| { | |
| "best_metric": 0.4280732274055481, | |
| "best_model_checkpoint": "output_pipe/H3K36me3/origin/checkpoint-800", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1744, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22935779816513763, | |
| "grad_norm": 2.1494369506835938, | |
| "learning_rate": 2.911452184179457e-05, | |
| "loss": 0.5777, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.45871559633027525, | |
| "grad_norm": 1.6609880924224854, | |
| "learning_rate": 2.734356552538371e-05, | |
| "loss": 0.4721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45871559633027525, | |
| "eval_accuracy": 0.8038990825688074, | |
| "eval_f1": 0.8010969467637002, | |
| "eval_loss": 0.46640852093696594, | |
| "eval_matthews_correlation": 0.6065805143345595, | |
| "eval_precision": 0.8070928143073897, | |
| "eval_recall": 0.7995347849478525, | |
| "eval_runtime": 2.1053, | |
| "eval_samples_per_second": 1656.767, | |
| "eval_steps_per_second": 26.124, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6880733944954128, | |
| "grad_norm": 1.708346962928772, | |
| "learning_rate": 2.5572609208972848e-05, | |
| "loss": 0.461, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "grad_norm": 1.2805379629135132, | |
| "learning_rate": 2.3801652892561986e-05, | |
| "loss": 0.4456, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "eval_accuracy": 0.8064793577981652, | |
| "eval_f1": 0.8018879379423894, | |
| "eval_loss": 0.45171523094177246, | |
| "eval_matthews_correlation": 0.6159889855047799, | |
| "eval_precision": 0.8163431052143798, | |
| "eval_recall": 0.7998662085633785, | |
| "eval_runtime": 2.1815, | |
| "eval_samples_per_second": 1598.918, | |
| "eval_steps_per_second": 25.212, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.146788990825688, | |
| "grad_norm": 1.489649772644043, | |
| "learning_rate": 2.203069657615112e-05, | |
| "loss": 0.4097, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3761467889908257, | |
| "grad_norm": 2.946652889251709, | |
| "learning_rate": 2.025974025974026e-05, | |
| "loss": 0.3829, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.3761467889908257, | |
| "eval_accuracy": 0.8142201834862385, | |
| "eval_f1": 0.8117443868739206, | |
| "eval_loss": 0.4401949644088745, | |
| "eval_matthews_correlation": 0.6272620585162307, | |
| "eval_precision": 0.8171275731086864, | |
| "eval_recall": 0.8101730371448755, | |
| "eval_runtime": 2.1024, | |
| "eval_samples_per_second": 1659.06, | |
| "eval_steps_per_second": 26.161, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6055045871559632, | |
| "grad_norm": 2.1041178703308105, | |
| "learning_rate": 1.8488783943329397e-05, | |
| "loss": 0.3716, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "grad_norm": 2.9231131076812744, | |
| "learning_rate": 1.6717827626918536e-05, | |
| "loss": 0.3727, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "eval_accuracy": 0.8173738532110092, | |
| "eval_f1": 0.8154185050206181, | |
| "eval_loss": 0.4280732274055481, | |
| "eval_matthews_correlation": 0.6329743138352378, | |
| "eval_precision": 0.8188588427916856, | |
| "eval_recall": 0.8141331117457388, | |
| "eval_runtime": 2.1003, | |
| "eval_samples_per_second": 1660.737, | |
| "eval_steps_per_second": 26.187, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.0642201834862384, | |
| "grad_norm": 3.482365608215332, | |
| "learning_rate": 1.4946871310507674e-05, | |
| "loss": 0.3561, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.293577981651376, | |
| "grad_norm": 3.236065149307251, | |
| "learning_rate": 1.3175914994096814e-05, | |
| "loss": 0.2345, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.293577981651376, | |
| "eval_accuracy": 0.807052752293578, | |
| "eval_f1": 0.8065878914909347, | |
| "eval_loss": 0.5243167877197266, | |
| "eval_matthews_correlation": 0.613704462645569, | |
| "eval_precision": 0.8063077976186559, | |
| "eval_recall": 0.807397632707333, | |
| "eval_runtime": 2.1036, | |
| "eval_samples_per_second": 1658.107, | |
| "eval_steps_per_second": 26.146, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.522935779816514, | |
| "grad_norm": 4.0755205154418945, | |
| "learning_rate": 1.1404958677685952e-05, | |
| "loss": 0.2349, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.7522935779816513, | |
| "grad_norm": 4.44528865814209, | |
| "learning_rate": 9.634002361275088e-06, | |
| "loss": 0.2152, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.7522935779816513, | |
| "eval_accuracy": 0.8056192660550459, | |
| "eval_f1": 0.8049255622426355, | |
| "eval_loss": 0.5453046560287476, | |
| "eval_matthews_correlation": 0.6099411413248217, | |
| "eval_precision": 0.8046985828754918, | |
| "eval_recall": 0.8052428012379753, | |
| "eval_runtime": 2.0998, | |
| "eval_samples_per_second": 1661.077, | |
| "eval_steps_per_second": 26.192, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.981651376146789, | |
| "grad_norm": 4.702061176300049, | |
| "learning_rate": 7.863046044864227e-06, | |
| "loss": 0.2309, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.2110091743119265, | |
| "grad_norm": 2.323010206222534, | |
| "learning_rate": 6.092089728453366e-06, | |
| "loss": 0.1026, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.2110091743119265, | |
| "eval_accuracy": 0.7984518348623854, | |
| "eval_f1": 0.7976974244633697, | |
| "eval_loss": 0.6576951146125793, | |
| "eval_matthews_correlation": 0.5954530597834314, | |
| "eval_precision": 0.7975068594343605, | |
| "eval_recall": 0.797946362547381, | |
| "eval_runtime": 2.1031, | |
| "eval_samples_per_second": 1658.538, | |
| "eval_steps_per_second": 26.152, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.4403669724770642, | |
| "grad_norm": 4.731839656829834, | |
| "learning_rate": 4.338842975206611e-06, | |
| "loss": 0.073, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "grad_norm": 4.688155651092529, | |
| "learning_rate": 2.5678866587957494e-06, | |
| "loss": 0.074, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "eval_accuracy": 0.801605504587156, | |
| "eval_f1": 0.8008974765072326, | |
| "eval_loss": 0.742794394493103, | |
| "eval_matthews_correlation": 0.601884517391137, | |
| "eval_precision": 0.800673863555817, | |
| "eval_recall": 0.8012108934170056, | |
| "eval_runtime": 2.1017, | |
| "eval_samples_per_second": 1659.598, | |
| "eval_steps_per_second": 26.169, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.8990825688073394, | |
| "grad_norm": 4.111555576324463, | |
| "learning_rate": 7.969303423848879e-07, | |
| "loss": 0.0688, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1744, | |
| "total_flos": 2.842276654439424e+16, | |
| "train_loss": 0.2929335802520087, | |
| "train_runtime": 273.562, | |
| "train_samples_per_second": 408.01, | |
| "train_steps_per_second": 6.375 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1744, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.842276654439424e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |