Training in progress, epoch 1

config.json

@@ -1,22 +1,21 @@
 {
-  "_name_or_path": "google-bert/bert-large-cased",
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "directionality": "bidi",
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "pooler_fc_size": 768,
   "pooler_num_attention_heads": 12,
@@ -29,5 +28,5 @@
   "transformers_version": "4.46.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9461e6e8a22c990fe77ceb3e4298ca18703d48c00823f7047af1960d59122bcc
-size 1334372264
+oid sha256:6bcf0472168aa246a42c479c08c0ec03a8567c2adbea5ab77551564c6d02fd32
+size 711443456

runs/Nov26_01-56-52_6921bf48f74f/events.out.tfevents.1732586220.6921bf48f74f.11032.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9192a0e6c0090d939b2c1c86a703827b6ccc623445e9170d9f335576a86ce883
+size 7086

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a216ddbcdd28bd31e0e788c353cb5f315c0d6b6f59249ddcf997554545e0f3
+oid sha256:7cd8e50f3f77f423b6e36feb7984acf5bd3031344b87b696ee69aded89c1437f
 size 5304