Training in progress, epoch 1

config.json

@@ -1,13 +1,17 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "bert-base-cased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForMultilabelSequenceClassification"
   ],
   "attention_dropout": 0.1,
+  "attention_probs_dropout_prob": 0.1,
   "dim": 768,
   "dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
   "hidden_dim": 3072,
+  "hidden_dropout_prob": 0.1,
   "id2label": [
     {
       "0": "admiration",
@@ -41,6 +45,7 @@
     }
   ],
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "admiration": 0,
     "amusement": 1,
@@ -71,16 +76,19 @@
     "sadness": 25,
     "surprise": 26
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,
-  "n_layers": 6,
+  "n_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.1",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a9d489bdc72976ab51281fb7f571a4f12b02fe60ea1961ad6c6e2e16f7ce09
-size 267912544
+oid sha256:4413b3e1e0140983503d6848ef6f8afd31b5597a28b3b0c7f83910eb5220ff19
+size 433345360

runs/Nov15_02-58-57_8ef5647a71ed/events.out.tfevents.1700017176.8ef5647a71ed.1876.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f120204611f0717e0e06510e90521d8672bc165bdf35b77a873d6c491b6373e
+size 6909

tokenizer_config.json

@@ -43,13 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "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:e88732b27c565a9c2fb0bc09e57b159ef6bc0f0eff810fe65ad8661768bf6836
+oid sha256:f942bfd1c3c866f40cfc4ca7b88dc43495f4475520ea98e222691ccf68e3d506
 size 4664