tharindu commited on Mar 19

Commit

32af448

•

1 Parent(s): c47abf6

Upload folder using huggingface_hub

Browse files

Files changed (32) hide show

best_model/config.json +39 -0
best_model/eval_results.txt +4 -0
best_model/merges.txt +0 -0
best_model/model.safetensors +3 -0
best_model/model_args.json +1 -0
best_model/optimizer.pt +3 -0
best_model/scheduler.pt +3 -0
best_model/special_tokens_map.json +51 -0
best_model/tokenizer_config.json +57 -0
best_model/training_args.bin +3 -0
best_model/vocab.json +0 -0
checkpoint-8725-epoch-5/config.json +39 -0
checkpoint-8725-epoch-5/eval_results.txt +4 -0
checkpoint-8725-epoch-5/merges.txt +0 -0
checkpoint-8725-epoch-5/model.safetensors +3 -0
checkpoint-8725-epoch-5/model_args.json +1 -0
checkpoint-8725-epoch-5/optimizer.pt +3 -0
checkpoint-8725-epoch-5/scheduler.pt +3 -0
checkpoint-8725-epoch-5/special_tokens_map.json +51 -0
checkpoint-8725-epoch-5/tokenizer_config.json +57 -0
checkpoint-8725-epoch-5/training_args.bin +3 -0
checkpoint-8725-epoch-5/vocab.json +0 -0
config.json +39 -0
eval_results.txt +4 -0
merges.txt +0 -0
model.safetensors +3 -0
model_args.json +1 -0
special_tokens_map.json +51 -0
tokenizer_config.json +57 -0
training_args.bin +3 -0
training_progress_scores.csv +20 -0
vocab.json +0 -0

best_model/config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "_name_or_path": "NLPC-UOM/SinBERT-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

best_model/eval_results.txt ADDED Viewed

	@@ -0,0 +1,4 @@

+eval_loss = 0.21681966317683152
+macro_f1 = 0.9363705923825345
+mcc = 0.9163726036647536
+weighted_f1 = 0.9362311531774655

best_model/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

best_model/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:006a890ae5c1478448e9546d9319b78271061fa5b69307115ed689142ef36f9e
+size 506311456

best_model/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"adam_epsilon": 1e-08, "best_model_dir": "outputs/SinBERT-large/best_model", "cache_dir": "cache_dir/SinBERT-large", "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, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 600, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 600, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "NLPC-UOM/SinBERT-large", "model_type": "roberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/SinBERT-large", "overwrite_output_dir": true, "process_count": 78, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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_recent_only": true, "save_steps": 600, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": "NSINa_category_prediction", "warmup_ratio": 0.06, "warmup_steps": 524, "weight_decay": 0.0, "model_class": "LCPModel", "labels_list": [0, 1, 2, 3], "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}

best_model/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:83bc8d1668a74ffd784e59cf6d1ec0ddae8dc4852290f7c35b6a2aa75703f76a
+size 1007967802

best_model/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:db102accab4047f842462446421435028dd1c3f65cfb35a26f0ae579a93e5ad1
+size 1064

best_model/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

best_model/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

best_model/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9690c764ae76781eef6e9164a6bc27b6745385c84e2585caff73316a612cec7f
+size 3576

best_model/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-8725-epoch-5/config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "_name_or_path": "NLPC-UOM/SinBERT-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-8725-epoch-5/eval_results.txt ADDED Viewed

	@@ -0,0 +1,4 @@

+eval_loss = 0.35019068319525104
+macro_f1 = 0.9371727749427544
+mcc = 0.9165943698038781
+weighted_f1 = 0.9372502407778476

checkpoint-8725-epoch-5/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-8725-epoch-5/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d18fed3ee40c937a987c028c5f5687c9662abbc1fd00bc867a1fdd5c5887f8
+size 506311456

checkpoint-8725-epoch-5/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-8725-epoch-5/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:32fad313413349bff3e903649e144e6af52ad6c3b215b38f9aaba44a5361a3b3
+size 1007967802

checkpoint-8725-epoch-5/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:faf3b20aae09053b469f456c0a1ae63775158cccfb279532733245f8dd12b35b
+size 1064

checkpoint-8725-epoch-5/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-8725-epoch-5/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-8725-epoch-5/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9690c764ae76781eef6e9164a6bc27b6745385c84e2585caff73316a612cec7f
+size 3576

checkpoint-8725-epoch-5/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "_name_or_path": "NLPC-UOM/SinBERT-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

eval_results.txt ADDED Viewed

	@@ -0,0 +1,4 @@

+eval_loss = 0.35019068319525104
+macro_f1 = 0.9371727749427544
+mcc = 0.9165943698038781
+weighted_f1 = 0.9372502407778476

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d18fed3ee40c937a987c028c5f5687c9662abbc1fd00bc867a1fdd5c5887f8
+size 506311456

model_args.json ADDED Viewed

	@@ -0,0 +1 @@

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9690c764ae76781eef6e9164a6bc27b6745385c84e2585caff73316a612cec7f
+size 3576

training_progress_scores.csv ADDED Viewed

	@@ -0,0 +1,20 @@

+global_step,mcc,train_loss,eval_loss,macro_f1,weighted_f1
+600,0.8586218410398948,0.03937673568725586,0.3243057405211262,0.8934597509510229,0.8940074854716451
+1200,0.8880456556141589,0.10992908477783203,0.27570400417772767,0.9125397562882632,0.912045163133305
+1745,0.9095818626100802,0.272040456533432,0.22852692486161424,0.9312991147257818,0.9314908632911428
+1800,0.9081609311855388,0.017532706260681152,0.2360150751840208,0.9297402750539504,0.9297381320599136
+2400,0.9089356189252266,0.6510375738143921,0.22538994926690442,0.9309233513369503,0.9309543352611926
+3000,0.9141198181989681,0.07086089253425598,0.2388584490471817,0.9352456781054004,0.9351272096671566
+3490,0.9163726036647536,0.6905561685562134,0.21681966317683152,0.9363705923825345,0.9362311531774655
+3600,0.9183992486619676,0.3702475428581238,0.23464486745579802,0.9379726486311781,0.9378618223403414
+4200,0.9110995364352387,0.017334148287773132,0.25100942412103266,0.9332041844869458,0.9329692578421809
+4800,0.9175064582393759,0.38122090697288513,0.25642930632985206,0.9374653755765934,0.9372747689584016
+5235,0.9138124152210487,0.09636306762695312,0.2760989813130474,0.9343578537920475,0.934226648180557
+5400,0.9139278606640884,0.00464998185634613,0.2708434431493215,0.9347945405513579,0.9347766400718157
+6000,0.9083328107781999,0.001109011471271515,0.3353042191112913,0.9315740926574485,0.9314478267677656
+6600,0.9166418517805649,0.006841644644737244,0.31161130876424387,0.9372170042851029,0.9372191434166729
+6980,0.9156723190858234,0.05192357674241066,0.3323965809075762,0.9366327535999623,0.9366528154514633
+7200,0.9158383882950369,0.001010708510875702,0.31759343657296957,0.9364003268730573,0.936571535947253
+7800,0.9179323772952851,0.00028868764638900757,0.3352872972514963,0.9381821420825974,0.9382092949156446
+8400,0.9183692988263616,0.0002934113144874573,0.34579374569305577,0.9383956072964578,0.9384924540991418
+8725,0.9165943698038781,0.0001783912885002792,0.35019068319525104,0.9371727749427544,0.9372502407778476

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff