| { | |
| "best_metric": 0.10140984505414963, | |
| "best_model_checkpoint": "./beans_outputs/checkpoint-650", | |
| "epoch": 5.0, | |
| "global_step": 650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0003076923076923077, | |
| "loss": 1.0889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006153846153846154, | |
| "loss": 1.0728, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0009230769230769232, | |
| "loss": 1.0675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0012307692307692308, | |
| "loss": 0.9244, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0015384615384615387, | |
| "loss": 0.8006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0018461538461538463, | |
| "loss": 0.7104, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0019996395276708854, | |
| "loss": 0.5492, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00199675730813421, | |
| "loss": 0.438, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0019910011792459085, | |
| "loss": 0.5676, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0019823877374156645, | |
| "loss": 0.4354, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.001970941817426052, | |
| "loss": 0.3349, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0019566964208274254, | |
| "loss": 0.7846, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0019396926207859084, | |
| "loss": 0.9524, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8646616541353384, | |
| "eval_loss": 0.28258681297302246, | |
| "eval_runtime": 0.9861, | |
| "eval_samples_per_second": 134.87, | |
| "eval_steps_per_second": 17.239, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0019199794436588243, | |
| "loss": 0.5461, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0018976137276390142, | |
| "loss": 0.7203, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0018726599588756144, | |
| "loss": 0.4123, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.001845190085543795, | |
| "loss": 0.5495, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0018152833103995444, | |
| "loss": 0.4613, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0017830258624176223, | |
| "loss": 0.4326, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.001748510748171101, | |
| "loss": 0.3239, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0017118374836693406, | |
| "loss": 0.5905, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0016731118074275702, | |
| "loss": 0.5519, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0016324453755953772, | |
| "loss": 0.2935, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.001589955440023123, | |
| "loss": 0.3501, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0015457645101945045, | |
| "loss": 0.4842, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0015, | |
| "loss": 0.3596, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9022556390977443, | |
| "eval_loss": 0.22159069776535034, | |
| "eval_runtime": 0.9658, | |
| "eval_samples_per_second": 137.712, | |
| "eval_steps_per_second": 17.602, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0014527938603696375, | |
| "loss": 0.578, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0014042821988243049, | |
| "loss": 0.3116, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0013546048870425357, | |
| "loss": 0.3378, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0013039051575742468, | |
| "loss": 0.3679, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.0012523291908642217, | |
| "loss": 0.38, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0012000256937760446, | |
| "loss": 0.3309, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.001147145470831716, | |
| "loss": 0.2248, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0010938409894031794, | |
| "loss": 0.3261, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0010402659401094153, | |
| "loss": 0.2697, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.0009865747936866028, | |
| "loss": 0.3062, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.0009329223556089975, | |
| "loss": 0.3551, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.0008794633197446771, | |
| "loss": 0.2783, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0008263518223330697, | |
| "loss": 0.2419, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9473684210526315, | |
| "eval_loss": 0.13237899541854858, | |
| "eval_runtime": 0.9783, | |
| "eval_samples_per_second": 135.946, | |
| "eval_steps_per_second": 17.377, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0007737409975702781, | |
| "loss": 0.2691, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.0007217825360835474, | |
| "loss": 0.3115, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0006706262475679205, | |
| "loss": 0.2924, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0006204196288461038, | |
| "loss": 0.2037, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.0005713074385969457, | |
| "loss": 0.2782, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.0005234312799786921, | |
| "loss": 0.1141, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.00047692919235042255, | |
| "loss": 0.504, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 0.0004319352532688443, | |
| "loss": 0.1391, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0003885791919079877, | |
| "loss": 0.4455, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.0003469860150164151, | |
| "loss": 0.1956, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00030727564649040063, | |
| "loss": 0.2292, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.00026956258160229697, | |
| "loss": 0.2151, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0002339555568810221, | |
| "loss": 0.3248, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9699248120300752, | |
| "eval_loss": 0.11242649704217911, | |
| "eval_runtime": 0.9749, | |
| "eval_samples_per_second": 136.426, | |
| "eval_steps_per_second": 17.438, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.00020055723659649904, | |
| "loss": 0.0799, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.00016946391675198836, | |
| "loss": 0.1854, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00014076524743778318, | |
| "loss": 0.2312, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 0.0001145439743467902, | |
| "loss": 0.1739, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 9.08757001972762e-05, | |
| "loss": 0.1797, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 6.98286667506618e-05, | |
| "loss": 0.1376, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 5.146355805285452e-05, | |
| "loss": 0.11, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 3.5833325466437696e-05, | |
| "loss": 0.1737, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.2983034998182995e-05, | |
| "loss": 0.1018, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.2949737362087154e-05, | |
| "loss": 0.2031, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 5.7623611525721155e-06, | |
| "loss": 0.1868, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 1.4416294358582382e-06, | |
| "loss": 0.1781, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1557, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9699248120300752, | |
| "eval_loss": 0.10140984505414963, | |
| "eval_runtime": 1.0018, | |
| "eval_samples_per_second": 132.757, | |
| "eval_steps_per_second": 16.969, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 650, | |
| "total_flos": 1.0979660327860224e+17, | |
| "train_loss": 0.3958505061039558, | |
| "train_runtime": 122.678, | |
| "train_samples_per_second": 42.143, | |
| "train_steps_per_second": 5.298 | |
| } | |
| ], | |
| "max_steps": 650, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.0979660327860224e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |