| { | |
| "best_metric": 0.5993899703025818, | |
| "best_model_checkpoint": "output_pipe/H3K4me2/origin/checkpoint-600", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1536, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2604166666666667, | |
| "grad_norm": 1.312898874282837, | |
| "learning_rate": 2.8990578734858683e-05, | |
| "loss": 0.6687, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "grad_norm": 2.9508161544799805, | |
| "learning_rate": 2.6971736204576044e-05, | |
| "loss": 0.6281, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5208333333333334, | |
| "eval_accuracy": 0.6285434995112414, | |
| "eval_f1": 0.5024471908501684, | |
| "eval_loss": 0.6490753889083862, | |
| "eval_matthews_correlation": 0.2086399181537894, | |
| "eval_precision": 0.6864785107900588, | |
| "eval_recall": 0.5583587557391902, | |
| "eval_runtime": 1.8488, | |
| "eval_samples_per_second": 1660.0, | |
| "eval_steps_per_second": 25.963, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.962492048740387, | |
| "learning_rate": 2.4952893674293406e-05, | |
| "loss": 0.6215, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0416666666666667, | |
| "grad_norm": 2.185643196105957, | |
| "learning_rate": 2.293405114401077e-05, | |
| "loss": 0.6117, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0416666666666667, | |
| "eval_accuracy": 0.6614532420984034, | |
| "eval_f1": 0.6577790055568811, | |
| "eval_loss": 0.610870361328125, | |
| "eval_matthews_correlation": 0.3219078238538063, | |
| "eval_precision": 0.6586412781887111, | |
| "eval_recall": 0.6633002586738914, | |
| "eval_runtime": 1.8461, | |
| "eval_samples_per_second": 1662.442, | |
| "eval_steps_per_second": 26.001, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3020833333333333, | |
| "grad_norm": 1.5712463855743408, | |
| "learning_rate": 2.091520861372813e-05, | |
| "loss": 0.5579, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 1.733756422996521, | |
| "learning_rate": 1.8896366083445493e-05, | |
| "loss": 0.5406, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "eval_accuracy": 0.6656891495601173, | |
| "eval_f1": 0.6606768458059544, | |
| "eval_loss": 0.5993899703025818, | |
| "eval_matthews_correlation": 0.32485375836499847, | |
| "eval_precision": 0.6603972055360026, | |
| "eval_recall": 0.6644822364130554, | |
| "eval_runtime": 1.8474, | |
| "eval_samples_per_second": 1661.26, | |
| "eval_steps_per_second": 25.983, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8229166666666665, | |
| "grad_norm": 1.8414597511291504, | |
| "learning_rate": 1.6877523553162854e-05, | |
| "loss": 0.5476, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0833333333333335, | |
| "grad_norm": 3.3911778926849365, | |
| "learning_rate": 1.4858681022880215e-05, | |
| "loss": 0.4847, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.0833333333333335, | |
| "eval_accuracy": 0.6764418377321603, | |
| "eval_f1": 0.6664955835944539, | |
| "eval_loss": 0.6927724480628967, | |
| "eval_matthews_correlation": 0.33299131530494724, | |
| "eval_precision": 0.6665149724192277, | |
| "eval_recall": 0.66647634512612, | |
| "eval_runtime": 1.8456, | |
| "eval_samples_per_second": 1662.868, | |
| "eval_steps_per_second": 26.008, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.34375, | |
| "grad_norm": 4.598505973815918, | |
| "learning_rate": 1.2839838492597578e-05, | |
| "loss": 0.3215, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.6041666666666665, | |
| "grad_norm": 6.187351226806641, | |
| "learning_rate": 1.082099596231494e-05, | |
| "loss": 0.2986, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6041666666666665, | |
| "eval_accuracy": 0.6722059302704464, | |
| "eval_f1": 0.6665124930330224, | |
| "eval_loss": 0.7655965089797974, | |
| "eval_matthews_correlation": 0.3354089433290383, | |
| "eval_precision": 0.665851832445941, | |
| "eval_recall": 0.6695778056925763, | |
| "eval_runtime": 1.8471, | |
| "eval_samples_per_second": 1661.506, | |
| "eval_steps_per_second": 25.986, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.8645833333333335, | |
| "grad_norm": 6.935540199279785, | |
| "learning_rate": 8.8021534320323e-06, | |
| "loss": 0.2776, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "grad_norm": 3.6287009716033936, | |
| "learning_rate": 6.7833109017496635e-06, | |
| "loss": 0.165, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "eval_accuracy": 0.6715542521994134, | |
| "eval_f1": 0.6602836723667622, | |
| "eval_loss": 1.1591715812683105, | |
| "eval_matthews_correlation": 0.3207000488328631, | |
| "eval_precision": 0.660941771459814, | |
| "eval_recall": 0.659760453095114, | |
| "eval_runtime": 1.8438, | |
| "eval_samples_per_second": 1664.518, | |
| "eval_steps_per_second": 26.034, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.3854166666666665, | |
| "grad_norm": 3.4551613330841064, | |
| "learning_rate": 4.764468371467026e-06, | |
| "loss": 0.0605, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.6458333333333335, | |
| "grad_norm": 1.9309793710708618, | |
| "learning_rate": 2.7456258411843877e-06, | |
| "loss": 0.0536, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.6458333333333335, | |
| "eval_accuracy": 0.6614532420984034, | |
| "eval_f1": 0.6480922910837987, | |
| "eval_loss": 1.3020259141921997, | |
| "eval_matthews_correlation": 0.2968783195103293, | |
| "eval_precision": 0.6497979913241463, | |
| "eval_recall": 0.6470926542742468, | |
| "eval_runtime": 1.8472, | |
| "eval_samples_per_second": 1661.427, | |
| "eval_steps_per_second": 25.985, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.90625, | |
| "grad_norm": 6.031075954437256, | |
| "learning_rate": 7.267833109017497e-07, | |
| "loss": 0.0562, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1536, | |
| "total_flos": 2.50013189805102e+16, | |
| "train_loss": 0.38483377111454803, | |
| "train_runtime": 235.9383, | |
| "train_samples_per_second": 416.126, | |
| "train_steps_per_second": 6.51 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1536, | |
| "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": 2.50013189805102e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |