Hello icelandic typo-detector

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "ner",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-TYPO"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-TYPO": 1,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.9.0.dev0",
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce25ee545588a9b4339d4addd48d667825881464daf0cb31fc7d65759a7abe2
+size 538981877

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9d50efb27c7838248993b7e60929f0ca9e6da3e6a05b8c5642e761a3b05194
+size 539068832

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-multilingual-cased", "tokenizer_class": "DistilBertTokenizer"}

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 24591,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.3901427351470052e-05,
+      "loss": 0.1006,
+      "step": 5000
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.972805888299768,
+      "eval_f1": 0.9542635564090959,
+      "eval_loss": 0.07431062310934067,
+      "eval_precision": 0.9702985074626865,
+      "eval_recall": 0.9387499699164882,
+      "eval_runtime": 29.2474,
+      "eval_samples_per_second": 236.021,
+      "eval_steps_per_second": 14.771,
+      "step": 5000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.780407466146151e-05,
+      "loss": 0.0687,
+      "step": 10000
+    },
+    {
+      "epoch": 1.22,
+      "eval_accuracy": 0.9766388107030903,
+      "eval_f1": 0.9604958921631328,
+      "eval_loss": 0.06732712686061859,
+      "eval_precision": 0.9821666624745328,
+      "eval_recall": 0.9397607759139371,
+      "eval_runtime": 28.7775,
+      "eval_samples_per_second": 239.875,
+      "eval_steps_per_second": 15.012,
+      "step": 10000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.170550201293156e-05,
+      "loss": 0.0555,
+      "step": 15000
+    },
+    {
+      "epoch": 1.83,
+      "eval_accuracy": 0.9789952943058919,
+      "eval_f1": 0.9645339555446395,
+      "eval_loss": 0.06241472437977791,
+      "eval_precision": 0.9847538804884777,
+      "eval_recall": 0.9451276744242015,
+      "eval_runtime": 28.8228,
+      "eval_samples_per_second": 239.498,
+      "eval_steps_per_second": 14.988,
+      "step": 15000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 5.610589239965841e-06,
+      "loss": 0.0444,
+      "step": 20000
+    },
+    {
+      "epoch": 2.44,
+      "eval_accuracy": 0.9803844559359386,
+      "eval_f1": 0.9670321610620118,
+      "eval_loss": 0.06139765679836273,
+      "eval_precision": 0.9825864467408585,
+      "eval_recall": 0.9519626483117133,
+      "eval_runtime": 29.0028,
+      "eval_samples_per_second": 238.011,
+      "eval_steps_per_second": 14.895,
+      "step": 20000
+    },
+    {
+      "epoch": 3.0,
+      "step": 24591,
+      "total_flos": 3.1729035119402496e+16,
+      "train_loss": 0.06211166688984918,
+      "train_runtime": 4046.4754,
+      "train_samples_per_second": 97.228,
+      "train_steps_per_second": 6.077
+    }
+  ],
+  "max_steps": 24591,
+  "num_train_epochs": 3,
+  "total_flos": 3.1729035119402496e+16,
+  "trial_name": null,
+  "trial_params": null
+}