Training in progress, epoch 1

config.json

@@ -1,49 +1,34 @@
 {
-  "_name_or_path": "NazaGara/NER-fine-tuned-BETO",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "BertForTokenClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "O",
-    "1": "B-PER",
-    "2": "I-PER",
-    "3": "B-ORG",
-    "4": "I-ORG",
-    "5": "B-LOC",
-    "6": "I-LOC",
-    "7": "B-MISC",
-    "8": "I-MISC"
+    "0": "World",
+    "1": "Sports",
+    "2": "Business",
+    "3": "Sci/Tech"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "B-LOC": 5,
-    "B-MISC": 7,
-    "B-ORG": 3,
-    "B-PER": 1,
-    "I-LOC": 6,
-    "I-MISC": 8,
-    "I-ORG": 4,
-    "I-PER": 2,
-    "O": 0
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2",
-  "type_vocab_size": 2,
+  "transformers_version": "4.41.1",
+  "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 sha256:5ee23b210df83ffc1dac912b6a7edef11bf0147309f11ecae0c1a8153fc89f12
-size 437092180
+oid sha256:5d96c5089ced5e56e503ff6e9a7f01977c816cdfa37e5c86b2b4738867452d74
+size 498618976

runs/May23_22-28-11_raul-MS-7B98/events.out.tfevents.1716521296.raul-MS-7B98.11594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95b14653d69623292bbd34452d040ecaf8e1e600b834cdc8d1db29206d19c70
+size 11529

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390038fe87c8d4101dbf69f527dcff1f9d740fddd8a6ab8d64125d4d1dc64146
-size 4984
+oid sha256:0ffe2913de08b805188ed9f675dbd274993e980802bb6b6a104f069e08e442fb
+size 4667