Training in progress, step 500

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "games",
+    "1": "geometry",
+    "2": "graphs",
+    "3": "math",
+    "4": "number theory",
+    "5": "probabilities",
+    "6": "strings",
+    "7": "trees"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "games": "0",
+    "geometry": "1",
+    "graphs": "2",
+    "math": "3",
+    "number theory": "4",
+    "probabilities": "5",
+    "strings": "6",
+    "trees": "7"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd95de1e082355d2b1596abf3a4351a775e0b60fd5a2872547653befc454fd1
+size 1340647360

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30859eee3881caa155f720ed818c0776cfa493f88c0890f0812ba7356907feb2
+size 5368