| { | |
| "best_metric": 0.4943845868110657, | |
| "best_model_checkpoint": "output_pipe/H3K9ac/origin/checkpoint-600", | |
| "epoch": 4.0, | |
| "eval_steps": 200, | |
| "global_step": 1392, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28735632183908044, | |
| "grad_norm": 1.4087169170379639, | |
| "learning_rate": 2.88822652757079e-05, | |
| "loss": 0.6217, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "grad_norm": 3.3012173175811768, | |
| "learning_rate": 2.66467958271237e-05, | |
| "loss": 0.52, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "eval_accuracy": 0.7578265563152213, | |
| "eval_f1": 0.7549710520630523, | |
| "eval_loss": 0.5086966156959534, | |
| "eval_matthews_correlation": 0.5103459941497681, | |
| "eval_precision": 0.7560774747837139, | |
| "eval_recall": 0.7542717140239462, | |
| "eval_runtime": 1.6882, | |
| "eval_samples_per_second": 1646.122, | |
| "eval_steps_per_second": 26.063, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 1.5346935987472534, | |
| "learning_rate": 2.4411326378539494e-05, | |
| "loss": 0.5199, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "grad_norm": 7.659835338592529, | |
| "learning_rate": 2.2175856929955293e-05, | |
| "loss": 0.443, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "eval_accuracy": 0.7563871896365599, | |
| "eval_f1": 0.7504115513772263, | |
| "eval_loss": 0.5552314519882202, | |
| "eval_matthews_correlation": 0.5070473896046841, | |
| "eval_precision": 0.7586580933925764, | |
| "eval_recall": 0.7484912147275411, | |
| "eval_runtime": 1.686, | |
| "eval_samples_per_second": 1648.303, | |
| "eval_steps_per_second": 26.098, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.4367816091954024, | |
| "grad_norm": 1.856019139289856, | |
| "learning_rate": 1.9940387481371088e-05, | |
| "loss": 0.4195, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 2.136723279953003, | |
| "learning_rate": 1.7704918032786887e-05, | |
| "loss": 0.399, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "eval_accuracy": 0.7758186397984886, | |
| "eval_f1": 0.7724525296845135, | |
| "eval_loss": 0.4943845868110657, | |
| "eval_matthews_correlation": 0.5463200014700549, | |
| "eval_precision": 0.7751836832061069, | |
| "eval_recall": 0.7711512002900043, | |
| "eval_runtime": 1.6866, | |
| "eval_samples_per_second": 1647.677, | |
| "eval_steps_per_second": 26.088, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0114942528735633, | |
| "grad_norm": 2.3200464248657227, | |
| "learning_rate": 1.5469448584202682e-05, | |
| "loss": 0.3854, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 4.425991058349609, | |
| "learning_rate": 1.323397913561848e-05, | |
| "loss": 0.2017, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "eval_accuracy": 0.7646635480388629, | |
| "eval_f1": 0.7636386004958545, | |
| "eval_loss": 0.7006317377090454, | |
| "eval_matthews_correlation": 0.5283106605840528, | |
| "eval_precision": 0.7632509869632658, | |
| "eval_recall": 0.765062780301851, | |
| "eval_runtime": 1.6874, | |
| "eval_samples_per_second": 1646.889, | |
| "eval_steps_per_second": 26.075, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.586206896551724, | |
| "grad_norm": 4.091574192047119, | |
| "learning_rate": 1.0998509687034278e-05, | |
| "loss": 0.1758, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "grad_norm": 3.942636489868164, | |
| "learning_rate": 8.785394932935916e-06, | |
| "loss": 0.1622, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "eval_accuracy": 0.7646635480388629, | |
| "eval_f1": 0.7646525468502346, | |
| "eval_loss": 0.6856089234352112, | |
| "eval_matthews_correlation": 0.5404152294488869, | |
| "eval_precision": 0.7698917317808079, | |
| "eval_recall": 0.7705238673794199, | |
| "eval_runtime": 1.6865, | |
| "eval_samples_per_second": 1647.769, | |
| "eval_steps_per_second": 26.089, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.160919540229885, | |
| "grad_norm": 3.2131688594818115, | |
| "learning_rate": 6.549925484351714e-06, | |
| "loss": 0.1089, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 2.8835015296936035, | |
| "learning_rate": 4.314456035767512e-06, | |
| "loss": 0.0635, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "eval_accuracy": 0.760705289672544, | |
| "eval_f1": 0.7605354936561897, | |
| "eval_loss": 0.9777570962905884, | |
| "eval_matthews_correlation": 0.527558821780822, | |
| "eval_precision": 0.7628614911549043, | |
| "eval_recall": 0.7647005360275044, | |
| "eval_runtime": 1.6867, | |
| "eval_samples_per_second": 1647.607, | |
| "eval_steps_per_second": 26.087, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.735632183908046, | |
| "grad_norm": 1.047171950340271, | |
| "learning_rate": 2.0789865871833086e-06, | |
| "loss": 0.0533, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1392, | |
| "total_flos": 2.263716899665344e+16, | |
| "train_loss": 0.29601662700203646, | |
| "train_runtime": 210.7551, | |
| "train_samples_per_second": 421.798, | |
| "train_steps_per_second": 6.605 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1392, | |
| "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": 2.263716899665344e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |