Delete checkpoint-396

checkpoint-396/config.json

@@ -1,86 +0,0 @@
-{
-  "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": "AGE",
-    "1": "CREDIT_CARD",
-    "2": "DATE_TIME",
-    "3": "DOMAIN_NAME",
-    "4": "EMAIL_ADDRESS",
-    "5": "GPE",
-    "6": "IBAN_CODE",
-    "7": "IP_ADDRESS",
-    "8": "NO_PII",
-    "9": "NRP",
-    "10": "ORGANIZATION",
-    "11": "PERSON",
-    "12": "PHONE_NUMBER",
-    "13": "STREET_ADDRESS",
-    "14": "TITLE",
-    "15": "US_DRIVER_LICENSE",
-    "16": "US_SSN",
-    "17": "ZIP_CODE"
-  },
-  "initializer_cutoff_factor": 2.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 1152,
-  "label2id": {
-    "AGE": 0,
-    "CREDIT_CARD": 1,
-    "DATE_TIME": 2,
-    "DOMAIN_NAME": 3,
-    "EMAIL_ADDRESS": 4,
-    "GPE": 5,
-    "IBAN_CODE": 6,
-    "IP_ADDRESS": 7,
-    "NO_PII": 8,
-    "NRP": 9,
-    "ORGANIZATION": 10,
-    "PERSON": 11,
-    "PHONE_NUMBER": 12,
-    "STREET_ADDRESS": 13,
-    "TITLE": 14,
-    "US_DRIVER_LICENSE": 15,
-    "US_SSN": 16,
-    "ZIP_CODE": 17
-  },
-  "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": "4.54.1",
-  "vocab_size": 50368
-}

checkpoint-396/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c805ffa11eb42a105777473d6c15ece8f1edbd042f695ad860a6b9bd445d4cd7
-size 598489008

checkpoint-396/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4f825ddc5bf4a0878168aec2b913f72a8adb5ad4951f2e6c9cf76d951532dfd3
-size 1197066315

checkpoint-396/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9fd9432b50864b1799d071a2391f13a188cc959e985675ab69fd688672db2853
-size 14645

checkpoint-396/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:15481c2efe0ee4c3f739eaea3b176ff3a31af2aab89e2b7f41bf029020f18c56
-size 1465

checkpoint-396/trainer_state.json

@@ -1,85 +0,0 @@
-{
-  "best_global_step": 396,
-  "best_metric": 0.9674286242857673,
-  "best_model_checkpoint": "pii_classifier_modernbert-base_model/checkpoint-396",
-  "epoch": 3.0,
-  "eval_steps": 500,
-  "global_step": 396,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.7575757575757576,
-      "grad_norm": 15.822543144226074,
-      "learning_rate": 9.900000000000002e-06,
-      "loss": 2.387,
-      "step": 100
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8444444444444444,
-      "eval_f1": 0.8201940521734123,
-      "eval_loss": 0.7109369039535522,
-      "eval_runtime": 9.3515,
-      "eval_samples_per_second": 24.06,
-      "eval_steps_per_second": 3.101,
-      "step": 132
-    },
-    {
-      "epoch": 1.5151515151515151,
-      "grad_norm": 44.086917877197266,
-      "learning_rate": 1.9900000000000003e-05,
-      "loss": 0.6038,
-      "step": 200
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.9288888888888889,
-      "eval_f1": 0.9239100517009231,
-      "eval_loss": 0.30152201652526855,
-      "eval_runtime": 9.2706,
-      "eval_samples_per_second": 24.27,
-      "eval_steps_per_second": 3.128,
-      "step": 264
-    },
-    {
-      "epoch": 2.2727272727272725,
-      "grad_norm": 0.5022214651107788,
-      "learning_rate": 2.9900000000000002e-05,
-      "loss": 0.1797,
-      "step": 300
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.9688888888888889,
-      "eval_f1": 0.9674286242857673,
-      "eval_loss": 0.18659120798110962,
-      "eval_runtime": 9.2646,
-      "eval_samples_per_second": 24.286,
-      "eval_steps_per_second": 3.13,
-      "step": 396
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 660,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 1073506278297600.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-396/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:057a7aa2553eac3d64bcb87db40e93bb3fe3ab14aadcdced12723c7e1524b795
-size 5777