End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4358
-- Accuracy: 0.8060
-- F1: 0.5738
-- Precision: 0.6364
-- Recall: 0.5224
+- Loss: 0.4202
+- Accuracy: 0.8030
+- F1: 0.6467
+- Precision: 0.5843
+- Recall: 0.7239
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8029739776951673,
+    "eval_f1": 0.6466666666666667,
+    "eval_loss": 0.4201844036579132,
+    "eval_precision": 0.5843373493975904,
+    "eval_recall": 0.7238805970149254,
+    "eval_runtime": 2.1692,
+    "eval_samples": 268,
+    "eval_samples_per_second": 248.019,
+    "eval_steps_per_second": 4.149,
+    "train_loss": 0.37881522374926696,
+    "train_runtime": 182.4457,
+    "train_samples": 1878,
+    "train_samples_per_second": 1029.347,
+    "train_steps_per_second": 32.338
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8029739776951673,
+    "eval_f1": 0.6466666666666667,
+    "eval_loss": 0.4201844036579132,
+    "eval_precision": 0.5843373493975904,
+    "eval_recall": 0.7238805970149254,
+    "eval_runtime": 2.1692,
+    "eval_samples": 268,
+    "eval_samples_per_second": 248.019,
+    "eval_steps_per_second": 4.149
+}

predict_results.txt

@@ -0,0 +1,539 @@
+index	prediction
+0	0
+1	0
+2	0
+3	1
+4	1
+5	0
+6	1
+7	1
+8	0
+9	0
+10	0
+11	0
+12	1
+13	0
+14	0
+15	1
+16	0
+17	1
+18	1
+19	0
+20	0
+21	0
+22	0
+23	1
+24	0
+25	0
+26	1
+27	1
+28	0
+29	0
+30	0
+31	1
+32	0
+33	1
+34	1
+35	0
+36	0
+37	0
+38	0
+39	0
+40	0
+41	0
+42	0
+43	0
+44	1
+45	0
+46	0
+47	0
+48	0
+49	0
+50	0
+51	0
+52	0
+53	1
+54	0
+55	0
+56	0
+57	0
+58	0
+59	0
+60	1
+61	0
+62	0
+63	0
+64	0
+65	0
+66	0
+67	0
+68	0
+69	0
+70	1
+71	1
+72	0
+73	1
+74	1
+75	1
+76	1
+77	0
+78	0
+79	0
+80	0
+81	0
+82	0
+83	1
+84	1
+85	0
+86	1
+87	0
+88	1
+89	0
+90	0
+91	0
+92	1
+93	1
+94	0
+95	0
+96	0
+97	1
+98	0
+99	1
+100	0
+101	0
+102	0
+103	0
+104	0
+105	1
+106	0
+107	0
+108	1
+109	0
+110	0
+111	1
+112	0
+113	0
+114	0
+115	0
+116	0
+117	0
+118	0
+119	1
+120	0
+121	1
+122	0
+123	0
+124	1
+125	0
+126	0
+127	0
+128	0
+129	0
+130	1
+131	0
+132	0
+133	0
+134	0
+135	0
+136	1
+137	0
+138	0
+139	0
+140	1
+141	1
+142	1
+143	0
+144	1
+145	0
+146	0
+147	1
+148	1
+149	1
+150	1
+151	1
+152	0
+153	0
+154	1
+155	0
+156	0
+157	0
+158	0
+159	0
+160	0
+161	0
+162	0
+163	1
+164	1
+165	0
+166	0
+167	1
+168	0
+169	0
+170	0
+171	1
+172	1
+173	0
+174	1
+175	0
+176	1
+177	0
+178	0
+179	1
+180	1
+181	0
+182	1
+183	1
+184	0
+185	1
+186	1
+187	1
+188	0
+189	1
+190	0
+191	0
+192	0
+193	0
+194	0
+195	1
+196	0
+197	1
+198	1
+199	0
+200	0
+201	0
+202	1
+203	1
+204	0
+205	1
+206	1
+207	0
+208	1
+209	0
+210	0
+211	0
+212	1
+213	0
+214	0
+215	0
+216	1
+217	1
+218	1
+219	0
+220	0
+221	0
+222	0
+223	0
+224	0
+225	0
+226	1
+227	0
+228	1
+229	0
+230	0
+231	1
+232	1
+233	0
+234	1
+235	0
+236	0
+237	1
+238	0
+239	0
+240	0
+241	0
+242	0
+243	0
+244	0
+245	0
+246	1
+247	0
+248	0
+249	1
+250	1
+251	1
+252	1
+253	0
+254	1
+255	0
+256	0
+257	0
+258	0
+259	0
+260	1
+261	1
+262	0
+263	0
+264	0
+265	1
+266	0
+267	0
+268	0
+269	0
+270	0
+271	1
+272	1
+273	0
+274	0
+275	0
+276	0
+277	0
+278	1
+279	0
+280	0
+281	0
+282	0
+283	0
+284	0
+285	0
+286	0
+287	0
+288	0
+289	0
+290	0
+291	0
+292	0
+293	1
+294	1
+295	0
+296	0
+297	0
+298	0
+299	0
+300	0
+301	1
+302	0
+303	1
+304	1
+305	0
+306	1
+307	0
+308	1
+309	1
+310	0
+311	0
+312	0
+313	1
+314	0
+315	0
+316	0
+317	0
+318	1
+319	0
+320	0
+321	0
+322	0
+323	0
+324	1
+325	1
+326	1
+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	1
+341	1
+342	0
+343	0
+344	1
+345	0
+346	1
+347	1
+348	1
+349	0
+350	0
+351	0
+352	0
+353	1
+354	0
+355	0
+356	0
+357	0
+358	0
+359	1
+360	0
+361	0
+362	0
+363	0
+364	1
+365	0
+366	1
+367	0
+368	1
+369	0
+370	0
+371	1
+372	0
+373	1
+374	0
+375	0
+376	0
+377	0
+378	1
+379	0
+380	1
+381	0
+382	1
+383	0
+384	1
+385	1
+386	0
+387	1
+388	0
+389	0
+390	1
+391	0
+392	1
+393	0
+394	1
+395	0
+396	1
+397	0
+398	1
+399	0
+400	0
+401	0
+402	0
+403	0
+404	0
+405	1
+406	1
+407	1
+408	0
+409	1
+410	0
+411	1
+412	0
+413	0
+414	0
+415	0
+416	1
+417	1
+418	0
+419	1
+420	1
+421	0
+422	1
+423	1
+424	0
+425	1
+426	1
+427	0
+428	0
+429	0
+430	0
+431	1
+432	0
+433	1
+434	1
+435	0
+436	1
+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	1
+450	0
+451	0
+452	0
+453	0
+454	0
+455	0
+456	1
+457	0
+458	0
+459	0
+460	0
+461	0
+462	0
+463	0
+464	0
+465	0
+466	1
+467	1
+468	0
+469	1
+470	0
+471	1
+472	1
+473	0
+474	0
+475	1
+476	0
+477	0
+478	0
+479	0
+480	1
+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	1
+494	1
+495	1
+496	1
+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	1
+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	0
+535	1
+536	1
+537	1

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.37881522374926696,
+    "train_runtime": 182.4457,
+    "train_samples": 1878,
+    "train_samples_per_second": 1029.347,
+    "train_steps_per_second": 32.338
+}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": 0.662251655629139,
+  "best_model_checkpoint": "outputs/indobert-base-uncased-twitter-indonesia-sarcastic/checkpoint-236",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 413,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.997697221833061e-06,
+      "loss": 0.5531,
+      "step": 59
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7723880597014925,
+      "eval_f1": 0.4077669902912622,
+      "eval_loss": 0.4976803660392761,
+      "eval_precision": 0.5833333333333334,
+      "eval_recall": 0.31343283582089554,
+      "eval_runtime": 1.068,
+      "eval_samples_per_second": 250.933,
+      "eval_steps_per_second": 4.682,
+      "step": 59
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.990791008447151e-06,
+      "loss": 0.4992,
+      "step": 118
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7723880597014925,
+      "eval_f1": 0.3440860215053763,
+      "eval_loss": 0.47853246331214905,
+      "eval_precision": 0.6153846153846154,
+      "eval_recall": 0.23880597014925373,
+      "eval_runtime": 1.066,
+      "eval_samples_per_second": 251.4,
+      "eval_steps_per_second": 4.69,
+      "step": 118
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.979044933876465e-06,
+      "loss": 0.44,
+      "step": 177
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7798507462686567,
+      "eval_f1": 0.3655913978494624,
+      "eval_loss": 0.48192882537841797,
+      "eval_precision": 0.6538461538461539,
+      "eval_recall": 0.2537313432835821,
+      "eval_runtime": 1.0667,
+      "eval_samples_per_second": 251.249,
+      "eval_steps_per_second": 4.687,
+      "step": 177
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.962224338961997e-06,
+      "loss": 0.3815,
+      "step": 236
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8097014925373134,
+      "eval_f1": 0.662251655629139,
+      "eval_loss": 0.4523766338825226,
+      "eval_precision": 0.5952380952380952,
+      "eval_recall": 0.746268656716418,
+      "eval_runtime": 1.0729,
+      "eval_samples_per_second": 249.795,
+      "eval_steps_per_second": 4.66,
+      "step": 236
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.940506627721576e-06,
+      "loss": 0.3104,
+      "step": 295
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8171641791044776,
+      "eval_f1": 0.5420560747663551,
+      "eval_loss": 0.4547075927257538,
+      "eval_precision": 0.725,
+      "eval_recall": 0.43283582089552236,
+      "eval_runtime": 1.0733,
+      "eval_samples_per_second": 249.7,
+      "eval_steps_per_second": 4.659,
+      "step": 295
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 9.913913232914188e-06,
+      "loss": 0.2592,
+      "step": 354
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8171641791044776,
+      "eval_f1": 0.5663716814159292,
+      "eval_loss": 0.40578439831733704,
+      "eval_precision": 0.6956521739130435,
+      "eval_recall": 0.47761194029850745,
+      "eval_runtime": 1.0671,
+      "eval_samples_per_second": 251.149,
+      "eval_steps_per_second": 4.686,
+      "step": 354
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 9.882470399009847e-06,
+      "loss": 0.2083,
+      "step": 413
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8059701492537313,
+      "eval_f1": 0.5737704918032788,
+      "eval_loss": 0.4358327090740204,
+      "eval_precision": 0.6363636363636364,
+      "eval_recall": 0.5223880597014925,
+      "eval_runtime": 1.0662,
+      "eval_samples_per_second": 251.356,
+      "eval_steps_per_second": 4.689,
+      "step": 413
+    },
+    {
+      "epoch": 7.0,
+      "step": 413,
+      "total_flos": 864714483440640.0,
+      "train_loss": 0.37881522374926696,
+      "train_runtime": 182.4457,
+      "train_samples_per_second": 1029.347,
+      "train_steps_per_second": 32.338
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 864714483440640.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}