Training in progress, epoch 1

config.json

@@ -0,0 +1,57 @@
+{
+  "_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": 0,
+    "1": 1,
+    "2": 2
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "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": false,
+  "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:e5ebee7ead1a08b3d9db3fe0499d789ad32303dab135b36aaf1bfd27084834c1
+size 598442860

runs/Jan10_13-50-21_AIDEV/events.out.tfevents.1736509823.AIDEV.30756.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df3d6a36ec3ae9211af4aca23136a581e56ed04db30137f36c570db0d2c0cdc
+size 5795

runs/Jan10_13-57-01_AIDEV/events.out.tfevents.1736510223.AIDEV.28488.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b348fd1c2e9416928acdff1aea125d7d0998a3aaa4a49d3630f4269abd59761
+size 5796

runs/Jan10_13-58-06_AIDEV/events.out.tfevents.1736510288.AIDEV.16704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baddf01ba1f293002f37249574cb85143ae3b56d20b1aca124ebd639c9041716
+size 8852

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7f80b62cbf42820753895f410bce70bd59d1a99b07948c1528bb6368d687a1
+size 5432