Upload 10 files

config.json

@@ -0,0 +1,105 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-CARDINAL",
+    "1": "I-CARDINAL",
+    "2": "B-DATE",
+    "3": "I-DATE",
+    "4": "B-EVENT",
+    "5": "I-EVENT",
+    "6": "B-FAC",
+    "7": "I-FAC",
+    "8": "B-GPE",
+    "9": "I-GPE",
+    "10": "B-LANGUAGE",
+    "11": "I-LANGUAGE",
+    "12": "B-LAW",
+    "13": "I-LAW",
+    "14": "B-LOC",
+    "15": "I-LOC",
+    "16": "B-MONEY",
+    "17": "I-MONEY",
+    "18": "B-NORP",
+    "19": "I-NORP",
+    "20": "B-ORDINAL",
+    "21": "I-ORDINAL",
+    "22": "B-ORG",
+    "23": "I-ORG",
+    "24": "B-PERCENT",
+    "25": "I-PERCENT",
+    "26": "B-PERSON",
+    "27": "I-PERSON",
+    "28": "B-PRODUCT",
+    "29": "I-PRODUCT",
+    "30": "B-QUANTITY",
+    "31": "I-QUANTITY",
+    "32": "B-TIME",
+    "33": "I-TIME",
+    "34": "B-WORK_OF_ART",
+    "35": "I-WORK_OF_ART",
+    "36": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CARDINAL": 0,
+    "B-DATE": 2,
+    "B-EVENT": 4,
+    "B-FAC": 6,
+    "B-GPE": 8,
+    "B-LANGUAGE": 10,
+    "B-LAW": 12,
+    "B-LOC": 14,
+    "B-MONEY": 16,
+    "B-NORP": 18,
+    "B-ORDINAL": 20,
+    "B-ORG": 22,
+    "B-PERCENT": 24,
+    "B-PERSON": 26,
+    "B-PRODUCT": 28,
+    "B-QUANTITY": 30,
+    "B-TIME": 32,
+    "B-WORK_OF_ART": 34,
+    "I-CARDINAL": 1,
+    "I-DATE": 3,
+    "I-EVENT": 5,
+    "I-FAC": 7,
+    "I-GPE": 9,
+    "I-LANGUAGE": 11,
+    "I-LAW": 13,
+    "I-LOC": 15,
+    "I-MONEY": 17,
+    "I-NORP": 19,
+    "I-ORDINAL": 21,
+    "I-ORG": 23,
+    "I-PERCENT": 25,
+    "I-PERSON": 27,
+    "I-PRODUCT": 29,
+    "I-QUANTITY": 31,
+    "I-TIME": 33,
+    "I-WORK_OF_ART": 35,
+    "O": 36
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 0.08307243298469602
+f1_score = 0.8707822598618231
+precision = 0.8569924548166346
+recall = 0.8850231041043762

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:184b948ccd52b2fd4f1d9c687bbc183e009684c785ee5df73443a0fe7c5660a1
+size 496357908

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0.01, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 2, "encoding": null, "eval_batch_size": 128, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 4, "learning_rate": 0.0001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "roberta-base", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 128, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {"name": "RoBERTa"}, "wandb_project": "ner-transformer-finetuning", "warmup_ratio": 0.06, "warmup_steps": 45, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": true, "labels_list": ["B-CARDINAL", "I-CARDINAL", "B-DATE", "I-DATE", "B-EVENT", "I-EVENT", "B-FAC", "I-FAC", "B-GPE", "I-GPE", "B-LANGUAGE", "I-LANGUAGE", "B-LAW", "I-LAW", "B-LOC", "I-LOC", "B-MONEY", "I-MONEY", "B-NORP", "I-NORP", "B-ORDINAL", "I-ORDINAL", "B-ORG", "I-ORG", "B-PERCENT", "I-PERCENT", "B-PERSON", "I-PERSON", "B-PRODUCT", "I-PRODUCT", "B-QUANTITY", "I-QUANTITY", "B-TIME", "I-TIME", "B-WORK_OF_ART", "I-WORK_OF_ART", "O"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccd66a03d0113f1af9fc31c2a46f999d2176c02ba1789086132e7165b7e3ada
+size 4024