| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.256317689530686, | |
| "global_step": 25000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.969915764139591e-05, | |
| "loss": 3.07, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.939831528279182e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9097472924187726e-05, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8796630565583636e-05, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8495788206979545e-05, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.8194945848375454e-05, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.789410348977136e-05, | |
| "loss": 0.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.759326113116727e-05, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.729241877256318e-05, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.699157641395909e-05, | |
| "loss": 0.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.6690734055354995e-05, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.6389891696750904e-05, | |
| "loss": 0.0, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.608904933814681e-05, | |
| "loss": 0.0, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.5788206979542723e-05, | |
| "loss": 0.0, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.548736462093863e-05, | |
| "loss": 0.0, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5186522262334538e-05, | |
| "loss": 0.0, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.4885679903730446e-05, | |
| "loss": 0.0, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.4584837545126355e-05, | |
| "loss": 0.0, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4283995186522264e-05, | |
| "loss": 0.0, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.3983152827918172e-05, | |
| "loss": 0.0, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.368231046931408e-05, | |
| "loss": 0.0, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.338146811070999e-05, | |
| "loss": 0.0, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.3735, | |
| "eval_samples_per_second": 149.336, | |
| "eval_steps_per_second": 18.667, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.3080625752105897e-05, | |
| "loss": 0.0, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.2779783393501806e-05, | |
| "loss": 0.0, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.2478941034897714e-05, | |
| "loss": 0.0, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.2178098676293623e-05, | |
| "loss": 0.0, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.1877256317689531e-05, | |
| "loss": 0.0, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.157641395908544e-05, | |
| "loss": 0.0, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.127557160048135e-05, | |
| "loss": 0.0, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.0974729241877257e-05, | |
| "loss": 0.0, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.0673886883273165e-05, | |
| "loss": 0.0, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.0373044524669073e-05, | |
| "loss": 0.0, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0072202166064984e-05, | |
| "loss": 0.0, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.771359807460892e-06, | |
| "loss": 0.0, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.4705174488568e-06, | |
| "loss": 0.0, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.169675090252709e-06, | |
| "loss": 0.0, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.868832731648616e-06, | |
| "loss": 0.0, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.567990373044526e-06, | |
| "loss": 0.0, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.267148014440433e-06, | |
| "loss": 0.0, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.966305655836343e-06, | |
| "loss": 0.0, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.66546329723225e-06, | |
| "loss": 0.0, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.36462093862816e-06, | |
| "loss": 0.0, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.0637785800240674e-06, | |
| "loss": 0.0, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.762936221419977e-06, | |
| "loss": 0.0, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.2454, | |
| "eval_samples_per_second": 149.601, | |
| "eval_steps_per_second": 18.7, | |
| "step": 22160 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.4620938628158845e-06, | |
| "loss": 0.0, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.161251504211794e-06, | |
| "loss": 0.0, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.8604091456077015e-06, | |
| "loss": 0.0, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.559566787003611e-06, | |
| "loss": 0.0, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.258724428399519e-06, | |
| "loss": 0.0, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.957882069795428e-06, | |
| "loss": 0.0, | |
| "step": 25000 | |
| } | |
| ], | |
| "max_steps": 33240, | |
| "num_train_epochs": 3, | |
| "total_flos": 3312504218990592.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |