Training in progress, step 500

config.json

@@ -1,13 +1,14 @@
 {
- "_name_or_path": "distilbert-base-uncased",
- "activation": "gelu",
+ "_name_or_path": "bert-base-cased",
  "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,
  "id2label": {
  "0": "LABEL_0",
  "1": "LABEL_1",
@@ -16,6 +17,7 @@
  "4": "LABEL_4"
  },
  "initializer_range": 0.02,
+ "intermediate_size": 3072,
  "label2id": {
  "LABEL_0": 0,
  "LABEL_1": 1,
@@ -23,17 +25,17 @@
  "LABEL_3": 3,
  "LABEL_4": 4
  },
+ "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": "4.34.1",
- "vocab_size": 30522
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 28996
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9e33c1c647b8b0296a688d52aa90916232148ab91937e0f9fa960ce50781f7
-size 267865194
+oid sha256:68dbc9d8751b8e4076453876cb419a08654d7d950dc9af94d0e06d09d369f5e0
+size 433325294

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c24954ad06ba2f60e557838193abd83e76ea667313bc455fcab543037c96aa
+oid sha256:95ec66e15834b18abbf3d72191130b3a931c7ff7b1cef0632679fb84c9589efc
 size 4472