| { | |
| "best_metric": 1.5952510833740234, | |
| "best_model_checkpoint": "output/egor-letov/checkpoint-162", | |
| "epoch": 1.0, | |
| "global_step": 162, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013687777179141117, | |
| "loss": 2.4061, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013591411430903858, | |
| "loss": 2.0285, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013431808054484255, | |
| "loss": 2.1022, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001321046642918459, | |
| "loss": 2.0273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012929465928631872, | |
| "loss": 2.0219, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012591446386292745, | |
| "loss": 1.8839, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00012199583295799738, | |
| "loss": 1.8914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011757557979067189, | |
| "loss": 1.9117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00011269523002449659, | |
| "loss": 1.7911, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010740063165837655, | |
| "loss": 1.883, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001017415243117494, | |
| "loss": 1.8814, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.577107195028616e-05, | |
| "loss": 1.8308, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.954536344188477e-05, | |
| "loss": 1.8842, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.312288563493759e-05, | |
| "loss": 1.7583, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.65639739089908e-05, | |
| "loss": 1.9336, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.993024535954715e-05, | |
| "loss": 1.8095, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.328401994190555e-05, | |
| "loss": 1.665, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.668773501204858e-05, | |
| "loss": 1.7316, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 5.0203358764620266e-05, | |
| "loss": 1.8011, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.389180807839688e-05, | |
| "loss": 1.6939, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.7812376238248296e-05, | |
| "loss": 1.7563, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.2022175909803996e-05, | |
| "loss": 1.6453, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.6575602599746285e-05, | |
| "loss": 1.7147, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.152382364220488e-05, | |
| "loss": 1.7494, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6914297511922475e-05, | |
| "loss": 1.8658, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.279032797996043e-05, | |
| "loss": 1.7932, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 1.7533, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.149102249722346e-06, | |
| "loss": 1.762, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.694236438323532e-06, | |
| "loss": 1.6914, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.849121878224087e-06, | |
| "loss": 1.6333, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.310923291716113e-07, | |
| "loss": 1.7231, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 5.1590458209819155e-08, | |
| "loss": 1.6988, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5952510833740234, | |
| "eval_runtime": 10.0961, | |
| "eval_samples_per_second": 22.286, | |
| "eval_steps_per_second": 2.872, | |
| "step": 162 | |
| } | |
| ], | |
| "max_steps": 162, | |
| "num_train_epochs": 1, | |
| "total_flos": 168402714624000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |