End of training

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.5543336676785267,
-    "train_runtime": 347.758,
+    "epoch": 5.0,
+    "train_loss": 0.4667576571544969,
+    "train_runtime": 491.7868,
     "train_samples": 7964,
-    "train_samples_per_second": 68.703,
-    "train_steps_per_second": 2.864
+    "train_samples_per_second": 80.97,
+    "train_steps_per_second": 1.688
 }

predict_results_spanish-offensive-language.txt

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

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.5543336676785267,
-    "train_runtime": 347.758,
+    "epoch": 5.0,
+    "train_loss": 0.4667576571544969,
+    "train_runtime": 491.7868,
     "train_samples": 7964,
-    "train_samples_per_second": 68.703,
-    "train_steps_per_second": 2.864
+    "train_samples_per_second": 80.97,
+    "train_steps_per_second": 1.688
 }

trainer_state.json

@@ -1,70 +1,100 @@
 {
-  "best_metric": 0.6014237329035705,
-  "best_model_checkpoint": "models/spanish-offensive-language-bert-base-spanish-wwm-cased/checkpoint-996",
-  "epoch": 3.0,
-  "global_step": 996,
+  "best_metric": 0.5861096817040292,
+  "best_model_checkpoint": "models/spanish-offensive-language-bert-base-spanish-wwm-cased/checkpoint-664",
+  "epoch": 5.0,
+  "global_step": 830,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 1.3333333333333333e-05,
-      "loss": 0.6335,
-      "step": 332
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.6383,
+      "step": 166
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.5017770187437626,
-      "eval_loss": 0.6012123823165894,
-      "eval_runtime": 5.4247,
-      "eval_samples_per_second": 181.393,
-      "eval_steps_per_second": 7.558,
+      "eval_f1": 0.49156525826500225,
+      "eval_loss": 0.6105424165725708,
+      "eval_runtime": 4.1796,
+      "eval_samples_per_second": 211.743,
+      "eval_steps_per_second": 4.546,
+      "step": 166
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5779,
       "step": 332
     },
     {
       "epoch": 2.0,
-      "learning_rate": 6.666666666666667e-06,
-      "loss": 0.5659,
+      "eval_f1": 0.5531108537740815,
+      "eval_loss": 0.6026707887649536,
+      "eval_runtime": 4.3621,
+      "eval_samples_per_second": 202.885,
+      "eval_steps_per_second": 4.356,
+      "step": 332
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4791,
+      "step": 498
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.5851959878843573,
+      "eval_loss": 0.6503026485443115,
+      "eval_runtime": 4.2153,
+      "eval_samples_per_second": 209.95,
+      "eval_steps_per_second": 4.507,
+      "step": 498
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3626,
       "step": 664
     },
     {
-      "epoch": 2.0,
-      "eval_f1": 0.5776452050829993,
-      "eval_loss": 0.5975989103317261,
-      "eval_runtime": 5.271,
-      "eval_samples_per_second": 186.682,
-      "eval_steps_per_second": 7.778,
+      "epoch": 4.0,
+      "eval_f1": 0.5861096817040292,
+      "eval_loss": 0.7753247022628784,
+      "eval_runtime": 4.374,
+      "eval_samples_per_second": 202.334,
+      "eval_steps_per_second": 4.344,
       "step": 664
     },
     {
-      "epoch": 3.0,
+      "epoch": 5.0,
       "learning_rate": 0.0,
-      "loss": 0.4636,
-      "step": 996
+      "loss": 0.2758,
+      "step": 830
     },
     {
-      "epoch": 3.0,
-      "eval_f1": 0.6014237329035705,
-      "eval_loss": 0.6521763801574707,
-      "eval_runtime": 5.4331,
-      "eval_samples_per_second": 181.113,
-      "eval_steps_per_second": 7.546,
-      "step": 996
+      "epoch": 5.0,
+      "eval_f1": 0.5855743933442549,
+      "eval_loss": 0.8416333794593811,
+      "eval_runtime": 4.2197,
+      "eval_samples_per_second": 209.729,
+      "eval_steps_per_second": 4.503,
+      "step": 830
     },
     {
-      "epoch": 3.0,
-      "step": 996,
-      "total_flos": 6286249334661120.0,
-      "train_loss": 0.5543336676785267,
-      "train_runtime": 347.758,
-      "train_samples_per_second": 68.703,
-      "train_steps_per_second": 2.864
+      "epoch": 5.0,
+      "step": 830,
+      "total_flos": 1.04770822244352e+16,
+      "train_loss": 0.4667576571544969,
+      "train_runtime": 491.7868,
+      "train_samples_per_second": 80.97,
+      "train_steps_per_second": 1.688
     }
   ],
-  "max_steps": 996,
-  "num_train_epochs": 3,
-  "total_flos": 6286249334661120.0,
+  "max_steps": 830,
+  "num_train_epochs": 5,
+  "total_flos": 1.04770822244352e+16,
   "trial_name": null,
   "trial_params": null
 }