Training in progress, epoch 1

config.json

@@ -0,0 +1,82 @@
+{
+  "activation_function": "gelu",
+  "allow_embedding_resizing": true,
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_layer": "rope",
+  "attention_probs_dropout_prob": 0.0,
+  "attn_out_bias": false,
+  "attn_out_dropout_prob": 0.1,
+  "attn_qkv_bias": false,
+  "bert_layer": "prenorm",
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "compile_model": true,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embed_dropout_prob": 0.0,
+  "embed_norm": true,
+  "embedding_dropout": 0.0,
+  "embedding_layer": "sans_pos",
+  "eos_token_id": 50282,
+  "final_norm": true,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "head_pred_act": "gelu",
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "init_method": "full_megatron",
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "local_attention": 128,
+  "local_attn_rotary_emb_base": 10000.0,
+  "local_rope_theta": 10000.0,
+  "loss_function": "fa_cross_entropy",
+  "loss_kwargs": {
+    "reduction": "mean"
+  },
+  "masked_prediction": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "mlp_dropout_prob": 0.0,
+  "mlp_in_bias": false,
+  "mlp_layer": "glu",
+  "mlp_out_bias": false,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "norm_kwargs": {
+    "bias": false,
+    "eps": 1e-05
+  },
+  "normalization": "layernorm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "padding": "unpadded",
+  "problem_type": "single_label_classification",
+  "repad_logits_with_grad": false,
+  "rotary_emb_base": 160000.0,
+  "rotary_emb_dim": null,
+  "rotary_emb_interleaved": false,
+  "rotary_emb_scale_base": null,
+  "sep_token_id": 50282,
+  "skip_first_prenorm": true,
+  "sliding_window": 128,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "unpad_embeddings": true,
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e504c2ce129125897d2d0f00ad8c1bf15ee32a69dbf6340c02b603cbefc750b
+size 598439784

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068a581faa5f24a80920b90e265edf5afd44075e108030a01a5bf14054b6ad59
+size 5240