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 = 0.8253615127919911
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.9058    0.7409    0.8151       467
+         1.0     0.7660    0.9167    0.8346       432
+
+    accuracy                         0.8254       899
+   macro avg     0.8359    0.8288    0.8248       899
+weighted avg     0.8386    0.8254    0.8244       899
+
+eval_loss = 0.43703388969103496
+fn = 36
+fp = 121
+macro_f1 = 0.8248196291179979
+mcc = 0.6646036563914847
+tn = 346
+tp = 396
+weighted_f1 = 0.8244403105462026
+weighted_p = 0.8358583045560878
+weighted_r = 0.8287830121341899

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": 64, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 100, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 100, "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": 3, "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": 100, "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": "en-en_xlm-roberta-large_E_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 304, "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": "E", "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:c7f4472c7b0526970d017d7353e40c002c1652f0653f7270b44d7534a5592f16
+size 4504578173

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9cdb49caab2d9c59a9d89ee89bef85ee118bd0bc716951f63f04192a4e7d11
+size 2256539453

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ef68f01b43f2b1912f460ca1fb9d60980828d5ab7f9aa0a78053fd4872f9dd
+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.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.9430    0.8600    0.8996       500
+           T     0.8713    0.9480    0.9080       500
+
+    accuracy                         0.9040      1000
+   macro avg     0.9072    0.9040    0.9038      1000
+weighted avg     0.9072    0.9040    0.9038      1000
+
+
+ADJ
+Accuracy = 0.875
+Weighted Recall = 0.875
+Weighted Precision = 0.8847402597402598
+Weighted F1 = 0.8735247836349331
+Macro Recall = 0.8699690402476781
+Macro Precision = 0.887987012987013
+Macro F1 = 0.8725413060582219
+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 = 0.9128787878787878
+Weighted Recall = 0.9128787878787878
+Weighted Precision = 0.9140602560766669
+Weighted F1 = 0.9128262600161825
+Macro Recall = 0.912977975464524
+Macro Precision = 0.9139758654911041
+Macro F1 = 0.9128337639965547
+VERB
+Accuracy = 0.9194630872483222
+Weighted Recall = 0.9194630872483222
+Weighted Precision = 0.9222015686630095
+Weighted F1 = 0.9193322806226032
+Macro Recall = 0.919463087248322
+Macro Precision = 0.9222015686630095
+Macro F1 = 0.9193322806226032

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": {}, "model_max_length": 512, "do_lower_case": false, "special_tokens_map_file": null, "tokenizer_file": "/data2/hh2/hf_cache/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 sha256:0fde191ee38a4dbc6399f48aa2c570bef0cb33a03e4214da74e181680bce3a95
+size 2811