Training in progress, step 500

config.json

@@ -1,33 +1,33 @@
 {
-  "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "MPNetForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "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": "Depressive",
     "1": "Non-Depressive"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Depressive": 0,
     "Non-Depressive": 1
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
-  "relative_attention_num_buckets": 32,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
-  "vocab_size": 30527
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42b8a4c5d2dfcbce6e3b63396806f4cb2b702f83f91402452392f296e04e5fb
-size 438017646
+oid sha256:494f2419badc276c9d445801ffb25da9945f1326b35778557808a33e6dd111dc
+size 267854570

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90d52e4fc5ae7998de9c6cc4dde02f5d6a5ab571e9483b84fe3282449a4f447
+oid sha256:e9c7d924972eb3f899d51a0c563bb5d9813502467507c74ba801c6e3ce76045f
 size 4472