Training in progress, epoch 1

config.json

@@ -0,0 +1,80 @@
+{
+  "_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": "embeddings",
+    "1": "ai ethics",
+    "10": "data engineering",
+    "11": "robotics",
+    "12": "speech & audio",
+    "13": "code models",
+    "2": "game development",
+    "3": "llm evaluation",
+    "4": "rlhf",
+    "5": "deployment & infrastructure",
+    "6": "ml fundamentals",
+    "7": "vision & multimodal",
+    "8": "diffusion models",
+    "9": "hub & platform"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "ai ethics": "1",
+    "code models": "13",
+    "data engineering": "10",
+    "deployment & infrastructure": "5",
+    "diffusion models": "8",
+    "embeddings": "0",
+    "game development": "2",
+    "hub & platform": "9",
+    "llm evaluation": "3",
+    "ml fundamentals": "6",
+    "rlhf": "4",
+    "robotics": "11",
+    "speech & audio": "12",
+    "vision & multimodal": "7"
+  },
+  "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,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d20b448f2f1e56947f9495f23738cab63c3a59b36c91579b04650bc64e5d60f
+size 598476704

runs/Jan11_16-39-02_834d97628c17/events.out.tfevents.1736613545.834d97628c17.2054.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b15df76b3d21766d9c89e1d37aaca663da379ff6adf1ba8953b6c5979cbcd47
+size 6857

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b6c8990d1827224f787d8ad0c707136106b70f5996435b5225a8e04fdfdaa5
+size 5432