| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 171, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.8643, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 1.7663, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.4851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.3257, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001999156886888064, | |
| "loss": 1.2837, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019896881839082556, | |
| "loss": 1.2272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019697969360350098, | |
| "loss": 1.2551, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.2263, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00018996922709216455, | |
| "loss": 1.2222, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018502171357296144, | |
| "loss": 1.242, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00017917882447886582, | |
| "loss": 1.214, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00017250209209335927, | |
| "loss": 1.2186, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001650618300204242, | |
| "loss": 1.2202, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00015693639270213136, | |
| "loss": 1.1952, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001482113502570349, | |
| "loss": 1.2162, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00013897858732926793, | |
| "loss": 1.1951, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00012933533543848461, | |
| "loss": 1.1806, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00011938314902110701, | |
| "loss": 1.2158, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00010922683594633021, | |
| "loss": 1.1702, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.897335376977102e-05, | |
| "loss": 1.186, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.87306833484679e-05, | |
| "loss": 1.1802, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 7.860669167935028e-05, | |
| "loss": 1.1626, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.870799593678459e-05, | |
| "loss": 1.177, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.913884067217685e-05, | |
| "loss": 1.1495, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.1842, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.1387716331478565e-05, | |
| "loss": 1.1736, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.339268683227499e-05, | |
| "loss": 1.1638, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.6099108277934103e-05, | |
| "loss": 1.1465, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.9583790365845822e-05, | |
| "loss": 1.1706, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.3915346821563235e-05, | |
| "loss": 1.152, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.153472818047625e-06, | |
| "loss": 1.1454, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.348316317440549e-06, | |
| "loss": 1.1639, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.539949955849985e-06, | |
| "loss": 1.1614, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.579490328064265e-07, | |
| "loss": 1.1605, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.108004964086474e-08, | |
| "loss": 1.1641, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2067391872406006, | |
| "eval_runtime": 235.4134, | |
| "eval_samples_per_second": 2.68, | |
| "eval_steps_per_second": 0.671, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 171, | |
| "total_flos": 6.011757435184742e+16, | |
| "train_loss": 1.2207316202029848, | |
| "train_runtime": 1132.3581, | |
| "train_samples_per_second": 0.604, | |
| "train_steps_per_second": 0.151 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 171, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 6.011757435184742e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |