| { | |
| "best_metric": 1.2660315036773682, | |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-100", | |
| "epoch": 4.310344827586207, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001931034482758621, | |
| "loss": 1.7999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.25555555555555554, | |
| "eval_loss": 1.9382611513137817, | |
| "eval_runtime": 128.8894, | |
| "eval_samples_per_second": 2.095, | |
| "eval_steps_per_second": 0.264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00018620689655172415, | |
| "loss": 1.5424, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.4148148148148148, | |
| "eval_loss": 1.5738633871078491, | |
| "eval_runtime": 7.0871, | |
| "eval_samples_per_second": 38.097, | |
| "eval_steps_per_second": 4.797, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001793103448275862, | |
| "loss": 1.257, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.5777777777777777, | |
| "eval_loss": 1.3710002899169922, | |
| "eval_runtime": 8.6728, | |
| "eval_samples_per_second": 31.132, | |
| "eval_steps_per_second": 3.92, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00017241379310344826, | |
| "loss": 1.0721, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.5074074074074074, | |
| "eval_loss": 1.4735559225082397, | |
| "eval_runtime": 7.1381, | |
| "eval_samples_per_second": 37.825, | |
| "eval_steps_per_second": 4.763, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00016551724137931035, | |
| "loss": 1.1026, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.6370370370370371, | |
| "eval_loss": 1.2928471565246582, | |
| "eval_runtime": 8.3556, | |
| "eval_samples_per_second": 32.314, | |
| "eval_steps_per_second": 4.069, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00015862068965517243, | |
| "loss": 0.9359, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.6074074074074074, | |
| "eval_loss": 1.2788481712341309, | |
| "eval_runtime": 7.1042, | |
| "eval_samples_per_second": 38.006, | |
| "eval_steps_per_second": 4.786, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00015172413793103449, | |
| "loss": 0.7, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.6592592592592592, | |
| "eval_loss": 1.2249455451965332, | |
| "eval_runtime": 7.5614, | |
| "eval_samples_per_second": 35.708, | |
| "eval_steps_per_second": 4.497, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00014482758620689657, | |
| "loss": 0.5367, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.6222222222222222, | |
| "eval_loss": 1.3300864696502686, | |
| "eval_runtime": 7.852, | |
| "eval_samples_per_second": 34.386, | |
| "eval_steps_per_second": 4.33, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00013793103448275863, | |
| "loss": 0.6017, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.2042837142944336, | |
| "eval_runtime": 8.2241, | |
| "eval_samples_per_second": 32.83, | |
| "eval_steps_per_second": 4.134, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00013103448275862068, | |
| "loss": 0.6007, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_accuracy": 0.6703703703703704, | |
| "eval_loss": 1.2660315036773682, | |
| "eval_runtime": 8.6405, | |
| "eval_samples_per_second": 31.248, | |
| "eval_steps_per_second": 3.935, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00012413793103448277, | |
| "loss": 0.6083, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_loss": 1.2744337320327759, | |
| "eval_runtime": 8.1117, | |
| "eval_samples_per_second": 33.285, | |
| "eval_steps_per_second": 4.191, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.00011724137931034482, | |
| "loss": 0.4428, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.6481481481481481, | |
| "eval_loss": 1.3982332944869995, | |
| "eval_runtime": 9.593, | |
| "eval_samples_per_second": 28.145, | |
| "eval_steps_per_second": 3.544, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0001103448275862069, | |
| "loss": 0.3967, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_loss": 1.2987446784973145, | |
| "eval_runtime": 7.0774, | |
| "eval_samples_per_second": 38.15, | |
| "eval_steps_per_second": 4.804, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00010344827586206898, | |
| "loss": 0.3308, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 1.3469077348709106, | |
| "eval_runtime": 7.0247, | |
| "eval_samples_per_second": 38.436, | |
| "eval_steps_per_second": 4.84, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.655172413793105e-05, | |
| "loss": 0.2844, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_accuracy": 0.6962962962962963, | |
| "eval_loss": 1.2884557247161865, | |
| "eval_runtime": 9.6127, | |
| "eval_samples_per_second": 28.088, | |
| "eval_steps_per_second": 3.537, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 8.96551724137931e-05, | |
| "loss": 0.2313, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_loss": 1.4098496437072754, | |
| "eval_runtime": 8.6491, | |
| "eval_samples_per_second": 31.217, | |
| "eval_steps_per_second": 3.931, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 8.275862068965517e-05, | |
| "loss": 0.2378, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_loss": 1.4552189111709595, | |
| "eval_runtime": 8.3406, | |
| "eval_samples_per_second": 32.372, | |
| "eval_steps_per_second": 4.076, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 7.586206896551724e-05, | |
| "loss": 0.1724, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_loss": 1.3009414672851562, | |
| "eval_runtime": 7.8433, | |
| "eval_samples_per_second": 34.424, | |
| "eval_steps_per_second": 4.335, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 0.1712, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.3433070182800293, | |
| "eval_runtime": 7.412, | |
| "eval_samples_per_second": 36.427, | |
| "eval_steps_per_second": 4.587, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.206896551724138e-05, | |
| "loss": 0.1521, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.4084450006484985, | |
| "eval_runtime": 7.1569, | |
| "eval_samples_per_second": 37.726, | |
| "eval_steps_per_second": 4.751, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 5.517241379310345e-05, | |
| "loss": 0.1178, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_accuracy": 0.6925925925925925, | |
| "eval_loss": 1.4383904933929443, | |
| "eval_runtime": 15.5468, | |
| "eval_samples_per_second": 17.367, | |
| "eval_steps_per_second": 2.187, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 4.827586206896552e-05, | |
| "loss": 0.0968, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.44044029712677, | |
| "eval_runtime": 8.8794, | |
| "eval_samples_per_second": 30.407, | |
| "eval_steps_per_second": 3.829, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.1471, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.4447485208511353, | |
| "eval_runtime": 9.2898, | |
| "eval_samples_per_second": 29.064, | |
| "eval_steps_per_second": 3.66, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 0.1114, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.4719408750534058, | |
| "eval_runtime": 12.6934, | |
| "eval_samples_per_second": 21.271, | |
| "eval_steps_per_second": 2.679, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 0.0967, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_accuracy": 0.6925925925925925, | |
| "eval_loss": 1.4684562683105469, | |
| "eval_runtime": 7.9455, | |
| "eval_samples_per_second": 33.982, | |
| "eval_steps_per_second": 4.279, | |
| "step": 250 | |
| } | |
| ], | |
| "max_steps": 290, | |
| "num_train_epochs": 5, | |
| "total_flos": 3.059548271717253e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |