Upload 11 files

config.json

@@ -0,0 +1,49 @@
+{
+ "_name_or_path": "gklmip/bert-tagalog-base-uncased",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "directionality": "bidi",
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "Age",
+ "1": "Gender",
+ "2": "Physical",
+ "3": "Race",
+ "4": "Religion",
+ "5": "Others"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "Age": 0,
+ "Gender": 1,
+ "Others": 5,
+ "Physical": 2,
+ "Race": 3,
+ "Religion": 4
+ },
+ "layer_norm_eps": 1e-12,
+ "max_position_embeddings": 512,
+ "model_type": "bert",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "pad_token_id": 0,
+ "pooler_fc_size": 768,
+ "pooler_num_attention_heads": 12,
+ "pooler_num_fc_layers": 3,
+ "pooler_size_per_head": 128,
+ "pooler_type": "first_token_transform",
+ "position_embedding_type": "absolute",
+ "problem_type": "multi_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.41.2",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 52099
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfacbd6ce1e1f00afa0f95a9c83999336188eb37235f79bd3b544f668d3b89e8
+size 504255504

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96627a13cb0f9557d9d8049dae3fd2c12494609e980e7efc95baad43607eba5f
+size 1008632058

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10751bce6411252ba7ea497c44ee39e5601afdea1b3956302c9677e6e73470af
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b82c227050b6c3f704bc63c89f4c99ed1b0e1d71eefea8dbbc7985739a0434
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "100": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_basic_tokenize": true,
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 512,
+ "never_split": null,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+ "best_metric": 0.876997915218902,
+ "best_model_checkpoint": "bert-multilabel-tagalog-hate-speech-classifier/checkpoint-790",
+ "epoch": 5.0,
+ "eval_steps": 500,
+ "global_step": 790,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.4650793650793651,
+ "eval_f1": 0.6538124452234881,
+ "eval_loss": 0.2858085036277771,
+ "eval_roc_auc": 0.749062395824874,
+ "eval_runtime": 16.739,
+ "eval_samples_per_second": 37.637,
+ "eval_steps_per_second": 4.72,
+ "step": 158
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.7285714285714285,
+ "eval_f1": 0.8368690563277249,
+ "eval_loss": 0.1806272566318512,
+ "eval_roc_auc": 0.8807496256986324,
+ "eval_runtime": 16.7646,
+ "eval_samples_per_second": 37.579,
+ "eval_steps_per_second": 4.712,
+ "step": 316
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.7682539682539683,
+ "eval_f1": 0.8638631503920171,
+ "eval_loss": 0.14880089461803436,
+ "eval_roc_auc": 0.9036774632664203,
+ "eval_runtime": 17.0606,
+ "eval_samples_per_second": 36.927,
+ "eval_steps_per_second": 4.631,
+ "step": 474
+ },
+ {
+ "epoch": 3.1645569620253164,
+ "grad_norm": 1.8442691564559937,
+ "learning_rate": 7.341772151898735e-06,
+ "loss": 0.2518,
+ "step": 500
+ },
+ {
+ "epoch": 4.0,
+ "eval_accuracy": 0.7761904761904762,
+ "eval_f1": 0.8720848056537103,
+ "eval_loss": 0.14489033818244934,
+ "eval_roc_auc": 0.911037414882052,
+ "eval_runtime": 17.6671,
+ "eval_samples_per_second": 35.66,
+ "eval_steps_per_second": 4.472,
+ "step": 632
+ },
+ {
+ "epoch": 5.0,
+ "eval_accuracy": 0.780952380952381,
+ "eval_f1": 0.876997915218902,
+ "eval_loss": 0.13758358359336853,
+ "eval_roc_auc": 0.9189734563461635,
+ "eval_runtime": 17.8108,
+ "eval_samples_per_second": 35.372,
+ "eval_steps_per_second": 4.436,
+ "step": 790
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 790,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 5,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": true
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 414414795110400.0,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64dd6df4367f52352575621681c3862aeeaa1921cdc2c22c20704c357240ad31
+size 5176