Training in progress, epoch 1

config.json

@@ -1,25 +1,27 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-large-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": 1024,
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "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": "4.20.1",
+  "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:a855b6e4e1301979f16d135ddb508b5aa702ebb7e4cbce5bf569dc8bcd5d0490
-size 267854321
+oid sha256:7f6552fb2772b8cd5994bd8b6e97bb01bcab6ef72fae505871f9d8863e2dcaf0
+size 1340711725

runs/Dec12_10-28-10_299f558e0da5/1670840978.649266/events.out.tfevents.1670840978.299f558e0da5.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d301a0cc19c4bfbf6e0882607a0c11fb0a6d4f28d00e9e44353278d12bb2e374
+size 5408

runs/Dec12_10-28-10_299f558e0da5/events.out.tfevents.1670840978.299f558e0da5.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6285bb87789acf6efb1c9b10f7bc07c8d805b293a9542000eaf5c9bbebb7d365
+size 4006

tokenizer_config.json

@@ -3,12 +3,12 @@
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased",
+  "name_or_path": "bert-large-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:dda7da70aeb49325cee25c8303ba2484481528dcf2fa79c2c3ee9d4c727f539c
+oid sha256:198fa307f41bc01c94a2d6a097d03afd5ac217625e709f9c5f09673502c7fc2a
 size 3439