| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-9", | |
| "epoch": 39.857142857142854, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.9574468085106383, | |
| "eval_loss": 0.14558981359004974, | |
| "eval_runtime": 3.0797, | |
| "eval_samples_per_second": 15.261, | |
| "eval_steps_per_second": 0.649, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.08996303379535675, | |
| "eval_runtime": 3.5219, | |
| "eval_samples_per_second": 13.345, | |
| "eval_steps_per_second": 0.568, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.062098320573568344, | |
| "eval_runtime": 3.3535, | |
| "eval_samples_per_second": 14.015, | |
| "eval_steps_per_second": 0.596, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.06347361207008362, | |
| "eval_runtime": 3.0769, | |
| "eval_samples_per_second": 15.275, | |
| "eval_steps_per_second": 0.65, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.05354984849691391, | |
| "eval_runtime": 3.0814, | |
| "eval_samples_per_second": 15.253, | |
| "eval_steps_per_second": 0.649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_accuracy": 0.9574468085106383, | |
| "eval_loss": 0.06630665063858032, | |
| "eval_runtime": 3.3475, | |
| "eval_samples_per_second": 14.04, | |
| "eval_steps_per_second": 0.597, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.3029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.04919619858264923, | |
| "eval_runtime": 3.3837, | |
| "eval_samples_per_second": 13.89, | |
| "eval_steps_per_second": 0.591, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.05591897666454315, | |
| "eval_runtime": 3.0774, | |
| "eval_samples_per_second": 15.273, | |
| "eval_steps_per_second": 0.65, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.0664142519235611, | |
| "eval_runtime": 3.4113, | |
| "eval_samples_per_second": 13.778, | |
| "eval_steps_per_second": 0.586, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.06434692442417145, | |
| "eval_runtime": 3.3792, | |
| "eval_samples_per_second": 13.908, | |
| "eval_steps_per_second": 0.592, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.05577840283513069, | |
| "eval_runtime": 3.3341, | |
| "eval_samples_per_second": 14.097, | |
| "eval_steps_per_second": 0.6, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03647231683135033, | |
| "eval_runtime": 3.076, | |
| "eval_samples_per_second": 15.28, | |
| "eval_steps_per_second": 0.65, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.043758317828178406, | |
| "eval_runtime": 3.3173, | |
| "eval_samples_per_second": 14.168, | |
| "eval_steps_per_second": 0.603, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2212, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.045602452009916306, | |
| "eval_runtime": 3.3351, | |
| "eval_samples_per_second": 14.093, | |
| "eval_steps_per_second": 0.6, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.040249306708574295, | |
| "eval_runtime": 3.0799, | |
| "eval_samples_per_second": 15.26, | |
| "eval_steps_per_second": 0.649, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.03505050763487816, | |
| "eval_runtime": 3.2192, | |
| "eval_samples_per_second": 14.6, | |
| "eval_steps_per_second": 0.621, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.03594408929347992, | |
| "eval_runtime": 3.2905, | |
| "eval_samples_per_second": 14.284, | |
| "eval_steps_per_second": 0.608, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.04266700521111488, | |
| "eval_runtime": 3.4643, | |
| "eval_samples_per_second": 13.567, | |
| "eval_steps_per_second": 0.577, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.9574468085106383, | |
| "eval_loss": 0.04897385463118553, | |
| "eval_runtime": 3.0853, | |
| "eval_samples_per_second": 15.234, | |
| "eval_steps_per_second": 0.648, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.186, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.039550021290779114, | |
| "eval_runtime": 3.1131, | |
| "eval_samples_per_second": 15.097, | |
| "eval_steps_per_second": 0.642, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.9787234042553191, | |
| "eval_loss": 0.029103364795446396, | |
| "eval_runtime": 3.3495, | |
| "eval_samples_per_second": 14.032, | |
| "eval_steps_per_second": 0.597, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 21.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.015161500312387943, | |
| "eval_runtime": 3.3942, | |
| "eval_samples_per_second": 13.847, | |
| "eval_steps_per_second": 0.589, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.014185278676450253, | |
| "eval_runtime": 3.0833, | |
| "eval_samples_per_second": 15.244, | |
| "eval_steps_per_second": 0.649, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 23.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01784444786608219, | |
| "eval_runtime": 3.3662, | |
| "eval_samples_per_second": 13.962, | |
| "eval_steps_per_second": 0.594, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.017597978934645653, | |
| "eval_runtime": 3.4018, | |
| "eval_samples_per_second": 13.816, | |
| "eval_steps_per_second": 0.588, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.015114851295948029, | |
| "eval_runtime": 3.1308, | |
| "eval_samples_per_second": 15.012, | |
| "eval_steps_per_second": 0.639, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1751, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.011016697622835636, | |
| "eval_runtime": 3.366, | |
| "eval_samples_per_second": 13.963, | |
| "eval_steps_per_second": 0.594, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.012051686644554138, | |
| "eval_runtime": 3.3303, | |
| "eval_samples_per_second": 14.113, | |
| "eval_steps_per_second": 0.601, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01581379771232605, | |
| "eval_runtime": 3.3324, | |
| "eval_samples_per_second": 14.104, | |
| "eval_steps_per_second": 0.6, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.02497912012040615, | |
| "eval_runtime": 3.1285, | |
| "eval_samples_per_second": 15.023, | |
| "eval_steps_per_second": 0.639, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.02920253947377205, | |
| "eval_runtime": 3.3575, | |
| "eval_samples_per_second": 13.999, | |
| "eval_steps_per_second": 0.596, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 31.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.025970185175538063, | |
| "eval_runtime": 3.3707, | |
| "eval_samples_per_second": 13.944, | |
| "eval_steps_per_second": 0.593, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.020575150847434998, | |
| "eval_runtime": 3.152, | |
| "eval_samples_per_second": 14.911, | |
| "eval_steps_per_second": 0.635, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 33.29, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1614, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.018124328926205635, | |
| "eval_runtime": 3.4042, | |
| "eval_samples_per_second": 13.807, | |
| "eval_steps_per_second": 0.588, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.017009548842906952, | |
| "eval_runtime": 3.4107, | |
| "eval_samples_per_second": 13.78, | |
| "eval_steps_per_second": 0.586, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 35.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0170438252389431, | |
| "eval_runtime": 3.0972, | |
| "eval_samples_per_second": 15.175, | |
| "eval_steps_per_second": 0.646, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.017739199101924896, | |
| "eval_runtime": 3.4084, | |
| "eval_samples_per_second": 13.789, | |
| "eval_steps_per_second": 0.587, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.018777411431074142, | |
| "eval_runtime": 3.4191, | |
| "eval_samples_per_second": 13.746, | |
| "eval_steps_per_second": 0.585, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 38.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01889665052294731, | |
| "eval_runtime": 3.0931, | |
| "eval_samples_per_second": 15.195, | |
| "eval_steps_per_second": 0.647, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.1483, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.018766822293400764, | |
| "eval_runtime": 3.369, | |
| "eval_samples_per_second": 13.951, | |
| "eval_steps_per_second": 0.594, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "step": 120, | |
| "total_flos": 4.138238964234977e+17, | |
| "train_loss": 0.19912103215853375, | |
| "train_runtime": 1848.5966, | |
| "train_samples_per_second": 9.023, | |
| "train_steps_per_second": 0.065 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 40, | |
| "total_flos": 4.138238964234977e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |