Training in progress, epoch 1

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "google/bert_uncased_L-6_H-768_A-12",
   "adapters": {
     "adapters": {},
     "config_map": {},
@@ -8,32 +7,34 @@
     "fusions": {}
   },
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "entailment",
     "1": "not_entailment"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "entailment": "0",
     "not_entailment": "1"
   },
+  "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": 6,
   "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": "4.21.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

logs/1663299284.0096412/events.out.tfevents.1663299284.cd02b94e3af8.3404.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fdaa9b84b2116f2d4eedb5228b414c992c4d1fc2955a3bdcd8a860db3c4f7d
+size 5437

logs/events.out.tfevents.1663298059.cd02b94e3af8.3404.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2fdd11ec9796d0410902230e7e3e3a68610f29040f0247933bab5bc9862b73
-size 4586
+oid sha256:f6cbe7e6d6390e1f87e0e1496e84f51c5d03d668a149e949233c6760f292d399
+size 10808

logs/events.out.tfevents.1663299279.cd02b94e3af8.3404.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659377f41c236c5d51108524dd023c107d593bcbb4ab84a676a52d3bdab12ce6
+size 4631

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a651a5dfe4a8f5c59fdb7b37447db58c95af90d3a05e2f1f5d124754514bc0a3
-size 267854321
+oid sha256:cd7f14ed8348d149a2a10dcc13ad1ae2342830ee8f94b2758599c3e8993bd06a
+size 267864813

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {