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 = 0.8509454949944383
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.8758    0.8308    0.8527       467
+         1.0     0.8268    0.8727    0.8491       432
+
+    accuracy                         0.8509       899
+   macro avg     0.8513    0.8518    0.8509       899
+weighted avg     0.8523    0.8509    0.8510       899
+
+eval_loss = 0.3458882043759028
+fn = 55
+fp = 79
+macro_f1 = 0.850923175923176
+mcc = 0.7030604447320151
+tn = 388
+tp = 377
+weighted_f1 = 0.8509941911499198
+weighted_p = 0.8513004435467901
+weighted_r = 0.8517601514791022

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_ET_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": "ET", "special_tags": ["</e>"], "merge_n": 2, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815ffc60446110253c6e5215fbdbabdd56ca203cb2cac58030467dc799cb63b5
+size 4504578173

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da730cdf051a7c1c31883929ff60a37203ecd40c9b4eed1f43bd9678b433690
+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     0.9108    0.8980    0.9043       500
+           T     0.8994    0.9120    0.9057       500
+
+    accuracy                         0.9050      1000
+   macro avg     0.9051    0.9050    0.9050      1000
+weighted avg     0.9051    0.9050    0.9050      1000
+
+
+ADJ
+Accuracy = 0.8819444444444444
+Weighted Recall = 0.8819444444444444
+Weighted Precision = 0.8819269453597811
+Weighted F1 = 0.8818930041152263
+Macro Recall = 0.8811919504643964
+Macro Precision = 0.8818569490211281
+Macro F1 = 0.8814814814814814
+ADV
+Accuracy = 0.7666666666666667
+Weighted Recall = 0.7666666666666667
+Weighted Precision = 0.7866666666666667
+Weighted F1 = 0.7690235690235689
+Macro Recall = 0.7777777777777778
+Macro Precision = 0.7666666666666666
+Macro F1 = 0.7643097643097643
+NOUN
+Accuracy = 0.9128787878787878
+Weighted Recall = 0.9128787878787878
+Weighted Precision = 0.9129785847627769
+Weighted F1 = 0.9128762878081337
+Macro Recall = 0.9129062343066217
+Macro Precision = 0.9129536355417797
+Macro F1 = 0.9128775378434608
+VERB
+Accuracy = 0.9161073825503355
+Weighted Recall = 0.9161073825503355
+Weighted Precision = 0.9161261261261262
+Weighted F1 = 0.9161064378455684
+Macro Recall = 0.9161073825503356
+Macro Precision = 0.9161261261261262
+Macro F1 = 0.9161064378455683

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:c57028f603668ea4885883c670ef331bbcdca046f046bf0ec44b3a6f831a62da
+size 2875