Upload 8 files

config.json

@@ -0,0 +1,54 @@
+{
+  "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
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.0.dev0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc5f5b3e5e6448ec7583eea6a80ef01a428682962f08a9c6fd44f98c7252d0c
+size 598439784

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7bf5789f6516649fc9fd9cdabb3430f1065804bfcaeb6d8db9bff40cf5dcba
+size 1196969338

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4e3f2c76c841a93a5381323cca8b4d90b8a05fa008a32306c4211971f113cc
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffb6ab86afd8a1b76a16f7a0e015b06dbb79dc500dae39323cc69f06851bdbd
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fde6d6e0d7232d24b4d1970e0a6ea412eee818d835b1a59a1e8535381a03130
+size 1064

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_global_step": 3495,
+  "best_metric": 0.9739681176533734,
+  "best_model_checkpoint": "/content/drive/MyDrive/ModernBERT-domain-classifier_v6/checkpoint-3495",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3495,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.0307705402374268,
+      "learning_rate": 4.218091714923157e-05,
+      "loss": 0.2001,
+      "step": 1165
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9665523156089194,
+      "eval_f1": 0.9661788617886179,
+      "eval_loss": 0.09094209969043732,
+      "eval_precision": 0.9771954829514308,
+      "eval_recall": 0.9554078679386858,
+      "eval_runtime": 45.4419,
+      "eval_samples_per_second": 410.546,
+      "eval_steps_per_second": 6.426,
+      "step": 1165
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1918050050735474,
+      "learning_rate": 1.5125189709385162e-05,
+      "loss": 0.05,
+      "step": 2330
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9726093481989708,
+      "eval_f1": 0.972610816315592,
+      "eval_loss": 0.08524948358535767,
+      "eval_precision": 0.9726629502572899,
+      "eval_recall": 0.9725586879622682,
+      "eval_runtime": 42.7827,
+      "eval_samples_per_second": 436.064,
+      "eval_steps_per_second": 6.825,
+      "step": 2330
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.105299472808838,
+      "learning_rate": 1.2472928209716906e-11,
+      "loss": 0.0072,
+      "step": 3495
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9740030017152659,
+      "eval_f1": 0.9739681176533734,
+      "eval_loss": 0.11646562814712524,
+      "eval_precision": 0.9753816383573425,
+      "eval_recall": 0.9725586879622682,
+      "eval_runtime": 42.8653,
+      "eval_samples_per_second": 435.224,
+      "eval_steps_per_second": 6.812,
+      "step": 3495
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3495,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.617369041410867e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083bb34ae0c615dce71400c20e16c8892d0f8923d45edc7208692a397589a6f9
+size 5432