Training complete

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: mrm8488/electricidad-base-discriminator
+license: cc-by-4.0
+base_model: bertin-project/bertin-base-ner-conll2002-es
 tags:
 - classification
 - generated_from_trainer
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DiagTrast
 
-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 [bertin-project/bertin-base-ner-conll2002-es](https://huggingface.co/bertin-project/bertin-base-ner-conll2002-es) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0024
+- Loss: 0.0004
 - Accuracy: 1.0
 
 ## Model description
@@ -49,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 134  | 0.0092          | 1.0      |
-| No log        | 2.0   | 268  | 0.0031          | 1.0      |
-| No log        | 3.0   | 402  | 0.0024          | 1.0      |
+| No log        | 1.0   | 134  | 0.0008          | 1.0      |
+| No log        | 2.0   | 268  | 0.0005          | 1.0      |
+| No log        | 3.0   | 402  | 0.0004          | 1.0      |
 
 
 ### Framework versions

config.json

@@ -1,11 +1,14 @@
 {
-  "_name_or_path": "mrm8488/electricidad-base-discriminator",
+  "_name_or_path": "bertin-project/bertin-base-ner-conll2002-es",
   "architectures": [
-    "ElectraForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "embedding_size": 768,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -25,21 +28,17 @@
     "LABEL_3": 3,
     "LABEL_4": 4
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "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": "4.35.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 31002
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a5ce1de39e350ffaa1685277a358376be91afb6e4661abb9c0843224fcfc05
-size 439443036
+oid sha256:715da91ba0b9297baf3ab2445089e2282b5fb0fe2616e5ba9647e1a84914ebd9
+size 498622052

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,7 +1,8 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "[MASK]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,49 +10,55 @@
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[CLS]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "[SEP]",
-      "lstrip": false,
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
-  "unk_token": "[UNK]"
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:577256af483deea9e811f24780f3ec050fb29fd08bbaafbe6421baa61acd5d03
+oid sha256:4bc3806ada792af750a7fdf89a6befaa896d5b32a76fa8a4886bb8b6b9db7509
 size 4664