Update model

README.md

@@ -9,9 +9,10 @@ tags:
 - roberta-base-bne
 widget:
 - text: "Fue antes de llegar a Sigüeiro, en el Camino de Santiago."
-- text: "El proyecto lo financia el Ministerio de Industria y Competitividad."
+- text: "Si te metes en el Franco desde la Alameda, vas hacia la Catedral."
+- text: "Y allí precisamente es Santiago el patrón del pueblo."
 model-index:
-- name: roberta-bne-ner-cds
+- name: es_trf_ner_cds_bne-base
   results: []
 ---
 
@@ -44,13 +45,13 @@ ToDo
 
 entity|precision|recall|f1
 -|-|-|-
-PER|0.965|0.924|0.944
-ORG|0.900|0.701|0.788
-LOC|0.982|0.985|0.983
-MISC|0.798|0.874|0.834
-micro avg|0.964|0.968|0.966|4265
-macro avg|0.911|0.871|0.887
-weighted avg|0.965|0.968|0.966
+LOC|0.986|0.982|0.984
+MISC|0.800|0.911|0.852
+ORG|0.896|0.779|0.833
+PER|0.953|0.937|0.945
+micro avg|0.967|0.971|0.969
+macro avg|0.909|0.902|0.903
+weighted avg|0.968|0.971|0.969
 
 ## Training procedure
 
@@ -67,7 +68,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.25.1
-- Pytorch 1.13.0+cu117
-- Datasets 2.7.1
-- Tokenizers 0.13.2
+- Transformers 4.28.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9983546594777942,
+    "eval_f1": 0.9674450707465777,
+    "eval_loss": 0.007044909987598658,
+    "eval_precision": 0.9653351698806244,
+    "eval_recall": 0.9695642148950888,
+    "eval_runtime": 16.6647,
+    "eval_samples": 15178,
+    "eval_samples_per_second": 910.788,
+    "eval_steps_per_second": 113.893,
+    "train_loss": 0.009494402144574594,
+    "train_runtime": 283.3545,
+    "train_samples": 45533,
+    "train_samples_per_second": 482.078,
+    "train_steps_per_second": 15.066
+}

config.json

@@ -44,7 +44,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
+  "transformers_version": "4.28.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50262

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
+#version: 0.2
 Ġ d
 Ġ e
 Ġd e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54853750d9a7acb21f7ab654bfdbed2a01f46f209e9d1aaf9502cf1952e8c4ed
+oid sha256:2e8e6d0cf96f427fbddf174a0d9bc41f7fb4d1b73748577b86c83194d9e87fbc
 size 496311341

tokenizer.json

@@ -87,6 +87,7 @@
     "continuing_subword_prefix": "",
     "end_of_word_suffix": "",
     "fuse_unk": false,
+    "byte_fallback": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

tokenizer_config.json

@@ -8,6 +8,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "clean_up_tokenization_spaces": true,
   "cls_token": {
     "__type": "AddedToken",
     "content": "<s>",
@@ -35,7 +36,6 @@
   },
   "max_len": 512,
   "model_max_length": 512,
-  "name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
   "pad_token": {
     "__type": "AddedToken",
     "content": "<pad>",
@@ -52,7 +52,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "special_tokens_map_file": null,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
   "unk_token": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1283c01fe20d44d8f566f373f9c0086927abb23b9c7e7c7f8d3a5c64e28dff
-size 3515
+oid sha256:4f96df4c64e04e69808c64c6b2f9a77af877cb3296b929a31ceaaa1e32e0cb04
+size 3579