Upload model

Initial model upload, without optimizer and weights (but with License file). The aforementioned ones will be uploaded separately because of their sheer size

LICENSE.txt

@@ -0,0 +1,7 @@
+This model is licensed under the Creative Commons Attribution-NonCommercial-
+ShareAlike 4.0 Generic License. To view a copy of this license, visit
+
+http://creativecommons.org/licenses/by-nc-sa/4.0/
+
+or send a letter to
+Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "models/allUDLonger.POS/best_model/",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "CCONJ",
+    "5": "DET",
+    "6": "INTJ",
+    "7": "NOUN",
+    "8": "NUM",
+    "9": "PART",
+    "10": "PRON",
+    "11": "PROPN",
+    "12": "PUNCT",
+    "13": "SCONJ",
+    "14": "SYM",
+    "15": "VERB",
+    "16": "X",
+    "17": "_",
+    "18": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "CCONJ": 4,
+    "DET": 5,
+    "INTJ": 6,
+    "NOUN": 7,
+    "NUM": 8,
+    "O": 18,
+    "PART": 9,
+    "PRON": 10,
+    "PROPN": 11,
+    "PUNCT": 12,
+    "SCONJ": 13,
+    "SYM": 14,
+    "VERB": 15,
+    "X": 16,
+    "_": 17
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,15 @@
+accuracy = 0.9808408728046834
+eval_loss = 0.10505632257887296
+f1_macro = 0.8119795782322581
+f1_micro = 0.9845183486238532
+f1_score = 0.976265370317415
+f1_weighted = 0.9844535733765792
+feats_acc = 1.0
+pr_macro = 0.8138805652000092
+pr_micro = 0.9839541547277937
+pr_weighted = 0.9841307618299782
+precision = 0.9759862778730704
+rc_macro = 0.8111773061863014
+rc_micro = 0.985083189902467
+rc_weighted = 0.985083189902467
+recall = 0.9765446224256293

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": "models/eFontesBenchmark.POS/best_model/", "cache_dir": "/net/tscratch/people/plgjziebura/cache/", "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": "f1_micro", "early_stopping_metric_minimize": false, "early_stopping_patience": 30, "encoding": null, "eval_batch_size": 12, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 100, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 0, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "models/allUDLonger.POS/best_model/", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "models/eFontesBenchmark.POS", "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": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 0, "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": 12, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"entity": "enelpol"}, "wandb_project": "efontes-tests", "warmup_ratio": 0.06, "warmup_steps": 2184, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["ADJ", "ADP", "ADV", "AUX", "CCONJ", "DET", "INTJ", "NOUN", "NUM", "PART", "PRON", "PROPN", "PUNCT", "SCONJ", "SYM", "VERB", "X", "_", "O"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d76096686e220936467999bc915a65e6f2a88177745aa97260b12bc2acb5fa
+size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "ignore_mismatched_sizes": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8b87d40ba748ef0738f4dab5c61f8438e5c8af81dd2814fd5c20f00f74973e
+size 3835