| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9997473471450227, | |
| "global_step": 7915, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.6880803486829639, | |
| "eval_loss": 0.6034769415855408, | |
| "eval_runtime": 15.5577, | |
| "eval_samples_per_second": 339.188, | |
| "eval_steps_per_second": 10.606, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.8736735725113694e-05, | |
| "loss": 0.621, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.7134735645252984, | |
| "eval_loss": 0.5855737328529358, | |
| "eval_runtime": 15.4335, | |
| "eval_samples_per_second": 341.918, | |
| "eval_steps_per_second": 10.691, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.7197271176805002, | |
| "eval_loss": 0.5775426030158997, | |
| "eval_runtime": 15.4427, | |
| "eval_samples_per_second": 341.716, | |
| "eval_steps_per_second": 10.685, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.747347145022739e-05, | |
| "loss": 0.6011, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.7199166192912639, | |
| "eval_loss": 0.573106050491333, | |
| "eval_runtime": 15.5167, | |
| "eval_samples_per_second": 340.085, | |
| "eval_steps_per_second": 10.634, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.6210207175341085e-05, | |
| "loss": 0.5993, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.719348114458973, | |
| "eval_loss": 0.575564444065094, | |
| "eval_runtime": 15.5001, | |
| "eval_samples_per_second": 340.45, | |
| "eval_steps_per_second": 10.645, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.734697744930832, | |
| "eval_loss": 0.5668568015098572, | |
| "eval_runtime": 16.1562, | |
| "eval_samples_per_second": 326.623, | |
| "eval_steps_per_second": 10.213, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.4946942900454776e-05, | |
| "loss": 0.5901, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.7394352851999242, | |
| "eval_loss": 0.5582404732704163, | |
| "eval_runtime": 15.7671, | |
| "eval_samples_per_second": 334.684, | |
| "eval_steps_per_second": 10.465, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.7470153496304719, | |
| "eval_loss": 0.5583205819129944, | |
| "eval_runtime": 15.5702, | |
| "eval_samples_per_second": 338.917, | |
| "eval_steps_per_second": 10.597, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.368367862556847e-05, | |
| "loss": 0.578, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.7436043206367254, | |
| "eval_loss": 0.5834795236587524, | |
| "eval_runtime": 15.6308, | |
| "eval_samples_per_second": 337.602, | |
| "eval_steps_per_second": 10.556, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.242041435068217e-05, | |
| "loss": 0.579, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.7220011370096646, | |
| "eval_loss": 0.5708434581756592, | |
| "eval_runtime": 15.582, | |
| "eval_samples_per_second": 338.66, | |
| "eval_steps_per_second": 10.589, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.762933484934622, | |
| "eval_loss": 0.5381360650062561, | |
| "eval_runtime": 15.5571, | |
| "eval_samples_per_second": 339.201, | |
| "eval_steps_per_second": 10.606, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.115715007579586e-05, | |
| "loss": 0.5735, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.7642599962099678, | |
| "eval_loss": 0.539585530757904, | |
| "eval_runtime": 15.6069, | |
| "eval_samples_per_second": 338.12, | |
| "eval_steps_per_second": 10.572, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.7652075042637863, | |
| "eval_loss": 0.5309613347053528, | |
| "eval_runtime": 15.6636, | |
| "eval_samples_per_second": 336.896, | |
| "eval_steps_per_second": 10.534, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.989388580090955e-05, | |
| "loss": 0.5534, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.7638809929884404, | |
| "eval_loss": 0.5623990297317505, | |
| "eval_runtime": 15.5126, | |
| "eval_samples_per_second": 340.174, | |
| "eval_steps_per_second": 10.636, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.863314805457302e-05, | |
| "loss": 0.4267, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.7400037900322153, | |
| "eval_loss": 0.611989438533783, | |
| "eval_runtime": 15.5686, | |
| "eval_samples_per_second": 338.951, | |
| "eval_steps_per_second": 10.598, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_accuracy": 0.7657760090960773, | |
| "eval_loss": 0.5793063640594482, | |
| "eval_runtime": 15.5802, | |
| "eval_samples_per_second": 338.7, | |
| "eval_steps_per_second": 10.59, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.736988377968671e-05, | |
| "loss": 0.4283, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_accuracy": 0.7633124881561494, | |
| "eval_loss": 0.5923583507537842, | |
| "eval_runtime": 15.5465, | |
| "eval_samples_per_second": 339.432, | |
| "eval_steps_per_second": 10.613, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.7619859768808035, | |
| "eval_loss": 0.5652284622192383, | |
| "eval_runtime": 15.5292, | |
| "eval_samples_per_second": 339.811, | |
| "eval_steps_per_second": 10.625, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3.61066195048004e-05, | |
| "loss": 0.4306, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.7589539511085844, | |
| "eval_loss": 0.571613073348999, | |
| "eval_runtime": 15.6239, | |
| "eval_samples_per_second": 337.753, | |
| "eval_steps_per_second": 10.561, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.48433552299141e-05, | |
| "loss": 0.4268, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.768429031646769, | |
| "eval_loss": 0.5530590415000916, | |
| "eval_runtime": 15.5281, | |
| "eval_samples_per_second": 339.836, | |
| "eval_steps_per_second": 10.626, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_accuracy": 0.7595224559408755, | |
| "eval_loss": 0.5949699282646179, | |
| "eval_runtime": 15.5065, | |
| "eval_samples_per_second": 340.31, | |
| "eval_steps_per_second": 10.641, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.3582617483577566e-05, | |
| "loss": 0.4296, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.7748720864127345, | |
| "eval_loss": 0.5415990352630615, | |
| "eval_runtime": 15.6991, | |
| "eval_samples_per_second": 336.134, | |
| "eval_steps_per_second": 10.51, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.7686185332575327, | |
| "eval_loss": 0.5780544281005859, | |
| "eval_runtime": 15.5645, | |
| "eval_samples_per_second": 339.04, | |
| "eval_steps_per_second": 10.601, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.231935320869126e-05, | |
| "loss": 0.43, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_accuracy": 0.7744930831912071, | |
| "eval_loss": 0.5756574869155884, | |
| "eval_runtime": 15.5129, | |
| "eval_samples_per_second": 340.168, | |
| "eval_steps_per_second": 10.636, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.105608893380496e-05, | |
| "loss": 0.4317, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.7761985976880803, | |
| "eval_loss": 0.5252366065979004, | |
| "eval_runtime": 15.6912, | |
| "eval_samples_per_second": 336.304, | |
| "eval_steps_per_second": 10.515, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.7835891605078643, | |
| "eval_loss": 0.5250930190086365, | |
| "eval_runtime": 15.5911, | |
| "eval_samples_per_second": 338.462, | |
| "eval_steps_per_second": 10.583, | |
| "step": 7800 | |
| } | |
| ], | |
| "max_steps": 19790, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.69413405769332e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |