Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1 @@
+{"<e>": 250002, "</e>": 250003}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250004
+}

eval_results.txt

@@ -0,0 +1,20 @@
+accuracy = 0.8321732405259087
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.8973    0.7568    0.8211       658
+         1.0     0.7832    0.9102    0.8420       635
+
+    accuracy                         0.8322      1293
+   macro avg     0.8402    0.8335    0.8315      1293
+weighted avg     0.8413    0.8322    0.8313      1293
+
+eval_loss = 0.40320912780769075
+fn = 57
+fp = 160
+macro_f1 = 0.8315283145866369
+mcc = 0.6737517155988195
+tn = 498
+tp = 578
+weighted_f1 = 0.8313428983790963
+weighted_p = 0.8402475646378086
+weighted_r = 0.8335375631237585

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "begin_tag": "<e>", "best_model_dir": "best_model", "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": "all_xlm-roberta-large_CLS-ET_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 729, "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": "CLS-ET", "special_tags": ["<s>", "</e>"], "merge_n": 3, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc642b936050dd6ee691ea4610ceee7db8aa8b6b8fe751be82709128e767fb4
+size 4546546317

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e67e7cafb5e6d9bffcbeb5bdf1048d27ebbc904922a850f80953068918244d
+size 2277523261

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15b54c7e9ec18a99b445915e63b86e5862929c5dcfafe22338672a963e77821
+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 @@
+{"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_ar.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8511    0.7200    0.7801       500
+           T     0.7574    0.8740    0.8115       500
+
+    accuracy                         0.7970      1000
+   macro avg     0.8042    0.7970    0.7958      1000
+weighted avg     0.8042    0.7970    0.7958      1000
+
+
+ADJ
+Accuracy = 0.7346938775510204
+Weighted Recall = 0.7346938775510204
+Weighted Precision = 0.7688370873382583
+Weighted F1 = 0.7311342146921662
+Macro Recall = 0.7463312368972745
+Macro Precision = 0.7603012848914488
+Macro F1 = 0.7329140461215934
+ADV
+Accuracy = 0.8
+Weighted Recall = 0.8
+Weighted Precision = 0.64
+Weighted F1 = 0.7111111111111111
+Macro Recall = 0.5
+Macro Precision = 0.4
+Macro F1 = 0.4444444444444445
+NOUN
+Accuracy = 0.8076923076923077
+Weighted Recall = 0.8076923076923077
+Weighted Precision = 0.8111648454026467
+Weighted F1 = 0.8069870256602342
+Macro Recall = 0.8069999999999999
+Macro Precision = 0.8115506829260177
+Macro F1 = 0.8068302963197735
+VERB
+Accuracy = 0.7989949748743719
+Weighted Recall = 0.7989949748743719
+Weighted Precision = 0.8072385648560104
+Weighted F1 = 0.7978523501915108
+Macro Recall = 0.799782811829179
+Macro Precision = 0.8067233404821581
+Macro F1 = 0.7979951782768684

test_eval_en.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.9156    0.8680    0.8912       500
+           T     0.8745    0.9200    0.8967       500
+
+    accuracy                         0.8940      1000
+   macro avg     0.8951    0.8940    0.8939      1000
+weighted avg     0.8951    0.8940    0.8939      1000
+
+
+ADJ
+Accuracy = 0.875
+Weighted Recall = 0.875
+Weighted Precision = 0.8815156375300722
+Weighted F1 = 0.8738977072310407
+Macro Recall = 0.8707430340557275
+Macro Precision = 0.884121892542101
+Macro F1 = 0.873015873015873
+ADV
+Accuracy = 0.7333333333333333
+Weighted Recall = 0.7333333333333333
+Weighted Precision = 0.7642857142857142
+Weighted F1 = 0.7357142857142857
+Macro Recall = 0.75
+Macro Precision = 0.7410714285714286
+Macro F1 = 0.7321428571428572
+NOUN
+Accuracy = 0.9071969696969697
+Weighted Recall = 0.9071969696969697
+Weighted Precision = 0.9079195926446487
+Weighted F1 = 0.9071640044974563
+Macro Recall = 0.907274553411292
+Macro Precision = 0.9078538996494052
+Macro F1 = 0.9071699981700951
+VERB
+Accuracy = 0.8959731543624161
+Weighted Recall = 0.8959731543624161
+Weighted Precision = 0.895990990990991
+Weighted F1 = 0.8959719829285047
+Macro Recall = 0.8959731543624161
+Macro Precision = 0.895990990990991
+Macro F1 = 0.8959719829285047

test_eval_fr.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8533    0.7560    0.8017       500
+           T     0.7810    0.8700    0.8231       500
+
+    accuracy                         0.8130      1000
+   macro avg     0.8171    0.8130    0.8124      1000
+weighted avg     0.8171    0.8130    0.8124      1000
+
+
+ADJ
+Accuracy = 0.7554347826086957
+Weighted Recall = 0.7554347826086957
+Weighted Precision = 0.7572586357197342
+Weighted F1 = 0.7524385891869387
+Macro Recall = 0.7460932840271979
+Macro Precision = 0.7585213032581454
+Macro F1 = 0.7482900136798907
+ADV
+Accuracy = 0.8333333333333334
+Weighted Recall = 0.8333333333333334
+Weighted Precision = 0.8653846153846154
+Weighted F1 = 0.8101472995090016
+Macro Recall = 0.7222222222222222
+Macro Precision = 0.9038461538461539
+Macro F1 = 0.7545008183306054
+NOUN
+Accuracy = 0.7937743190661478
+Weighted Recall = 0.7937743190661478
+Weighted Precision = 0.7998856018417498
+Weighted F1 = 0.7923988516887349
+Macro Recall = 0.7925734102645647
+Macro Precision = 0.8005288947654974
+Macro F1 = 0.7921092796092797
+VERB
+Accuracy = 0.8860294117647058
+Weighted Recall = 0.8860294117647058
+Weighted Precision = 0.8861698184666779
+Weighted F1 = 0.8860874839504073
+Macro Recall = 0.8842845326716294
+Macro Precision = 0.8835020911292097
+Macro F1 = 0.8838807408937548

test_eval_ru.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.7675    0.6800    0.7211       500
+           T     0.7127    0.7940    0.7512       500
+
+    accuracy                         0.7370      1000
+   macro avg     0.7401    0.7370    0.7361      1000
+weighted avg     0.7401    0.7370    0.7361      1000
+
+
+ADJ
+Accuracy = 0.8
+Weighted Recall = 0.8
+Weighted Precision = 0.8
+Weighted F1 = 0.8
+Macro Recall = 0.784688995215311
+Macro Precision = 0.784688995215311
+Macro F1 = 0.784688995215311
+ADV
+Accuracy = 0.4375
+Weighted Recall = 0.4375
+Weighted Precision = 0.45436507936507936
+Weighted F1 = 0.44433198380566796
+Macro Recall = 0.41666666666666663
+Macro Precision = 0.42063492063492064
+Macro F1 = 0.4170040485829959
+NOUN
+Accuracy = 0.7371134020618557
+Weighted Recall = 0.7371134020618557
+Weighted Precision = 0.7430375062432769
+Weighted F1 = 0.7363803869023894
+Macro Recall = 0.7390425531914894
+Macro Precision = 0.741737093130282
+Macro F1 = 0.7367021984358136
+VERB
+Accuracy = 0.7446236559139785
+Weighted Recall = 0.7446236559139785
+Weighted Precision = 0.746310170214211
+Weighted F1 = 0.7438993285371143
+Macro Recall = 0.7438199323445225
+Macro Precision = 0.7466077903848403
+Macro F1 = 0.7436436835805738

test_eval_zh.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.6613    0.5780    0.6169       500
+           T     0.6252    0.7040    0.6623       500
+
+    accuracy                         0.6410      1000
+   macro avg     0.6433    0.6410    0.6396      1000
+weighted avg     0.6433    0.6410    0.6396      1000
+
+
+ADJ
+Accuracy = 0.6612903225806451
+Weighted Recall = 0.6612903225806451
+Weighted Precision = 0.677891259648768
+Weighted F1 = 0.6653407970647991
+Macro Recall = 0.6622807017543859
+Macro Precision = 0.654649947753396
+Macro F1 = 0.6539994685091681
+ADV
+Accuracy = 0.55
+Weighted Recall = 0.55
+Weighted Precision = 0.7656565656565656
+Weighted F1 = 0.592
+Macro Recall = 0.625
+Macro Precision = 0.5808080808080808
+Macro F1 = 0.52
+NOUN
+Accuracy = 0.6389891696750902
+Weighted Recall = 0.6389891696750902
+Weighted Precision = 0.6472738929092112
+Weighted F1 = 0.6359683170323295
+Macro Recall = 0.6414058424621805
+Macro Precision = 0.6462740125188862
+Macro F1 = 0.6366974883598924
+VERB
+Accuracy = 0.6456043956043956
+Weighted Recall = 0.6456043956043956
+Weighted Precision = 0.6479747262403385
+Weighted F1 = 0.645376997710716
+Macro Recall = 0.6467601547388782
+Macro Precision = 0.6471381389570645
+Macro F1 = 0.6455375138709605

tokenizer_config.json

@@ -0,0 +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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9976bf62de2055a8257dfd1fdd8cb6c4658ac9321405ddfc1dd8950c9e143bf
+size 2875