| { | |
| "best_metric": 0.42953088879585266, | |
| "best_model_checkpoint": "output_pipe/H3K79me3/origin/checkpoint-400", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1444, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2770083102493075, | |
| "grad_norm": 1.8821665048599243, | |
| "learning_rate": 2.8923959827833574e-05, | |
| "loss": 0.5372, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.554016620498615, | |
| "grad_norm": 2.4539694786071777, | |
| "learning_rate": 2.677187948350072e-05, | |
| "loss": 0.4595, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.554016620498615, | |
| "eval_accuracy": 0.8072122052704577, | |
| "eval_f1": 0.8032749878787759, | |
| "eval_loss": 0.4524916112422943, | |
| "eval_matthews_correlation": 0.612219415419701, | |
| "eval_precision": 0.8113202632712555, | |
| "eval_recall": 0.8009863610213059, | |
| "eval_runtime": 1.7594, | |
| "eval_samples_per_second": 1639.22, | |
| "eval_steps_per_second": 26.146, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8310249307479224, | |
| "grad_norm": 1.6477127075195312, | |
| "learning_rate": 2.4619799139167864e-05, | |
| "loss": 0.445, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.10803324099723, | |
| "grad_norm": 1.393030047416687, | |
| "learning_rate": 2.2467718794835007e-05, | |
| "loss": 0.415, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.10803324099723, | |
| "eval_accuracy": 0.8214285714285714, | |
| "eval_f1": 0.8197900442268229, | |
| "eval_loss": 0.42953088879585266, | |
| "eval_matthews_correlation": 0.6398255645053356, | |
| "eval_precision": 0.8206609712558366, | |
| "eval_recall": 0.819166338977338, | |
| "eval_runtime": 1.757, | |
| "eval_samples_per_second": 1641.395, | |
| "eval_steps_per_second": 26.18, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3850415512465375, | |
| "grad_norm": 3.5757462978363037, | |
| "learning_rate": 2.0315638450502154e-05, | |
| "loss": 0.3501, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.662049861495845, | |
| "grad_norm": 2.4975414276123047, | |
| "learning_rate": 1.8163558106169297e-05, | |
| "loss": 0.3606, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.662049861495845, | |
| "eval_accuracy": 0.8224687933425797, | |
| "eval_f1": 0.8207303807303807, | |
| "eval_loss": 0.4307219684123993, | |
| "eval_matthews_correlation": 0.6418496215168715, | |
| "eval_precision": 0.8219002683598478, | |
| "eval_recall": 0.8199523090959455, | |
| "eval_runtime": 1.7563, | |
| "eval_samples_per_second": 1642.083, | |
| "eval_steps_per_second": 26.191, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.9390581717451525, | |
| "grad_norm": 2.746671438217163, | |
| "learning_rate": 1.601147776183644e-05, | |
| "loss": 0.3371, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.21606648199446, | |
| "grad_norm": 1.7420034408569336, | |
| "learning_rate": 1.3880918220946917e-05, | |
| "loss": 0.2358, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.21606648199446, | |
| "eval_accuracy": 0.8186546463245492, | |
| "eval_f1": 0.8168151679603981, | |
| "eval_loss": 0.5184203386306763, | |
| "eval_matthews_correlation": 0.6341105917898584, | |
| "eval_precision": 0.81814806200303, | |
| "eval_recall": 0.8159662831894405, | |
| "eval_runtime": 1.7567, | |
| "eval_samples_per_second": 1641.737, | |
| "eval_steps_per_second": 26.186, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4930747922437675, | |
| "grad_norm": 4.050608158111572, | |
| "learning_rate": 1.1728837876614062e-05, | |
| "loss": 0.1672, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.770083102493075, | |
| "grad_norm": 3.5075011253356934, | |
| "learning_rate": 9.576757532281205e-06, | |
| "loss": 0.1697, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.770083102493075, | |
| "eval_accuracy": 0.8203883495145631, | |
| "eval_f1": 0.8182058021806853, | |
| "eval_loss": 0.5386074185371399, | |
| "eval_matthews_correlation": 0.6375735235430674, | |
| "eval_precision": 0.820656871218669, | |
| "eval_recall": 0.8169275590276635, | |
| "eval_runtime": 1.7547, | |
| "eval_samples_per_second": 1643.609, | |
| "eval_steps_per_second": 26.216, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0470914127423825, | |
| "grad_norm": 2.130587339401245, | |
| "learning_rate": 7.4246771879483506e-06, | |
| "loss": 0.1413, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.32409972299169, | |
| "grad_norm": 6.416651248931885, | |
| "learning_rate": 5.2725968436154954e-06, | |
| "loss": 0.0616, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.32409972299169, | |
| "eval_accuracy": 0.8179611650485437, | |
| "eval_f1": 0.8165939975446539, | |
| "eval_loss": 0.7715341448783875, | |
| "eval_matthews_correlation": 0.6332041129097091, | |
| "eval_precision": 0.8167739924362117, | |
| "eval_recall": 0.8164302137954947, | |
| "eval_runtime": 1.7555, | |
| "eval_samples_per_second": 1642.811, | |
| "eval_steps_per_second": 26.203, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.6011080332409975, | |
| "grad_norm": 0.6951963305473328, | |
| "learning_rate": 3.12051649928264e-06, | |
| "loss": 0.0595, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.878116343490305, | |
| "grad_norm": 0.43994560837745667, | |
| "learning_rate": 9.684361549497848e-07, | |
| "loss": 0.0478, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.878116343490305, | |
| "eval_accuracy": 0.8259361997226075, | |
| "eval_f1": 0.8251118714433917, | |
| "eval_loss": 0.771431028842926, | |
| "eval_matthews_correlation": 0.6505767750838901, | |
| "eval_precision": 0.8246353603951226, | |
| "eval_recall": 0.8259427282993795, | |
| "eval_runtime": 1.7543, | |
| "eval_samples_per_second": 1644.004, | |
| "eval_steps_per_second": 26.222, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1444, | |
| "total_flos": 2.349787849099164e+16, | |
| "train_loss": 0.26351343272795635, | |
| "train_runtime": 224.2333, | |
| "train_samples_per_second": 411.518, | |
| "train_steps_per_second": 6.44 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1444, | |
| "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": 2.349787849099164e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |