Upload 11 files

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "toxic",
+    "1": "severe_toxic",
+    "2": "obscene",
+    "3": "threat",
+    "4": "insult",
+    "5": "identity_hate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "identity_hate": "5",
+    "insult": "4",
+    "obscene": "2",
+    "severe_toxic": "1",
+    "threat": "3",
+    "toxic": "0"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc06adcf78c0a07772197feb59d827e7285b2d8b4daafc3dbbef4e10c69cbac3
+size 90874112

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4023fd2010f265e2d33bf01816c93464ec88f8f45b29e3256297cbb3ae796152
+size 181811781

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4901343f1db59d78bb10278a4c5bf0aa675f3fdaee60b00b12be742e68de004a
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d073ca29c5b5c00ca86ac7cf2513d21cbd4551c1105f04d1724baadfb572a8
+size 627

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_metric": 0.9861040423241723,
+  "best_model_checkpoint": "nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large-finetuned-toxic/checkpoint-6000",
+  "epoch": 3.909774436090226,
+  "eval_steps": 1000,
+  "global_step": 13000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 7.518796992481203e-06,
+      "loss": 0.6315,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5037593984962406e-05,
+      "loss": 0.2862,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.2286241501569748,
+      "eval_roc_auc_score": 0.8322393690478088,
+      "eval_runtime": 1448.3474,
+      "eval_samples_per_second": 44.173,
+      "eval_steps_per_second": 0.92,
+      "step": 1000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.255639097744361e-05,
+      "loss": 0.1326,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.007518796992481e-05,
+      "loss": 0.0947,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.1304231733083725,
+      "eval_roc_auc_score": 0.875743139169344,
+      "eval_runtime": 1447.2229,
+      "eval_samples_per_second": 44.207,
+      "eval_steps_per_second": 0.921,
+      "step": 2000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.759398496240601e-05,
+      "loss": 0.081,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.511278195488722e-05,
+      "loss": 0.0646,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.08389352262020111,
+      "eval_roc_auc_score": 0.967879018591784,
+      "eval_runtime": 1447.7446,
+      "eval_samples_per_second": 44.191,
+      "eval_steps_per_second": 0.921,
+      "step": 3000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.970760233918128e-05,
+      "loss": 0.058,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.887218045112782e-05,
+      "loss": 0.0481,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.06747555732727051,
+      "eval_roc_auc_score": 0.9834643964057315,
+      "eval_runtime": 1447.8097,
+      "eval_samples_per_second": 44.19,
+      "eval_steps_per_second": 0.921,
+      "step": 4000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.803675856307435e-05,
+      "loss": 0.0454,
+      "step": 4500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.720133667502089e-05,
+      "loss": 0.0432,
+      "step": 5000
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.06311842054128647,
+      "eval_roc_auc_score": 0.9851907554305832,
+      "eval_runtime": 1447.771,
+      "eval_samples_per_second": 44.191,
+      "eval_steps_per_second": 0.921,
+      "step": 5000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.6365914786967416e-05,
+      "loss": 0.0403,
+      "step": 5500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.553049289891395e-05,
+      "loss": 0.0395,
+      "step": 6000
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.05904868617653847,
+      "eval_roc_auc_score": 0.9861040423241723,
+      "eval_runtime": 1447.5158,
+      "eval_samples_per_second": 44.198,
+      "eval_steps_per_second": 0.921,
+      "step": 6000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.4695071010860486e-05,
+      "loss": 0.0391,
+      "step": 6500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.3859649122807014e-05,
+      "loss": 0.0355,
+      "step": 7000
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 0.0542282797396183,
+      "eval_roc_auc_score": 0.9848519740606182,
+      "eval_runtime": 1447.9782,
+      "eval_samples_per_second": 44.184,
+      "eval_steps_per_second": 0.921,
+      "step": 7000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 4.302422723475355e-05,
+      "loss": 0.0338,
+      "step": 7500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 4.2188805346700084e-05,
+      "loss": 0.0331,
+      "step": 8000
+    },
+    {
+      "epoch": 2.41,
+      "eval_loss": 0.05404088273644447,
+      "eval_roc_auc_score": 0.9859118025622516,
+      "eval_runtime": 1448.289,
+      "eval_samples_per_second": 44.175,
+      "eval_steps_per_second": 0.92,
+      "step": 8000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.135338345864662e-05,
+      "loss": 0.0332,
+      "step": 8500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.051796157059315e-05,
+      "loss": 0.0321,
+      "step": 9000
+    },
+    {
+      "epoch": 2.71,
+      "eval_loss": 0.047978416085243225,
+      "eval_roc_auc_score": 0.9852137903731366,
+      "eval_runtime": 1448.4616,
+      "eval_samples_per_second": 44.17,
+      "eval_steps_per_second": 0.92,
+      "step": 9000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 0.0324,
+      "step": 9500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 3.884711779448622e-05,
+      "loss": 0.0319,
+      "step": 10000
+    },
+    {
+      "epoch": 3.01,
+      "eval_loss": 0.055611222982406616,
+      "eval_roc_auc_score": 0.9852909213651101,
+      "eval_runtime": 1448.1598,
+      "eval_samples_per_second": 44.179,
+      "eval_steps_per_second": 0.92,
+      "step": 10000
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 3.8011695906432746e-05,
+      "loss": 0.0278,
+      "step": 10500
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.717627401837928e-05,
+      "loss": 0.028,
+      "step": 11000
+    },
+    {
+      "epoch": 3.31,
+      "eval_loss": 0.04669087007641792,
+      "eval_roc_auc_score": 0.9856710846934756,
+      "eval_runtime": 1447.7255,
+      "eval_samples_per_second": 44.192,
+      "eval_steps_per_second": 0.921,
+      "step": 11000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 3.6340852130325816e-05,
+      "loss": 0.0283,
+      "step": 11500
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 3.5505430242272344e-05,
+      "loss": 0.0287,
+      "step": 12000
+    },
+    {
+      "epoch": 3.61,
+      "eval_loss": 0.05279074236750603,
+      "eval_roc_auc_score": 0.9854943814780995,
+      "eval_runtime": 1448.314,
+      "eval_samples_per_second": 44.174,
+      "eval_steps_per_second": 0.92,
+      "step": 12000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 3.467000835421888e-05,
+      "loss": 0.0277,
+      "step": 12500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 3.3834586466165414e-05,
+      "loss": 0.029,
+      "step": 13000
+    },
+    {
+      "epoch": 3.91,
+      "eval_loss": 0.052444275468587875,
+      "eval_roc_auc_score": 0.9860021739433819,
+      "eval_runtime": 1449.0313,
+      "eval_samples_per_second": 44.152,
+      "eval_steps_per_second": 0.92,
+      "step": 13000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 33250,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "total_flos": 2.069553146242867e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aeecd425e761739ae15f420cac1046cfbe65564d028196d8edba00d6797c136
+size 4283