Upload 8 files

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": 32, "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": 5e-05, "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": 32, "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": 28, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["B-NAME", "L-NAME", "O", "U-EMAIL", "B-PHONE", "I-PHONE", "L-PHONE", "B-T_EXP", "I-T_EXP", "L-T_EXP", "B-SKILLS", "I-SKILLS", "L-SKILLS", "B-EXP_COMPANY_WISE", "I-EXP_COMPANY_WISE", "L-EXP_COMPANY_WISE", "B-PROJECTS", "I-PROJECTS", "L-PROJECTS", "B-G_CLG", "I-G_CLG", "L-G_CLG", "B-GRAD_PER", "L-GRAD_PER", "U-DOB", "B-C_DESIG", "I-C_DESIG", "L-C_DESIG", "B-CANDIDATE_ADDRESS", "I-CANDIDATE_ADDRESS", "L-CANDIDATE_ADDRESS", "B-G_IN", "I-G_IN", "L-G_IN", "U-G_YEAR", "B-INTER_FROM", "I-INTER_FROM", "L-INTER_FROM", "B-INTER_PER", "L-INTER_PER", "B-HIGH_FROM", "I-HIGH_FROM", "L-HIGH_FROM", "B-DOB", "I-DOB", "L-DOB", "U-PHONE", "U-EXP_COMPANY_WISE", "I-NAME", "B-HIGH_PER", "L-HIGH_PER", "B-CERTIFICATE", "I-CERTIFICATE", "L-CERTIFICATE", "U-G_IN", "B-G_YEAR", "I-G_YEAR", "L-G_YEAR", "U-SKILLS", "B-PG_YEAR", "L-PG_YEAR", "B-PG_FROM", "I-PG_FROM", "L-PG_FROM", "U-GRAD_PER", "U-INTER_FROM", "U-HIGH_FROM", "U-INTER_PER", "U-HIGH_PER", "U-CANDIDATE_ADDRESS", "B-PG_IN", "I-PG_IN", "L-PG_IN", "U-G_CLG", "I-GRAD_PER", "I-HIGH_PER", "I-PG_YEAR", "U-PG_IN", "U-PG_YEAR", "B-EMAIL", "L-EMAIL", "U-PROJECTS", "U-NAME", "U-CERTIFICATE", "I-INTER_PER", "U-PG_FROM"], "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>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "ignore_mismatched_sizes": true,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "kunalr63/roberta-parser",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de58b71dce17db8abbff5750314f930706a03209310ac10d6430a0d49b96dae
-size 3375
+oid sha256:6c93b70bca31eb061e2a761aae6c8281501c743dd2c546ac7a5652f1beb5931d
+size 4335