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 = 0.8097886540600667
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.8083    0.8308    0.8194       467
+         1.0     0.8115    0.7870    0.7991       432
+
+    accuracy                         0.8098       899
+   macro avg     0.8099    0.8089    0.8092       899
+weighted avg     0.8098    0.8098    0.8096       899
+
+eval_loss = 0.44339214960734047
+fn = 92
+fp = 79
+macro_f1 = 0.8092448538709041
+mcc = 0.6188299253739279
+tn = 388
+tp = 340
+weighted_f1 = 0.8096413748421686
+weighted_p = 0.8098945902943516
+weighted_r = 0.8089360774050283

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_CLS-BT_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": "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:d6a8fb1e8027b7e46dd48307334d637dd836cba797ab655936e1ead893110069
+size 4546546317

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1c0524420489b10fe29835238def4f7fa27cd0899f7eedb7987e7b8061c76e
+size 2277523261

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11acce0fb52b8757c3d574c10c706a2d7dc09b528af0598c82a31906fa3cd495
+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     0.8774    0.9300    0.9029       500
+           T     0.9255    0.8700    0.8969       500
+
+    accuracy                         0.9000      1000
+   macro avg     0.9014    0.9000    0.8999      1000
+weighted avg     0.9014    0.9000    0.8999      1000
+
+
+ADJ
+Accuracy = 0.8958333333333334
+Weighted Recall = 0.8958333333333334
+Weighted Precision = 0.8967618496366325
+Weighted F1 = 0.8959087763346368
+Macro Recall = 0.896671826625387
+Macro Precision = 0.8955238278989002
+Macro F1 = 0.8957075949978273
+ADV
+Accuracy = 0.7333333333333333
+Weighted Recall = 0.7333333333333333
+Weighted Precision = 0.7446428571428572
+Weighted F1 = 0.7357466063348416
+Macro Recall = 0.7361111111111112
+Macro Precision = 0.7276785714285714
+Macro F1 = 0.7285067873303168
+NOUN
+Accuracy = 0.9090909090909091
+Weighted Recall = 0.9090909090909091
+Weighted Precision = 0.9102267656484524
+Weighted F1 = 0.9090177974598931
+Macro Recall = 0.9089891670851568
+Macro Precision = 0.9103078982597055
+Macro F1 = 0.9090073529411765
+VERB
+Accuracy = 0.9026845637583892
+Weighted Recall = 0.9026845637583892
+Weighted Precision = 0.9068074262832179
+Weighted F1 = 0.9024373722891429
+Macro Recall = 0.9026845637583892
+Macro Precision = 0.906807426283218
+Macro F1 = 0.902437372289143

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 sha256:4029803ef4aa52ffc1a368a9ef9788613a80cee18d0a7f0a695cbb946b420632
+size 2875