Upload 12 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "models/xlm-roberta-tw",
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,10 @@
+accuracy = 0.9646017699115044
+auprc = 0.7904051049177349
+auroc = 0.9528789923526766
+eval_loss = 0.16820087955178073
+f1_score = 0.8333333333333333
+fn = 2
+fp = 18
+mcc = 0.8230951397366015
+tn = 495
+tp = 50

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903056cfbd0a1d7467ce4b2d9e9d3bbf54d992967e034102b816fd2b9da0c6a1
+size 1112205008

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "models/models/xlm-roberta-tw-mlma/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "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": 3, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "models/xlm-roberta-tw", "model_type": "xlmroberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 8, "optimizer": "AdamW", "output_dir": "models/models/xlm-roberta-tw-mlma", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 6, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "models/xlm-roberta-tw", "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 493, "weight_decay": 0.0, "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, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24df8de0a567bdbaa60fc3c93a34d3a7a7f91efc93a0e12cd33291d83a38f105
+size 2224529594

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fe75e5a3ae7ecc199e58524e7a187b554c47936fccfe4400acd88668d82902
+size 1064

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349ddbc97c4742ad2a4f2da1ecf985a03c45bff47d712556b3a73db66512977a
+size 17098516

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf303deee5e260343201734a31695fb20d551bc03ec1235e2fac618dd9eb9b9
+size 3704

training_progress_scores.csv

@@ -0,0 +1,13 @@
+global_step,train_loss,mcc,accuracy,f1_score,tp,tn,fp,fn,auroc,auprc,eval_loss
+1027,0.01094818115234375,0.8230951397366015,0.9646017699115044,0.8333333333333333,50,495,18,2,0.9528789923526766,0.7904051049177349,0.16820087955178073
+2000,0.003082275390625,0.8230951397366015,0.9646017699115044,0.8333333333333333,50,495,18,2,0.9683985605038236,0.7592408192816069,0.19815611099087013
+2054,0.003502368927001953,0.8301249010593955,0.9663716814159292,0.8403361344537815,50,496,17,2,0.9560466336782127,0.7367229044419245,0.18864733562804759
+3081,0.00023224949836730957,0.7543644451089591,0.9451327433628318,0.7633587786259542,50,484,29,2,0.9573961613435298,0.6761286796091319,0.31085181919236976
+4000,0.6298749446868896,0.8162112105054001,0.9628318584070796,0.8264462809917356,50,494,19,2,0.9791010646273804,0.8174420078748461,0.20243463476072066
+4108,0.0027300119400024414,0.7975120241484319,0.95929203539823,0.8099173553719008,49,493,20,3,0.9791947818263607,0.8272973451996808,0.24941252311206577
+5135,0.0034151673316955566,0.7268473816305496,0.952212389380531,0.7522935779816514,41,497,16,11,0.9695606537711802,0.7749483701441352,0.2434404417872429
+6000,0.0009245127439498901,0.6614516427927278,0.9469026548672567,0.6875,33,502,11,19,0.9562153246363773,0.7461486809236214,0.4087824399272601
+6162,0.0009687542915344238,0.7065182508636935,0.9486725663716814,0.7339449541284404,40,496,17,12,0.9622507122507122,0.7111230315983186,0.38319096341729164
+7189,1.71661376953125e-05,0.687844867013511,0.9469026548672567,0.7169811320754716,38,497,16,14,0.9644811815864448,0.6873732188660728,0.433009793361028
+8000,0.00014576315879821777,0.6611186084870295,0.9433628318584071,0.6923076923076923,36,497,16,16,0.9601139601139601,0.6579775685207898,0.4993491396307945
+8216,8.109211921691895e-05,0.6611186084870295,0.9433628318584071,0.6923076923076923,36,497,16,16,0.9593454790823213,0.6561292130983117,0.4998985876639684