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": 0.8951533135509396,
+    "epoch": 20.0,
+    "eval_accuracy": 0.9022556390977443,
+    "eval_f1": 0.8856624319419237,
+    "eval_loss": 0.2808963358402252,
+    "eval_precision": 0.8758364312267658,
+    "eval_recall": 0.8983451536643026,
+    "eval_runtime": 5.0348,
+    "eval_samples": 399,
+    "eval_samples_per_second": 79.249,
+    "eval_steps_per_second": 9.931,
+    "f1": 0.8767129906585063,
+    "precision": 0.8693150573790442,
+    "recall": 0.8856260060054406,
+    "train_loss": 0.22104478507745462,
+    "train_runtime": 1931.1343,
+    "train_samples": 3638,
+    "train_samples_per_second": 37.677,
+    "train_steps_per_second": 1.264
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.9022556390977443,
+    "eval_f1": 0.8856624319419237,
+    "eval_loss": 0.2808963358402252,
+    "eval_precision": 0.8758364312267658,
+    "eval_recall": 0.8983451536643026,
+    "eval_runtime": 5.0348,
+    "eval_samples": 399,
+    "eval_samples_per_second": 79.249,
+    "eval_steps_per_second": 9.931
+}

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	1
+13	1
+14	1
+15	0
+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	1
+42	1
+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	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	1
+70	1
+71	1
+72	1
+73	1
+74	1
+75	1
+76	1
+77	1
+78	1
+79	1
+80	0
+81	1
+82	1
+83	1
+84	1
+85	0
+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	0
+100	1
+101	0
+102	1
+103	1
+104	1
+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	1
+136	0
+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	0
+156	1
+157	1
+158	1
+159	1
+160	1
+161	1
+162	1
+163	1
+164	1
+165	0
+166	1
+167	1
+168	0
+169	1
+170	1
+171	1
+172	1
+173	0
+174	1
+175	1
+176	1
+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	1
+191	1
+192	1
+193	1
+194	1
+195	1
+196	1
+197	1
+198	1
+199	0
+200	1
+201	1
+202	1
+203	1
+204	1
+205	0
+206	1
+207	0
+208	1
+209	1
+210	1
+211	1
+212	1
+213	1
+214	0
+215	1
+216	0
+217	1
+218	0
+219	1
+220	0
+221	1
+222	1
+223	1
+224	0
+225	1
+226	0
+227	0
+228	1
+229	0
+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	0
+247	1
+248	1
+249	1
+250	0
+251	1
+252	1
+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	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	1
+294	1
+295	1
+296	1
+297	1
+298	0
+299	0
+300	0
+301	0
+302	1
+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	1
+329	0
+330	1
+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	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	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	1
+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	1
+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	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	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	1
+525	0
+526	0
+527	0
+528	0
+529	1
+530	0
+531	0
+532	0
+533	0
+534	0
+535	0
+536	1
+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	1
+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	0
+589	0
+590	0
+591	0
+592	0
+593	0
+594	0
+595	0
+596	1
+597	0
+598	0
+599	0
+600	0
+601	0
+602	0
+603	0
+604	0
+605	0
+606	0
+607	0
+608	1
+609	0
+610	1
+611	1
+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	0
+625	0
+626	1
+627	0
+628	1
+629	0
+630	0
+631	0
+632	0
+633	1
+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	0
+649	0
+650	0
+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	1
+664	0
+665	0
+666	0
+667	0
+668	0
+669	1
+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	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	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	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	1
+766	0
+767	0
+768	0
+769	0
+770	1
+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	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	1
+815	0
+816	0
+817	0
+818	0
+819	1
+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	1
+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	1
+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	0
+892	0
+893	0
+894	0
+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	1
+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	1
+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	1
+970	0
+971	0
+972	0
+973	0
+974	0
+975	0
+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	0
+992	1
+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

runs/May18_04-57-06_indolem-petl-vm/events.out.tfevents.1716010183.indolem-petl-vm.1583852.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a04174ec0a6de21234f27d1e7399c24289f7dc63b2286ec3c3729d91a348a80
+size 560

test_results.json

@@ -0,0 +1,6 @@
+{
+    "accuracy": 0.8951533135509396,
+    "f1": 0.8767129906585063,
+    "precision": 0.8693150573790442,
+    "recall": 0.8856260060054406
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 0.22104478507745462,
+    "train_runtime": 1931.1343,
+    "train_samples": 3638,
+    "train_samples_per_second": 37.677,
+    "train_steps_per_second": 1.264
+}

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": 4.245405197143555,
+      "learning_rate": 4.75e-05,
+      "loss": 0.5417,
+      "step": 122
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7368421052631579,
+      "eval_f1": 0.6531440162271805,
+      "eval_loss": 0.4691583514213562,
+      "eval_precision": 0.6762575228471654,
+      "eval_recall": 0.6437988725222767,
+      "eval_runtime": 5.1902,
+      "eval_samples_per_second": 76.876,
+      "eval_steps_per_second": 9.634,
+      "step": 122
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.8213655948638916,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4301,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7769423558897243,
+      "eval_f1": 0.7593078346448687,
+      "eval_loss": 0.4378258287906647,
+      "eval_precision": 0.7546743295019157,
+      "eval_recall": 0.8021913075104565,
+      "eval_runtime": 5.0762,
+      "eval_samples_per_second": 78.602,
+      "eval_steps_per_second": 9.85,
+      "step": 244
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.3787574768066406,
+      "learning_rate": 4.25e-05,
+      "loss": 0.3347,
+      "step": 366
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8446115288220551,
+      "eval_f1": 0.8086360542112754,
+      "eval_loss": 0.34514203667640686,
+      "eval_precision": 0.8158019614046188,
+      "eval_recall": 0.8025550100018185,
+      "eval_runtime": 5.1656,
+      "eval_samples_per_second": 77.242,
+      "eval_steps_per_second": 9.679,
+      "step": 366
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8603061437606812,
+      "learning_rate": 4e-05,
+      "loss": 0.2954,
+      "step": 488
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8646616541353384,
+      "eval_f1": 0.8359175094431583,
+      "eval_loss": 0.33369535207748413,
+      "eval_precision": 0.8376607470912432,
+      "eval_recall": 0.8342425895617385,
+      "eval_runtime": 5.0988,
+      "eval_samples_per_second": 78.253,
+      "eval_steps_per_second": 9.806,
+      "step": 488
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.168339967727661,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.2632,
+      "step": 610
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_f1": 0.8321363988633428,
+      "eval_loss": 0.33563923835754395,
+      "eval_precision": 0.8247520756457565,
+      "eval_recall": 0.8414257137661394,
+      "eval_runtime": 5.0925,
+      "eval_samples_per_second": 78.35,
+      "eval_steps_per_second": 9.818,
+      "step": 610
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.1380066871643066,
+      "learning_rate": 3.5e-05,
+      "loss": 0.2492,
+      "step": 732
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8446115288220551,
+      "eval_f1": 0.8231484129253646,
+      "eval_loss": 0.32611119747161865,
+      "eval_precision": 0.8109975961538461,
+      "eval_recall": 0.84506273867976,
+      "eval_runtime": 5.0755,
+      "eval_samples_per_second": 78.613,
+      "eval_steps_per_second": 9.851,
+      "step": 732
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.41156822443008423,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.227,
+      "step": 854
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8796992481203008,
+      "eval_f1": 0.8602043795620438,
+      "eval_loss": 0.2977831959724426,
+      "eval_precision": 0.849624060150376,
+      "eval_recall": 0.8748863429714493,
+      "eval_runtime": 5.0954,
+      "eval_samples_per_second": 78.306,
+      "eval_steps_per_second": 9.813,
+      "step": 854
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.2771873474121094,
+      "learning_rate": 3e-05,
+      "loss": 0.2189,
+      "step": 976
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8947368421052632,
+      "eval_f1": 0.8703663593044124,
+      "eval_loss": 0.2742370069026947,
+      "eval_precision": 0.8789149003479912,
+      "eval_recall": 0.8630205491907619,
+      "eval_runtime": 5.1766,
+      "eval_samples_per_second": 77.078,
+      "eval_steps_per_second": 9.659,
+      "step": 976
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 7.185235023498535,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 0.2068,
+      "step": 1098
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8922305764411027,
+      "eval_f1": 0.8715803025426456,
+      "eval_loss": 0.28745463490486145,
+      "eval_precision": 0.8673433153814287,
+      "eval_recall": 0.8762502273140571,
+      "eval_runtime": 5.0492,
+      "eval_samples_per_second": 79.023,
+      "eval_steps_per_second": 9.903,
+      "step": 1098
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 6.480859756469727,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1935,
+      "step": 1220
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8872855539522206,
+      "eval_loss": 0.2693336009979248,
+      "eval_precision": 0.8903508771929824,
+      "eval_recall": 0.8843880705582834,
+      "eval_runtime": 5.0696,
+      "eval_samples_per_second": 78.704,
+      "eval_steps_per_second": 9.863,
+      "step": 1220
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.1324069499969482,
+      "learning_rate": 2.25e-05,
+      "loss": 0.1729,
+      "step": 1342
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8900228699985846,
+      "eval_loss": 0.27149420976638794,
+      "eval_precision": 0.8840175953079179,
+      "eval_recall": 0.8968903436988543,
+      "eval_runtime": 5.066,
+      "eval_samples_per_second": 78.761,
+      "eval_steps_per_second": 9.87,
+      "step": 1342
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.9420219659805298,
+      "learning_rate": 2e-05,
+      "loss": 0.1639,
+      "step": 1464
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.882467302933899,
+      "eval_loss": 0.2754858136177063,
+      "eval_precision": 0.8732988802756245,
+      "eval_recall": 0.8940716493907983,
+      "eval_runtime": 5.0731,
+      "eval_samples_per_second": 78.65,
+      "eval_steps_per_second": 9.856,
+      "step": 1464
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 3.3185982704162598,
+      "learning_rate": 1.75e-05,
+      "loss": 0.1564,
+      "step": 1586
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8817957385392532,
+      "eval_loss": 0.2662343382835388,
+      "eval_precision": 0.8827677592299257,
+      "eval_recall": 0.8808419712675032,
+      "eval_runtime": 5.1649,
+      "eval_samples_per_second": 77.253,
+      "eval_steps_per_second": 9.681,
+      "step": 1586
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 6.053642272949219,
+      "learning_rate": 1.5e-05,
+      "loss": 0.1495,
+      "step": 1708
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.899749373433584,
+      "eval_f1": 0.8835036496350365,
+      "eval_loss": 0.29733341932296753,
+      "eval_precision": 0.8721804511278195,
+      "eval_recall": 0.8990725586470267,
+      "eval_runtime": 5.0495,
+      "eval_samples_per_second": 79.018,
+      "eval_steps_per_second": 9.902,
+      "step": 1708
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.5649229884147644,
+      "learning_rate": 1.25e-05,
+      "loss": 0.1487,
+      "step": 1830
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9097744360902256,
+      "eval_f1": 0.8932457339913193,
+      "eval_loss": 0.27316734194755554,
+      "eval_precision": 0.8864525547445254,
+      "eval_recall": 0.9011638479723586,
+      "eval_runtime": 5.0523,
+      "eval_samples_per_second": 78.973,
+      "eval_steps_per_second": 9.896,
+      "step": 1830
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.219386100769043,
+      "learning_rate": 1e-05,
+      "loss": 0.141,
+      "step": 1952
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8888416422287391,
+      "eval_loss": 0.2841818034648895,
+      "eval_precision": 0.8783752990771334,
+      "eval_recall": 0.9026186579378068,
+      "eval_runtime": 5.0622,
+      "eval_samples_per_second": 78.82,
+      "eval_steps_per_second": 9.877,
+      "step": 1952
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 3.3799021244049072,
+      "learning_rate": 7.5e-06,
+      "loss": 0.1276,
+      "step": 2074
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.9047619047619048,
+      "eval_f1": 0.8878351186601172,
+      "eval_loss": 0.2794151306152344,
+      "eval_precision": 0.879776516905975,
+      "eval_recall": 0.8976177486815784,
+      "eval_runtime": 5.0922,
+      "eval_samples_per_second": 78.355,
+      "eval_steps_per_second": 9.819,
+      "step": 2074
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 4.4008965492248535,
+      "learning_rate": 5e-06,
+      "loss": 0.1383,
+      "step": 2196
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.9072681704260651,
+      "eval_f1": 0.8910359080340997,
+      "eval_loss": 0.2787146270275116,
+      "eval_precision": 0.8822647601476015,
+      "eval_recall": 0.9018912529550827,
+      "eval_runtime": 5.077,
+      "eval_samples_per_second": 78.589,
+      "eval_steps_per_second": 9.848,
+      "step": 2196
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 3.290771245956421,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1371,
+      "step": 2318
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8856624319419237,
+      "eval_loss": 0.2780250012874603,
+      "eval_precision": 0.8758364312267658,
+      "eval_recall": 0.8983451536643026,
+      "eval_runtime": 5.0678,
+      "eval_samples_per_second": 78.733,
+      "eval_steps_per_second": 9.866,
+      "step": 2318
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.2898199558258057,
+      "learning_rate": 0.0,
+      "loss": 0.1248,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.9022556390977443,
+      "eval_f1": 0.8856624319419237,
+      "eval_loss": 0.2808963358402252,
+      "eval_precision": 0.8758364312267658,
+      "eval_recall": 0.8983451536643026,
+      "eval_runtime": 5.0985,
+      "eval_samples_per_second": 78.259,
+      "eval_steps_per_second": 9.807,
+      "step": 2440
+    },
+    {
+      "epoch": 20.0,
+      "step": 2440,
+      "total_flos": 8444128359504000.0,
+      "train_loss": 0.22104478507745462,
+      "train_runtime": 1931.1343,
+      "train_samples_per_second": 37.677,
+      "train_steps_per_second": 1.264
+    }
+  ],
+  "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
+}