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 = 0.8307573415765069
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.8679    0.7876    0.8258       659
+         1.0     0.7989    0.8756    0.8355       635
+
+    accuracy                         0.8308      1294
+   macro avg     0.8334    0.8316    0.8306      1294
+weighted avg     0.8340    0.8308    0.8305      1294
+
+eval_loss = 0.3976426025691592
+fn = 79
+fp = 140
+macro_f1 = 0.8306188574635684
+mcc = 0.6649430724287243
+tn = 519
+tp = 556
+weighted_f1 = 0.8305290299308514
+weighted_p = 0.8333717756506362
+weighted_r = 0.8315737277908547

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-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": "CLS-BT", "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:c9b96bf3dae48b0f0ca1e954feb4041de73ea98190726045ae4e8b1ad87d50be
+size 4546546317

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e849dc2cfd2e5372a9b8247939ec0b8cd5def5bc3bd350162e53b9919b0c59
+size 2277523261

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26707f9d2ee18f8efcee9786e913e0ba9ed2de668b042ff857e776c37c6a2a48
+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     0.8401    0.7460    0.7903       500
+           T     0.7716    0.8580    0.8125       500
+
+    accuracy                         0.8020      1000
+   macro avg     0.8058    0.8020    0.8014      1000
+weighted avg     0.8058    0.8020    0.8014      1000
+
+
+ADJ
+Accuracy = 0.7653061224489796
+Weighted Recall = 0.7653061224489796
+Weighted Precision = 0.7898926812104152
+Weighted F1 = 0.7637135656016242
+Macro Recall = 0.7746331236897275
+Macro Precision = 0.7823275862068966
+Macro F1 = 0.7646936005846121
+ADV
+Accuracy = 0.9
+Weighted Recall = 0.9
+Weighted Precision = 0.9111111111111111
+Weighted F1 = 0.8862745098039216
+Macro Recall = 0.75
+Macro Precision = 0.9444444444444444
+Macro F1 = 0.803921568627451
+NOUN
+Accuracy = 0.8016194331983806
+Weighted Recall = 0.8016194331983806
+Weighted Precision = 0.8058517969978864
+Weighted F1 = 0.8007367974063984
+Macro Recall = 0.8008524590163935
+Macro Precision = 0.8062750333778371
+Macro F1 = 0.8005602702480019
+VERB
+Accuracy = 0.8090452261306532
+Weighted Recall = 0.8090452261306532
+Weighted Precision = 0.8102878637128836
+Weighted F1 = 0.8089294521108764
+Macro Recall = 0.809328989569917
+Macro Precision = 0.8100807574491785
+Macro F1 = 0.808968043450802

test_eval_en.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8941    0.8780    0.8860       500
+           T     0.8802    0.8960    0.8880       500
+
+    accuracy                         0.8870      1000
+   macro avg     0.8871    0.8870    0.8870      1000
+weighted avg     0.8871    0.8870    0.8870      1000
+
+
+ADJ
+Accuracy = 0.875
+Weighted Recall = 0.875
+Weighted Precision = 0.87578125
+Weighted F1 = 0.8747086247086249
+Macro Recall = 0.8730650154798762
+Macro Precision = 0.8765625
+Macro F1 = 0.8741258741258742
+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 = 0.8958333333333334
+Weighted Recall = 0.8958333333333334
+Weighted Precision = 0.8958405073461891
+Weighted F1 = 0.8958337069811766
+Macro Recall = 0.8958390128416673
+Macro Precision = 0.8958333333333333
+Macro F1 = 0.8958329596854901
+VERB
+Accuracy = 0.8926174496644296
+Weighted Recall = 0.8926174496644296
+Weighted Precision = 0.8926174496644296
+Weighted F1 = 0.8926174496644297
+Macro Recall = 0.8926174496644296
+Macro Precision = 0.8926174496644296
+Macro F1 = 0.8926174496644297

test_eval_fr.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8202    0.7940    0.8069       500
+           T     0.8004    0.8260    0.8130       500
+
+    accuracy                         0.8100      1000
+   macro avg     0.8103    0.8100    0.8100      1000
+weighted avg     0.8103    0.8100    0.8100      1000
+
+
+ADJ
+Accuracy = 0.7989130434782609
+Weighted Recall = 0.7989130434782609
+Weighted Precision = 0.7998764470398878
+Weighted F1 = 0.799182108122294
+Macro Recall = 0.7985804604556841
+Macro Precision = 0.7969862363550071
+Macro F1 = 0.7975677202580953
+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 = 0.7840466926070039
+Weighted Recall = 0.7840466926070039
+Weighted Precision = 0.7850740775183058
+Weighted F1 = 0.783698474648116
+Macro Recall = 0.7834794723850196
+Macro Precision = 0.7853158151444946
+Macro F1 = 0.7835346073733453
+VERB
+Accuracy = 0.8639705882352942
+Weighted Recall = 0.8639705882352942
+Weighted Precision = 0.8637219794646706
+Weighted F1 = 0.8637391785061397
+Macro Recall = 0.8596912048524952
+Macro Precision = 0.8621474572507217
+Macro F1 = 0.8608079886035158

test_eval_ru.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.7375    0.7640    0.7505       500
+           T     0.7552    0.7280    0.7413       500
+
+    accuracy                         0.7460      1000
+   macro avg     0.7463    0.7460    0.7459      1000
+weighted avg     0.7463    0.7460    0.7459      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 = 0.4375
+Weighted Recall = 0.4375
+Weighted Precision = 0.5113636363636364
+Weighted F1 = 0.42647058823529416
+Macro Recall = 0.4833333333333333
+Macro Precision = 0.4818181818181818
+Macro F1 = 0.43529411764705883
+NOUN
+Accuracy = 0.7491408934707904
+Weighted Recall = 0.7491408934707904
+Weighted Precision = 0.749099279228316
+Weighted F1 = 0.7491112344331189
+Macro Recall = 0.7487943262411347
+Macro Precision = 0.7489120151371806
+Macro F1 = 0.7488443030940755
+VERB
+Accuracy = 0.7553763440860215
+Weighted Recall = 0.7553763440860215
+Weighted Precision = 0.7561659946236561
+Weighted F1 = 0.7553286126409651
+Macro Recall = 0.7557030098013704
+Macro Precision = 0.7559027777777778
+Macro F1 = 0.755360433604336

test_eval_zh.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.6026    0.6520    0.6263       500
+           T     0.6209    0.5700    0.5944       500
+
+    accuracy                         0.6110      1000
+   macro avg     0.6118    0.6110    0.6103      1000
+weighted avg     0.6118    0.6110    0.6103      1000
+
+
+ADJ
+Accuracy = 0.5645161290322581
+Weighted Recall = 0.5645161290322581
+Weighted Precision = 0.6082607953575695
+Weighted F1 = 0.5682634478697901
+Macro Recall = 0.5833333333333333
+Macro Precision = 0.5804232804232804
+Macro F1 = 0.5634941329856584
+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 = 0.6191335740072202
+Weighted Recall = 0.6191335740072202
+Weighted Precision = 0.6197037756321901
+Weighted F1 = 0.6191745264522859
+Macro Recall = 0.6193922796035471
+Macro Precision = 0.6193409200526638
+Macro F1 = 0.619122405158566
+VERB
+Accuracy = 0.6153846153846154
+Weighted Recall = 0.6153846153846154
+Weighted Precision = 0.6167832167832168
+Weighted F1 = 0.611236802413273
+Macro Recall = 0.6120647969052224
+Macro Precision = 0.6170454545454546
+Macro F1 = 0.6096813725490197

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 sha256:8a1cb2df9afe0255ecde81e196b3ee018d6143fc8ea2eba57c675857fca7c79f
+size 2875