| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.99965225454967, |
| "global_step": 21560, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23, |
| "learning_rate": 2.9327458256029684e-06, |
| "loss": 2.8974, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 2.865491651205937e-06, |
| "loss": 2.6495, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 2.798237476808905e-06, |
| "loss": 2.5817, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 2.730983302411874e-06, |
| "loss": 2.5431, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.508946657180786, |
| "eval_runtime": 7.4005, |
| "eval_samples_per_second": 274.846, |
| "step": 2156 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 2.6637291280148424e-06, |
| "loss": 2.5157, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 2.5964749536178107e-06, |
| "loss": 2.487, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 2.529220779220779e-06, |
| "loss": 2.4657, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 2.461966604823748e-06, |
| "loss": 2.4489, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.421372413635254, |
| "eval_runtime": 7.4016, |
| "eval_samples_per_second": 274.805, |
| "step": 4312 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 2.3947124304267163e-06, |
| "loss": 2.4348, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 2.3274582560296846e-06, |
| "loss": 2.4173, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 2.2602040816326534e-06, |
| "loss": 2.4072, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 2.192949907235622e-06, |
| "loss": 2.3947, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.36946177482605, |
| "eval_runtime": 7.3581, |
| "eval_samples_per_second": 276.432, |
| "step": 6468 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 2.12569573283859e-06, |
| "loss": 2.3883, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 2.0584415584415585e-06, |
| "loss": 2.3753, |
| "step": 7000 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 1.991187384044527e-06, |
| "loss": 2.3672, |
| "step": 7500 |
| }, |
| { |
| "epoch": 3.71, |
| "learning_rate": 1.9239332096474953e-06, |
| "loss": 2.3598, |
| "step": 8000 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 1.8566790352504636e-06, |
| "loss": 2.3535, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 2.3385844230651855, |
| "eval_runtime": 7.2305, |
| "eval_samples_per_second": 281.308, |
| "step": 8624 |
| }, |
| { |
| "epoch": 4.17, |
| "learning_rate": 1.789424860853432e-06, |
| "loss": 2.3509, |
| "step": 9000 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 1.7221706864564008e-06, |
| "loss": 2.3405, |
| "step": 9500 |
| }, |
| { |
| "epoch": 4.64, |
| "learning_rate": 1.6549165120593692e-06, |
| "loss": 2.3338, |
| "step": 10000 |
| }, |
| { |
| "epoch": 4.87, |
| "learning_rate": 1.5876623376623378e-06, |
| "loss": 2.3324, |
| "step": 10500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 2.3173904418945312, |
| "eval_runtime": 7.3244, |
| "eval_samples_per_second": 277.701, |
| "step": 10780 |
| }, |
| { |
| "epoch": 5.1, |
| "learning_rate": 1.5204081632653061e-06, |
| "loss": 2.3301, |
| "step": 11000 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 1.4531539888682747e-06, |
| "loss": 2.3218, |
| "step": 11500 |
| }, |
| { |
| "epoch": 5.57, |
| "learning_rate": 1.385899814471243e-06, |
| "loss": 2.319, |
| "step": 12000 |
| }, |
| { |
| "epoch": 5.8, |
| "learning_rate": 1.3186456400742119e-06, |
| "loss": 2.3136, |
| "step": 12500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 2.3008077144622803, |
| "eval_runtime": 7.2793, |
| "eval_samples_per_second": 279.423, |
| "step": 12936 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 1.2513914656771802e-06, |
| "loss": 2.3135, |
| "step": 13000 |
| }, |
| { |
| "epoch": 6.26, |
| "learning_rate": 1.1841372912801486e-06, |
| "loss": 2.3073, |
| "step": 13500 |
| }, |
| { |
| "epoch": 6.49, |
| "learning_rate": 1.116883116883117e-06, |
| "loss": 2.3051, |
| "step": 14000 |
| }, |
| { |
| "epoch": 6.73, |
| "learning_rate": 1.0496289424860854e-06, |
| "loss": 2.3025, |
| "step": 14500 |
| }, |
| { |
| "epoch": 6.96, |
| "learning_rate": 9.823747680890537e-07, |
| "loss": 2.2988, |
| "step": 15000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 2.290546178817749, |
| "eval_runtime": 7.6918, |
| "eval_samples_per_second": 264.438, |
| "step": 15092 |
| }, |
| { |
| "epoch": 7.19, |
| "learning_rate": 9.151205936920222e-07, |
| "loss": 2.3011, |
| "step": 15500 |
| }, |
| { |
| "epoch": 7.42, |
| "learning_rate": 8.478664192949909e-07, |
| "loss": 2.2951, |
| "step": 16000 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 7.806122448979594e-07, |
| "loss": 2.2928, |
| "step": 16500 |
| }, |
| { |
| "epoch": 7.88, |
| "learning_rate": 7.133580705009277e-07, |
| "loss": 2.292, |
| "step": 17000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 2.2825968265533447, |
| "eval_runtime": 7.4803, |
| "eval_samples_per_second": 271.914, |
| "step": 17248 |
| }, |
| { |
| "epoch": 8.12, |
| "learning_rate": 6.461038961038962e-07, |
| "loss": 2.295, |
| "step": 17500 |
| }, |
| { |
| "epoch": 8.35, |
| "learning_rate": 5.788497217068646e-07, |
| "loss": 2.2893, |
| "step": 18000 |
| }, |
| { |
| "epoch": 8.58, |
| "learning_rate": 5.11595547309833e-07, |
| "loss": 2.2864, |
| "step": 18500 |
| }, |
| { |
| "epoch": 8.81, |
| "learning_rate": 4.443413729128013e-07, |
| "loss": 2.2859, |
| "step": 19000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 2.277188539505005, |
| "eval_runtime": 7.6113, |
| "eval_samples_per_second": 267.234, |
| "step": 19404 |
| }, |
| { |
| "epoch": 9.04, |
| "learning_rate": 3.770871985157698e-07, |
| "loss": 2.2881, |
| "step": 19500 |
| }, |
| { |
| "epoch": 9.28, |
| "learning_rate": 3.0983302411873853e-07, |
| "loss": 2.2851, |
| "step": 20000 |
| }, |
| { |
| "epoch": 9.51, |
| "learning_rate": 2.4257884972170696e-07, |
| "loss": 2.2844, |
| "step": 20500 |
| }, |
| { |
| "epoch": 9.74, |
| "learning_rate": 1.7532467532467535e-07, |
| "loss": 2.2839, |
| "step": 21000 |
| }, |
| { |
| "epoch": 9.97, |
| "learning_rate": 1.0807050092764375e-07, |
| "loss": 2.2814, |
| "step": 21500 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 2.2749264240264893, |
| "eval_runtime": 7.3513, |
| "eval_samples_per_second": 276.685, |
| "step": 21560 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 21560, |
| "total_flos": 8.526747522191754e+17, |
| "train_runtime": 43960.8836, |
| "train_samples_per_second": 0.49 |
| } |
| ], |
| "max_steps": 21560, |
| "num_train_epochs": 10, |
| "total_flos": 8.526747522191754e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
