Training in progress, step 10000

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
   "architectures": [
     "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -17,10 +17,15 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 105879
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5390d4f48aa37a636c7471c846fcf27433ee3f8202774acc74202c85cebf9fa5
-size 438080896
+oid sha256:cf1c1f0c1c574f644b6d9b6e54f4bca46cd34998964efe3fa79b8ce80b306815
+size 669879044

runs/Jul17_09-51-55_01ee59820869/events.out.tfevents.1721209916.01ee59820869.1560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f8635080cc6569190b5167a6c4d68f2d6f0fb5fac0465a750a3f48e5fdc27c
+size 9172

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a63232994577ce5f013da8f126842ca6faafe907f92c4e37fdcd433c12f991b
+oid sha256:053580fd51e727821ad03bdd8a3c10cb065707c65fd9dd63561531a69ef8597e
 size 5112