| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 10, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.47685462377997e-07, | |
| "loss": 1.1777, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.266284080291269e-07, | |
| "loss": 1.1847, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.1642409563064575, | |
| "eval_runtime": 70.6255, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-06, | |
| "loss": 1.1025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.1332802772521973, | |
| "eval_runtime": 70.733, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0927, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-06, | |
| "loss": 1.1003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.1125657558441162, | |
| "eval_runtime": 70.756, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0789, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.0948463678359985, | |
| "eval_runtime": 70.7686, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0963, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0648, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.087746262550354, | |
| "eval_runtime": 70.9688, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.028, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0504, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0568, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.083579659461975, | |
| "eval_runtime": 70.7858, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0472, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0587, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.080450177192688, | |
| "eval_runtime": 70.8142, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0609, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-06, | |
| "loss": 1.021, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.0777862071990967, | |
| "eval_runtime": 70.7864, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-06, | |
| "loss": 1.048, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0857, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.075345516204834, | |
| "eval_runtime": 70.7802, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0077, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-06, | |
| "loss": 1.035, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.0735156536102295, | |
| "eval_runtime": 70.9576, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.028, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0042, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0547, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.0722615718841553, | |
| "eval_runtime": 70.7348, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0077, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0646, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.07070791721344, | |
| "eval_runtime": 70.8054, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-06, | |
| "loss": 0.9997, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0396, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.0689507722854614, | |
| "eval_runtime": 70.8505, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0387, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0197, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.0676530599594116, | |
| "eval_runtime": 70.7124, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0274, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0331, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.066578984260559, | |
| "eval_runtime": 70.851, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1e-06, | |
| "loss": 0.9796, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1e-06, | |
| "loss": 0.9945, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.0656859874725342, | |
| "eval_runtime": 70.6043, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0549, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0134, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.0651814937591553, | |
| "eval_runtime": 70.8302, | |
| "eval_samples_per_second": 0.212, | |
| "eval_steps_per_second": 0.028, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1e-06, | |
| "loss": 0.9615, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1e-06, | |
| "loss": 0.9737, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.0644478797912598, | |
| "eval_runtime": 70.9689, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.028, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1e-06, | |
| "loss": 1.0104, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-06, | |
| "loss": 1.027, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.0634864568710327, | |
| "eval_runtime": 71.0057, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.028, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1e-06, | |
| "loss": 1.028, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-06, | |
| "loss": 0.9929, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.062495470046997, | |
| "eval_runtime": 71.1183, | |
| "eval_samples_per_second": 0.211, | |
| "eval_steps_per_second": 0.028, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 10, | |
| "total_flos": 214104589467648.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |