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 = 0.8153013910355487
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.8454    0.7800    0.8114       659
+         1.0     0.7886    0.8520    0.8191       635
+
+    accuracy                         0.8153      1294
+   macro avg     0.8170    0.8160    0.8152      1294
+weighted avg     0.8175    0.8153    0.8151      1294
+
+eval_loss = 0.44760561182543085
+fn = 94
+fp = 145
+macro_f1 = 0.815220943689666
+mcc = 0.6329804551177601
+tn = 514
+tp = 541
+weighted_f1 = 0.8151494349377705
+weighted_p = 0.8170122372257174
+weighted_r = 0.8159690774616755

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_BT_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 730, "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": "BT", "special_tags": ["<e>"], "merge_n": 2, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253d0b0a262f7f2792718e2371ddf56874a39f4959bf8fde04ecd9ce53e6a713
+size 4504578173

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c1b6487921ae5aa38009f546fbfe7673522e322a3df56cdb5419cf172791f6
+size 2256539453

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ea4ca977f31a40cf77bd371a13f753ce0aaba08ec608fa34384e28eb80cf1a
+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     0.8750    0.6720    0.7602       500
+           T     0.7338    0.9040    0.8100       500
+
+    accuracy                         0.7880      1000
+   macro avg     0.8044    0.7880    0.7851      1000
+weighted avg     0.8044    0.7880    0.7851      1000
+
+
+ADJ
+Accuracy = 0.7755102040816326
+Weighted Recall = 0.7755102040816326
+Weighted Precision = 0.8044417245385769
+Weighted F1 = 0.7735393488499079
+Macro Recall = 0.7857442348008385
+Macro Precision = 0.7961755758365928
+Macro F1 = 0.774665551839465
+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 = 0.791497975708502
+Weighted Recall = 0.791497975708502
+Weighted Precision = 0.8020009793987886
+Weighted F1 = 0.7893449060168418
+Macro Recall = 0.7903114754098362
+Macro Precision = 0.802671383889658
+Macro F1 = 0.7890700460562043
+VERB
+Accuracy = 0.7864321608040201
+Weighted Recall = 0.7864321608040201
+Weighted Precision = 0.8087896237946488
+Weighted F1 = 0.7828768722621846
+Macro Recall = 0.7877490718993863
+Macro Precision = 0.8079459459459459
+Macro F1 = 0.7831451959257194

test_eval_en.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.9076    0.8840    0.8956       500
+           T     0.8869    0.9100    0.8983       500
+
+    accuracy                         0.8970      1000
+   macro avg     0.8973    0.8970    0.8970      1000
+weighted avg     0.8973    0.8970    0.8970      1000
+
+
+ADJ
+Accuracy = 0.875
+Weighted Recall = 0.875
+Weighted Precision = 0.878968253968254
+Weighted F1 = 0.87421875
+Macro Recall = 0.8715170278637772
+Macro Precision = 0.8809523809523809
+Macro F1 = 0.8734375000000001
+ADV
+Accuracy = 0.7333333333333333
+Weighted Recall = 0.7333333333333333
+Weighted Precision = 0.7944444444444445
+Weighted F1 = 0.7333333333333333
+Macro Recall = 0.7638888888888888
+Macro Precision = 0.7638888888888888
+Macro F1 = 0.7333333333333334
+NOUN
+Accuracy = 0.9071969696969697
+Weighted Recall = 0.9071969696969697
+Weighted Precision = 0.9072041437098255
+Weighted F1 = 0.90719730258323
+Macro Recall = 0.9072028122533897
+Macro Precision = 0.9071969696969697
+Macro F1 = 0.9071966368107094
+VERB
+Accuracy = 0.9060402684563759
+Weighted Recall = 0.9060402684563759
+Weighted Precision = 0.9061134387529846
+Weighted F1 = 0.9060360360360362
+Macro Recall = 0.9060402684563759
+Macro Precision = 0.9061134387529847
+Macro F1 = 0.9060360360360361

test_eval_fr.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8362    0.7660    0.7996       500
+           T     0.7841    0.8500    0.8157       500
+
+    accuracy                         0.8080      1000
+   macro avg     0.8102    0.8080    0.8077      1000
+weighted avg     0.8102    0.8080    0.8077      1000
+
+
+ADJ
+Accuracy = 0.7771739130434783
+Weighted Recall = 0.7771739130434783
+Weighted Precision = 0.776750627090301
+Weighted F1 = 0.7767538010136036
+Macro Recall = 0.7734104735774783
+Macro Precision = 0.7754807692307693
+Macro F1 = 0.7742331288343558
+ADV
+Accuracy = 0.8666666666666667
+Weighted Recall = 0.8666666666666667
+Weighted Precision = 0.8658385093167702
+Weighted F1 = 0.8613636363636362
+Macro Recall = 0.8095238095238095
+Macro Precision = 0.8633540372670807
+Macro F1 = 0.8295454545454545
+NOUN
+Accuracy = 0.7859922178988327
+Weighted Recall = 0.7859922178988327
+Weighted Precision = 0.7912650505847443
+Weighted F1 = 0.7846996520220378
+Macro Recall = 0.7848499992428029
+Macro Precision = 0.791850920883179
+Macro F1 = 0.7844124151605278
+VERB
+Accuracy = 0.8639705882352942
+Weighted Recall = 0.8639705882352942
+Weighted Precision = 0.8641328449715788
+Weighted F1 = 0.8640399001988731
+Macro Recall = 0.861786600496278
+Macro Precision = 0.8610499669821703
+Macro F1 = 0.8614060455828685

test_eval_ru.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.7639    0.7120    0.7371       500
+           T     0.7303    0.7800    0.7544       500
+
+    accuracy                         0.7460      1000
+   macro avg     0.7471    0.7460    0.7457      1000
+weighted avg     0.7471    0.7460    0.7457      1000
+
+
+ADJ
+Accuracy = 0.7333333333333333
+Weighted Recall = 0.7333333333333333
+Weighted Precision = 0.7472096530920059
+Weighted F1 = 0.7370370370370372
+Macro Recall = 0.7320574162679425
+Macro Precision = 0.7194570135746606
+Macro F1 = 0.7222222222222223
+ADV
+Accuracy = 0.5
+Weighted Recall = 0.5
+Weighted Precision = 0.5666666666666667
+Weighted F1 = 0.5
+Macro Recall = 0.5333333333333333
+Macro Precision = 0.5333333333333333
+Macro F1 = 0.5
+NOUN
+Accuracy = 0.7422680412371134
+Weighted Recall = 0.7422680412371134
+Weighted Precision = 0.7442593402217998
+Weighted F1 = 0.7422010796880176
+Macro Recall = 0.7431914893617022
+Macro Precision = 0.7434447179098826
+Macro F1 = 0.7422558664100051
+VERB
+Accuracy = 0.7634408602150538
+Weighted Recall = 0.7634408602150538
+Weighted Precision = 0.7655658974032046
+Weighted F1 = 0.7626992955135335
+Macro Recall = 0.7625986642380085
+Macro Precision = 0.7659200702678963
+Macro F1 = 0.7624521072796935

test_eval_zh.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.6066    0.6600    0.6322       500
+           T     0.6272    0.5720    0.5983       500
+
+    accuracy                         0.6160      1000
+   macro avg     0.6169    0.6160    0.6153      1000
+weighted avg     0.6169    0.6160    0.6153      1000
+
+
+ADJ
+Accuracy = 0.5967741935483871
+Weighted Recall = 0.5967741935483871
+Weighted Precision = 0.6420208226659839
+Weighted F1 = 0.6002439332127687
+Macro Recall = 0.6173245614035088
+Macro Precision = 0.6132275132275132
+Macro F1 = 0.5958279009126466
+ADV
+Accuracy = 0.45
+Weighted Recall = 0.45
+Weighted Precision = 0.7318681318681318
+Weighted F1 = 0.4879795396419436
+Macro Recall = 0.5625
+Macro Precision = 0.5439560439560439
+Macro F1 = 0.43734015345268534
+NOUN
+Accuracy = 0.6371841155234657
+Weighted Recall = 0.6371841155234657
+Weighted Precision = 0.6376268566649375
+Weighted F1 = 0.6372373158936345
+Macro Recall = 0.6373630672926448
+Macro Precision = 0.6372825024437927
+Macro F1 = 0.637154559762261
+VERB
+Accuracy = 0.5961538461538461
+Weighted Recall = 0.5961538461538461
+Weighted Precision = 0.5969369996519317
+Weighted F1 = 0.5915573339905185
+Macro Recall = 0.5927224371373307
+Macro Precision = 0.5970793911970382
+Macro F1 = 0.5898858750220356

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 sha256:4ef834aafe7b53c79fba3e94f547d50608db20bc867e2b3bf0385f4a1eb19839
+size 2811