Training in progress, step 500

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "transformersbook/bert-base-uncased-finetuned-clinc",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "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": "restaurant_reviews",
     "1": "nutrition_info",
@@ -163,7 +162,6 @@
     "150": "change_volume"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "accept_reservations": 9,
     "account_blocked": 2,
@@ -317,17 +315,17 @@
     "who_made_you": 96,
     "yes": 107
   },
-  "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": "4.39.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae0cde19a3ccf1842be67bb2f9e5ac0d15db8d0eb22df4fad2a53de3792e349
-size 438416972
+oid sha256:577de16c52f88b45cbda69ff39ce5d835270d4474331fd2e0568e3c60c29443a
+size 268290900

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {