| { | |
| "best_metric": 2.3343088626861572, | |
| "best_model_checkpoint": "dq158/pingusPongus/checkpoint-25292", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 25292, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8e-05, | |
| "loss": 3.4297, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.999965623174768e-05, | |
| "loss": 2.9121, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.999862493289958e-05, | |
| "loss": 2.8542, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.999690612118205e-05, | |
| "loss": 2.7645, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 7.999449982613875e-05, | |
| "loss": 2.7235, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.99914060891301e-05, | |
| "loss": 2.712, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.998762496333249e-05, | |
| "loss": 2.6692, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 7.998315651373749e-05, | |
| "loss": 2.6532, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.997800081715064e-05, | |
| "loss": 2.6572, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.99721579621902e-05, | |
| "loss": 2.6498, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.996562804928555e-05, | |
| "loss": 2.6156, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.995841119067557e-05, | |
| "loss": 2.6079, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 7.995050751040655e-05, | |
| "loss": 2.5754, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.994191714433023e-05, | |
| "loss": 2.5303, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.993264024010138e-05, | |
| "loss": 2.6282, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 7.992267695717525e-05, | |
| "loss": 2.558, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.991202746680485e-05, | |
| "loss": 2.57, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.9900691952038e-05, | |
| "loss": 2.6049, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.988867060771425e-05, | |
| "loss": 2.6004, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 7.987596364046138e-05, | |
| "loss": 2.5497, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 7.986257126869202e-05, | |
| "loss": 2.5397, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.984849372259976e-05, | |
| "loss": 2.5058, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.983373124415528e-05, | |
| "loss": 2.5385, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.981828408710215e-05, | |
| "loss": 2.523, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.980215251695248e-05, | |
| "loss": 2.5043, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": 2.393324613571167, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 1439232, | |
| "eval_runtime": 1581.2805, | |
| "eval_samples_per_second": 1.778, | |
| "eval_steps_per_second": 0.889, | |
| "eval_translation_length": 1439232, | |
| "step": 12646 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.978533681098235e-05, | |
| "loss": 2.4976, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.976783725822707e-05, | |
| "loss": 2.4559, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.974965415947614e-05, | |
| "loss": 2.5159, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.97307878272682e-05, | |
| "loss": 2.4853, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.971123858588551e-05, | |
| "loss": 2.5642, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 7.969100677134854e-05, | |
| "loss": 2.4762, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 7.967009273141005e-05, | |
| "loss": 2.4515, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 7.964849682554919e-05, | |
| "loss": 2.5239, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 7.962621942496528e-05, | |
| "loss": 2.4723, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 7.96032609125715e-05, | |
| "loss": 2.5052, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 7.957962168298823e-05, | |
| "loss": 2.4817, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 7.95553021425363e-05, | |
| "loss": 2.505, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.953030270922999e-05, | |
| "loss": 2.5106, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.950462381276989e-05, | |
| "loss": 2.4658, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 7.947826589453548e-05, | |
| "loss": 2.4544, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 7.94512294075775e-05, | |
| "loss": 2.462, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 7.942351481661027e-05, | |
| "loss": 2.4447, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 7.93951225980036e-05, | |
| "loss": 2.4918, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 7.936605323977468e-05, | |
| "loss": 2.4594, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 7.933630724157962e-05, | |
| "loss": 2.5028, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 7.93058851147049e-05, | |
| "loss": 2.4924, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.92747873820586e-05, | |
| "loss": 2.4138, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.924301457816139e-05, | |
| "loss": 2.4198, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.921056724913732e-05, | |
| "loss": 2.4524, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 7.917744595270448e-05, | |
| "loss": 2.4497, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": 2.3343088626861572, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 1439232, | |
| "eval_runtime": 1578.692, | |
| "eval_samples_per_second": 1.781, | |
| "eval_steps_per_second": 0.891, | |
| "eval_translation_length": 1439232, | |
| "step": 25292 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 379380, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 4.3332645393373594e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |