Upload 11 files

config.json

@@ -0,0 +1,231 @@
+{
+  "_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": "U-PER",
+    "1": "O",
+    "2": "B-T_EXP",
+    "3": "I-T_EXP",
+    "4": "L-T_EXP",
+    "5": "B-PER",
+    "6": "L-PER",
+    "7": "U-PHONE",
+    "8": "U-EMAIL",
+    "9": "B-CERTIFICATE",
+    "10": "I-CERTIFICATE",
+    "11": "L-CERTIFICATE",
+    "12": "B-G_YEAR",
+    "13": "I-G_YEAR",
+    "14": "L-G_YEAR",
+    "15": "B-G_IN",
+    "16": "I-G_IN",
+    "17": "L-G_IN",
+    "18": "B-G_CLG",
+    "19": "I-G_CLG",
+    "20": "L-G_CLG",
+    "21": "B-INTER_YEAR",
+    "22": "I-INTER_YEAR",
+    "23": "L-INTER_YEAR",
+    "24": "B-12_PER",
+    "25": "L-12_PER",
+    "26": "B-HIGH_YEAR",
+    "27": "I-HIGH_YEAR",
+    "28": "L-HIGH_YEAR",
+    "29": "B-HIGH_FROM",
+    "30": "I-HIGH_FROM",
+    "31": "L-HIGH_FROM",
+    "32": "B-10_PER",
+    "33": "L-10_PER",
+    "34": "U-DOB",
+    "35": "I-PER",
+    "36": "B-PHONE",
+    "37": "I-PHONE",
+    "38": "L-PHONE",
+    "39": "B-C_DESIG",
+    "40": "L-C_DESIG",
+    "41": "B-O_COMPANY",
+    "42": "I-O_COMPANY",
+    "43": "L-O_COMPANY",
+    "44": "B-GRAD_PER",
+    "45": "L-GRAD_PER",
+    "46": "B-INTER_FROM",
+    "47": "I-INTER_FROM",
+    "48": "L-INTER_FROM",
+    "49": "B-SKILLS",
+    "50": "I-SKILLS",
+    "51": "L-SKILLS",
+    "52": "U-PG_IN",
+    "53": "B-PG_FROM",
+    "54": "I-PG_FROM",
+    "55": "L-PG_FROM",
+    "56": "B-PG_YEAR",
+    "57": "L-PG_YEAR",
+    "58": "B-C_COMPANY",
+    "59": "I-C_COMPANY",
+    "60": "L-C_COMPANY",
+    "61": "B-PG_IN",
+    "62": "I-PG_IN",
+    "63": "L-PG_IN",
+    "64": "U-PG_YEAR",
+    "65": "U-G_IN",
+    "66": "U-G_YEAR",
+    "67": "I-C_DESIG",
+    "68": "U-SKILLS",
+    "69": "U-GRAD_PER",
+    "70": "B-PROJECTS",
+    "71": "I-PROJECTS",
+    "72": "L-PROJECTS",
+    "73": "U-C_COMPANY",
+    "74": "U-INTER_YEAR",
+    "75": "U-HIGH_YEAR",
+    "76": "B-EMAIL",
+    "77": "I-EMAIL",
+    "78": "L-EMAIL",
+    "79": "B-TOOLS_USED",
+    "80": "I-TOOLS_USED",
+    "81": "L-TOOLS_USED",
+    "82": "I-PG_YEAR",
+    "83": "I-GRAD_PER",
+    "84": "U-TOOLS_USED",
+    "85": "I-12_PER",
+    "86": "I-10_PER",
+    "87": "U-T_EXP",
+    "88": "U-PROJECTS",
+    "89": "B-DOB",
+    "90": "L-DOB",
+    "91": "U-HIGH_FROM",
+    "92": "I-DOB",
+    "93": "U-12_PER",
+    "94": "U-10_PER",
+    "95": "U-G_CLG",
+    "96": "U-O_COMPANY",
+    "97": "U-INTER_FROM",
+    "98": "U-C_DESIG",
+    "99": "U-PG_FROM"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-10_PER": 32,
+    "B-12_PER": 24,
+    "B-CERTIFICATE": 9,
+    "B-C_COMPANY": 58,
+    "B-C_DESIG": 39,
+    "B-DOB": 89,
+    "B-EMAIL": 76,
+    "B-GRAD_PER": 44,
+    "B-G_CLG": 18,
+    "B-G_IN": 15,
+    "B-G_YEAR": 12,
+    "B-HIGH_FROM": 29,
+    "B-HIGH_YEAR": 26,
+    "B-INTER_FROM": 46,
+    "B-INTER_YEAR": 21,
+    "B-O_COMPANY": 41,
+    "B-PER": 5,
+    "B-PG_FROM": 53,
+    "B-PG_IN": 61,
+    "B-PG_YEAR": 56,
+    "B-PHONE": 36,
+    "B-PROJECTS": 70,
+    "B-SKILLS": 49,
+    "B-TOOLS_USED": 79,
+    "B-T_EXP": 2,
+    "I-10_PER": 86,
+    "I-12_PER": 85,
+    "I-CERTIFICATE": 10,
+    "I-C_COMPANY": 59,
+    "I-C_DESIG": 67,
+    "I-DOB": 92,
+    "I-EMAIL": 77,
+    "I-GRAD_PER": 83,
+    "I-G_CLG": 19,
+    "I-G_IN": 16,
+    "I-G_YEAR": 13,
+    "I-HIGH_FROM": 30,
+    "I-HIGH_YEAR": 27,
+    "I-INTER_FROM": 47,
+    "I-INTER_YEAR": 22,
+    "I-O_COMPANY": 42,
+    "I-PER": 35,
+    "I-PG_FROM": 54,
+    "I-PG_IN": 62,
+    "I-PG_YEAR": 82,
+    "I-PHONE": 37,
+    "I-PROJECTS": 71,
+    "I-SKILLS": 50,
+    "I-TOOLS_USED": 80,
+    "I-T_EXP": 3,
+    "L-10_PER": 33,
+    "L-12_PER": 25,
+    "L-CERTIFICATE": 11,
+    "L-C_COMPANY": 60,
+    "L-C_DESIG": 40,
+    "L-DOB": 90,
+    "L-EMAIL": 78,
+    "L-GRAD_PER": 45,
+    "L-G_CLG": 20,
+    "L-G_IN": 17,
+    "L-G_YEAR": 14,
+    "L-HIGH_FROM": 31,
+    "L-HIGH_YEAR": 28,
+    "L-INTER_FROM": 48,
+    "L-INTER_YEAR": 23,
+    "L-O_COMPANY": 43,
+    "L-PER": 6,
+    "L-PG_FROM": 55,
+    "L-PG_IN": 63,
+    "L-PG_YEAR": 57,
+    "L-PHONE": 38,
+    "L-PROJECTS": 72,
+    "L-SKILLS": 51,
+    "L-TOOLS_USED": 81,
+    "L-T_EXP": 4,
+    "O": 1,
+    "U-10_PER": 94,
+    "U-12_PER": 93,
+    "U-C_COMPANY": 73,
+    "U-C_DESIG": 98,
+    "U-DOB": 34,
+    "U-EMAIL": 8,
+    "U-GRAD_PER": 69,
+    "U-G_CLG": 95,
+    "U-G_IN": 65,
+    "U-G_YEAR": 66,
+    "U-HIGH_FROM": 91,
+    "U-HIGH_YEAR": 75,
+    "U-INTER_FROM": 97,
+    "U-INTER_YEAR": 74,
+    "U-O_COMPANY": 96,
+    "U-PER": 0,
+    "U-PG_FROM": 99,
+    "U-PG_IN": 52,
+    "U-PG_YEAR": 64,
+    "U-PHONE": 7,
+    "U-PROJECTS": 88,
+    "U-SKILLS": 68,
+    "U-TOOLS_USED": 84,
+    "U-T_EXP": 87
+  },
+  "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": "4.22.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

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, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "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": 20, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 18, "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": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 87, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["U-PER", "O", "B-T_EXP", "I-T_EXP", "L-T_EXP", "B-PER", "L-PER", "U-PHONE", "U-EMAIL", "B-CERTIFICATE", "I-CERTIFICATE", "L-CERTIFICATE", "B-G_YEAR", "I-G_YEAR", "L-G_YEAR", "B-G_IN", "I-G_IN", "L-G_IN", "B-G_CLG", "I-G_CLG", "L-G_CLG", "B-INTER_YEAR", "I-INTER_YEAR", "L-INTER_YEAR", "B-12_PER", "L-12_PER", "B-HIGH_YEAR", "I-HIGH_YEAR", "L-HIGH_YEAR", "B-HIGH_FROM", "I-HIGH_FROM", "L-HIGH_FROM", "B-10_PER", "L-10_PER", "U-DOB", "I-PER", "B-PHONE", "I-PHONE", "L-PHONE", "B-C_DESIG", "L-C_DESIG", "B-O_COMPANY", "I-O_COMPANY", "L-O_COMPANY", "B-GRAD_PER", "L-GRAD_PER", "B-INTER_FROM", "I-INTER_FROM", "L-INTER_FROM", "B-SKILLS", "I-SKILLS", "L-SKILLS", "U-PG_IN", "B-PG_FROM", "I-PG_FROM", "L-PG_FROM", "B-PG_YEAR", "L-PG_YEAR", "B-C_COMPANY", "I-C_COMPANY", "L-C_COMPANY", "B-PG_IN", "I-PG_IN", "L-PG_IN", "U-PG_YEAR", "U-G_IN", "U-G_YEAR", "I-C_DESIG", "U-SKILLS", "U-GRAD_PER", "B-PROJECTS", "I-PROJECTS", "L-PROJECTS", "U-C_COMPANY", "U-INTER_YEAR", "U-HIGH_YEAR", "B-EMAIL", "I-EMAIL", "L-EMAIL", "B-TOOLS_USED", "I-TOOLS_USED", "L-TOOLS_USED", "I-PG_YEAR", "I-GRAD_PER", "U-TOOLS_USED", "I-12_PER", "I-10_PER", "U-T_EXP", "U-PROJECTS", "B-DOB", "L-DOB", "U-HIGH_FROM", "I-DOB", "U-12_PER", "U-10_PER", "U-G_CLG", "U-O_COMPANY", "U-INTER_FROM", "U-C_DESIG", "U-PG_FROM"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e61e5b1d6d6fee16d27cbc243a8d1d18a5d3738669dbb2facbbd2018e96360e
+size 993219927

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb8d77a1992098856592218b302077aa5447c2eda343eb1ee368752830955bc
+size 496598833

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dae8af04cc4eda79058d9f9b5ecc65298424f0272c970dcf82c14083a08f5f
+size 623

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 +1,17 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "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 sha256:8148d2dc0a436ed82b2d2cebae0bb023641d1fd8c6807f21a54b2299783d8eae
+size 4527