tharindu commited on Mar 19

Commit

b45a997

•

1 Parent(s): 2dab544

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-small",
+  "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": 6,
+  "num_hidden_layers": 6,
+  "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": 30000
+}

best_model/eval_results.txt ADDED Viewed

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

+eval_loss = 0.2251052070101819
+macro_f1 = 0.9344670266675152
+mcc = 0.9136671206228468
+weighted_f1 = 0.9344463083069552

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 sha256:4edc30aea03628c2f47ab8f5bb19fd4177440ff4345cdcf42ce3a4afdab58a14
+size 268606904

best_model/model_args.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"adam_epsilon": 1e-08, "best_model_dir": "outputs/SinBERT-small/best_model", "cache_dir": "cache_dir/SinBERT-small", "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-small", "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-small", "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 sha256:90710b23389092e0083fb9684de92882efc4e7b3feb37db8f1d35136b93bb037
+size 532525626

best_model/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1849ef9dccf2273bd0d99eee5a2105e3a48df76b7f67065ab0acfa8eeadf2891
+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:ead8667e7a44b12598c22fdcddbd2353229fe2f112bb97674b0e5ba0c5e8970c
+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-small",
+  "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": 6,
+  "num_hidden_layers": 6,
+  "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": 30000
+}

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

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

+eval_loss = 0.34151758549293293
+macro_f1 = 0.9348709907176311
+mcc = 0.9137948691306516
+weighted_f1 = 0.9347992521817201

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:f71aa9b6626275387b8712c40d1f1340b825e1e5448dd225fa6807661185581d
+size 268606904

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 sha256:48b1c993870d1bc442ace81cb0e74a9bfedf056de14e367f2d87b0b383c2c931
+size 532525626

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:ead8667e7a44b12598c22fdcddbd2353229fe2f112bb97674b0e5ba0c5e8970c
+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-small",
+  "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": 6,
+  "num_hidden_layers": 6,
+  "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": 30000
+}

eval_results.txt ADDED Viewed

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

+eval_loss = 0.34151758549293293
+macro_f1 = 0.9348709907176311
+mcc = 0.9137948691306516
+weighted_f1 = 0.9347992521817201

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:f71aa9b6626275387b8712c40d1f1340b825e1e5448dd225fa6807661185581d
+size 268606904

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:ead8667e7a44b12598c22fdcddbd2353229fe2f112bb97674b0e5ba0c5e8970c
+size 3576

training_progress_scores.csv ADDED Viewed

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

+global_step,mcc,train_loss,eval_loss,macro_f1,weighted_f1
+600,0.8451001777407532,0.6267027854919434,0.42548112847755865,0.8763067552108569,0.8765308447570479
+1200,0.9048039517961178,0.030068397521972656,0.23929377291927634,0.9275202235458081,0.9274125233946232
+1745,0.9062583657506975,0.34391680359840393,0.24556800749959404,0.927483326651353,0.9274128859954716
+1800,0.9027066860191246,0.029545724391937256,0.2442612595395329,0.9263008267060205,0.9262922312881837
+2400,0.9067855672881595,0.025686800479888916,0.23043710719217958,0.9297298976381554,0.9296972996852427
+3000,0.9136671206228468,0.0807458758354187,0.2251052070101819,0.9344670266675152,0.9344463083069552
+3490,0.9113358777538344,0.06360704451799393,0.23269699087616094,0.931444493408386,0.9313860115029243
+3600,0.9185602865187334,0.09718459844589233,0.23973123358140133,0.9379101834455777,0.9378391753722314
+4200,0.9139737027285477,0.011538177728652954,0.26021608564349796,0.9342872831078035,0.9341762076477511
+4800,0.9115670572825137,0.2669558823108673,0.28040378065491767,0.9323808276135623,0.932220897651101
+5235,0.9127381225612987,0.39511868357658386,0.248866192161192,0.9343326060066529,0.9342617842809896
+5400,0.913887124756079,0.0023157894611358643,0.2744390949434073,0.9343231302985977,0.9342464618079723
+6000,0.9156342782485888,0.0008873343467712402,0.29891661082192794,0.936151290188949,0.9360863514883322
+6600,0.9165694176505395,0.001615770161151886,0.30422155288307323,0.9366535952308646,0.9366250514347939
+6980,0.9148972006159578,0.0021776719950139523,0.30714788280197025,0.9354657733680298,0.9353310628487513
+7200,0.9099136069127632,0.00806216150522232,0.2981736860478047,0.9320368482346593,0.9318945911316381
+7800,0.9150740086690342,0.0008878186345100403,0.3436338660720083,0.9359163931287442,0.9358057302346845
+8400,0.9116390887372987,0.0005716383457183838,0.3371976923927204,0.9332466833043666,0.9331948099294777
+8725,0.9137948691306516,0.0006029605865478516,0.34151758549293293,0.9348709907176311,0.9347992521817201

vocab.json ADDED Viewed

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