| { | |
| "best_metric": 3.4699020385742188, | |
| "best_model_checkpoint": "output/logic/checkpoint-166", | |
| "epoch": 1.0, | |
| "global_step": 166, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00013689310231466715, | |
| "loss": 4.1499, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001359751552117083, | |
| "loss": 3.8329, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001344543719809531, | |
| "loss": 3.9919, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00013234435976098498, | |
| "loss": 3.6771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012966399778988942, | |
| "loss": 3.7582, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00012643726848413238, | |
| "loss": 3.8118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001226930428569831, | |
| "loss": 3.6305, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011846482219643966, | |
| "loss": 3.8223, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011379043831398306, | |
| "loss": 3.7137, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010871171504616964, | |
| "loss": 3.8248, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00010327409403776145, | |
| "loss": 3.5061, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.752622815468262e-05, | |
| "loss": 3.5028, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.151954616472095e-05, | |
| "loss": 3.599, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.530779258097404e-05, | |
| "loss": 3.5615, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.894654678527026e-05, | |
| "loss": 3.7261, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.249272573418489e-05, | |
| "loss": 3.6186, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.600407469716782e-05, | |
| "loss": 3.6312, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9538650583379234e-05, | |
| "loss": 3.4797, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.315430248014319e-05, | |
| "loss": 3.515, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.6908154050877874e-05, | |
| "loss": 3.7826, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.0856092423722846e-05, | |
| "loss": 3.3625, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.505226814400944e-05, | |
| "loss": 3.5743, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.954861066472669e-05, | |
| "loss": 3.6889, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.4394363710109435e-05, | |
| "loss": 3.5212, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.963564466966226e-05, | |
| "loss": 3.5788, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5315031964920546e-05, | |
| "loss": 3.3559, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1471184080966003e-05, | |
| "loss": 3.4134, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.138493671395088e-06, | |
| "loss": 3.6262, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.34677983161971e-06, | |
| "loss": 3.577, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.121021293871321e-06, | |
| "loss": 3.3871, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.4811329311337175e-06, | |
| "loss": 3.5072, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.4178756972551454e-07, | |
| "loss": 3.5187, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.2284704855989247e-08, | |
| "loss": 3.5082, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.4699020385742188, | |
| "eval_runtime": 10.9862, | |
| "eval_samples_per_second": 22.847, | |
| "eval_steps_per_second": 2.913, | |
| "step": 166 | |
| } | |
| ], | |
| "max_steps": 166, | |
| "num_train_epochs": 1, | |
| "total_flos": 172844679168000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |