End of training

README.md

@@ -1,13 +1,27 @@
 ---
 library_name: transformers
+language:
+- es
 base_model: dccuchile/bert-base-spanish-wwm-cased
 tags:
 - generated_from_trainer
+datasets:
+- jpherrerap/es_fakenews_dataset
 metrics:
 - f1
 model-index:
 - name: fake-news-bert-base-spanish-wwm-cased
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: jpherrerap/es_fakenews_dataset
+      type: jpherrerap/es_fakenews_dataset
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.8378378378378378
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fake-news-bert-base-spanish-wwm-cased
 
-This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
+This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the jpherrerap/es_fakenews_dataset dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3234
 - F1: 0.8378

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
-    "total_flos": 52622211072000.0,
-    "train_loss": 69.59579685756138,
-    "train_runtime": 22.694,
-    "train_samples": 100,
-    "train_samples_per_second": 8.813,
-    "train_steps_per_second": 0.617
+    "total_flos": 589368764006400.0,
+    "train_loss": 0.39655887058803013,
+    "train_runtime": 130.5105,
+    "train_samples": 1120,
+    "train_samples_per_second": 17.163,
+    "train_steps_per_second": 1.073
 }

predict_results_fake-news.txt

@@ -1,241 +1,241 @@
 index	prediction
 0	1
-1	1
+1	0
 2	1
 3	1
 4	1
 5	1
 6	1
 7	1
-8	1
-9	1
-10	1
-11	1
-12	1
-13	1
+8	0
+9	0
+10	0
+11	0
+12	0
+13	0
 14	1
-15	1
-16	1
-17	1
+15	0
+16	0
+17	0
 18	1
-19	1
-20	1
+19	0
+20	0
 21	1
 22	1
-23	1
+23	0
 24	1
 25	1
 26	1
 27	1
-28	1
+28	0
 29	1
-30	1
-31	1
+30	0
+31	0
 32	1
 33	1
 34	1
 35	1
 36	1
 37	1
-38	1
-39	1
-40	1
+38	0
+39	0
+40	0
 41	1
 42	1
 43	1
-44	1
-45	1
+44	0
+45	0
 46	1
-47	1
-48	1
-49	1
-50	1
-51	1
-52	1
+47	0
+48	0
+49	0
+50	0
+51	0
+52	0
 53	1
 54	1
-55	1
-56	1
+55	0
+56	0
 57	1
 58	1
 59	1
 60	1
 61	1
-62	1
-63	1
+62	0
+63	0
 64	1
 65	1
-66	1
-67	1
-68	1
+66	0
+67	0
+68	0
 69	1
-70	1
-71	1
+70	0
+71	0
 72	1
-73	1
+73	0
 74	1
-75	1
-76	1
-77	1
-78	1
+75	0
+76	0
+77	0
+78	0
 79	1
 80	1
-81	1
+81	0
 82	1
 83	1
 84	1
 85	1
-86	1
+86	0
 87	1
-88	1
+88	0
 89	1
-90	1
+90	0
 91	1
 92	1
 93	1
-94	1
-95	1
+94	0
+95	0
 96	1
-97	1
+97	0
 98	1
 99	1
 100	1
-101	1
-102	1
-103	1
+101	0
+102	0
+103	0
 104	1
-105	1
-106	1
+105	0
+106	0
 107	1
 108	1
 109	1
-110	1
-111	1
+110	0
+111	0
 112	1
-113	1
+113	0
 114	1
 115	1
-116	1
-117	1
-118	1
-119	1
-120	1
-121	1
-122	1
+116	0
+117	0
+118	0
+119	0
+120	0
+121	0
+122	0
 123	1
 124	1
 125	1
-126	1
-127	1
+126	0
+127	0
 128	1
-129	1
-130	1
+129	0
+130	0
 131	1
-132	1
-133	1
-134	1
+132	0
+133	0
+134	0
 135	1
-136	1
+136	0
 137	1
 138	1
-139	1
-140	1
-141	1
-142	1
+139	0
+140	0
+141	0
+142	0
 143	1
 144	1
-145	1
-146	1
+145	0
+146	0
 147	1
 148	1
-149	1
-150	1
+149	0
+150	0
 151	1
-152	1
+152	0
 153	1
-154	1
-155	1
+154	0
+155	0
 156	1
 157	1
 158	1
 159	1
 160	1
-161	1
-162	1
+161	0
+162	0
 163	1
-164	1
-165	1
-166	1
+164	0
+165	0
+166	0
 167	1
-168	1
+168	0
 169	1
 170	1
 171	1
 172	1
 173	1
-174	1
-175	1
-176	1
+174	0
+175	0
+176	0
 177	1
-178	1
+178	0
 179	1
-180	1
+180	0
 181	1
 182	1
-183	1
+183	0
 184	1
 185	1
-186	1
-187	1
+186	0
+187	0
 188	1
-189	1
-190	1
-191	1
-192	1
+189	0
+190	0
+191	0
+192	0
 193	1
-194	1
+194	0
 195	1
-196	1
+196	0
 197	1
-198	1
+198	0
 199	1
-200	1
+200	0
 201	1
 202	1
 203	1
 204	1
 205	1
-206	1
-207	1
-208	1
-209	1
+206	0
+207	0
+208	0
+209	0
 210	1
-211	1
-212	1
-213	1
-214	1
+211	0
+212	0
+213	0
+214	0
 215	1
-216	1
-217	1
+216	0
+217	0
 218	1
 219	1
 220	1
-221	1
+221	0
 222	1
-223	1
-224	1
-225	1
+223	0
+224	0
+225	0
 226	1
 227	1
-228	1
+228	0
 229	1
-230	1
-231	1
+230	0
+231	0
 232	1
-233	1
+233	0
 234	1
 235	1
 236	1
-237	1
-238	1
+237	0
+238	0
 239	1

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
-    "total_flos": 52622211072000.0,
-    "train_loss": 69.59579685756138,
-    "train_runtime": 22.694,
-    "train_samples": 100,
-    "train_samples_per_second": 8.813,
-    "train_steps_per_second": 0.617
+    "total_flos": 589368764006400.0,
+    "train_loss": 0.39655887058803013,
+    "train_runtime": 130.5105,
+    "train_samples": 1120,
+    "train_samples_per_second": 17.163,
+    "train_steps_per_second": 1.073
 }

trainer_state.json

@@ -1,58 +1,58 @@
 {
-  "best_global_step": 7,
-  "best_metric": 0.6516853932584269,
-  "best_model_checkpoint": "models/fake-news-bert-base-spanish-wwm-cased/checkpoint-7",
+  "best_global_step": 140,
+  "best_metric": 0.8378378378378378,
+  "best_model_checkpoint": "models/fake-news-bert-base-spanish-wwm-cased/checkpoint-140",
   "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 14,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 30.80777359008789,
-      "learning_rate": 0.2857142857142857,
-      "loss": 94.2083,
-      "step": 7
+      "grad_norm": 6.333802223205566,
+      "learning_rate": 1.0142857142857143e-05,
+      "loss": 0.5238,
+      "step": 70
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.6516853932584269,
-      "eval_loss": 81.0190658569336,
-      "eval_runtime": 3.5376,
-      "eval_samples_per_second": 67.842,
-      "eval_steps_per_second": 4.24,
-      "step": 7
+      "eval_f1": 0.7599999999999999,
+      "eval_loss": 0.42333319783210754,
+      "eval_runtime": 4.1419,
+      "eval_samples_per_second": 57.944,
+      "eval_steps_per_second": 3.621,
+      "step": 70
     },
     {
       "epoch": 2.0,
-      "grad_norm": 30.307811737060547,
-      "learning_rate": 0.03571428571428571,
-      "loss": 44.9833,
-      "step": 14
+      "grad_norm": 15.530929565429688,
+      "learning_rate": 1.4285714285714287e-07,
+      "loss": 0.2693,
+      "step": 140
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.0,
-      "eval_loss": 1.4185813665390015,
-      "eval_runtime": 3.5702,
-      "eval_samples_per_second": 67.224,
-      "eval_steps_per_second": 4.201,
-      "step": 14
+      "eval_f1": 0.8378378378378378,
+      "eval_loss": 0.3234243392944336,
+      "eval_runtime": 4.0599,
+      "eval_samples_per_second": 59.114,
+      "eval_steps_per_second": 3.695,
+      "step": 140
     },
     {
       "epoch": 2.0,
-      "step": 14,
-      "total_flos": 52622211072000.0,
-      "train_loss": 69.59579685756138,
-      "train_runtime": 22.694,
-      "train_samples_per_second": 8.813,
-      "train_steps_per_second": 0.617
+      "step": 140,
+      "total_flos": 589368764006400.0,
+      "train_loss": 0.39655887058803013,
+      "train_runtime": 130.5105,
+      "train_samples_per_second": 17.163,
+      "train_steps_per_second": 1.073
     }
   ],
   "logging_steps": 500,
-  "max_steps": 14,
+  "max_steps": 140,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 500,
@@ -68,7 +68,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 52622211072000.0,
+  "total_flos": 589368764006400.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null