| { | |
| "best_metric": 0.511212944984436, | |
| "best_model_checkpoint": "output_pipe/H3K4me1/origin/checkpoint-800", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1584, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25252525252525254, | |
| "grad_norm": 2.8624508380889893, | |
| "learning_rate": 2.9022164276401565e-05, | |
| "loss": 0.6197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 3.410557270050049, | |
| "learning_rate": 2.7066492829204693e-05, | |
| "loss": 0.5415, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "eval_accuracy": 0.7616792929292929, | |
| "eval_f1": 0.7607729152020279, | |
| "eval_loss": 0.5343340635299683, | |
| "eval_matthews_correlation": 0.5216009133490279, | |
| "eval_precision": 0.7606072333239515, | |
| "eval_recall": 0.760993823287651, | |
| "eval_runtime": 1.923, | |
| "eval_samples_per_second": 1647.436, | |
| "eval_steps_per_second": 26.001, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 1.4580295085906982, | |
| "learning_rate": 2.511082138200782e-05, | |
| "loss": 0.5157, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "grad_norm": 2.2710134983062744, | |
| "learning_rate": 2.3155149934810953e-05, | |
| "loss": 0.5295, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "eval_accuracy": 0.7761994949494949, | |
| "eval_f1": 0.7725553629449594, | |
| "eval_loss": 0.5141143202781677, | |
| "eval_matthews_correlation": 0.5506653820018602, | |
| "eval_precision": 0.7795613839562128, | |
| "eval_recall": 0.7711679619732008, | |
| "eval_runtime": 1.9228, | |
| "eval_samples_per_second": 1647.574, | |
| "eval_steps_per_second": 26.003, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2626262626262625, | |
| "grad_norm": 1.2207655906677246, | |
| "learning_rate": 2.119947848761408e-05, | |
| "loss": 0.4729, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 1.5364807844161987, | |
| "learning_rate": 1.924380704041721e-05, | |
| "loss": 0.4629, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "eval_accuracy": 0.7755681818181818, | |
| "eval_f1": 0.7714154656610406, | |
| "eval_loss": 0.5175797343254089, | |
| "eval_matthews_correlation": 0.5500618417358605, | |
| "eval_precision": 0.7801796351451973, | |
| "eval_recall": 0.7699768218138402, | |
| "eval_runtime": 4.2491, | |
| "eval_samples_per_second": 745.574, | |
| "eval_steps_per_second": 11.767, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7676767676767677, | |
| "grad_norm": 3.395381212234497, | |
| "learning_rate": 1.728813559322034e-05, | |
| "loss": 0.4766, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "grad_norm": 1.879275918006897, | |
| "learning_rate": 1.533246414602347e-05, | |
| "loss": 0.4686, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "eval_accuracy": 0.7746212121212122, | |
| "eval_f1": 0.7727430555555556, | |
| "eval_loss": 0.511212944984436, | |
| "eval_matthews_correlation": 0.5463418750991603, | |
| "eval_precision": 0.7743439291360682, | |
| "eval_recall": 0.7720029612344936, | |
| "eval_runtime": 1.9185, | |
| "eval_samples_per_second": 1651.262, | |
| "eval_steps_per_second": 26.062, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 4.8738484382629395, | |
| "learning_rate": 1.3376792698826597e-05, | |
| "loss": 0.342, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.525252525252525, | |
| "grad_norm": 2.3210840225219727, | |
| "learning_rate": 1.1421121251629727e-05, | |
| "loss": 0.3251, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.525252525252525, | |
| "eval_accuracy": 0.7657828282828283, | |
| "eval_f1": 0.7601378281776338, | |
| "eval_loss": 0.5649052858352661, | |
| "eval_matthews_correlation": 0.5320366808458905, | |
| "eval_precision": 0.7733505537083345, | |
| "eval_recall": 0.7588828026186666, | |
| "eval_runtime": 1.9198, | |
| "eval_samples_per_second": 1650.147, | |
| "eval_steps_per_second": 26.044, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 5.395249843597412, | |
| "learning_rate": 9.465449804432857e-06, | |
| "loss": 0.3096, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "grad_norm": 1.488246202468872, | |
| "learning_rate": 7.509778357235985e-06, | |
| "loss": 0.3006, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "eval_accuracy": 0.7705176767676768, | |
| "eval_f1": 0.7669679176367754, | |
| "eval_loss": 0.6334746479988098, | |
| "eval_matthews_correlation": 0.5388668724823326, | |
| "eval_precision": 0.773245758524131, | |
| "eval_recall": 0.7656743034432558, | |
| "eval_runtime": 1.9184, | |
| "eval_samples_per_second": 1651.336, | |
| "eval_steps_per_second": 26.063, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.282828282828283, | |
| "grad_norm": 3.6328012943267822, | |
| "learning_rate": 5.554106910039114e-06, | |
| "loss": 0.0893, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.5353535353535355, | |
| "grad_norm": 3.510218381881714, | |
| "learning_rate": 3.6179921773142113e-06, | |
| "loss": 0.0743, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.5353535353535355, | |
| "eval_accuracy": 0.76010101010101, | |
| "eval_f1": 0.7579302456892183, | |
| "eval_loss": 0.9358654618263245, | |
| "eval_matthews_correlation": 0.5169954898766244, | |
| "eval_precision": 0.7598433049182238, | |
| "eval_recall": 0.7571591527410038, | |
| "eval_runtime": 1.9208, | |
| "eval_samples_per_second": 1649.325, | |
| "eval_steps_per_second": 26.031, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.787878787878788, | |
| "grad_norm": 4.385198593139648, | |
| "learning_rate": 1.6623207301173403e-06, | |
| "loss": 0.0826, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1584, | |
| "total_flos": 2.581211751008796e+16, | |
| "train_loss": 0.35833474180915137, | |
| "train_runtime": 278.9972, | |
| "train_samples_per_second": 363.315, | |
| "train_steps_per_second": 5.677 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1584, | |
| "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": 2.581211751008796e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |