adding model finetuned on NER

all_results.json

@@ -0,0 +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,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 780.931,
+    "eval_steps_per_second": 24.455,
+    "train_loss": 0.1520482674623147,
+    "train_runtime": 60.137,
+    "train_samples": 8324,
+    "train_samples_per_second": 415.252,
+    "train_steps_per_second": 6.485
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

eval_results.json

@@ -0,0 +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,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 780.931,
+    "eval_steps_per_second": 24.455
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3f6f2a34b4ed4a4d2438d9b58e02d2b5e00d3b25b05c70a86cd8f726ab131e
+size 437152241

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +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"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.1520482674623147,
+    "train_runtime": 60.137,
+    "train_samples": 8324,
+    "train_samples_per_second": 415.252,
+    "train_steps_per_second": 6.485
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.996168582375479,
+  "global_step": 390,
+  "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
+    }
+  ],
+  "max_steps": 390,
+  "num_train_epochs": 3,
+  "total_flos": 1317394636151616.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b3d18d1ce5672169916be5447d419ae0d2664c40264be77bcd86e31352b753
+size 2863