Training in progress, epoch 1

config.json

@@ -1,35 +1,35 @@
 {
-  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "finetuning_task": "sst-2",
-  "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": "Consumer",
     "1": "Enterprise"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Consumer": 0,
     "Enterprise": 1
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "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": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134caca83e4571ac508131b624c84c73881d734c7ddef06cf5c3c7b2bcd3fb9b
-size 267855533
+oid sha256:a2ff2becb805daab1992882f55e5e5ab4fb3499fa21cc4375860ec58e95aec8d
+size 438007925

runs/Jan25_03-04-25_07f50fc0e54b/events.out.tfevents.1674615868.07f50fc0e54b.617.24

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b32c9535739ebace6cdd66151f0a7bfd0a5efaa1302db052137d902503fa69
-size 4257
+oid sha256:ae44c159f2ec3bf22eb22c371f6a3ce95951dd72954d46d22347ba6638c726f3
+size 5580

runs/Jan25_03-14-30_07f50fc0e54b/1674616475.0142648/events.out.tfevents.1674616475.07f50fc0e54b.617.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f7af5f29bdc370a5174580382cccffaa59dac0f59f595454cac1ad9fb3bd85
+size 5697

runs/Jan25_03-14-30_07f50fc0e54b/events.out.tfevents.1674616475.07f50fc0e54b.617.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d204033bcd6acaafd10cef4d0425de0af8eac61d3d5a70b36bc73fdd7717dfb4
+size 4279

tokenizer_config.json

@@ -1,16 +1,14 @@
 {
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
-  "never_split": null,
+  "name_or_path": "bert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
+  "tokenizer_class": "BertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffbadcf8848674decd5b74c0eac4319750e7c7f3638a6827e052cd4871d5206
+oid sha256:bd5f6168c666e5c5e54463e5e1fdc0ae4fc3c407acbb795882fc68bfd1179812
 size 3515