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 sha256:9972374713979be6b6daad5b39fe7e97715a1987a1fdaefc1d4a8d3bb52bdbbd
-size 1334372264
+oid sha256:3e573660d723641833d4b5725a404e20e4877c522b33603457f55ba5de36a811
+size 711443456

runs/Nov26_01-37-15_6921bf48f74f/events.out.tfevents.1732585038.6921bf48f74f.1996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512b05ea30fcee191b5f826a66916189ee2d988f8cbf55e655dff389a5db0bb5
+size 7089

runs/Nov26_01-43-32_6921bf48f74f/events.out.tfevents.1732585417.6921bf48f74f.11032.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5cbb96a112f08f3b8b272ac098ec3d7120626eff0817250ec4080cc5d1c3d4
+size 7089

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb7255cb1c14701cafeccb45e8a9972ab1ebe738383d8236a9a34aab44fdd1d
+oid sha256:ee111fd96b4ae24e84fc984b687f62e5aee8aa473bd3c795f91685cca7a2db23
 size 5304