jziebura commited on
Commit
c9f5647
1 Parent(s): 099f7a1

Upload model

Browse files

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 ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ This model is licensed under the Creative Commons Attribution-NonCommercial-
2
+ ShareAlike 4.0 Generic License. To view a copy of this license, visit
3
+
4
+ http://creativecommons.org/licenses/by-nc-sa/4.0/
5
+
6
+ or send a letter to
7
+ Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/allUDLonger.POS/best_model/",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "ADJ",
15
+ "1": "ADP",
16
+ "2": "ADV",
17
+ "3": "AUX",
18
+ "4": "CCONJ",
19
+ "5": "DET",
20
+ "6": "INTJ",
21
+ "7": "NOUN",
22
+ "8": "NUM",
23
+ "9": "PART",
24
+ "10": "PRON",
25
+ "11": "PROPN",
26
+ "12": "PUNCT",
27
+ "13": "SCONJ",
28
+ "14": "SYM",
29
+ "15": "VERB",
30
+ "16": "X",
31
+ "17": "_",
32
+ "18": "O"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 4096,
36
+ "label2id": {
37
+ "ADJ": 0,
38
+ "ADP": 1,
39
+ "ADV": 2,
40
+ "AUX": 3,
41
+ "CCONJ": 4,
42
+ "DET": 5,
43
+ "INTJ": 6,
44
+ "NOUN": 7,
45
+ "NUM": 8,
46
+ "O": 18,
47
+ "PART": 9,
48
+ "PRON": 10,
49
+ "PROPN": 11,
50
+ "PUNCT": 12,
51
+ "SCONJ": 13,
52
+ "SYM": 14,
53
+ "VERB": 15,
54
+ "X": 16,
55
+ "_": 17
56
+ },
57
+ "layer_norm_eps": 1e-05,
58
+ "max_position_embeddings": 514,
59
+ "model_type": "xlm-roberta",
60
+ "num_attention_heads": 16,
61
+ "num_hidden_layers": 24,
62
+ "output_past": true,
63
+ "pad_token_id": 1,
64
+ "position_embedding_type": "absolute",
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.30.1",
67
+ "type_vocab_size": 1,
68
+ "use_cache": true,
69
+ "vocab_size": 250002
70
+ }
eval_results.txt ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ accuracy = 0.9808408728046834
2
+ eval_loss = 0.10505632257887296
3
+ f1_macro = 0.8119795782322581
4
+ f1_micro = 0.9845183486238532
5
+ f1_score = 0.976265370317415
6
+ f1_weighted = 0.9844535733765792
7
+ feats_acc = 1.0
8
+ pr_macro = 0.8138805652000092
9
+ pr_micro = 0.9839541547277937
10
+ pr_weighted = 0.9841307618299782
11
+ precision = 0.9759862778730704
12
+ rc_macro = 0.8111773061863014
13
+ rc_micro = 0.985083189902467
14
+ rc_weighted = 0.985083189902467
15
+ recall = 0.9765446224256293
model_args.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d76096686e220936467999bc915a65e6f2a88177745aa97260b12bc2acb5fa
3
+ size 627
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "do_lower_case": false,
6
+ "eos_token": "</s>",
7
+ "ignore_mismatched_sizes": true,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "sp_model_kwargs": {},
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8b87d40ba748ef0738f4dab5c61f8438e5c8af81dd2814fd5c20f00f74973e
3
+ size 3835