Training in progress, step 500

config.json

@@ -1,42 +1,27 @@
 {
-  "_name_or_path": "desarrolloasesoreslocales/bert-leg-al-corpus",
+  "_name_or_path": "joelniklaus/legal-xlm-roberta-base",
   "architectures": [
     "RobertaForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "attention_window": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 4098,
+  "max_position_embeddings": 514,
   "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 52000
+  "vocab_size": 128000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614eb35893a35e82de0f71c0e1222e66ee0bf72fcb908b0f64fcea30837b8295
-size 515160864
+oid sha256:2f64fe4447e80abdbbccc84fef0d243bdb6a968594770e7a6d8b8f00eb252cff
+size 737926808

runs/Jun11_07-48-30_5be8417a0bdc/events.out.tfevents.1718092215.5be8417a0bdc.271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b975e63b483183376c91669df5ca0796e8d2a1eedccce8f097dd32a82b08693b
+size 5618

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73423fda268e60b49256a63174380beac125cdeecfd3739ef6bde078e027e0d9
-size 4920
+oid sha256:d9772064032f07786056ebb2a709eab2d4cf045f23b641ef5eb2a2a67631f3bd
+size 5112