First commit

added_tokens.json

@@ -0,0 +1,7 @@
+{
+ "[CLS]": 101,
+ "[MASK]": 103,
+ "[PAD]": 0,
+ "[SEP]": 102,
+ "[UNK]": 100
+}

config.json

@@ -0,0 +1,43 @@
+{
+ "_name_or_path": "bert-large-uncased",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 1024,
+ "id2label": {
+ "0": "Knowledge",
+ "1": "Comprehension",
+ "2": "Application",
+ "3": "Analysis",
+ "4": "Synthesis",
+ "5": "Evaluation"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "label2id": {
+ "Analysis": 3,
+ "Application": 2,
+ "Comprehension": 1,
+ "Evaluation": 5,
+ "Knowledge": 0,
+ "Synthesis": 4
+ },
+ "layer_norm_eps": 1e-12,
+ "max_position_embeddings": 512,
+ "model_type": "bert",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "pad_token_id": 0,
+ "position_embedding_type": "absolute",
+ "problem_type": "single_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.34.0",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9328113ca2a2c61e763ce827b9c2dd4d5072658f2574459740dbb2113740b0
+size 2681512760

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b714895521df58bbd5de168d42ad81241eecbb87546d66d68d85b12cffd121
+size 1340726577

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ad9768ce19300657441de3b9273c47b9c04ef155b1e325dd830348040f7dc8
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9055abc17030374b2c46b6002ce0976792187dc796436315f5f291553a394e
+size 627

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 +1,56 @@
+{
+ "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
+ }
+ },
+ "additional_special_tokens": [],
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 512,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "BertTokenizer",
+ "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+ "best_metric": 0.0809762105345726,
+ "best_model_checkpoint": "bert_large_finetune_bloom_question_classifier_enhanced\\checkpoint-390",
+ "epoch": 4.0,
+ "eval_steps": 500,
+ "global_step": 520,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 1.0,
+ "eval_accuracy": 0.9486301369863014,
+ "eval_loss": 0.18780267238616943,
+ "eval_runtime": 14.9911,
+ "eval_samples_per_second": 38.956,
+ "eval_steps_per_second": 2.201,
+ "step": 130
+ },
+ {
+ "epoch": 2.0,
+ "eval_accuracy": 0.964041095890411,
+ "eval_loss": 0.15712498128414154,
+ "eval_runtime": 14.9873,
+ "eval_samples_per_second": 38.966,
+ "eval_steps_per_second": 2.202,
+ "step": 260
+ },
+ {
+ "epoch": 3.0,
+ "eval_accuracy": 0.9811643835616438,
+ "eval_loss": 0.0809762105345726,
+ "eval_runtime": 14.9624,
+ "eval_samples_per_second": 39.031,
+ "eval_steps_per_second": 2.206,
+ "step": 390
+ },
+ {
+ "epoch": 3.85,
+ "learning_rate": 7.692307692307694e-07,
+ "loss": 0.2409,
+ "step": 500
+ },
+ {
+ "epoch": 4.0,
+ "eval_accuracy": 0.9811643835616438,
+ "eval_loss": 0.08374008536338806,
+ "eval_runtime": 14.9759,
+ "eval_samples_per_second": 38.996,
+ "eval_steps_per_second": 2.204,
+ "step": 520
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 520,
+ "num_train_epochs": 4,
+ "save_steps": 500,
+ "total_flos": 8496707809392000.0,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f0c829c50eda89ab587f9fcec6fde2810844eea8869b2b4bbac191bea7d15f
+size 4219