Adapter training

config.json

@@ -1,34 +1,29 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
   "architectures": [
-    "CustomAlbert"
+    "BertForSequenceClassificationAdapters"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
-  "hidden_size": 768,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
-  "num_users": 50000,
+  "num_hidden_layers": 6,
+  "num_users": 2062,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.30.1",
   "type_vocab_size": 2,
-  "vocab_size": 30000
+  "use_cache": true,
+  "user_dropout_prob": 0.5,
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb3a92e58b832791639ce5c8498f49e1b624fe760567df36a9c9615a5ae6499
-size 79846694
+oid sha256:864b62fa285ec3093fa8e7bc62c167815f6bb8e0f8806c3cbbcd70dafc068dd3
+size 99607641