Delete checkpoint-1581

checkpoint-1581/config.json

@@ -1,78 +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": "biology",
-    "1": "business",
-    "2": "chemistry",
-    "3": "computer science",
-    "4": "economics",
-    "5": "engineering",
-    "6": "health",
-    "7": "history",
-    "8": "law",
-    "9": "math",
-    "10": "other",
-    "11": "philosophy",
-    "12": "physics",
-    "13": "psychology"
-  },
-  "initializer_cutoff_factor": 2.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 1152,
-  "label2id": {
-    "biology": 0,
-    "business": 1,
-    "chemistry": 2,
-    "computer science": 3,
-    "economics": 4,
-    "engineering": 5,
-    "health": 6,
-    "history": 7,
-    "law": 8,
-    "math": 9,
-    "other": 10,
-    "philosophy": 11,
-    "physics": 12,
-    "psychology": 13
-  },
-  "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-1581/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5ac997d635f7abf77e40553d15af381cf775aad0f20362c3e8f2e0e9d0353abe
-size 598476704

checkpoint-1581/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ab5fd545939a0ffbfa90c61540791d620b14b692771bf33258fba692272dea88
-size 1197041611

checkpoint-1581/rng_state.pth

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

checkpoint-1581/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eaacdaca7f5ba1987daf70dedbbd84f6bb29fe206fed8137a2ada171cfdbba73
-size 1383

checkpoint-1581/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:294112b4d1e11bb26a28298da95b125fbee5d1be6cff4bde7a6cfe23baaa3ac0
-size 1465

checkpoint-1581/trainer_state.json

@@ -1,281 +0,0 @@
-{
-  "best_global_step": 1581,
-  "best_metric": 0.8520959341897945,
-  "best_model_checkpoint": "category_classifier_modernbert-base_model/checkpoint-1581",
-  "epoch": 3.0,
-  "eval_steps": 50,
-  "global_step": 1581,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0949667616334283,
-      "grad_norm": 26.28024673461914,
-      "learning_rate": 9.4e-06,
-      "loss": 4.8361,
-      "step": 50
-    },
-    {
-      "epoch": 0.1899335232668566,
-      "grad_norm": 47.78547668457031,
-      "learning_rate": 1.9e-05,
-      "loss": 3.0818,
-      "step": 100
-    },
-    {
-      "epoch": 0.2849002849002849,
-      "grad_norm": 31.4428653717041,
-      "learning_rate": 1.9392302498311952e-05,
-      "loss": 2.3862,
-      "step": 150
-    },
-    {
-      "epoch": 0.3798670465337132,
-      "grad_norm": 35.3805046081543,
-      "learning_rate": 1.8717083051991896e-05,
-      "loss": 1.8361,
-      "step": 200
-    },
-    {
-      "epoch": 0.4748338081671415,
-      "grad_norm": 37.02923583984375,
-      "learning_rate": 1.8041863605671847e-05,
-      "loss": 1.7958,
-      "step": 250
-    },
-    {
-      "epoch": 0.5698005698005698,
-      "grad_norm": 35.95353698730469,
-      "learning_rate": 1.7380148548278194e-05,
-      "loss": 1.6075,
-      "step": 300
-    },
-    {
-      "epoch": 0.6647673314339981,
-      "grad_norm": 25.86146354675293,
-      "learning_rate": 1.6704929101958138e-05,
-      "loss": 1.4157,
-      "step": 350
-    },
-    {
-      "epoch": 0.7597340930674265,
-      "grad_norm": 27.28266143798828,
-      "learning_rate": 1.6029709655638085e-05,
-      "loss": 1.2871,
-      "step": 400
-    },
-    {
-      "epoch": 0.8547008547008547,
-      "grad_norm": 23.334003448486328,
-      "learning_rate": 1.535449020931803e-05,
-      "loss": 1.3432,
-      "step": 450
-    },
-    {
-      "epoch": 0.949667616334283,
-      "grad_norm": 22.965452194213867,
-      "learning_rate": 1.4679270762997975e-05,
-      "loss": 1.1439,
-      "step": 500
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.814404432132964,
-      "eval_f1": 0.8113336458431522,
-      "eval_loss": 0.5748739242553711,
-      "eval_runtime": 25.3512,
-      "eval_samples_per_second": 71.2,
-      "eval_steps_per_second": 8.915,
-      "step": 527
-    },
-    {
-      "epoch": 1.043684710351377,
-      "grad_norm": 18.52866554260254,
-      "learning_rate": 1.4004051316677922e-05,
-      "loss": 1.0409,
-      "step": 550
-    },
-    {
-      "epoch": 1.1386514719848053,
-      "grad_norm": 35.10245895385742,
-      "learning_rate": 1.3328831870357868e-05,
-      "loss": 0.6951,
-      "step": 600
-    },
-    {
-      "epoch": 1.2336182336182335,
-      "grad_norm": 30.905532836914062,
-      "learning_rate": 1.2653612424037814e-05,
-      "loss": 0.7904,
-      "step": 650
-    },
-    {
-      "epoch": 1.328584995251662,
-      "grad_norm": 24.192922592163086,
-      "learning_rate": 1.197839297771776e-05,
-      "loss": 0.6591,
-      "step": 700
-    },
-    {
-      "epoch": 1.4235517568850902,
-      "grad_norm": 29.2019100189209,
-      "learning_rate": 1.1303173531397703e-05,
-      "loss": 0.6313,
-      "step": 750
-    },
-    {
-      "epoch": 1.5185185185185186,
-      "grad_norm": 18.22878646850586,
-      "learning_rate": 1.0627954085077653e-05,
-      "loss": 0.6533,
-      "step": 800
-    },
-    {
-      "epoch": 1.6134852801519468,
-      "grad_norm": 31.645309448242188,
-      "learning_rate": 9.952734638757598e-06,
-      "loss": 0.6614,
-      "step": 850
-    },
-    {
-      "epoch": 1.708452041785375,
-      "grad_norm": 23.406362533569336,
-      "learning_rate": 9.277515192437542e-06,
-      "loss": 0.6948,
-      "step": 900
-    },
-    {
-      "epoch": 1.8034188034188035,
-      "grad_norm": 14.599939346313477,
-      "learning_rate": 8.60229574611749e-06,
-      "loss": 0.7048,
-      "step": 950
-    },
-    {
-      "epoch": 1.8983855650522319,
-      "grad_norm": 28.323495864868164,
-      "learning_rate": 7.927076299797435e-06,
-      "loss": 0.5931,
-      "step": 1000
-    },
-    {
-      "epoch": 1.99335232668566,
-      "grad_norm": 21.900310516357422,
-      "learning_rate": 7.25185685347738e-06,
-      "loss": 0.5982,
-      "step": 1050
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.838781163434903,
-      "eval_f1": 0.837644547917988,
-      "eval_loss": 0.49527764320373535,
-      "eval_runtime": 23.9517,
-      "eval_samples_per_second": 75.36,
-      "eval_steps_per_second": 9.436,
-      "step": 1054
-    },
-    {
-      "epoch": 2.087369420702754,
-      "grad_norm": 32.3466796875,
-      "learning_rate": 6.576637407157327e-06,
-      "loss": 0.2672,
-      "step": 1100
-    },
-    {
-      "epoch": 2.1823361823361824,
-      "grad_norm": 4.753382205963135,
-      "learning_rate": 5.9014179608372725e-06,
-      "loss": 0.2645,
-      "step": 1150
-    },
-    {
-      "epoch": 2.2773029439696106,
-      "grad_norm": 36.18887710571289,
-      "learning_rate": 5.226198514517219e-06,
-      "loss": 0.1706,
-      "step": 1200
-    },
-    {
-      "epoch": 2.372269705603039,
-      "grad_norm": 47.72605895996094,
-      "learning_rate": 4.550979068197165e-06,
-      "loss": 0.2658,
-      "step": 1250
-    },
-    {
-      "epoch": 2.467236467236467,
-      "grad_norm": 3.4928948879241943,
-      "learning_rate": 3.8757596218771104e-06,
-      "loss": 0.2461,
-      "step": 1300
-    },
-    {
-      "epoch": 2.5622032288698957,
-      "grad_norm": 4.592565536499023,
-      "learning_rate": 3.2005401755570566e-06,
-      "loss": 0.2486,
-      "step": 1350
-    },
-    {
-      "epoch": 2.657169990503324,
-      "grad_norm": 5.244246959686279,
-      "learning_rate": 2.5253207292370023e-06,
-      "loss": 0.1956,
-      "step": 1400
-    },
-    {
-      "epoch": 2.752136752136752,
-      "grad_norm": 4.432636260986328,
-      "learning_rate": 1.8501012829169482e-06,
-      "loss": 0.1664,
-      "step": 1450
-    },
-    {
-      "epoch": 2.8471035137701803,
-      "grad_norm": 3.5479092597961426,
-      "learning_rate": 1.174881836596894e-06,
-      "loss": 0.2159,
-      "step": 1500
-    },
-    {
-      "epoch": 2.9420702754036085,
-      "grad_norm": 28.90547752380371,
-      "learning_rate": 4.9966239027684e-07,
-      "loss": 0.2,
-      "step": 1550
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.853185595567867,
-      "eval_f1": 0.8520959341897945,
-      "eval_loss": 0.4962720572948456,
-      "eval_runtime": 23.9113,
-      "eval_samples_per_second": 75.487,
-      "eval_steps_per_second": 9.452,
-      "step": 1581
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 1581,
-  "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": 8610303988518912.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1581/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c469ad6d75724ea5e403a6a9e14cd2b3afbb0aebef6b5e8e129064bdaf81e4ab
-size 5777