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 = 0.7996906419180201
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.7790    0.8465    0.8114       658
+         1.0     0.8253    0.7512    0.7865       635
+
+    accuracy                         0.7997      1293
+   macro avg     0.8021    0.7988    0.7989      1293
+weighted avg     0.8017    0.7997    0.7991      1293
+
+eval_loss = 0.4485675318189609
+fn = 158
+fp = 101
+macro_f1 = 0.7989208916034054
+mcc = 0.6009740320695361
+tn = 557
+tp = 477
+weighted_f1 = 0.7991421948188572
+weighted_p = 0.8021402472959567
+weighted_r = 0.7988428308163606

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_P_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": "P", "special_tags": ["<e>", "</e>"], "merge_n": 2, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb11ec5673760792b1f7a6b600aadce1575f5654578ff3a328d76a1e9c0d1a68
+size 4504578173

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e37dca701c36ca7038957b022bc446ac558ba51e115ec10987d618d49e39fe
+size 2256539517

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d390f69ee9173b5a24de5849a4c781ca11142415bd7ea7442bbe07008fc485
+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     0.8291    0.7760    0.8017       500
+           T     0.7895    0.8400    0.8140       500
+
+    accuracy                         0.8080      1000
+   macro avg     0.8093    0.8080    0.8078      1000
+weighted avg     0.8093    0.8080    0.8078      1000
+
+
+ADJ
+Accuracy = 0.7857142857142857
+Weighted Recall = 0.7857142857142857
+Weighted Precision = 0.7987012987012988
+Weighted F1 = 0.7855134556165483
+Macro Recall = 0.7918238993710691
+Macro Precision = 0.7929292929292929
+Macro F1 = 0.7856919712589814
+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 = 0.8020173708432817
+Weighted F1 = 0.8014892301846458
+Macro Recall = 0.8013442622950819
+Macro Precision = 0.8021367521367522
+Macro F1 = 0.8014111083764048
+VERB
+Accuracy = 0.8190954773869347
+Weighted Recall = 0.8190954773869347
+Weighted Precision = 0.820368646605092
+Weighted F1 = 0.8189857967366196
+Macro Recall = 0.8193802560800061
+Macro Precision = 0.8201564517353991
+Macro F1 = 0.8190223569533914

test_eval_en.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8798    0.9080    0.8937       500
+           T     0.9050    0.8760    0.8902       500
+
+    accuracy                         0.8920      1000
+   macro avg     0.8924    0.8920    0.8920      1000
+weighted avg     0.8924    0.8920    0.8920      1000
+
+
+ADJ
+Accuracy = 0.8819444444444444
+Weighted Recall = 0.8819444444444444
+Weighted Precision = 0.882109500805153
+Weighted F1 = 0.8819843917006387
+Macro Recall = 0.8819659442724458
+Macro Precision = 0.8814492753623189
+Macro F1 = 0.8816648136510852
+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 = 0.8882575757575758
+Weighted Recall = 0.8882575757575758
+Weighted Precision = 0.8889153569860092
+Weighted F1 = 0.8882002236169277
+Macro Recall = 0.8881770571777028
+Macro Precision = 0.8889751552795031
+Macro F1 = 0.8881897959549916
+VERB
+Accuracy = 0.9194630872483222
+Weighted Recall = 0.9194630872483222
+Weighted Precision = 0.9213610243880368
+Weighted F1 = 0.9193722943722944
+Macro Recall = 0.9194630872483222
+Macro Precision = 0.9213610243880368
+Macro F1 = 0.9193722943722944

test_eval_fr.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.8016    0.8160    0.8087       500
+           T     0.8126    0.7980    0.8052       500
+
+    accuracy                         0.8070      1000
+   macro avg     0.8071    0.8070    0.8070      1000
+weighted avg     0.8071    0.8070    0.8070      1000
+
+
+ADJ
+Accuracy = 0.7934782608695652
+Weighted Recall = 0.7934782608695652
+Weighted Precision = 0.7974546491376786
+Weighted F1 = 0.7939677068682155
+Macro Recall = 0.7957771680782536
+Macro Precision = 0.7929812123360511
+Macro F1 = 0.7928664533712526
+ADV
+Accuracy = 0.9333333333333333
+Weighted Recall = 0.9333333333333333
+Weighted Precision = 0.9391304347826086
+Weighted F1 = 0.930681818181818
+Macro Recall = 0.8888888888888888
+Macro Precision = 0.9565217391304348
+Macro F1 = 0.9147727272727273
+NOUN
+Accuracy = 0.7859922178988327
+Weighted Recall = 0.7859922178988327
+Weighted Precision = 0.7868988198231214
+Weighted F1 = 0.7856804851459047
+Macro Recall = 0.7854557569699998
+Macro Precision = 0.7871254703041934
+Macro F1 = 0.7855246187694408
+VERB
+Accuracy = 0.8419117647058824
+Weighted Recall = 0.8419117647058824
+Weighted Precision = 0.8458034075699246
+Weighted F1 = 0.8394913284462723
+Macro Recall = 0.8288116901020127
+Macro Precision = 0.8496950504339666
+Macro F1 = 0.8346504559270518

test_eval_ru.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.7042    0.8000    0.7491       500
+           T     0.7685    0.6640    0.7124       500
+
+    accuracy                         0.7320      1000
+   macro avg     0.7364    0.7320    0.7308      1000
+weighted avg     0.7364    0.7320    0.7308      1000
+
+
+ADJ
+Accuracy = 0.6666666666666666
+Weighted Recall = 0.6666666666666666
+Weighted Precision = 0.7687400318979267
+Weighted F1 = 0.6666666666666666
+Macro Recall = 0.7177033492822966
+Macro Precision = 0.7177033492822966
+Macro F1 = 0.6666666666666666
+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 = 0.7439862542955327
+Weighted Recall = 0.7439862542955327
+Weighted Precision = 0.7459487120816265
+Weighted F1 = 0.7428299703669132
+Macro Recall = 0.7420921985815603
+Macro Precision = 0.7465184578904924
+Macro F1 = 0.7421585796986825
+VERB
+Accuracy = 0.7311827956989247
+Weighted Recall = 0.7311827956989247
+Weighted Precision = 0.7356482071769588
+Weighted F1 = 0.7303416466893777
+Macro Recall = 0.7321536993668141
+Macro Precision = 0.7350900307422046
+Macro F1 = 0.7305519339417644

test_eval_zh.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.6050    0.6740    0.6377       500
+           T     0.6321    0.5600    0.5938       500
+
+    accuracy                         0.6170      1000
+   macro avg     0.6185    0.6170    0.6158      1000
+weighted avg     0.6185    0.6170    0.6158      1000
+
+
+ADJ
+Accuracy = 0.532258064516129
+Weighted Recall = 0.532258064516129
+Weighted Precision = 0.5745007680491552
+Weighted F1 = 0.5362829625268115
+Macro Recall = 0.5493421052631579
+Macro Precision = 0.5476190476190476
+Macro F1 = 0.53116036505867
+ADV
+Accuracy = 0.6
+Weighted Recall = 0.6
+Weighted Precision = 0.8666666666666666
+Weighted F1 = 0.6333333333333333
+Macro Recall = 0.75
+Macro Precision = 0.6666666666666666
+Macro F1 = 0.5833333333333333
+NOUN
+Accuracy = 0.6299638989169675
+Weighted Recall = 0.6299638989169675
+Weighted Precision = 0.6298372139778151
+Weighted F1 = 0.6298492264125135
+Macro Recall = 0.6294992175273866
+Macro Precision = 0.6296598550630019
+Macro F1 = 0.6295281434000424
+VERB
+Accuracy = 0.6126373626373627
+Weighted Recall = 0.6126373626373627
+Weighted Precision = 0.6140917905623788
+Weighted F1 = 0.6082284632153951
+Macro Recall = 0.6092238878143134
+Macro Precision = 0.6143562320032908
+Macro F1 = 0.6066252270619524

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 sha256:24465011e92b2755b9b6aa176ffcc145b165321ff7ea74629d8389f33a39642a
+size 2811