Training in progress, step 500

config.json

@@ -1,27 +1,26 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
-    "RobertaForMaskedLM"
+    "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "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": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7088d91669259f25b84c4cc336661ab163dcae2125cfa2ea2fc0c564a66ff49f
-size 328693404
+oid sha256:71467fba6c9538de8ed450f2e6b7f71f98274a40b32ad958304b15a43861c205
+size 433386912

runs/Feb05_07-55-20_a00f031c4cdb/events.out.tfevents.1707119721.a00f031c4cdb.148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1a142d924c6403280b97c1528a9749219a2c923bdcf91ea430c8111610b8da
+size 4184

runs/Feb05_07-56-03_a00f031c4cdb/events.out.tfevents.1707119764.a00f031c4cdb.148.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8be506b0d091f9cf3e1380e972db6c09e2d1ef0a4e10c45bc156f7de0394ef7
+size 7892

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3102fa458e42caa7f3fdb00ebc04eb7eebfaac3c5b515c6c4fdbb74ce26af97a
+oid sha256:8b47453e969c01e1ae3474fce01a2efa64f88d047502729d6d711721c05e5a96
 size 4600