model_files

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:ed8050fbf0f037b16bdab19a0409c1029c8d22c88b7cab23f0cdfdf7dae0ea3a
+size 531053370

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8b80b0d6849e7410d303e7817351c8b09183bdd48a2fbf78cc608ed8846ee5
+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": 0.6893180012702942,
+      "eval_runtime": 28.4889,
+      "eval_samples_per_second": 18.218,
+      "eval_steps_per_second": 1.158,
+      "step": 33
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3626828193664551,
+      "eval_runtime": 29.737,
+      "eval_samples_per_second": 17.453,
+      "eval_steps_per_second": 1.11,
+      "step": 66
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.21266968548297882,
+      "eval_runtime": 28.4545,
+      "eval_samples_per_second": 18.24,
+      "eval_steps_per_second": 1.16,
+      "step": 99
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.1356026828289032,
+      "eval_runtime": 28.8969,
+      "eval_samples_per_second": 17.96,
+      "eval_steps_per_second": 1.142,
+      "step": 132
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.09372802078723907,
+      "eval_runtime": 42.6352,
+      "eval_samples_per_second": 12.173,
+      "eval_steps_per_second": 0.774,
+      "step": 165
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.06550699472427368,
+      "eval_runtime": 30.8112,
+      "eval_samples_per_second": 16.845,
+      "eval_steps_per_second": 1.071,
+      "step": 198
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.04331357032060623,
+      "eval_runtime": 138.921,
+      "eval_samples_per_second": 3.736,
+      "eval_steps_per_second": 0.238,
+      "step": 231
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.030439287424087524,
+      "eval_runtime": 29.4747,
+      "eval_samples_per_second": 17.608,
+      "eval_steps_per_second": 1.12,
+      "step": 264
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.02328161522746086,
+      "eval_runtime": 42.9504,
+      "eval_samples_per_second": 12.084,
+      "eval_steps_per_second": 0.768,
+      "step": 297
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.015175359323620796,
+      "eval_runtime": 34.7922,
+      "eval_samples_per_second": 14.917,
+      "eval_steps_per_second": 0.948,
+      "step": 330
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.011942080222070217,
+      "eval_runtime": 33.7878,
+      "eval_samples_per_second": 15.361,
+      "eval_steps_per_second": 0.977,
+      "step": 363
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.011739258654415607,
+      "eval_runtime": 33.1657,
+      "eval_samples_per_second": 15.649,
+      "eval_steps_per_second": 0.995,
+      "step": 396
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.00850769504904747,
+      "eval_runtime": 26.9611,
+      "eval_samples_per_second": 19.25,
+      "eval_steps_per_second": 1.224,
+      "step": 429
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.008818953298032284,
+      "eval_runtime": 25.3516,
+      "eval_samples_per_second": 20.472,
+      "eval_steps_per_second": 1.302,
+      "step": 462
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.0071915010921657085,
+      "eval_runtime": 29.0211,
+      "eval_samples_per_second": 17.884,
+      "eval_steps_per_second": 1.137,
+      "step": 495
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.2424242424242425e-05,
+      "loss": 0.172,
+      "step": 500
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.0059341141022741795,
+      "eval_runtime": 27.1402,
+      "eval_samples_per_second": 19.123,
+      "eval_steps_per_second": 1.216,
+      "step": 528
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.0058893621899187565,
+      "eval_runtime": 65.963,
+      "eval_samples_per_second": 7.868,
+      "eval_steps_per_second": 0.5,
+      "step": 561
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.005850458517670631,
+      "eval_runtime": 41.3311,
+      "eval_samples_per_second": 12.557,
+      "eval_steps_per_second": 0.798,
+      "step": 594
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.004295774735510349,
+      "eval_runtime": 46.3744,
+      "eval_samples_per_second": 11.192,
+      "eval_steps_per_second": 0.712,
+      "step": 627
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.004227998200803995,
+      "eval_runtime": 41.1438,
+      "eval_samples_per_second": 12.614,
+      "eval_steps_per_second": 0.802,
+      "step": 660
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 0.004431780893355608,
+      "eval_runtime": 41.907,
+      "eval_samples_per_second": 12.385,
+      "eval_steps_per_second": 0.787,
+      "step": 693
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 0.0034626370761543512,
+      "eval_runtime": 41.1621,
+      "eval_samples_per_second": 12.609,
+      "eval_steps_per_second": 0.802,
+      "step": 726
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 0.0033035443630069494,
+      "eval_runtime": 44.2482,
+      "eval_samples_per_second": 11.729,
+      "eval_steps_per_second": 0.746,
+      "step": 759
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 0.003542479360476136,
+      "eval_runtime": 42.5796,
+      "eval_samples_per_second": 12.189,
+      "eval_steps_per_second": 0.775,
+      "step": 792
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 0.00354805332608521,
+      "eval_runtime": 40.0541,
+      "eval_samples_per_second": 12.957,
+      "eval_steps_per_second": 0.824,
+      "step": 825
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 0.002963385311886668,
+      "eval_runtime": 41.546,
+      "eval_samples_per_second": 12.492,
+      "eval_steps_per_second": 0.794,
+      "step": 858
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 0.0030358233489096165,
+      "eval_runtime": 48.7828,
+      "eval_samples_per_second": 10.639,
+      "eval_steps_per_second": 0.676,
+      "step": 891
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 0.002670546527951956,
+      "eval_runtime": 40.7799,
+      "eval_samples_per_second": 12.727,
+      "eval_steps_per_second": 0.809,
+      "step": 924
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 0.002638536971062422,
+      "eval_runtime": 69.2191,
+      "eval_samples_per_second": 7.498,
+      "eval_steps_per_second": 0.477,
+      "step": 957
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 0.002552107907831669,
+      "eval_runtime": 47.5572,
+      "eval_samples_per_second": 10.913,
+      "eval_steps_per_second": 0.694,
+      "step": 990
+    },
+    {
+      "epoch": 30.3,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 0.0077,
+      "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 sha256:80a8e3f06aa8ffd702b066b0baa4285e92284225ad3fc2669a1e2e4269a35458
+size 4472