Training in progress, step 767

config.json

@@ -0,0 +1,88 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Self-direction: thought",
+    "1": "Self-direction: action",
+    "2": "Stimulation",
+    "3": "Hedonism",
+    "4": "Achievement",
+    "5": "Power: dominance",
+    "6": "Power: resources",
+    "7": "Face",
+    "8": "Security: personal",
+    "9": "Security: societal",
+    "10": "Tradition",
+    "11": "Conformity: rules",
+    "12": "Conformity: interpersonal",
+    "13": "Humility",
+    "14": "Benevolence: caring",
+    "15": "Benevolence: dependability",
+    "16": "Universalism: concern",
+    "17": "Universalism: nature",
+    "18": "Universalism: tolerance"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "Achievement": 4,
+    "Benevolence: caring": 14,
+    "Benevolence: dependability": 15,
+    "Conformity: interpersonal": 12,
+    "Conformity: rules": 11,
+    "Face": 7,
+    "Hedonism": 3,
+    "Humility": 13,
+    "Power: dominance": 5,
+    "Power: resources": 6,
+    "Security: personal": 8,
+    "Security: societal": 9,
+    "Self-direction: action": 1,
+    "Self-direction: thought": 0,
+    "Stimulation": 2,
+    "Tradition": 10,
+    "Universalism: concern": 16,
+    "Universalism: nature": 17,
+    "Universalism: tolerance": 18
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.2",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5e67a27ab599a17b2757a2a106470a5adfade3349718d8520a32f10365ea58
+size 598492084

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86511f6554febdeed7a872ba875ab0b800d4af19e7f34bcd1a22af2aa0138ba4
+size 5432