	0
+918	0
+919	0
+920	0
+921	0
+922	0
+923	0
+924	0
+925	0
+926	0
+927	0
+928	1
+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	1
+944	0
+945	0
+946	0
+947	0
+948	0
+949	0
+950	1
+951	0
+952	0
+953	0
+954	0
+955	0
+956	0
+957	1
+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	1
+976	0
+977	0
+978	0
+979	0
+980	1
+981	0
+982	0
+983	0
+984	0
+985	0
+986	1
+987	0
+988	0
+989	0
+990	0
+991	1
+992	1
+993	0
+994	0
+995	1
+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	1

runs/May17_13-08-27_indolem-petl-vm/events.out.tfevents.1715953289.indolem-petl-vm.1283387.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c282e2adae520ccba5c38e7804077016f8ede9788d3444e3431949ab5074a1
+size 560

test_results.json

@@ -0,0 +1,6 @@
+{
+    "accuracy": 0.857566765578635,
+    "f1": 0.829367088607595,
+    "precision": 0.8281181404646036,
+    "recall": 0.8306569274358274
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.39638843536376955,
+    "train_runtime": 1955.7644,
+    "train_samples": 3638,
+    "train_samples_per_second": 37.203,
+    "train_steps_per_second": 1.248
+}

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": 5.088006496429443,
+      "learning_rate": 4.75e-05,
+      "loss": 0.5634,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7192982456140351,
+      "eval_f1": 0.6524390243902439,
+      "eval_loss": 0.5107927322387695,
+      "eval_precision": 0.6572301881961337,
+      "eval_recall": 0.6488907074013457,
+      "eval_runtime": 5.0968,
+      "eval_samples_per_second": 78.284,
+      "eval_steps_per_second": 9.81,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.8167991638183594,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5081,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7218045112781954,
+      "eval_f1": 0.6887653635603403,
+      "eval_loss": 0.5049471855163574,
+      "eval_precision": 0.6829453441295547,
+      "eval_recall": 0.7081742134933624,
+      "eval_runtime": 5.0562,
+      "eval_samples_per_second": 78.913,
+      "eval_steps_per_second": 9.889,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.013192176818848,
+      "learning_rate": 4.25e-05,
+      "loss": 0.4924,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7493734335839599,
+      "eval_f1": 0.6976723040552828,
+      "eval_loss": 0.46672317385673523,
+      "eval_precision": 0.6976723040552828,
+      "eval_recall": 0.6976723040552828,
+      "eval_runtime": 5.0806,
+      "eval_samples_per_second": 78.535,
+      "eval_steps_per_second": 9.841,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.717806100845337,
+      "learning_rate": 4e-05,
+      "loss": 0.4698,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7794486215538847,
+      "eval_f1": 0.7206949217258496,
+      "eval_loss": 0.43917685747146606,
+      "eval_precision": 0.7348989898989899,
+      "eval_recall": 0.711447535915621,
+      "eval_runtime": 5.1289,
+      "eval_samples_per_second": 77.794,
+      "eval_steps_per_second": 9.749,
+      "step": 488
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.4102962017059326,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4519,
+      "step": 610
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7468671679197995,
+      "eval_f1": 0.7226057806810438,
+      "eval_loss": 0.4547964334487915,
+      "eval_precision": 0.7169434353918007,
+      "eval_recall": 0.7534097108565194,
+      "eval_runtime": 5.1149,
+      "eval_samples_per_second": 78.007,
+      "eval_steps_per_second": 9.775,
+      "step": 610
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.93445885181427,
+      "learning_rate": 3.5e-05,
+      "loss": 0.4356,
+      "step": 732
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8145363408521303,
+      "eval_f1": 0.7739895897121861,
+      "eval_loss": 0.41105952858924866,
+      "eval_precision": 0.7769509251810136,
+      "eval_recall": 0.7712765957446808,
+      "eval_runtime": 5.085,
+      "eval_samples_per_second": 78.466,
+      "eval_steps_per_second": 9.833,
+      "step": 732
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.6042848825454712,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.421,
+      "step": 854
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7944862155388471,
+      "eval_f1": 0.7611824817518249,
+      "eval_loss": 0.41012144088745117,
+      "eval_precision": 0.7537593984962405,
+      "eval_recall": 0.7720949263502455,
+      "eval_runtime": 5.0805,
+      "eval_samples_per_second": 78.536,
+      "eval_steps_per_second": 9.842,
+      "step": 854
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 18.006345748901367,
+      "learning_rate": 3e-05,
+      "loss": 0.4039,
+      "step": 976
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8295739348370927,
+      "eval_f1": 0.7933776044839771,
+      "eval_loss": 0.38294023275375366,
+      "eval_precision": 0.7949020208205757,
+      "eval_recall": 0.7919167121294781,
+      "eval_runtime": 5.064,
+      "eval_samples_per_second": 78.791,
+      "eval_steps_per_second": 9.874,
+      "step": 976
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.092437744140625,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.3887,
+      "step": 1098
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8320802005012531,
+      "eval_f1": 0.7979441442122369,
+      "eval_loss": 0.3800281286239624,
+      "eval_precision": 0.7972133421798662,
+      "eval_recall": 0.7986906710310966,
+      "eval_runtime": 5.0646,
+      "eval_samples_per_second": 78.782,
+      "eval_steps_per_second": 9.872,
+      "step": 1098
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.934494972229004,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3797,
+      "step": 1220
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8370927318295739,
+      "eval_f1": 0.8019881353214686,
+      "eval_loss": 0.37680280208587646,
+      "eval_precision": 0.8043859649122806,
+      "eval_recall": 0.7997363156937625,
+      "eval_runtime": 5.0723,
+      "eval_samples_per_second": 78.663,
+      "eval_steps_per_second": 9.857,
+      "step": 1220
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 3.9598286151885986,
+      "learning_rate": 2.25e-05,
+      "loss": 0.368,
+      "step": 1342
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8220551378446115,
+      "eval_f1": 0.791846991484015,
+      "eval_loss": 0.38417863845825195,
+      "eval_precision": 0.7845581927366314,
+      "eval_recall": 0.801600290961993,
+      "eval_runtime": 5.0582,
+      "eval_samples_per_second": 78.882,
+      "eval_steps_per_second": 9.885,
+      "step": 1342
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 11.679308891296387,
+      "learning_rate": 2e-05,
+      "loss": 0.3598,
+      "step": 1464
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8270676691729323,
+      "eval_f1": 0.7967966933608887,
+      "eval_loss": 0.37781035900115967,
+      "eval_precision": 0.7902444649446494,
+      "eval_recall": 0.8051463902527732,
+      "eval_runtime": 5.1525,
+      "eval_samples_per_second": 77.438,
+      "eval_steps_per_second": 9.704,
+      "step": 1464
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 1.9093892574310303,
+      "learning_rate": 1.75e-05,
+      "loss": 0.3548,
+      "step": 1586
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8471177944862155,
+      "eval_f1": 0.8141734808401475,
+      "eval_loss": 0.3623768091201782,
+      "eval_precision": 0.8166666666666667,
+      "eval_recall": 0.8118294235315512,
+      "eval_runtime": 5.0613,
+      "eval_samples_per_second": 78.833,
+      "eval_steps_per_second": 9.879,
+      "step": 1586
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 8.159423828125,
+      "learning_rate": 1.5e-05,
+      "loss": 0.3469,
+      "step": 1708
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8446115288220551,
+      "eval_f1": 0.8134839254478557,
+      "eval_loss": 0.36370429396629333,
+      "eval_precision": 0.8119747899159664,
+      "eval_recall": 0.8150572831423895,
+      "eval_runtime": 5.06,
+      "eval_samples_per_second": 78.854,
+      "eval_steps_per_second": 9.881,
+      "step": 1708
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.1732066869735718,
+      "learning_rate": 1.25e-05,
+      "loss": 0.3431,
+      "step": 1830
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.8395989974937343,
+      "eval_f1": 0.81021463820679,
+      "eval_loss": 0.3684653341770172,
+      "eval_precision": 0.8049051094890511,
+      "eval_recall": 0.8165120931078378,
+      "eval_runtime": 5.0473,
+      "eval_samples_per_second": 79.053,
+      "eval_steps_per_second": 9.906,
+      "step": 1830
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 6.608555316925049,
+      "learning_rate": 1e-05,
+      "loss": 0.3275,
+      "step": 1952
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.8370927318295739,
+      "eval_f1": 0.8085765951950401,
+      "eval_loss": 0.3663918673992157,
+      "eval_precision": 0.8017470018450185,
+      "eval_recall": 0.817239498090562,
+      "eval_runtime": 5.098,
+      "eval_samples_per_second": 78.267,
+      "eval_steps_per_second": 9.808,
+      "step": 1952
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 3.14452862739563,
+      "learning_rate": 7.5e-06,
+      "loss": 0.3288,
+      "step": 2074
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.8395989974937343,
+      "eval_f1": 0.8084033613445378,
+      "eval_loss": 0.359037846326828,
+      "eval_precision": 0.8055472976990309,
+      "eval_recall": 0.8115111838516094,
+      "eval_runtime": 5.0473,
+      "eval_samples_per_second": 79.052,
+      "eval_steps_per_second": 9.906,
+      "step": 2074
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 2.8248753547668457,
+      "learning_rate": 5e-06,
+      "loss": 0.3335,
+      "step": 2196
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8471177944862155,
+      "eval_f1": 0.8186863532409097,
+      "eval_loss": 0.36074599623680115,
+      "eval_precision": 0.8138123167155425,
+      "eval_recall": 0.8243316966721222,
+      "eval_runtime": 5.0588,
+      "eval_samples_per_second": 78.872,
+      "eval_steps_per_second": 9.884,
+      "step": 2196
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 4.17168664932251,
+      "learning_rate": 2.5e-06,
+      "loss": 0.3239,
+      "step": 2318
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.8446115288220551,
+      "eval_f1": 0.8161454307628278,
+      "eval_loss": 0.36129772663116455,
+      "eval_precision": 0.8107299270072992,
+      "eval_recall": 0.8225586470267321,
+      "eval_runtime": 5.0523,
+      "eval_samples_per_second": 78.975,
+      "eval_steps_per_second": 9.897,
+      "step": 2318
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 6.108452796936035,
+      "learning_rate": 0.0,
+      "loss": 0.327,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8471177944862155,
+      "eval_f1": 0.8186863532409097,
+      "eval_loss": 0.3607771396636963,
+      "eval_precision": 0.8138123167155425,
+      "eval_recall": 0.8243316966721222,
+      "eval_runtime": 5.1353,
+      "eval_samples_per_second": 77.698,
+      "eval_steps_per_second": 9.737,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "step": 2440,
+      "total_flos": 7590599775312000.0,
+      "train_loss": 0.39638843536376955,
+      "train_runtime": 1955.7644,
+      "train_samples_per_second": 37.203,
+      "train_steps_per_second": 1.248
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 7590599775312000.0,
+  "train_batch_size": 30,
+  "trial_name": null,
+  "trial_params": null
+}