Training in progress, step 100

config.json

@@ -1,32 +1,14 @@
 {
-  "_name_or_path": "google-bert/bert-large-uncased",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "custom_pipelines": {
-    "question-classifier": {
-      "default": {
-        "model": {
-          "pt": [
-            "ai-research-lab/bert-question-classifier",
-            "main"
-          ]
-        }
-      },
-      "impl": "classifier_pipeline.MultiTaskClassifierPipeline",
-      "pt": [
-        "AutoModelForSequenceClassification"
-      ],
-      "tf": [],
-      "type": "text"
-    }
-  },
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "d",
     "1": "y",
@@ -64,7 +46,7 @@
     "33": "positive_perception"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "accumulated wealth": 6,
     "business": 22,
@@ -104,8 +86,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "task_specific_params": {
@@ -286,7 +268,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.48.1",
+  "transformers_version": "4.49.0",
   "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 sha256:38841421c2a4c9d481c6a1c0af0e8323026294db894c62d366e5832b2bc8b19e
-size 1340753968
+oid sha256:9e01f75989b155d28668fcf4ab110ad6780b7b2783c7f4c5775859de89ab21fa
+size 438057080

tokenizer.json

@@ -6,16 +6,7 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24441a5c5eac7a327d27fb0efacbb46534247f26598002cfcbf4bfb03aefbcdd
-size 5368
+oid sha256:b00eb55177b98f1dc327e038c02b62a70d3904e2de165d2c342edbb856051d73
+size 5432