Training in progress, epoch 1

config.json

@@ -1,35 +1,37 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "google-bert/bert-base-cased",
   "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": "object-detection",
     "1": "zero-shot-object-detection",
     "2": "mask-generation"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "mask-generation": 2,
     "object-detection": 0,
     "zero-shot-object-detection": 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": 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": "4.48.3",
-  "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:dff16b496e8baef76ca1cc302a4547dfab467b5693553e93c6d3b46ed0e65951
-size 267835644
+oid sha256:84c59be3dc6f0dd4b256246799dc2e878214a8db254a9293eaa9f67ded5a3307
+size 433273844

runs/Mar04_14-09-26_75287a5389c5/events.out.tfevents.1741097368.75287a5389c5.593.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f75f78a9fc527d11b04747f0e800262ae5dc7c11e9254e422560cac59f59caa
-size 5483
+oid sha256:5c0f0e582b74a06c2df64535a62ca54ba1aa0f07948fe616f16562a94f4d59f5
+size 5800

runs/Mar04_14-14-24_75287a5389c5/events.out.tfevents.1741097669.75287a5389c5.9777.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71fbc9f95a4cba3d059f141e7cb9066161545be6542d9d6672645373a79bda5
+size 5240

runs/Mar04_14-17-57_75287a5389c5/events.out.tfevents.1741097878.75287a5389c5.9777.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4971f4cd3fb9d506365385f07aa30db9c4dc484e8da1ddbd8fd8a49a1fe64e0e
+size 5240

runs/Mar04_14-25-50_75287a5389c5/events.out.tfevents.1741098352.75287a5389c5.9777.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a1ace02c76e3bce3790b1d2eed6430ccf1f48341bc3bb50bdd7d31ff317cb6
+size 5605

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
@@ -51,6 +51,6 @@
   "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 sha256:2bde90a54bfd80a7e8b88c3332628a36b73c6c18cbeb4a6200508345ce8565d7
+oid sha256:8919a49db8939eaf1e74e8adf27d70621c9662073fcef9fb248d3159f4880537
 size 5368