| { | |
| "best_metric": 0.5504186153411865, | |
| "best_model_checkpoint": "bert_base_lda_5_v1_book_mrpc/checkpoint-60", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 135, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.0119743347167969, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.6274, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6764705882352942, | |
| "eval_combined_score": 0.7334733893557424, | |
| "eval_f1": 0.7904761904761904, | |
| "eval_loss": 0.6025893092155457, | |
| "eval_runtime": 0.271, | |
| "eval_samples_per_second": 1505.634, | |
| "eval_steps_per_second": 7.381, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.53873610496521, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.5872, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6985294117647058, | |
| "eval_combined_score": 0.7581535947712419, | |
| "eval_f1": 0.8177777777777778, | |
| "eval_loss": 0.5821090936660767, | |
| "eval_runtime": 0.2949, | |
| "eval_samples_per_second": 1383.379, | |
| "eval_steps_per_second": 6.781, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 14.746369361877441, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.5589, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7009803921568627, | |
| "eval_combined_score": 0.7545782463928967, | |
| "eval_f1": 0.8081761006289309, | |
| "eval_loss": 0.5608735680580139, | |
| "eval_runtime": 0.276, | |
| "eval_samples_per_second": 1478.466, | |
| "eval_steps_per_second": 7.247, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 5.324950695037842, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.52, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7181372549019608, | |
| "eval_combined_score": 0.7655726924916308, | |
| "eval_f1": 0.8130081300813008, | |
| "eval_loss": 0.5504186153411865, | |
| "eval_runtime": 0.3299, | |
| "eval_samples_per_second": 1236.774, | |
| "eval_steps_per_second": 6.063, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 13.772106170654297, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.4758, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_combined_score": 0.7254901960784313, | |
| "eval_f1": 0.7647058823529411, | |
| "eval_loss": 0.5648291707038879, | |
| "eval_runtime": 0.2772, | |
| "eval_samples_per_second": 1471.946, | |
| "eval_steps_per_second": 7.215, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 4.995352268218994, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.4144, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7279411764705882, | |
| "eval_combined_score": 0.7713161641952273, | |
| "eval_f1": 0.8146911519198664, | |
| "eval_loss": 0.5725027918815613, | |
| "eval_runtime": 0.2832, | |
| "eval_samples_per_second": 1440.628, | |
| "eval_steps_per_second": 7.062, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 8.98536491394043, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.3139, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7181372549019608, | |
| "eval_combined_score": 0.7627537195782836, | |
| "eval_f1": 0.8073701842546064, | |
| "eval_loss": 0.6853400468826294, | |
| "eval_runtime": 0.2692, | |
| "eval_samples_per_second": 1515.482, | |
| "eval_steps_per_second": 7.429, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 9.191425323486328, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.2645, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7475490196078431, | |
| "eval_combined_score": 0.791898516163222, | |
| "eval_f1": 0.8362480127186009, | |
| "eval_loss": 0.763433575630188, | |
| "eval_runtime": 0.2756, | |
| "eval_samples_per_second": 1480.293, | |
| "eval_steps_per_second": 7.256, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 7.379546642303467, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.2114, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7254901960784313, | |
| "eval_combined_score": 0.7752450980392156, | |
| "eval_f1": 0.825, | |
| "eval_loss": 0.8087183833122253, | |
| "eval_runtime": 0.2813, | |
| "eval_samples_per_second": 1450.164, | |
| "eval_steps_per_second": 7.109, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 135, | |
| "total_flos": 4342911079772160.0, | |
| "train_loss": 0.44148262871636285, | |
| "train_runtime": 81.5991, | |
| "train_samples_per_second": 2247.573, | |
| "train_steps_per_second": 9.191 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4342911079772160.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |