| { | |
| "best_metric": 0.61642986536026, | |
| "best_model_checkpoint": "ckpt/origin_vehicle_view/vehicle_environment/checkpoint-40", | |
| "epoch": 4.923076923076923, | |
| "eval_steps": 2, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9675, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 0.9305, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.8616295456886292, | |
| "eval_runtime": 44.7658, | |
| "eval_samples_per_second": 1.966, | |
| "eval_steps_per_second": 1.966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 0.8069, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 0.7265, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.7428572177886963, | |
| "eval_runtime": 44.6505, | |
| "eval_samples_per_second": 1.971, | |
| "eval_steps_per_second": 1.971, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 0.6581, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 0.7686, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.6930713057518005, | |
| "eval_runtime": 44.5391, | |
| "eval_samples_per_second": 1.976, | |
| "eval_steps_per_second": 1.976, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 0.7107, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 0.6861, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.6726558804512024, | |
| "eval_runtime": 44.3892, | |
| "eval_samples_per_second": 1.982, | |
| "eval_steps_per_second": 1.982, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 0.6788, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 0.633, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.6600349545478821, | |
| "eval_runtime": 44.5792, | |
| "eval_samples_per_second": 1.974, | |
| "eval_steps_per_second": 1.974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 0.688, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 0.6157, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.6478683948516846, | |
| "eval_runtime": 44.3912, | |
| "eval_samples_per_second": 1.982, | |
| "eval_steps_per_second": 1.982, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 0.6014, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5911, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.6389155387878418, | |
| "eval_runtime": 44.4689, | |
| "eval_samples_per_second": 1.979, | |
| "eval_steps_per_second": 1.979, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 0.5704, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 0.5488, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.6339431405067444, | |
| "eval_runtime": 44.2792, | |
| "eval_samples_per_second": 1.987, | |
| "eval_steps_per_second": 1.987, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 0.5357, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 0.5757, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.6298430562019348, | |
| "eval_runtime": 44.3397, | |
| "eval_samples_per_second": 1.985, | |
| "eval_steps_per_second": 1.985, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 0.4802, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 0.5275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 0.6287050247192383, | |
| "eval_runtime": 44.3397, | |
| "eval_samples_per_second": 1.985, | |
| "eval_steps_per_second": 1.985, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 0.5669, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 0.5597, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.6267156004905701, | |
| "eval_runtime": 44.3452, | |
| "eval_samples_per_second": 1.984, | |
| "eval_steps_per_second": 1.984, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 0.5352, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 0.5408, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 0.6237527132034302, | |
| "eval_runtime": 44.3608, | |
| "eval_samples_per_second": 1.984, | |
| "eval_steps_per_second": 1.984, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 0.5596, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 0.4639, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_loss": 0.6214306354522705, | |
| "eval_runtime": 44.405, | |
| "eval_samples_per_second": 1.982, | |
| "eval_steps_per_second": 1.982, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4747, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 0.524, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_loss": 0.6200035214424133, | |
| "eval_runtime": 44.3045, | |
| "eval_samples_per_second": 1.986, | |
| "eval_steps_per_second": 1.986, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 0.4932, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 0.5016, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_loss": 0.6185718774795532, | |
| "eval_runtime": 44.3925, | |
| "eval_samples_per_second": 1.982, | |
| "eval_steps_per_second": 1.982, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 0.5299, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 0.506, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 0.6176082491874695, | |
| "eval_runtime": 44.3018, | |
| "eval_samples_per_second": 1.986, | |
| "eval_steps_per_second": 1.986, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 0.5275, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 0.4777, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 0.6165757775306702, | |
| "eval_runtime": 44.3157, | |
| "eval_samples_per_second": 1.986, | |
| "eval_steps_per_second": 1.986, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 0.4367, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 0.5212, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_loss": 0.6167304515838623, | |
| "eval_runtime": 44.414, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 1.981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 0.4786, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 0.4695, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "eval_loss": 0.6164081692695618, | |
| "eval_runtime": 44.4173, | |
| "eval_samples_per_second": 1.981, | |
| "eval_steps_per_second": 1.981, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 0.538, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 0.0, | |
| "loss": 0.5674, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_loss": 0.61642986536026, | |
| "eval_runtime": 44.2772, | |
| "eval_samples_per_second": 1.987, | |
| "eval_steps_per_second": 1.987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "step": 40, | |
| "total_flos": 1.0722570250538189e+17, | |
| "train_loss": 0.5893283441662789, | |
| "train_runtime": 3029.6959, | |
| "train_samples_per_second": 0.639, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 40, | |
| "num_train_epochs": 5, | |
| "save_steps": 4, | |
| "total_flos": 1.0722570250538189e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |