End of training

Browse files

Files changed (6) hide show

README.md +5 -5
all_results.json +17 -0
eval_results.json +12 -0
predict_results.txt +539 -0
train_results.json +8 -0
trainer_state.json +192 -0

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8350
-- Accuracy: 0.8209
-- F1: 0.5385
-- Precision: 0.7568
-- Recall: 0.4179
 ## Model description

 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.4720
+- Accuracy: 0.8290
+- F1: 0.6462
+- Precision: 0.6667
+- Recall: 0.6269
 ## Model description

all_results.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.828996282527881,
+    "eval_f1": 0.6461538461538462,
+    "eval_loss": 0.4720025956630707,
+    "eval_precision": 0.6666666666666666,
+    "eval_recall": 0.6268656716417911,
+    "eval_runtime": 2.1632,
+    "eval_samples": 268,
+    "eval_samples_per_second": 248.706,
+    "eval_steps_per_second": 4.161,
+    "train_loss": 0.2750625179312323,
+    "train_runtime": 261.0331,
+    "train_samples": 1878,
+    "train_samples_per_second": 719.449,
+    "train_steps_per_second": 22.602
+}

eval_results.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.828996282527881,
+    "eval_f1": 0.6461538461538462,
+    "eval_loss": 0.4720025956630707,
+    "eval_precision": 0.6666666666666666,
+    "eval_recall": 0.6268656716417911,
+    "eval_runtime": 2.1632,
+    "eval_samples": 268,
+    "eval_samples_per_second": 248.706,
+    "eval_steps_per_second": 4.161
+}

predict_results.txt ADDED Viewed

	@@ -0,0 +1,539 @@

+index	prediction
+0	1
+1	0
+2	0
+3	1
+4	0
+5	0
+6	1
+7	1
+8	1
+9	0
+10	0
+11	0
+12	1
+13	0
+14	0
+15	1
+16	1
+17	0
+18	0
+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	0
+32	0
+33	1
+34	0
+35	0
+36	0
+37	0
+38	0
+39	0
+40	0
+41	0
+42	0
+43	0
+44	0
+45	0
+46	0
+47	0
+48	0
+49	0
+50	0
+51	0
+52	0
+53	0
+54	0
+55	0
+56	0
+57	0
+58	0
+59	0
+60	0
+61	0
+62	0
+63	0
+64	0
+65	0
+66	1
+67	0
+68	0
+69	0
+70	1
+71	0
+72	0
+73	1
+74	0
+75	1
+76	0
+77	1
+78	0
+79	0
+80	0
+81	1
+82	0
+83	1
+84	0
+85	0
+86	0
+87	0
+88	0
+89	0
+90	0
+91	0
+92	0
+93	0
+94	0
+95	0
+96	1
+97	1
+98	0
+99	0
+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	1
+118	0
+119	1
+120	0
+121	0
+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	0
+137	0
+138	0
+139	0
+140	1
+141	0
+142	1
+143	0
+144	1
+145	0
+146	0
+147	1
+148	0
+149	0
+150	0
+151	0
+152	0
+153	0
+154	0
+155	0
+156	0
+157	0
+158	0
+159	0
+160	0
+161	0
+162	0
+163	1
+164	0
+165	0
+166	0
+167	0
+168	0
+169	0
+170	0
+171	1
+172	0
+173	0
+174	1
+175	0
+176	1
+177	0
+178	0
+179	0
+180	1
+181	0
+182	0
+183	0
+184	0
+185	1
+186	1
+187	1
+188	0
+189	0
+190	0
+191	0
+192	0
+193	1
+194	0
+195	1
+196	0
+197	0
+198	1
+199	0
+200	0
+201	0
+202	1
+203	1
+204	0
+205	1
+206	0
+207	0
+208	0
+209	0
+210	0
+211	0
+212	0
+213	0
+214	0
+215	0
+216	1
+217	0
+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	0
+233	0
+234	0
+235	0
+236	0
+237	1
+238	0
+239	0
+240	1
+241	0
+242	0
+243	0
+244	0
+245	0
+246	1
+247	0
+248	0
+249	1
+250	0
+251	1
+252	0
+253	1
+254	0
+255	0
+256	0
+257	1
+258	0
+259	0
+260	1
+261	0
+262	0
+263	0
+264	0
+265	0
+266	1
+267	0
+268	0
+269	0
+270	0
+271	1
+272	0
+273	1
+274	0
+275	0
+276	0
+277	0
+278	1
+279	0
+280	0
+281	0
+282	1
+283	0
+284	0
+285	0
+286	0
+287	0
+288	0
+289	0
+290	0
+291	0
+292	1
+293	0
+294	1
+295	0
+296	0
+297	1
+298	1
+299	0
+300	0
+301	1
+302	0
+303	0
+304	0
+305	0
+306	1
+307	0
+308	1
+309	0
+310	0
+311	0
+312	0
+313	0
+314	0
+315	0
+316	0
+317	1
+318	0
+319	0
+320	1
+321	1
+322	0
+323	0
+324	0
+325	0
+326	1
+327	0
+328	0
+329	0
+330	1
+331	1
+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	0
+345	0
+346	1
+347	0
+348	0
+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	1
+363	0
+364	0
+365	0
+366	1
+367	0
+368	1
+369	0
+370	0
+371	1
+372	0
+373	0
+374	0
+375	0
+376	0
+377	0
+378	1
+379	1
+380	1
+381	0
+382	0
+383	0
+384	1
+385	0
+386	0
+387	0
+388	1
+389	0
+390	1
+391	0
+392	1
+393	0
+394	1
+395	0
+396	0
+397	0
+398	1
+399	0
+400	0
+401	0
+402	0
+403	1
+404	0
+405	1
+406	0
+407	1
+408	0
+409	0
+410	0
+411	0
+412	1
+413	0
+414	0
+415	0
+416	0
+417	0
+418	1
+419	0
+420	1
+421	0
+422	1
+423	1
+424	0
+425	0
+426	0
+427	0
+428	0
+429	0
+430	0
+431	1
+432	0
+433	0
+434	1
+435	0
+436	1
+437	0
+438	0
+439	0
+440	0
+441	1
+442	0
+443	0
+444	0
+445	0
+446	1
+447	0
+448	0
+449	1
+450	0
+451	1
+452	0
+453	0
+454	0
+455	0
+456	1
+457	0
+458	0
+459	0
+460	0
+461	0
+462	0
+463	1
+464	0
+465	0
+466	0
+467	0
+468	0
+469	1
+470	1
+471	1
+472	0
+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	1
+487	1
+488	0
+489	0
+490	0
+491	0
+492	0
+493	0
+494	1
+495	1
+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	1
+519	1
+520	0
+521	0
+522	0
+523	0
+524	0
+525	0
+526	0
+527	0
+528	0
+529	0
+530	1
+531	0
+532	0
+533	0
+534	0
+535	0
+536	1
+537	1

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 9.0,
+    "train_loss": 0.2750625179312323,
+    "train_runtime": 261.0331,
+    "train_samples": 1878,
+    "train_samples_per_second": 719.449,
+    "train_steps_per_second": 22.602
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,192 @@

+{
+  "best_metric": 0.706896551724138,
+  "best_model_checkpoint": "outputs/bert-base-multilingual-cased-twitter-indonesia-sarcastic/checkpoint-354",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 531,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.99761572031246e-06,
+      "loss": 0.5333,
+      "step": 59
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.75,
+      "eval_f1": 0.0,
+      "eval_loss": 0.47915688157081604,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 1.0725,
+      "eval_samples_per_second": 249.878,
+      "eval_steps_per_second": 4.662,
+      "step": 59
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.990465155165683e-06,
+      "loss": 0.4642,
+      "step": 118
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7910447761194029,
+      "eval_f1": 0.3,
+      "eval_loss": 0.4418473243713379,
+      "eval_precision": 0.9230769230769231,
+      "eval_recall": 0.1791044776119403,
+      "eval_runtime": 1.0651,
+      "eval_samples_per_second": 251.625,
+      "eval_steps_per_second": 4.694,
+      "step": 118
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.978555124138569e-06,
+      "loss": 0.3961,
+      "step": 177
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8134328358208955,
+      "eval_f1": 0.5192307692307693,
+      "eval_loss": 0.4319072365760803,
+      "eval_precision": 0.7297297297297297,
+      "eval_recall": 0.40298507462686567,
+      "eval_runtime": 1.0672,
+      "eval_samples_per_second": 251.127,
+      "eval_steps_per_second": 4.685,
+      "step": 177
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.961568226140335e-06,
+      "loss": 0.325,
+      "step": 236
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.746268656716418,
+      "eval_f1": 0.6179775280898877,
+      "eval_loss": 0.5264418721199036,
+      "eval_precision": 0.4954954954954955,
+      "eval_recall": 0.8208955223880597,
+      "eval_runtime": 1.0669,
+      "eval_samples_per_second": 251.206,
+      "eval_steps_per_second": 4.687,
+      "step": 236
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.93968485932029e-06,
+      "loss": 0.2432,
+      "step": 295
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8246268656716418,
+      "eval_f1": 0.6299212598425197,
+      "eval_loss": 0.4624307453632355,
+      "eval_precision": 0.6666666666666666,
+      "eval_recall": 0.5970149253731343,
+      "eval_runtime": 1.064,
+      "eval_samples_per_second": 251.884,
+      "eval_steps_per_second": 4.699,
+      "step": 295
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 9.912926619919478e-06,
+      "loss": 0.1819,
+      "step": 354
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8731343283582089,
+      "eval_f1": 0.706896551724138,
+      "eval_loss": 0.42611974477767944,
+      "eval_precision": 0.8367346938775511,
+      "eval_recall": 0.6119402985074627,
+      "eval_runtime": 1.0705,
+      "eval_samples_per_second": 250.352,
+      "eval_steps_per_second": 4.671,
+      "step": 354
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 9.881319915089625e-06,
+      "loss": 0.148,
+      "step": 413
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8544776119402985,
+      "eval_f1": 0.6776859504132231,
+      "eval_loss": 0.5371143817901611,
+      "eval_precision": 0.7592592592592593,
+      "eval_recall": 0.6119402985074627,
+      "eval_runtime": 1.0641,
+      "eval_samples_per_second": 251.866,
+      "eval_steps_per_second": 4.699,
+      "step": 413
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.844895936832474e-06,
+      "loss": 0.0995,
+      "step": 472
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8395522388059702,
+      "eval_f1": 0.6766917293233083,
+      "eval_loss": 0.6810328364372253,
+      "eval_precision": 0.6818181818181818,
+      "eval_recall": 0.6716417910447762,
+      "eval_runtime": 1.0652,
+      "eval_samples_per_second": 251.603,
+      "eval_steps_per_second": 4.694,
+      "step": 472
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 9.803690631217043e-06,
+      "loss": 0.0843,
+      "step": 531
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8208955223880597,
+      "eval_f1": 0.5384615384615384,
+      "eval_loss": 0.8350497484207153,
+      "eval_precision": 0.7567567567567568,
+      "eval_recall": 0.417910447761194,
+      "eval_runtime": 1.0631,
+      "eval_samples_per_second": 252.096,
+      "eval_steps_per_second": 4.703,
+      "step": 531
+    },
+    {
+      "epoch": 9.0,
+      "step": 531,
+      "total_flos": 1111775764423680.0,
+      "train_loss": 0.2750625179312323,
+      "train_runtime": 261.0331,
+      "train_samples_per_second": 719.449,
+      "train_steps_per_second": 22.602
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 1111775764423680.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}