| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.861111111111112e-05, | |
| "loss": 2.0531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.13333334028720856, | |
| "eval_loss": 2.159055471420288, | |
| "eval_runtime": 309.1055, | |
| "eval_samples_per_second": 4.659, | |
| "eval_steps_per_second": 1.165, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.722222222222223e-05, | |
| "loss": 2.1794, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.21111111342906952, | |
| "eval_loss": 2.074418783187866, | |
| "eval_runtime": 308.7598, | |
| "eval_samples_per_second": 4.664, | |
| "eval_steps_per_second": 1.166, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.583333333333334e-05, | |
| "loss": 2.0726, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_accuracy": 0.20277777314186096, | |
| "eval_loss": 2.005201578140259, | |
| "eval_runtime": 309.0551, | |
| "eval_samples_per_second": 4.659, | |
| "eval_steps_per_second": 1.165, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.444444444444444e-05, | |
| "loss": 1.9514, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.22430555522441864, | |
| "eval_loss": 1.9686204195022583, | |
| "eval_runtime": 310.3523, | |
| "eval_samples_per_second": 4.64, | |
| "eval_steps_per_second": 1.16, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.305555555555556e-05, | |
| "loss": 1.8919, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.22708334028720856, | |
| "eval_loss": 2.052751064300537, | |
| "eval_runtime": 307.799, | |
| "eval_samples_per_second": 4.678, | |
| "eval_steps_per_second": 1.17, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.166666666666667e-05, | |
| "loss": 1.9575, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.17916665971279144, | |
| "eval_loss": 2.038191080093384, | |
| "eval_runtime": 307.6143, | |
| "eval_samples_per_second": 4.681, | |
| "eval_steps_per_second": 1.17, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.027777777777779e-05, | |
| "loss": 1.9836, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.2701388895511627, | |
| "eval_loss": 1.7942837476730347, | |
| "eval_runtime": 307.309, | |
| "eval_samples_per_second": 4.686, | |
| "eval_steps_per_second": 1.171, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 1.9651, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.2819444537162781, | |
| "eval_loss": 1.7969180345535278, | |
| "eval_runtime": 310.9128, | |
| "eval_samples_per_second": 4.632, | |
| "eval_steps_per_second": 1.158, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.75e-05, | |
| "loss": 1.9382, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.27986112236976624, | |
| "eval_loss": 1.8196858167648315, | |
| "eval_runtime": 307.5957, | |
| "eval_samples_per_second": 4.681, | |
| "eval_steps_per_second": 1.17, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.611111111111112e-05, | |
| "loss": 1.8197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.18958333134651184, | |
| "eval_loss": 1.9207282066345215, | |
| "eval_runtime": 308.4662, | |
| "eval_samples_per_second": 4.668, | |
| "eval_steps_per_second": 1.167, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.472222222222222e-05, | |
| "loss": 1.7721, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.2881944477558136, | |
| "eval_loss": 1.7433712482452393, | |
| "eval_runtime": 309.686, | |
| "eval_samples_per_second": 4.65, | |
| "eval_steps_per_second": 1.162, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.8501, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.24861110746860504, | |
| "eval_loss": 1.7375705242156982, | |
| "eval_runtime": 305.6275, | |
| "eval_samples_per_second": 4.712, | |
| "eval_steps_per_second": 1.178, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.194444444444445e-05, | |
| "loss": 1.8136, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.3291666805744171, | |
| "eval_loss": 1.6771501302719116, | |
| "eval_runtime": 311.0209, | |
| "eval_samples_per_second": 4.63, | |
| "eval_steps_per_second": 1.157, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.055555555555556e-05, | |
| "loss": 1.672, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.29027777910232544, | |
| "eval_loss": 1.6961910724639893, | |
| "eval_runtime": 308.399, | |
| "eval_samples_per_second": 4.669, | |
| "eval_steps_per_second": 1.167, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.916666666666666e-05, | |
| "loss": 1.7787, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.3499999940395355, | |
| "eval_loss": 1.654746174812317, | |
| "eval_runtime": 306.8392, | |
| "eval_samples_per_second": 4.693, | |
| "eval_steps_per_second": 1.173, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 1.7144, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.36597222089767456, | |
| "eval_loss": 1.6828863620758057, | |
| "eval_runtime": 306.6648, | |
| "eval_samples_per_second": 4.696, | |
| "eval_steps_per_second": 1.174, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.638888888888889e-05, | |
| "loss": 1.558, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.3430555462837219, | |
| "eval_loss": 1.6398437023162842, | |
| "eval_runtime": 312.3754, | |
| "eval_samples_per_second": 4.61, | |
| "eval_steps_per_second": 1.152, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5197, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.3444444537162781, | |
| "eval_loss": 1.6192543506622314, | |
| "eval_runtime": 308.0294, | |
| "eval_samples_per_second": 4.675, | |
| "eval_steps_per_second": 1.169, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.361111111111111e-05, | |
| "loss": 1.5088, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.37708333134651184, | |
| "eval_loss": 1.5085088014602661, | |
| "eval_runtime": 305.6283, | |
| "eval_samples_per_second": 4.712, | |
| "eval_steps_per_second": 1.178, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 1.7442, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.43263888359069824, | |
| "eval_loss": 1.4439728260040283, | |
| "eval_runtime": 305.4203, | |
| "eval_samples_per_second": 4.715, | |
| "eval_steps_per_second": 1.179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.083333333333334e-05, | |
| "loss": 1.6021, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.5138888955116272, | |
| "eval_loss": 1.3366789817810059, | |
| "eval_runtime": 307.6606, | |
| "eval_samples_per_second": 4.68, | |
| "eval_steps_per_second": 1.17, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 1.607, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.4756944477558136, | |
| "eval_loss": 1.400604248046875, | |
| "eval_runtime": 305.6563, | |
| "eval_samples_per_second": 4.711, | |
| "eval_steps_per_second": 1.178, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.805555555555556e-05, | |
| "loss": 1.4012, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.5361111164093018, | |
| "eval_loss": 1.2899019718170166, | |
| "eval_runtime": 305.6072, | |
| "eval_samples_per_second": 4.712, | |
| "eval_steps_per_second": 1.178, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.4094, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.5868055820465088, | |
| "eval_loss": 1.1848715543746948, | |
| "eval_runtime": 310.5577, | |
| "eval_samples_per_second": 4.637, | |
| "eval_steps_per_second": 1.159, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.527777777777778e-05, | |
| "loss": 1.3252, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.5326389074325562, | |
| "eval_loss": 1.2207249402999878, | |
| "eval_runtime": 305.3735, | |
| "eval_samples_per_second": 4.716, | |
| "eval_steps_per_second": 1.179, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.388888888888888e-05, | |
| "loss": 1.2939, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.5722222328186035, | |
| "eval_loss": 1.127318263053894, | |
| "eval_runtime": 306.1632, | |
| "eval_samples_per_second": 4.703, | |
| "eval_steps_per_second": 1.176, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.25e-05, | |
| "loss": 1.1591, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_accuracy": 0.6090278029441833, | |
| "eval_loss": 1.0614306926727295, | |
| "eval_runtime": 306.437, | |
| "eval_samples_per_second": 4.699, | |
| "eval_steps_per_second": 1.175, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 1.421, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.5416666865348816, | |
| "eval_loss": 1.2863346338272095, | |
| "eval_runtime": 306.6206, | |
| "eval_samples_per_second": 4.696, | |
| "eval_steps_per_second": 1.174, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.972222222222223e-05, | |
| "loss": 1.3071, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.5666666626930237, | |
| "eval_loss": 1.1455507278442383, | |
| "eval_runtime": 308.2962, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 1.168, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 1.1463, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.6270833611488342, | |
| "eval_loss": 1.0083465576171875, | |
| "eval_runtime": 306.6088, | |
| "eval_samples_per_second": 4.697, | |
| "eval_steps_per_second": 1.174, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.6944444444444445e-05, | |
| "loss": 1.149, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.6000000238418579, | |
| "eval_loss": 1.039494276046753, | |
| "eval_runtime": 307.8298, | |
| "eval_samples_per_second": 4.678, | |
| "eval_steps_per_second": 1.169, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 1.0853, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.6319444179534912, | |
| "eval_loss": 0.9475428462028503, | |
| "eval_runtime": 310.5495, | |
| "eval_samples_per_second": 4.637, | |
| "eval_steps_per_second": 1.159, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.4166666666666664e-05, | |
| "loss": 1.0467, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.6618055701255798, | |
| "eval_loss": 0.938763439655304, | |
| "eval_runtime": 305.3429, | |
| "eval_samples_per_second": 4.716, | |
| "eval_steps_per_second": 1.179, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.2777777777777784e-05, | |
| "loss": 1.2562, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.5874999761581421, | |
| "eval_loss": 1.058403491973877, | |
| "eval_runtime": 309.582, | |
| "eval_samples_per_second": 4.651, | |
| "eval_steps_per_second": 1.163, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.138888888888889e-05, | |
| "loss": 1.0267, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.6819444298744202, | |
| "eval_loss": 0.9059543013572693, | |
| "eval_runtime": 308.1955, | |
| "eval_samples_per_second": 4.672, | |
| "eval_steps_per_second": 1.168, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7126, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.6243055462837219, | |
| "eval_loss": 0.9829866290092468, | |
| "eval_runtime": 309.2257, | |
| "eval_samples_per_second": 4.657, | |
| "eval_steps_per_second": 1.164, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.0441, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.675000011920929, | |
| "eval_loss": 0.909841001033783, | |
| "eval_runtime": 305.6628, | |
| "eval_samples_per_second": 4.711, | |
| "eval_steps_per_second": 1.178, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.0524, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.6458333134651184, | |
| "eval_loss": 0.954737663269043, | |
| "eval_runtime": 308.967, | |
| "eval_samples_per_second": 4.661, | |
| "eval_steps_per_second": 1.165, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.9355, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.6958333253860474, | |
| "eval_loss": 0.7970058917999268, | |
| "eval_runtime": 306.7636, | |
| "eval_samples_per_second": 4.694, | |
| "eval_steps_per_second": 1.174, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.0505, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.6777777671813965, | |
| "eval_loss": 0.8817840814590454, | |
| "eval_runtime": 306.413, | |
| "eval_samples_per_second": 4.7, | |
| "eval_steps_per_second": 1.175, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.7672, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.7041666507720947, | |
| "eval_loss": 0.8178666830062866, | |
| "eval_runtime": 306.6048, | |
| "eval_samples_per_second": 4.697, | |
| "eval_steps_per_second": 1.174, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.9586, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.761805534362793, | |
| "eval_loss": 0.7114083766937256, | |
| "eval_runtime": 307.286, | |
| "eval_samples_per_second": 4.686, | |
| "eval_steps_per_second": 1.172, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 1.0177, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_accuracy": 0.7590277791023254, | |
| "eval_loss": 0.7004179954528809, | |
| "eval_runtime": 305.701, | |
| "eval_samples_per_second": 4.71, | |
| "eval_steps_per_second": 1.178, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7575, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.7888888716697693, | |
| "eval_loss": 0.6390997171401978, | |
| "eval_runtime": 305.5003, | |
| "eval_samples_per_second": 4.714, | |
| "eval_steps_per_second": 1.178, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.7834, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.7604166865348816, | |
| "eval_loss": 0.6542982459068298, | |
| "eval_runtime": 306.1149, | |
| "eval_samples_per_second": 4.704, | |
| "eval_steps_per_second": 1.176, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.644, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.793055534362793, | |
| "eval_loss": 0.6248801946640015, | |
| "eval_runtime": 306.8175, | |
| "eval_samples_per_second": 4.693, | |
| "eval_steps_per_second": 1.173, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.7928, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.7715277671813965, | |
| "eval_loss": 0.6328664422035217, | |
| "eval_runtime": 308.2672, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 1.168, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7773, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_accuracy": 0.8125, | |
| "eval_loss": 0.5492955446243286, | |
| "eval_runtime": 305.9298, | |
| "eval_samples_per_second": 4.707, | |
| "eval_steps_per_second": 1.177, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.6163, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.7958333492279053, | |
| "eval_loss": 0.5877541303634644, | |
| "eval_runtime": 306.2121, | |
| "eval_samples_per_second": 4.703, | |
| "eval_steps_per_second": 1.176, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.6773, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.8222222328186035, | |
| "eval_loss": 0.5475648641586304, | |
| "eval_runtime": 306.3418, | |
| "eval_samples_per_second": 4.701, | |
| "eval_steps_per_second": 1.175, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.7042, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.8159722089767456, | |
| "eval_loss": 0.5389293432235718, | |
| "eval_runtime": 312.5784, | |
| "eval_samples_per_second": 4.607, | |
| "eval_steps_per_second": 1.152, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6488, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.8180555701255798, | |
| "eval_loss": 0.5231082439422607, | |
| "eval_runtime": 307.67, | |
| "eval_samples_per_second": 4.68, | |
| "eval_steps_per_second": 1.17, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.7165, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.800000011920929, | |
| "eval_loss": 0.567889928817749, | |
| "eval_runtime": 307.7956, | |
| "eval_samples_per_second": 4.678, | |
| "eval_steps_per_second": 1.17, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.716, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.8340277671813965, | |
| "eval_loss": 0.49685245752334595, | |
| "eval_runtime": 308.7124, | |
| "eval_samples_per_second": 4.665, | |
| "eval_steps_per_second": 1.166, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.8907, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.856249988079071, | |
| "eval_loss": 0.45114219188690186, | |
| "eval_runtime": 308.861, | |
| "eval_samples_per_second": 4.662, | |
| "eval_steps_per_second": 1.166, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.7081, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.8423610925674438, | |
| "eval_loss": 0.4767354726791382, | |
| "eval_runtime": 307.9876, | |
| "eval_samples_per_second": 4.676, | |
| "eval_steps_per_second": 1.169, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.6063, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.8458333611488342, | |
| "eval_loss": 0.4531818926334381, | |
| "eval_runtime": 307.4247, | |
| "eval_samples_per_second": 4.684, | |
| "eval_steps_per_second": 1.171, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.5105, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_accuracy": 0.831944465637207, | |
| "eval_loss": 0.45398369431495667, | |
| "eval_runtime": 306.6509, | |
| "eval_samples_per_second": 4.696, | |
| "eval_steps_per_second": 1.174, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.6397, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.8180555701255798, | |
| "eval_loss": 0.5045942664146423, | |
| "eval_runtime": 306.9645, | |
| "eval_samples_per_second": 4.691, | |
| "eval_steps_per_second": 1.173, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.5338, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.8534722328186035, | |
| "eval_loss": 0.42865610122680664, | |
| "eval_runtime": 308.1509, | |
| "eval_samples_per_second": 4.673, | |
| "eval_steps_per_second": 1.168, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.559, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.8569444417953491, | |
| "eval_loss": 0.4333796501159668, | |
| "eval_runtime": 308.3459, | |
| "eval_samples_per_second": 4.67, | |
| "eval_steps_per_second": 1.168, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.6952, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.863194465637207, | |
| "eval_loss": 0.4117491543292999, | |
| "eval_runtime": 306.5802, | |
| "eval_samples_per_second": 4.697, | |
| "eval_steps_per_second": 1.174, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.5286, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.8645833134651184, | |
| "eval_loss": 0.42295506596565247, | |
| "eval_runtime": 309.6096, | |
| "eval_samples_per_second": 4.651, | |
| "eval_steps_per_second": 1.163, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.6243, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.8458333611488342, | |
| "eval_loss": 0.4611164927482605, | |
| "eval_runtime": 308.2976, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 1.168, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.6353, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.8368055820465088, | |
| "eval_loss": 0.4841282367706299, | |
| "eval_runtime": 308.4373, | |
| "eval_samples_per_second": 4.669, | |
| "eval_steps_per_second": 1.167, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.4522, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.8548611402511597, | |
| "eval_loss": 0.4255611300468445, | |
| "eval_runtime": 310.2944, | |
| "eval_samples_per_second": 4.641, | |
| "eval_steps_per_second": 1.16, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.4701, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.8736110925674438, | |
| "eval_loss": 0.36990857124328613, | |
| "eval_runtime": 314.0357, | |
| "eval_samples_per_second": 4.585, | |
| "eval_steps_per_second": 1.146, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.482, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.8659722208976746, | |
| "eval_loss": 0.38237661123275757, | |
| "eval_runtime": 310.2911, | |
| "eval_samples_per_second": 4.641, | |
| "eval_steps_per_second": 1.16, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.305555555555556e-06, | |
| "loss": 0.5023, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.862500011920929, | |
| "eval_loss": 0.40548327565193176, | |
| "eval_runtime": 308.5687, | |
| "eval_samples_per_second": 4.667, | |
| "eval_steps_per_second": 1.167, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.916666666666667e-06, | |
| "loss": 0.3688, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_accuracy": 0.8673611283302307, | |
| "eval_loss": 0.391024112701416, | |
| "eval_runtime": 308.4404, | |
| "eval_samples_per_second": 4.669, | |
| "eval_steps_per_second": 1.167, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.5277777777777778e-06, | |
| "loss": 0.4829, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.8708333373069763, | |
| "eval_loss": 0.37891247868537903, | |
| "eval_runtime": 309.3769, | |
| "eval_samples_per_second": 4.655, | |
| "eval_steps_per_second": 1.164, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.388888888888889e-07, | |
| "loss": 0.4577, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8743055462837219, | |
| "eval_loss": 0.3733634948730469, | |
| "eval_runtime": 307.6988, | |
| "eval_samples_per_second": 4.68, | |
| "eval_steps_per_second": 1.17, | |
| "step": 720 | |
| } | |
| ], | |
| "max_steps": 720, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.1336795856108278e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |