| { | |
| "best_metric": 0.47284772992134094, | |
| "best_model_checkpoint": "output_pipe/H3K14ac/origin/checkpoint-600", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1656, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24154589371980675, | |
| "grad_norm": 3.318437337875366, | |
| "learning_rate": 2.9066002490660025e-05, | |
| "loss": 0.6051, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "grad_norm": 1.4331413507461548, | |
| "learning_rate": 2.7198007471980076e-05, | |
| "loss": 0.531, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "eval_accuracy": 0.783661119515885, | |
| "eval_f1": 0.7817658049229228, | |
| "eval_loss": 0.486021488904953, | |
| "eval_matthews_correlation": 0.57187675746879, | |
| "eval_precision": 0.7820563781934564, | |
| "eval_recall": 0.7898738080554106, | |
| "eval_runtime": 2.0006, | |
| "eval_samples_per_second": 1651.978, | |
| "eval_steps_per_second": 25.992, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "grad_norm": 2.053475856781006, | |
| "learning_rate": 2.5330012453300127e-05, | |
| "loss": 0.499, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "grad_norm": 1.5305663347244263, | |
| "learning_rate": 2.3462017434620174e-05, | |
| "loss": 0.5016, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "eval_accuracy": 0.7748865355521937, | |
| "eval_f1": 0.7739118729643131, | |
| "eval_loss": 0.4758010804653168, | |
| "eval_matthews_correlation": 0.5635286075721692, | |
| "eval_precision": 0.7780409552259819, | |
| "eval_recall": 0.7855375130743981, | |
| "eval_runtime": 1.9975, | |
| "eval_samples_per_second": 1654.589, | |
| "eval_steps_per_second": 26.033, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2077294685990339, | |
| "grad_norm": 2.332634210586548, | |
| "learning_rate": 2.1594022415940225e-05, | |
| "loss": 0.445, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "grad_norm": 2.8863093852996826, | |
| "learning_rate": 1.9726027397260273e-05, | |
| "loss": 0.4299, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "eval_accuracy": 0.7821482602118003, | |
| "eval_f1": 0.7804929886161871, | |
| "eval_loss": 0.47284772992134094, | |
| "eval_matthews_correlation": 0.5708358065591705, | |
| "eval_precision": 0.7814909978634529, | |
| "eval_recall": 0.789399590504956, | |
| "eval_runtime": 1.9983, | |
| "eval_samples_per_second": 1653.879, | |
| "eval_steps_per_second": 26.022, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6908212560386473, | |
| "grad_norm": 1.665223479270935, | |
| "learning_rate": 1.7858032378580327e-05, | |
| "loss": 0.4341, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "grad_norm": 3.228135108947754, | |
| "learning_rate": 1.5990037359900375e-05, | |
| "loss": 0.4256, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "eval_accuracy": 0.7791225416036308, | |
| "eval_f1": 0.7784282932921902, | |
| "eval_loss": 0.4730549156665802, | |
| "eval_matthews_correlation": 0.5758658388701079, | |
| "eval_precision": 0.784370037503801, | |
| "eval_recall": 0.7915404408359482, | |
| "eval_runtime": 1.9983, | |
| "eval_samples_per_second": 1653.945, | |
| "eval_steps_per_second": 26.023, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 2.9979915618896484, | |
| "learning_rate": 1.4122042341220424e-05, | |
| "loss": 0.3195, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.4154589371980677, | |
| "grad_norm": 3.590378761291504, | |
| "learning_rate": 1.2254047322540475e-05, | |
| "loss": 0.2755, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.4154589371980677, | |
| "eval_accuracy": 0.7694402420574886, | |
| "eval_f1": 0.7661674718555295, | |
| "eval_loss": 0.562730610370636, | |
| "eval_matthews_correlation": 0.5358397487319655, | |
| "eval_precision": 0.7648953790095512, | |
| "eval_recall": 0.7709789024960523, | |
| "eval_runtime": 1.9996, | |
| "eval_samples_per_second": 1652.833, | |
| "eval_steps_per_second": 26.005, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6570048309178746, | |
| "grad_norm": 6.192252159118652, | |
| "learning_rate": 1.0386052303860523e-05, | |
| "loss": 0.2545, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "grad_norm": 2.510988235473633, | |
| "learning_rate": 8.518057285180574e-06, | |
| "loss": 0.2534, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "eval_accuracy": 0.7736762481089259, | |
| "eval_f1": 0.7699071192215706, | |
| "eval_loss": 0.5492311716079712, | |
| "eval_matthews_correlation": 0.5420469548611992, | |
| "eval_precision": 0.7683862759128433, | |
| "eval_recall": 0.7736865924635743, | |
| "eval_runtime": 1.9963, | |
| "eval_samples_per_second": 1655.542, | |
| "eval_steps_per_second": 26.048, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.140096618357488, | |
| "grad_norm": 1.4343417882919312, | |
| "learning_rate": 6.650062266500623e-06, | |
| "loss": 0.1844, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.3816425120772946, | |
| "grad_norm": 2.109367609024048, | |
| "learning_rate": 4.782067247820672e-06, | |
| "loss": 0.1055, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.3816425120772946, | |
| "eval_accuracy": 0.7652042360060515, | |
| "eval_f1": 0.7595456805828178, | |
| "eval_loss": 0.8072924613952637, | |
| "eval_matthews_correlation": 0.5193230298881569, | |
| "eval_precision": 0.7586758108595886, | |
| "eval_recall": 0.7606509751298403, | |
| "eval_runtime": 2.0009, | |
| "eval_samples_per_second": 1651.764, | |
| "eval_steps_per_second": 25.988, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.6231884057971016, | |
| "grad_norm": 1.882584571838379, | |
| "learning_rate": 2.9327521793275218e-06, | |
| "loss": 0.0977, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.864734299516908, | |
| "grad_norm": 4.4943108558654785, | |
| "learning_rate": 1.0647571606475717e-06, | |
| "loss": 0.1006, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.864734299516908, | |
| "eval_accuracy": 0.7670196671709532, | |
| "eval_f1": 0.7616292444672245, | |
| "eval_loss": 0.7801188230514526, | |
| "eval_matthews_correlation": 0.5236209501273998, | |
| "eval_precision": 0.7605942097967625, | |
| "eval_recall": 0.7630324169771012, | |
| "eval_runtime": 1.999, | |
| "eval_samples_per_second": 1653.338, | |
| "eval_steps_per_second": 26.013, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1656, | |
| "total_flos": 2.692951196605128e+16, | |
| "train_loss": 0.3327603052203782, | |
| "train_runtime": 264.6128, | |
| "train_samples_per_second": 399.648, | |
| "train_steps_per_second": 6.258 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1656, | |
| "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": 2.692951196605128e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |