HHansi commited on
Commit
e1999a9
1 Parent(s): f5889cc

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<e>": 250002, "</e>": 250003}
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.16.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250004
28
+ }
eval_results.txt ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ accuracy = 0.89
2
+ cls_report = precision recall f1-score support
3
+
4
+ 0.0 0.9020 0.8846 0.8932 52
5
+ 1.0 0.8776 0.8958 0.8866 48
6
+
7
+ accuracy 0.8900 100
8
+ macro avg 0.8898 0.8902 0.8899 100
9
+ weighted avg 0.8902 0.8900 0.8900 100
10
+
11
+ eval_loss = 0.4262773199723317
12
+ fn = 5
13
+ fp = 6
14
+ macro_f1 = 0.8899009108197378
15
+ mcc = 0.7799801206576289
16
+ tn = 46
17
+ tp = 43
18
+ weighted_f1 = 0.8900330297267541
19
+ weighted_p = 0.8897559023609444
20
+ weighted_r = 0.890224358974359
model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adam_epsilon": 1e-08, "begin_tag": "<e>", "best_model_dir": "best_model/ru_ru", "cache_dir": "temp/cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 70, "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": 10, "encoding": null, "end_tag": "</e>", "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 20, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 20, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 120, "model_name": "xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 5, "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 70, "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": 20, "save_recent_only": true, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {"group": "ru_ru_xlm-roberta-large_ET_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 57, "weight_decay": 0, "skip_special_tokens": true, "model_class": "ClassificationModel", "labels_list": [0, 1], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "stride": 0.8, "tie_value": 1, "tagging": true, "strategy": "ET", "special_tags": ["</e>"], "merge_n": 2, "merge_type": "concat"}
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630a3f9820cc324c51634cb9b6c7b472942291fb76ea5629ee2d247c6a89cacf
3
+ size 4504577789
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dc2f2b000dba564107abee4ce7c9545e649c5dd8e458ff7f728a4683fa89dd
3
+ size 2256539453
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3fad00e06cbf99d02c84534eb29368206f7030d02e4dc29ae05b0f48955115
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 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
test_eval.txt ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Default classification report:
2
+ precision recall f1-score support
3
+
4
+ F 0.6731 0.7620 0.7148 500
5
+ T 0.7258 0.6300 0.6745 500
6
+
7
+ accuracy 0.6960 1000
8
+ macro avg 0.6995 0.6960 0.6947 1000
9
+ weighted avg 0.6995 0.6960 0.6947 1000
10
+
11
+
12
+ ADJ
13
+ Accuracy = 0.6333333333333333
14
+ Weighted Recall = 0.6333333333333333
15
+ Weighted Precision = 0.680952380952381
16
+ Weighted F1 = 0.6395061728395063
17
+ Macro Recall = 0.65311004784689
18
+ Macro Precision = 0.6428571428571428
19
+ Macro F1 = 0.6296296296296297
20
+ ADV
21
+ Accuracy = 0.5
22
+ Weighted Recall = 0.5
23
+ Weighted Precision = 0.5
24
+ Weighted F1 = 0.5
25
+ Macro Recall = 0.4666666666666667
26
+ Macro Precision = 0.4666666666666667
27
+ Macro F1 = 0.4666666666666667
28
+ NOUN
29
+ Accuracy = 0.7079037800687286
30
+ Weighted Recall = 0.7079037800687286
31
+ Weighted Precision = 0.7079506597291303
32
+ Weighted F1 = 0.7075162790129713
33
+ Macro Recall = 0.7068794326241135
34
+ Macro Precision = 0.7079807966536743
35
+ Macro F1 = 0.7070180633698548
36
+ VERB
37
+ Accuracy = 0.6908602150537635
38
+ Weighted Recall = 0.6908602150537635
39
+ Weighted Precision = 0.7051039053394702
40
+ Weighted F1 = 0.6865025025998203
41
+ Macro Recall = 0.6928181108508977
42
+ Macro Precision = 0.7041947336191059
43
+ Macro F1 = 0.6870588063173448
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/hh2/.cache/huggingface/transformers/7766c86e10505ed9b39af34e456480399bf06e35b36b8f2b917460a2dbe94e59.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f0ea093b62e9863f9b1cbf9d875ba5e2f4fcb4c4ece1203220f0e2d731897f
3
+ size 2811