Training complete

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: mrm8488/electricidad-base-discriminator
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-cased
 tags:
 - classification
 - generated_from_trainer
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clasificador-muchocine
 
-This model is a fine-tuned version of [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on the None dataset.
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4578
-- Accuracy: 0.4452
+- Loss: 1.5252
+- Accuracy: 0.3355
 
 ## Model description
 
@@ -49,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 388  | 1.3209          | 0.3935   |
-| 1.3791        | 2.0   | 776  | 1.3147          | 0.4297   |
-| 0.9521        | 3.0   | 1164 | 1.4578          | 0.4452   |
+| No log        | 1.0   | 388  | 1.5330          | 0.3355   |
+| 1.5357        | 2.0   | 776  | 1.5317          | 0.3355   |
+| 1.5245        | 3.0   | 1164 | 1.5252          | 0.3355   |
 
 
 ### Framework versions

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "mrm8488/electricidad-base-discriminator",
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
   "architectures": [
-    "ElectraForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "embedding_size": 768,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -27,19 +27,20 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "electra",
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "summary_activation": "gelu",
-  "summary_last_dropout": 0.1,
-  "summary_type": "first",
-  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 31002
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce233ac46b4dbff850438d87b86cf7e6d3bcf0185e3da548d0f923338414124a
-size 439443036
+oid sha256:44051a862c206ad9480860a82a6e6da15828b5a42cd25559681eccb7687011e5
+size 711452684

tokenizer_config.json

@@ -1,39 +1,39 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[MASK]",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[PAD]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[CLS]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "[SEP]",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -43,15 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
+  "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8141d4e1d807338042816937388b0928eeb5634a5fad55fca19466fbc65c36a0
+oid sha256:196d5aac643635701e3ad80df3643ce55c2ff528fc6870d9de8ae5520ee7bec5
 size 4984