Training in progress, epoch 1

config.json

@@ -1,36 +1,33 @@
 {
-  "_name_or_path": "textattack/bert-base-uncased-imdb",
+  "_name_or_path": "lvwerra/distilbert-imdb",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "finetuning_task": "imdb",
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "negative",
     "1": "positive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "negative": 0,
     "positive": 1
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_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": "4.30.2",
-  "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 sha256:8079af0e2a85a96f33bde107c230f225d4186b0c08a3512066cca40d702f2748
-size 438007925
+oid sha256:1e4e64f930afdc6c7789270f3266abb6caaff77b0b398beb62bc74677a16464f
+size 267855533

runs/Nov15_13-47-21_21020ac426d8/events.out.tfevents.1731678657.21020ac426d8.32.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946dfd7c760c729ed2200eeb6b8ab1f8b8f32bd0160b994078e62cbff1d95cd5
+size 4577

tokenizer_config.json

@@ -1,15 +1,13 @@
 {
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51d923d11a243d8c3edff979fda5f0aa41c255019f57d71033f08ba6d3933c1
+oid sha256:8bea198ea8b3d829dc4d296bccd4909da6e161986368956bffd000d96c2fe376
 size 3963