Training in progress, step 500

config.json

@@ -1,25 +1,27 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a933fd5f1a7eef6b7ebdfe4bbef11dac87e55574ff5aa575a84479f64d016f03
-size 267832560
+oid sha256:20e3c87ea8c2f19a986206a2b049e66c4f70686457bc9838d718080e2f11fe9b
+size 437958648

runs/May01_05-18-28_3ce9bfbf1681/events.out.tfevents.1714540791.3ce9bfbf1681.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b05b74e9e91c5909fd062c1bb75ff7aa81b88514d8c38f98aa0853dc8c0760d
+size 5696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cd1871a0aa128e3299729caa9638e2f1a70663856395648c5cf605dc9fa075
+oid sha256:1edfc4b9faefd467d453baeff195d400cd23269320f2763bddea4952827a7248
 size 4984