Training in progress, epoch 1

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "answerdotai/ModernBERT-base",
+  "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": "C\u00f4ng ngh\u1ec7",
+    "1": "Gi\u00e1o d\u1ee5c",
+    "10": "Xe c\u1ed9",
+    "11": "X\u00e3 h\u1ed9i",
+    "12": "\u0110\u1eddi s\u1ed1ng",
+    "2": "Gi\u1ea3i tr\u00ed",
+    "3": "Khoa h\u1ecdc",
+    "4": "Kinh t\u1ebf",
+    "5": "Nh\u00e0 \u0111\u1ea5t",
+    "6": "Ph\u00e1p lu\u1eadt",
+    "7": "Th\u1ebf gi\u1edbi",
+    "8": "Th\u1ec3 thao",
+    "9": "V\u0103n h\u00f3a"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "C\u00f4ng ngh\u1ec7": "0",
+    "Gi\u00e1o d\u1ee5c": "1",
+    "Gi\u1ea3i tr\u00ed": "2",
+    "Khoa h\u1ecdc": "3",
+    "Kinh t\u1ebf": "4",
+    "Nh\u00e0 \u0111\u1ea5t": "5",
+    "Ph\u00e1p lu\u1eadt": "6",
+    "Th\u1ebf gi\u1edbi": "7",
+    "Th\u1ec3 thao": "8",
+    "V\u0103n h\u00f3a": "9",
+    "Xe c\u1ed9": "10",
+    "X\u00e3 h\u1ed9i": "11",
+    "\u0110\u1eddi s\u1ed1ng": "12"
+  },
+  "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": "single_label_classification",
+  "reference_compile": true,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef032885b5916e6e429a75eb764db66124b4c67cb1a55f15b5d721b8a3d893d
+size 598473628

runs/Feb12_13-09-02_0359a1a1f113/events.out.tfevents.1739365744.0359a1a1f113.277.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92efe5fec6b1aa48d10701fe033c265ee26faa0496e4b7327855e6a830101e9
+size 6611

runs/Feb12_13-09-19_0359a1a1f113/events.out.tfevents.1739365761.0359a1a1f113.277.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6f3c1f9f4935f4d375f835b1eba298cbca59d23bc91a9fbae81c2a9b19c3d5
+size 6609

runs/Feb12_13-15-10_0359a1a1f113/events.out.tfevents.1739366111.0359a1a1f113.277.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646679c4993a56e5492217add4e69e7b88b356ee416cfb1ce9a0c451eaad3591
+size 6560

runs/Feb12_13-16-28_0359a1a1f113/events.out.tfevents.1739366189.0359a1a1f113.277.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb04cc6a1ddc8c9bff9e129943209bde774d1816461bb15d8b5dad2a8b84b370
+size 8985

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef32c0e7274d27dd88849cd56df95a426b0dab217f21767899435384ec38751b
+size 5432