| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 1.0, |
| "global_step": 32, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0625, |
| "eval_loss": 4.102813243865967, |
| "eval_runtime": 46.3336, |
| "eval_samples_per_second": 3.237, |
| "eval_steps_per_second": 0.065, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.125, |
| "eval_loss": 4.02440071105957, |
| "eval_runtime": 8.6463, |
| "eval_samples_per_second": 17.348, |
| "eval_steps_per_second": 0.347, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1875, |
| "eval_loss": 4.143311500549316, |
| "eval_runtime": 16.1378, |
| "eval_samples_per_second": 9.295, |
| "eval_steps_per_second": 0.186, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.25, |
| "eval_loss": 4.173377990722656, |
| "eval_runtime": 8.329, |
| "eval_samples_per_second": 18.009, |
| "eval_steps_per_second": 0.36, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.3125, |
| "eval_loss": 4.01168155670166, |
| "eval_runtime": 16.236, |
| "eval_samples_per_second": 9.239, |
| "eval_steps_per_second": 0.185, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.375, |
| "eval_loss": 4.010961055755615, |
| "eval_runtime": 8.3188, |
| "eval_samples_per_second": 18.031, |
| "eval_steps_per_second": 0.361, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.4375, |
| "eval_loss": 4.041440486907959, |
| "eval_runtime": 15.8046, |
| "eval_samples_per_second": 9.491, |
| "eval_steps_per_second": 0.19, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 4.010050296783447, |
| "eval_runtime": 8.7811, |
| "eval_samples_per_second": 17.082, |
| "eval_steps_per_second": 0.342, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.5625, |
| "eval_loss": 4.008200645446777, |
| "eval_runtime": 15.9749, |
| "eval_samples_per_second": 9.39, |
| "eval_steps_per_second": 0.188, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.625, |
| "eval_loss": 3.9981045722961426, |
| "eval_runtime": 8.2704, |
| "eval_samples_per_second": 18.137, |
| "eval_steps_per_second": 0.363, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6875, |
| "eval_loss": 3.9941446781158447, |
| "eval_runtime": 15.9208, |
| "eval_samples_per_second": 9.422, |
| "eval_steps_per_second": 0.188, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.75, |
| "eval_loss": 3.995903253555298, |
| "eval_runtime": 8.2167, |
| "eval_samples_per_second": 18.255, |
| "eval_steps_per_second": 0.365, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.8125, |
| "eval_loss": 3.9886744022369385, |
| "eval_runtime": 15.9708, |
| "eval_samples_per_second": 9.392, |
| "eval_steps_per_second": 0.188, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.875, |
| "eval_loss": 3.982693672180176, |
| "eval_runtime": 8.8265, |
| "eval_samples_per_second": 16.994, |
| "eval_steps_per_second": 0.34, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.9375, |
| "eval_loss": 3.9799349308013916, |
| "eval_runtime": 15.9139, |
| "eval_samples_per_second": 9.426, |
| "eval_steps_per_second": 0.189, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 3.9809114933013916, |
| "eval_runtime": 2.7645, |
| "eval_samples_per_second": 54.259, |
| "eval_steps_per_second": 1.085, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.0625, |
| "eval_loss": 3.9646639823913574, |
| "eval_runtime": 8.3504, |
| "eval_samples_per_second": 17.963, |
| "eval_steps_per_second": 0.359, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.125, |
| "eval_loss": 3.9485819339752197, |
| "eval_runtime": 2.9291, |
| "eval_samples_per_second": 51.21, |
| "eval_steps_per_second": 1.024, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.1875, |
| "eval_loss": 3.9438858032226562, |
| "eval_runtime": 15.8414, |
| "eval_samples_per_second": 9.469, |
| "eval_steps_per_second": 0.189, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.25, |
| "eval_loss": 3.941105842590332, |
| "eval_runtime": 2.7691, |
| "eval_samples_per_second": 54.17, |
| "eval_steps_per_second": 1.083, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.3125, |
| "eval_loss": 3.933875322341919, |
| "eval_runtime": 8.7798, |
| "eval_samples_per_second": 17.085, |
| "eval_steps_per_second": 0.342, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.375, |
| "eval_loss": 3.9402499198913574, |
| "eval_runtime": 3.0846, |
| "eval_samples_per_second": 48.629, |
| "eval_steps_per_second": 0.973, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.4375, |
| "eval_loss": 3.964958429336548, |
| "eval_runtime": 16.1126, |
| "eval_samples_per_second": 9.31, |
| "eval_steps_per_second": 0.186, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_loss": 3.963437080383301, |
| "eval_runtime": 2.8397, |
| "eval_samples_per_second": 52.822, |
| "eval_steps_per_second": 1.056, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.5625, |
| "eval_loss": 3.9432413578033447, |
| "eval_runtime": 8.5666, |
| "eval_samples_per_second": 17.51, |
| "eval_steps_per_second": 0.35, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.625, |
| "eval_loss": 3.9292993545532227, |
| "eval_runtime": 2.8879, |
| "eval_samples_per_second": 51.94, |
| "eval_steps_per_second": 1.039, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.6875, |
| "eval_loss": 3.916614532470703, |
| "eval_runtime": 16.1071, |
| "eval_samples_per_second": 9.313, |
| "eval_steps_per_second": 0.186, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.75, |
| "eval_loss": 3.9063076972961426, |
| "eval_runtime": 2.884, |
| "eval_samples_per_second": 52.01, |
| "eval_steps_per_second": 1.04, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.8125, |
| "eval_loss": 3.9020252227783203, |
| "eval_runtime": 8.445, |
| "eval_samples_per_second": 17.762, |
| "eval_steps_per_second": 0.355, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.875, |
| "eval_loss": 3.8990707397460938, |
| "eval_runtime": 3.0029, |
| "eval_samples_per_second": 49.952, |
| "eval_steps_per_second": 0.999, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.9375, |
| "eval_loss": 3.8950419425964355, |
| "eval_runtime": 16.0252, |
| "eval_samples_per_second": 9.36, |
| "eval_steps_per_second": 0.187, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 3.893137216567993, |
| "eval_runtime": 2.8946, |
| "eval_samples_per_second": 51.821, |
| "eval_steps_per_second": 1.036, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 32, |
| "total_flos": 266767525440000.0, |
| "train_loss": 4.029143333435059, |
| "train_runtime": 1253.0431, |
| "train_samples_per_second": 1.595, |
| "train_steps_per_second": 0.026 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 266767525440000.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
