adding model finetuned on NER

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9592208294396288,
+    "eval_f1": 0.7977113603854551,
+    "eval_loss": 0.142496719956398,
+    "eval_precision": 0.7950180072028812,
+    "eval_recall": 0.8004230246260764,
+    "eval_runtime": 1.7114,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 1119.532,
+    "eval_steps_per_second": 35.058,
+    "train_loss": 0.1423617688175362,
+    "train_runtime": 34.8094,
+    "train_samples": 8324,
+    "train_samples_per_second": 717.393,
+    "train_steps_per_second": 22.494
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "CenIA/distillbert-base-spanish-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "ner",
+  "hidden_dim": 3072,
+  "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,
+  "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
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "vocab_size": 31002
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9592208294396288,
+    "eval_f1": 0.7977113603854551,
+    "eval_loss": 0.142496719956398,
+    "eval_precision": 0.7950180072028812,
+    "eval_recall": 0.8004230246260764,
+    "eval_runtime": 1.7114,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 1119.532,
+    "eval_steps_per_second": 35.058
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed4d302c84626a363602f463b093875bd7710cc9602a0041a24818e4d153fd9
+size 266993141

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, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/distillbert-base-spanish-uncased", "tokenizer_class": "DistilBertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.1423617688175362,
+    "train_runtime": 34.8094,
+    "train_samples": 8324,
+    "train_samples_per_second": 717.393,
+    "train_steps_per_second": 22.494
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 783,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.826309067688378e-05,
+      "loss": 0.1857,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 783,
+      "total_flos": 630881172395712.0,
+      "train_loss": 0.1423617688175362,
+      "train_runtime": 34.8094,
+      "train_samples_per_second": 717.393,
+      "train_steps_per_second": 22.494
+    }
+  ],
+  "max_steps": 783,
+  "num_train_epochs": 3,
+  "total_flos": 630881172395712.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf6ad43cabf28d1f8700d1ffd4838c62088e573fc3604d73ed8c5c09ca6fa79
+size 2863