best beto-cased finetuned on ner

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.95851718399316,
-    "eval_f1": 0.8314965836455808,
-    "eval_loss": 0.14730381965637207,
-    "eval_precision": 0.8240498034076016,
-    "eval_recall": 0.8390791814946619,
-    "eval_runtime": 2.4535,
+    "epoch": 2.0,
+    "eval_accuracy": 0.9687422514257377,
+    "eval_f1": 0.8454963839579225,
+    "eval_loss": 0.11907459050416946,
+    "eval_precision": 0.8427260812581914,
+    "eval_recall": 0.8482849604221636,
+    "eval_runtime": 2.5002,
     "eval_samples": 1916,
-    "eval_samples_per_second": 780.931,
-    "eval_steps_per_second": 24.455,
-    "train_loss": 0.1520482674623147,
-    "train_runtime": 60.137,
+    "eval_samples_per_second": 766.338,
+    "eval_steps_per_second": 47.996,
+    "train_loss": 0.11060212357686117,
+    "train_runtime": 43.5566,
     "train_samples": 8324,
-    "train_samples_per_second": 415.252,
-    "train_steps_per_second": 6.485
+    "train_samples_per_second": 382.215,
+    "train_steps_per_second": 11.938
 }

config.json

@@ -43,7 +43,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.12.5",
+  "transformers_version": "4.11.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 31002

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.95851718399316,
-    "eval_f1": 0.8314965836455808,
-    "eval_loss": 0.14730381965637207,
-    "eval_precision": 0.8240498034076016,
-    "eval_recall": 0.8390791814946619,
-    "eval_runtime": 2.4535,
+    "epoch": 2.0,
+    "eval_accuracy": 0.9687422514257377,
+    "eval_f1": 0.8454963839579225,
+    "eval_loss": 0.11907459050416946,
+    "eval_precision": 0.8427260812581914,
+    "eval_recall": 0.8482849604221636,
+    "eval_runtime": 2.5002,
     "eval_samples": 1916,
-    "eval_samples_per_second": 780.931,
-    "eval_steps_per_second": 24.455
+    "eval_samples_per_second": 766.338,
+    "eval_steps_per_second": 47.996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3f6f2a34b4ed4a4d2438d9b58e02d2b5e00d3b25b05c70a86cd8f726ab131e
+oid sha256:c1efcfa19f5863956fed24c9ac37a1ee48b76dc8ba1340a27c546a8af3b94387
 size 437152241

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "name_or_path": "dccuchile/bert-base-spanish-wwm-cased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/data/sdonoso/cache/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "name_or_path": "dccuchile/bert-base-spanish-wwm-cased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/data/sdonoso/cache/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 0.1520482674623147,
-    "train_runtime": 60.137,
+    "epoch": 2.0,
+    "train_loss": 0.11060212357686117,
+    "train_runtime": 43.5566,
     "train_samples": 8324,
-    "train_samples_per_second": 415.252,
-    "train_steps_per_second": 6.485
+    "train_samples_per_second": 382.215,
+    "train_steps_per_second": 11.938
 }

trainer_state.json

@@ -1,25 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.996168582375479,
-  "global_step": 390,
+  "epoch": 1.9980806142034548,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.0,
-      "step": 390,
-      "total_flos": 1317394636151616.0,
-      "train_loss": 0.1520482674623147,
-      "train_runtime": 60.137,
-      "train_samples_per_second": 415.252,
-      "train_steps_per_second": 6.485
+      "epoch": 1.92,
+      "learning_rate": 2.211538461538462e-06,
+      "loss": 0.1134,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "step": 520,
+      "total_flos": 751961665666944.0,
+      "train_loss": 0.11060212357686117,
+      "train_runtime": 43.5566,
+      "train_samples_per_second": 382.215,
+      "train_steps_per_second": 11.938
     }
   ],
-  "max_steps": 390,
-  "num_train_epochs": 3,
-  "total_flos": 1317394636151616.0,
+  "max_steps": 520,
+  "num_train_epochs": 2,
+  "total_flos": 751961665666944.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b3d18d1ce5672169916be5447d419ae0d2664c40264be77bcd86e31352b753
+oid sha256:f0cbf9a88f9977fd62d1e683845de87db32f9d5f745b23bcea254a484eeffd4a
 size 2863