Upload folder using huggingface_hub

best/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "$START": 50265
+}

best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32514302c01cab5a24931df3ead6c76cff11b7a557fcf2b49d5f240666708d3a
+size 511632936

best/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "$START",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

best/tokenizer_config.json

@@ -0,0 +1,69 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "$START",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "$START"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

last/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "$START": 50265
+}

last/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32514302c01cab5a24931df3ead6c76cff11b7a557fcf2b49d5f240666708d3a
+size 511632936

last/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "$START",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

last/tokenizer_config.json

@@ -0,0 +1,69 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "$START",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "$START"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

log.json

@@ -0,0 +1,194 @@
+{
+  "argparse": {
+    "train_file": "gector/data/train_preprocessed.pt",
+    "valid_file": "gector/data/valid_preprocessed.pt",
+    "model_id": "FacebookAI/roberta-base",
+    "batch_size": 32,
+    "early_stopper": 8,
+    "delimeter": "SEPL|||SEPR",
+    "additional_delimeter": "SEPL__SEPR",
+    "restore_dir": null,
+    "restore_vocab": null,
+    "restore_vocab_official": null,
+    "save_dir": "drive/MyDrive/outputs/gector_finerio",
+    "max_len": 128,
+    "n_max_labels": 5000,
+    "n_epochs": 120,
+    "p_dropout": 0.0,
+    "lr": 1e-05,
+    "cold_lr": 0.001,
+    "accumulation": 1,
+    "seed": 10,
+    "label_smoothing": 0.0,
+    "n_cold_epochs": 2,
+    "num_warmup_steps": 500,
+    "lr_scheduler_type": "constant"
+  },
+  "Epoch 0": {
+    "train_log": {
+      "loss": 1.7032910907026595,
+      "accuracy": 0.803969903675253,
+      "accuracy_d": 0.8724265860173506
+    },
+    "valid_log": {
+      "loss": 1.1267204428979771,
+      "accuracy": 0.8362742538576002,
+      "accuracy_d": 0.8833048800369362,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 1": {
+    "train_log": {
+      "loss": 1.2184834499734831,
+      "accuracy": 0.8329997152576303,
+      "accuracy_d": 0.8792239682540636
+    },
+    "valid_log": {
+      "loss": 0.9992180193510037,
+      "accuracy": 0.8476613973421157,
+      "accuracy_d": 0.8882333797736159,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 2": {
+    "train_log": {
+      "loss": 0.8153748830096256,
+      "accuracy": 0.8644381554725395,
+      "accuracy_d": 0.9125891849665446
+    },
+    "valid_log": {
+      "loss": 0.708008555180509,
+      "accuracy": 0.8810764396345461,
+      "accuracy_d": 0.9304811779775956,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 3": {
+    "train_log": {
+      "loss": 0.670869435280431,
+      "accuracy": 0.8802149062891003,
+      "accuracy_d": 0.9280548943165902
+    },
+    "valid_log": {
+      "loss": 0.6924886661192924,
+      "accuracy": 0.8869327425072056,
+      "accuracy_d": 0.9310040617696872,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 4": {
+    "train_log": {
+      "loss": 0.5957314862146635,
+      "accuracy": 0.88956841407807,
+      "accuracy_d": 0.9349972145328757
+    },
+    "valid_log": {
+      "loss": 0.6383009447624599,
+      "accuracy": 0.8902179040360318,
+      "accuracy_d": 0.9384833052339713,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 5": {
+    "train_log": {
+      "loss": 0.5390387795334833,
+      "accuracy": 0.8971076633320166,
+      "accuracy_d": 0.940645343271613
+    },
+    "valid_log": {
+      "loss": 0.6460947684376934,
+      "accuracy": 0.8933471329579327,
+      "accuracy_d": 0.9373614872099075,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 6": {
+    "train_log": {
+      "loss": 0.48871075836634,
+      "accuracy": 0.9041179819406858,
+      "accuracy_d": 0.9453216991100091
+    },
+    "valid_log": {
+      "loss": 0.6075716740235769,
+      "accuracy": 0.894183147373801,
+      "accuracy_d": 0.9401003544759662,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 7": {
+    "train_log": {
+      "loss": 0.4453746993235511,
+      "accuracy": 0.9112622401081515,
+      "accuracy_d": 0.9495536471997605
+    },
+    "valid_log": {
+      "loss": 0.620118053674919,
+      "accuracy": 0.8942456968640131,
+      "accuracy_d": 0.9408376017837666,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 8": {
+    "train_log": {
+      "loss": 0.4053901939949712,
+      "accuracy": 0.9178540091138886,
+      "accuracy_d": 0.9538734333239084
+    },
+    "valid_log": {
+      "loss": 0.6320258723727405,
+      "accuracy": 0.8951096773589918,
+      "accuracy_d": 0.9403002296396443,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 9": {
+    "train_log": {
+      "loss": 0.3688604742395323,
+      "accuracy": 0.9238926816214331,
+      "accuracy_d": 0.9574667460833989
+    },
+    "valid_log": {
+      "loss": 0.6419418054962865,
+      "accuracy": 0.8946705572237995,
+      "accuracy_d": 0.9425146041199537
+    }
+  },
+  "Epoch 10": {
+    "train_log": {
+      "loss": 0.33416874041144135,
+      "accuracy": 0.9297098048028365,
+      "accuracy_d": 0.9619453058886044
+    },
+    "valid_log": {
+      "loss": 0.6550916678000912,
+      "accuracy": 0.8971033769768554,
+      "accuracy_d": 0.9415456193718706,
+      "message": "The best checkpoint has been updated."
+    }
+  },
+  "Epoch 11": {
+    "train_log": {
+      "loss": 0.303828910638019,
+      "accuracy": 0.935022974531346,
+      "accuracy_d": 0.9651207187191879
+    },
+    "valid_log": {
+      "loss": 0.6778709775386361,
+      "accuracy": 0.8962904538869415,
+      "accuracy_d": 0.9426721779004099
+    }
+  },
+  "Epoch 12": {
+    "train_log": {
+      "loss": 0.2758491554175579,
+      "accuracy": 0.9401938989966029,
+      "accuracy_d": 0.9684101530294043
+    },
+    "valid_log": {
+      "loss": 0.695371216380751,
+      "accuracy": 0.897200845168119,
+      "accuracy_d": 0.9425573480593694,
+      "message": "The best checkpoint has been updated."
+    }
+  }
+}