model

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-Clean-up_Standards",
+    "2": "B-Impacted_Media",
+    "3": "B-Regulatory_Program",
+    "4": "B-Remedial_Components",
+    "5": "B-Types_of_Contaminants",
+    "6": "I-Clean-up_Standards",
+    "7": "I-Impacted_Media",
+    "8": "I-Regulatory_Program",
+    "9": "I-Remedial_Components",
+    "10": "I-Types_of_Contaminants"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-Clean-up_Standards": 1,
+    "B-Impacted_Media": 2,
+    "B-Regulatory_Program": 3,
+    "B-Remedial_Components": 4,
+    "B-Types_of_Contaminants": 5,
+    "I-Clean-up_Standards": 6,
+    "I-Impacted_Media": 7,
+    "I-Regulatory_Program": 8,
+    "I-Remedial_Components": 9,
+    "I-Types_of_Contaminants": 10,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f024224d860ad973809d56a2a2858ffbaa200be625bb8405d34a3458797ca77
+size 531053370

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8328807e1aa2b39f534edc43a7f73503046ecaf901f49f06a477ac1519cbb170
+size 265519202

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a22f491fbc0d88c20da41fe3eec83a3e23a1aad62e52e4a43649fcfd68220d8
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b40f9793686376d734c9061f93e730570d8c850d986b48ac3127b9a7cbd3b1
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,271 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.303030303030305,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6655681133270264,
+      "eval_runtime": 31.9535,
+      "eval_samples_per_second": 16.242,
+      "eval_steps_per_second": 1.033,
+      "step": 33
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.34202826023101807,
+      "eval_runtime": 32.6272,
+      "eval_samples_per_second": 15.907,
+      "eval_steps_per_second": 1.011,
+      "step": 66
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1993253082036972,
+      "eval_runtime": 34.1947,
+      "eval_samples_per_second": 15.178,
+      "eval_steps_per_second": 0.965,
+      "step": 99
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.12108779698610306,
+      "eval_runtime": 33.5003,
+      "eval_samples_per_second": 15.492,
+      "eval_steps_per_second": 0.985,
+      "step": 132
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.08059267699718475,
+      "eval_runtime": 33.0363,
+      "eval_samples_per_second": 15.71,
+      "eval_steps_per_second": 0.999,
+      "step": 165
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.0539543516933918,
+      "eval_runtime": 33.3191,
+      "eval_samples_per_second": 15.577,
+      "eval_steps_per_second": 0.99,
+      "step": 198
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.033514220267534256,
+      "eval_runtime": 33.9315,
+      "eval_samples_per_second": 15.296,
+      "eval_steps_per_second": 0.973,
+      "step": 231
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.02793893776834011,
+      "eval_runtime": 33.1021,
+      "eval_samples_per_second": 15.679,
+      "eval_steps_per_second": 0.997,
+      "step": 264
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.017579322680830956,
+      "eval_runtime": 33.1929,
+      "eval_samples_per_second": 15.636,
+      "eval_steps_per_second": 0.994,
+      "step": 297
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.017992401495575905,
+      "eval_runtime": 33.5989,
+      "eval_samples_per_second": 15.447,
+      "eval_steps_per_second": 0.982,
+      "step": 330
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.011186002753674984,
+      "eval_runtime": 33.2114,
+      "eval_samples_per_second": 15.627,
+      "eval_steps_per_second": 0.994,
+      "step": 363
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.009413644671440125,
+      "eval_runtime": 33.6973,
+      "eval_samples_per_second": 15.402,
+      "eval_steps_per_second": 0.979,
+      "step": 396
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.008357277140021324,
+      "eval_runtime": 34.2116,
+      "eval_samples_per_second": 15.17,
+      "eval_steps_per_second": 0.965,
+      "step": 429
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.006698057986795902,
+      "eval_runtime": 32.3567,
+      "eval_samples_per_second": 16.04,
+      "eval_steps_per_second": 1.02,
+      "step": 462
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.005631112959235907,
+      "eval_runtime": 30.3383,
+      "eval_samples_per_second": 17.107,
+      "eval_steps_per_second": 1.088,
+      "step": 495
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.2424242424242425e-05,
+      "loss": 0.1575,
+      "step": 500
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.00457022013142705,
+      "eval_runtime": 30.6053,
+      "eval_samples_per_second": 16.958,
+      "eval_steps_per_second": 1.078,
+      "step": 528
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.005157523322850466,
+      "eval_runtime": 30.0767,
+      "eval_samples_per_second": 17.256,
+      "eval_steps_per_second": 1.097,
+      "step": 561
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.0044335490092635155,
+      "eval_runtime": 29.0299,
+      "eval_samples_per_second": 17.878,
+      "eval_steps_per_second": 1.137,
+      "step": 594
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.003722449066117406,
+      "eval_runtime": 28.4937,
+      "eval_samples_per_second": 18.215,
+      "eval_steps_per_second": 1.158,
+      "step": 627
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.004425578285008669,
+      "eval_runtime": 32.1425,
+      "eval_samples_per_second": 16.147,
+      "eval_steps_per_second": 1.027,
+      "step": 660
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 0.0040681445971131325,
+      "eval_runtime": 28.8069,
+      "eval_samples_per_second": 18.017,
+      "eval_steps_per_second": 1.146,
+      "step": 693
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 0.003019771073013544,
+      "eval_runtime": 28.6404,
+      "eval_samples_per_second": 18.121,
+      "eval_steps_per_second": 1.152,
+      "step": 726
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 0.002829624805599451,
+      "eval_runtime": 29.787,
+      "eval_samples_per_second": 17.424,
+      "eval_steps_per_second": 1.108,
+      "step": 759
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 0.002751641208305955,
+      "eval_runtime": 28.377,
+      "eval_samples_per_second": 18.289,
+      "eval_steps_per_second": 1.163,
+      "step": 792
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 0.002945221494883299,
+      "eval_runtime": 29.5958,
+      "eval_samples_per_second": 17.536,
+      "eval_steps_per_second": 1.115,
+      "step": 825
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 0.0026160639245063066,
+      "eval_runtime": 29.0161,
+      "eval_samples_per_second": 17.887,
+      "eval_steps_per_second": 1.137,
+      "step": 858
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 0.002537393243983388,
+      "eval_runtime": 28.4904,
+      "eval_samples_per_second": 18.217,
+      "eval_steps_per_second": 1.158,
+      "step": 891
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 0.00242584478110075,
+      "eval_runtime": 29.437,
+      "eval_samples_per_second": 17.631,
+      "eval_steps_per_second": 1.121,
+      "step": 924
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 0.0026495754718780518,
+      "eval_runtime": 28.3889,
+      "eval_samples_per_second": 18.282,
+      "eval_steps_per_second": 1.162,
+      "step": 957
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 0.0023259243462234735,
+      "eval_runtime": 28.1977,
+      "eval_samples_per_second": 18.406,
+      "eval_steps_per_second": 1.17,
+      "step": 990
+    },
+    {
+      "epoch": 30.3,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 0.0065,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1320,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 278856790097838.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7055907b6d27e74601fff328ea1fadd2feac1546e616919fc601fadf9570622d
+size 4472