Training in progress, epoch 1

config.json

@@ -1,13 +1,14 @@
 {
-  "_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,
   "id2label": {
     "0": "none",
     "1": "like",
@@ -22,6 +23,7 @@
     "9": "meme"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "express_abashed": "10",
     "express_sad": "7",
@@ -35,17 +37,17 @@
     "tease": "8",
     "unlike": "2"
   },
+  "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": "4.27.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

logs/1686802202.292625/events.out.tfevents.1686802202.ls.3992184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96485e654ffb97b19c331f55e4fd866235ff4d15f194353c294d318ad4e32f5
+size 5791

logs/events.out.tfevents.1686801844.ls.3984103.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c313a1e38b81f8aeb2e09835ef4ef622461aa005c6d2dcc470ca9531138cf6c
-size 5439
+oid sha256:52897bfb716fb465c7102bec650bf08b6da48267e94d6589d3ad6aeb320ea5ce
+size 7529

logs/events.out.tfevents.1686802202.ls.3992184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378b25914e6d91b230d41b96a82c2c26c51728a271f30aa6bfc87539a586c549
+size 4920

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce56f2d79f1e9f87740a5dd5e5b2cbac4f6124ca346c449b7e8a2a6017bb70b
-size 267883181
+oid sha256:4a4b6be2308653aa6d28764d1bdf1ef5f10d92e97471737b5b0bd1bd1ac6131d
+size 438035573

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:758effd6e8891c593a864281f10a42e9c315404096144e88f495c543577d6278
+oid sha256:b869e18eefa4186d81617a24c9d960f9e705a743f15586a5ab46a5ae640402fa
 size 3579