| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 60.0, | |
| "global_step": 18720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.4002273380756378, | |
| "eval_runtime": 7.899, | |
| "eval_samples_per_second": 35.068, | |
| "eval_steps_per_second": 4.431, | |
| "step": 312 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5306859205776173, | |
| "epoch": 1.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.003893162393162393, | |
| "loss": 0.545, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.4058210253715515, | |
| "eval_runtime": 7.9375, | |
| "eval_samples_per_second": 34.898, | |
| "eval_steps_per_second": 4.409, | |
| "step": 624 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 2.0, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.3971773684024811, | |
| "eval_runtime": 7.8277, | |
| "eval_samples_per_second": 35.387, | |
| "eval_steps_per_second": 4.471, | |
| "step": 936 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 3.0, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0037863247863247863, | |
| "loss": 0.4698, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.43598055839538574, | |
| "eval_runtime": 7.8598, | |
| "eval_samples_per_second": 35.243, | |
| "eval_steps_per_second": 4.453, | |
| "step": 1248 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 4.0, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.0036794871794871794, | |
| "loss": 0.4785, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5090252707581228, | |
| "eval_loss": 0.34939223527908325, | |
| "eval_runtime": 7.8681, | |
| "eval_samples_per_second": 35.205, | |
| "eval_steps_per_second": 4.448, | |
| "step": 1560 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 5.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4729241877256318, | |
| "eval_loss": 0.4100410044193268, | |
| "eval_runtime": 7.6697, | |
| "eval_samples_per_second": 36.116, | |
| "eval_steps_per_second": 4.563, | |
| "step": 1872 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 6.0, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 0.003572649572649573, | |
| "loss": 0.4322, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5306859205776173, | |
| "eval_loss": 0.5716891884803772, | |
| "eval_runtime": 7.1399, | |
| "eval_samples_per_second": 38.796, | |
| "eval_steps_per_second": 4.902, | |
| "step": 2184 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 7.0, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5379061371841155, | |
| "eval_loss": 0.4077668786048889, | |
| "eval_runtime": 7.1214, | |
| "eval_samples_per_second": 38.897, | |
| "eval_steps_per_second": 4.915, | |
| "step": 2496 | |
| }, | |
| { | |
| "best_epoch": 1, | |
| "best_eval_accuracy": 0.5379061371841155, | |
| "epoch": 8.0, | |
| "step": 2496 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.003465811965811966, | |
| "loss": 0.3946, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6570397111913358, | |
| "eval_loss": 0.3303951323032379, | |
| "eval_runtime": 7.7155, | |
| "eval_samples_per_second": 35.902, | |
| "eval_steps_per_second": 4.536, | |
| "step": 2808 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6570397111913358, | |
| "epoch": 9.0, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 0.003358974358974359, | |
| "loss": 0.36, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.3317576050758362, | |
| "eval_runtime": 7.9183, | |
| "eval_samples_per_second": 34.982, | |
| "eval_steps_per_second": 4.42, | |
| "step": 3120 | |
| }, | |
| { | |
| "best_epoch": 8, | |
| "best_eval_accuracy": 0.6570397111913358, | |
| "epoch": 10.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3275066316127777, | |
| "eval_runtime": 7.8656, | |
| "eval_samples_per_second": 35.217, | |
| "eval_steps_per_second": 4.45, | |
| "step": 3432 | |
| }, | |
| { | |
| "best_epoch": 10, | |
| "best_eval_accuracy": 0.6931407942238267, | |
| "epoch": 11.0, | |
| "step": 3432 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 0.0032521367521367523, | |
| "loss": 0.3478, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3313818871974945, | |
| "eval_runtime": 7.871, | |
| "eval_samples_per_second": 35.193, | |
| "eval_steps_per_second": 4.447, | |
| "step": 3744 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 12.0, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 0.0031452991452991454, | |
| "loss": 0.3359, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.3276725113391876, | |
| "eval_runtime": 7.9031, | |
| "eval_samples_per_second": 35.049, | |
| "eval_steps_per_second": 4.429, | |
| "step": 4056 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 13.0, | |
| "step": 4056 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7148014440433214, | |
| "eval_loss": 0.3307007849216461, | |
| "eval_runtime": 7.8214, | |
| "eval_samples_per_second": 35.416, | |
| "eval_steps_per_second": 4.475, | |
| "step": 4368 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 14.0, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 0.0030384615384615385, | |
| "loss": 0.3249, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6967509025270758, | |
| "eval_loss": 0.3245388865470886, | |
| "eval_runtime": 7.9087, | |
| "eval_samples_per_second": 35.025, | |
| "eval_steps_per_second": 4.425, | |
| "step": 4680 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 15.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6498194945848376, | |
| "eval_loss": 0.3625728487968445, | |
| "eval_runtime": 7.9254, | |
| "eval_samples_per_second": 34.951, | |
| "eval_steps_per_second": 4.416, | |
| "step": 4992 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 16.0, | |
| "step": 4992 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 0.0029316239316239316, | |
| "loss": 0.3253, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6859205776173285, | |
| "eval_loss": 0.35674089193344116, | |
| "eval_runtime": 7.8733, | |
| "eval_samples_per_second": 35.182, | |
| "eval_steps_per_second": 4.445, | |
| "step": 5304 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 17.0, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 0.002824786324786325, | |
| "loss": 0.3155, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.3278597295284271, | |
| "eval_runtime": 8.1927, | |
| "eval_samples_per_second": 33.811, | |
| "eval_steps_per_second": 4.272, | |
| "step": 5616 | |
| }, | |
| { | |
| "best_epoch": 11, | |
| "best_eval_accuracy": 0.7148014440433214, | |
| "epoch": 18.0, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.32572436332702637, | |
| "eval_runtime": 8.048, | |
| "eval_samples_per_second": 34.419, | |
| "eval_steps_per_second": 4.349, | |
| "step": 5928 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 19.0, | |
| "step": 5928 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 0.0027179487179487182, | |
| "loss": 0.3145, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.33365291357040405, | |
| "eval_runtime": 7.9631, | |
| "eval_samples_per_second": 34.786, | |
| "eval_steps_per_second": 4.395, | |
| "step": 6240 | |
| }, | |
| { | |
| "best_epoch": 18, | |
| "best_eval_accuracy": 0.7256317689530686, | |
| "epoch": 20.0, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 0.0026111111111111114, | |
| "loss": 0.3051, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.32888656854629517, | |
| "eval_runtime": 7.9481, | |
| "eval_samples_per_second": 34.851, | |
| "eval_steps_per_second": 4.404, | |
| "step": 6552 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 21.0, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6931407942238267, | |
| "eval_loss": 0.3523448705673218, | |
| "eval_runtime": 7.9194, | |
| "eval_samples_per_second": 34.977, | |
| "eval_steps_per_second": 4.42, | |
| "step": 6864 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 22.0, | |
| "step": 6864 | |
| }, | |
| { | |
| "epoch": 22.44, | |
| "learning_rate": 0.0025042735042735045, | |
| "loss": 0.3015, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.703971119133574, | |
| "eval_loss": 0.3459450900554657, | |
| "eval_runtime": 7.9377, | |
| "eval_samples_per_second": 34.897, | |
| "eval_steps_per_second": 4.409, | |
| "step": 7176 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 23.0, | |
| "step": 7176 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7075812274368231, | |
| "eval_loss": 0.33232513070106506, | |
| "eval_runtime": 7.8791, | |
| "eval_samples_per_second": 35.156, | |
| "eval_steps_per_second": 4.442, | |
| "step": 7488 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 24.0, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 24.04, | |
| "learning_rate": 0.0023974358974358976, | |
| "loss": 0.2952, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.34448423981666565, | |
| "eval_runtime": 7.9104, | |
| "eval_samples_per_second": 35.017, | |
| "eval_steps_per_second": 4.425, | |
| "step": 7800 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 25.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 0.0022905982905982907, | |
| "loss": 0.289, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.35538923740386963, | |
| "eval_runtime": 7.5655, | |
| "eval_samples_per_second": 36.614, | |
| "eval_steps_per_second": 4.626, | |
| "step": 8112 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 26.0, | |
| "step": 8112 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3209746778011322, | |
| "eval_runtime": 7.2479, | |
| "eval_samples_per_second": 38.218, | |
| "eval_steps_per_second": 4.829, | |
| "step": 8424 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 27.0, | |
| "step": 8424 | |
| }, | |
| { | |
| "epoch": 27.24, | |
| "learning_rate": 0.002183760683760684, | |
| "loss": 0.2876, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.3203848898410797, | |
| "eval_runtime": 7.4991, | |
| "eval_samples_per_second": 36.938, | |
| "eval_steps_per_second": 4.667, | |
| "step": 8736 | |
| }, | |
| { | |
| "best_epoch": 20, | |
| "best_eval_accuracy": 0.7364620938628159, | |
| "epoch": 28.0, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 0.0020769230769230773, | |
| "loss": 0.2862, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.3374094069004059, | |
| "eval_runtime": 8.1406, | |
| "eval_samples_per_second": 34.027, | |
| "eval_steps_per_second": 4.299, | |
| "step": 9048 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 29.0, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7111913357400722, | |
| "eval_loss": 0.37784236669540405, | |
| "eval_runtime": 8.2326, | |
| "eval_samples_per_second": 33.647, | |
| "eval_steps_per_second": 4.251, | |
| "step": 9360 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 30.0, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 0.0019700854700854704, | |
| "loss": 0.2814, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3352125287055969, | |
| "eval_runtime": 8.0359, | |
| "eval_samples_per_second": 34.47, | |
| "eval_steps_per_second": 4.355, | |
| "step": 9672 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 31.0, | |
| "step": 9672 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7256317689530686, | |
| "eval_loss": 0.3251102566719055, | |
| "eval_runtime": 7.9895, | |
| "eval_samples_per_second": 34.671, | |
| "eval_steps_per_second": 4.381, | |
| "step": 9984 | |
| }, | |
| { | |
| "best_epoch": 28, | |
| "best_eval_accuracy": 0.7509025270758123, | |
| "epoch": 32.0, | |
| "step": 9984 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 0.0018632478632478633, | |
| "loss": 0.2777, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7617328519855595, | |
| "eval_loss": 0.3574084937572479, | |
| "eval_runtime": 7.9489, | |
| "eval_samples_per_second": 34.848, | |
| "eval_steps_per_second": 4.403, | |
| "step": 10296 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 33.0, | |
| "step": 10296 | |
| }, | |
| { | |
| "epoch": 33.65, | |
| "learning_rate": 0.0017564102564102564, | |
| "loss": 0.2698, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7292418772563177, | |
| "eval_loss": 0.3329852819442749, | |
| "eval_runtime": 8.2079, | |
| "eval_samples_per_second": 33.748, | |
| "eval_steps_per_second": 4.264, | |
| "step": 10608 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 34.0, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7220216606498195, | |
| "eval_loss": 0.33876490592956543, | |
| "eval_runtime": 8.1527, | |
| "eval_samples_per_second": 33.977, | |
| "eval_steps_per_second": 4.293, | |
| "step": 10920 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 35.0, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 35.26, | |
| "learning_rate": 0.0016495726495726495, | |
| "loss": 0.2714, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7328519855595668, | |
| "eval_loss": 0.32217517495155334, | |
| "eval_runtime": 8.0843, | |
| "eval_samples_per_second": 34.264, | |
| "eval_steps_per_second": 4.329, | |
| "step": 11232 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 36.0, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "learning_rate": 0.0015427350427350429, | |
| "loss": 0.2695, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3481736183166504, | |
| "eval_runtime": 8.1996, | |
| "eval_samples_per_second": 33.782, | |
| "eval_steps_per_second": 4.269, | |
| "step": 11544 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 37.0, | |
| "step": 11544 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3447316884994507, | |
| "eval_runtime": 8.1931, | |
| "eval_samples_per_second": 33.809, | |
| "eval_steps_per_second": 4.272, | |
| "step": 11856 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 38.0, | |
| "step": 11856 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.001435897435897436, | |
| "loss": 0.2637, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33936700224876404, | |
| "eval_runtime": 7.9489, | |
| "eval_samples_per_second": 34.847, | |
| "eval_steps_per_second": 4.403, | |
| "step": 12168 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 39.0, | |
| "step": 12168 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3264324963092804, | |
| "eval_runtime": 8.0534, | |
| "eval_samples_per_second": 34.395, | |
| "eval_steps_per_second": 4.346, | |
| "step": 12480 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 40.0, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 40.06, | |
| "learning_rate": 0.001329059829059829, | |
| "loss": 0.2646, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.33107784390449524, | |
| "eval_runtime": 7.9509, | |
| "eval_samples_per_second": 34.839, | |
| "eval_steps_per_second": 4.402, | |
| "step": 12792 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 41.0, | |
| "step": 12792 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 0.0012222222222222224, | |
| "loss": 0.2613, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7364620938628159, | |
| "eval_loss": 0.33219507336616516, | |
| "eval_runtime": 3.505, | |
| "eval_samples_per_second": 79.03, | |
| "eval_steps_per_second": 9.986, | |
| "step": 13104 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 42.0, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.34114494919776917, | |
| "eval_runtime": 7.9723, | |
| "eval_samples_per_second": 34.745, | |
| "eval_steps_per_second": 4.39, | |
| "step": 13416 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 43.0, | |
| "step": 13416 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 0.0011153846153846155, | |
| "loss": 0.2539, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.3298494219779968, | |
| "eval_runtime": 7.9519, | |
| "eval_samples_per_second": 34.835, | |
| "eval_steps_per_second": 4.401, | |
| "step": 13728 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 44.0, | |
| "step": 13728 | |
| }, | |
| { | |
| "epoch": 44.87, | |
| "learning_rate": 0.0010085470085470086, | |
| "loss": 0.2543, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7436823104693141, | |
| "eval_loss": 0.3441672623157501, | |
| "eval_runtime": 8.0541, | |
| "eval_samples_per_second": 34.392, | |
| "eval_steps_per_second": 4.346, | |
| "step": 14040 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 45.0, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3398982882499695, | |
| "eval_runtime": 7.984, | |
| "eval_samples_per_second": 34.694, | |
| "eval_steps_per_second": 4.384, | |
| "step": 14352 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 46.0, | |
| "step": 14352 | |
| }, | |
| { | |
| "epoch": 46.47, | |
| "learning_rate": 0.0009017094017094017, | |
| "loss": 0.2516, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3330487310886383, | |
| "eval_runtime": 8.1523, | |
| "eval_samples_per_second": 33.978, | |
| "eval_steps_per_second": 4.293, | |
| "step": 14664 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 47.0, | |
| "step": 14664 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3299367427825928, | |
| "eval_runtime": 8.2276, | |
| "eval_samples_per_second": 33.667, | |
| "eval_steps_per_second": 4.254, | |
| "step": 14976 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 48.0, | |
| "step": 14976 | |
| }, | |
| { | |
| "epoch": 48.08, | |
| "learning_rate": 0.0007948717948717948, | |
| "loss": 0.2509, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.740072202166065, | |
| "eval_loss": 0.3406999409198761, | |
| "eval_runtime": 8.0877, | |
| "eval_samples_per_second": 34.249, | |
| "eval_steps_per_second": 4.328, | |
| "step": 15288 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 49.0, | |
| "step": 15288 | |
| }, | |
| { | |
| "epoch": 49.68, | |
| "learning_rate": 0.0006880341880341881, | |
| "loss": 0.2484, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.32676392793655396, | |
| "eval_runtime": 8.162, | |
| "eval_samples_per_second": 33.938, | |
| "eval_steps_per_second": 4.288, | |
| "step": 15600 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 50.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.33857765793800354, | |
| "eval_runtime": 7.8842, | |
| "eval_samples_per_second": 35.134, | |
| "eval_steps_per_second": 4.439, | |
| "step": 15912 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 51.0, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 51.28, | |
| "learning_rate": 0.0005811965811965813, | |
| "loss": 0.2491, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7581227436823105, | |
| "eval_loss": 0.33233577013015747, | |
| "eval_runtime": 7.2401, | |
| "eval_samples_per_second": 38.259, | |
| "eval_steps_per_second": 4.834, | |
| "step": 16224 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 52.0, | |
| "step": 16224 | |
| }, | |
| { | |
| "epoch": 52.88, | |
| "learning_rate": 0.00047435897435897434, | |
| "loss": 0.2483, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3448106646537781, | |
| "eval_runtime": 7.4942, | |
| "eval_samples_per_second": 36.962, | |
| "eval_steps_per_second": 4.67, | |
| "step": 16536 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 53.0, | |
| "step": 16536 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3339071571826935, | |
| "eval_runtime": 8.0188, | |
| "eval_samples_per_second": 34.544, | |
| "eval_steps_per_second": 4.365, | |
| "step": 16848 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 54.0, | |
| "step": 16848 | |
| }, | |
| { | |
| "epoch": 54.49, | |
| "learning_rate": 0.00036752136752136755, | |
| "loss": 0.2452, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3342669606208801, | |
| "eval_runtime": 7.9729, | |
| "eval_samples_per_second": 34.743, | |
| "eval_steps_per_second": 4.39, | |
| "step": 17160 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 55.0, | |
| "step": 17160 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7509025270758123, | |
| "eval_loss": 0.34084513783454895, | |
| "eval_runtime": 7.9976, | |
| "eval_samples_per_second": 34.636, | |
| "eval_steps_per_second": 4.376, | |
| "step": 17472 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 56.0, | |
| "step": 17472 | |
| }, | |
| { | |
| "epoch": 56.09, | |
| "learning_rate": 0.0002606837606837607, | |
| "loss": 0.2456, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3373964726924896, | |
| "eval_runtime": 8.095, | |
| "eval_samples_per_second": 34.219, | |
| "eval_steps_per_second": 4.324, | |
| "step": 17784 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 57.0, | |
| "step": 17784 | |
| }, | |
| { | |
| "epoch": 57.69, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 0.2429, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.33596983551979065, | |
| "eval_runtime": 7.9977, | |
| "eval_samples_per_second": 34.635, | |
| "eval_steps_per_second": 4.376, | |
| "step": 18096 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 58.0, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7545126353790613, | |
| "eval_loss": 0.3345196545124054, | |
| "eval_runtime": 7.9889, | |
| "eval_samples_per_second": 34.673, | |
| "eval_steps_per_second": 4.381, | |
| "step": 18408 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 59.0, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 4.700854700854701e-05, | |
| "loss": 0.2436, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7472924187725631, | |
| "eval_loss": 0.3361694812774658, | |
| "eval_runtime": 8.1052, | |
| "eval_samples_per_second": 34.175, | |
| "eval_steps_per_second": 4.318, | |
| "step": 18720 | |
| }, | |
| { | |
| "best_epoch": 32, | |
| "best_eval_accuracy": 0.7617328519855595, | |
| "epoch": 60.0, | |
| "step": 18720 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 18720, | |
| "total_flos": 6.96152728406016e+16, | |
| "train_loss": 0.30472259908659843, | |
| "train_runtime": 6884.7391, | |
| "train_samples_per_second": 21.7, | |
| "train_steps_per_second": 2.719 | |
| } | |
| ], | |
| "max_steps": 18720, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.96152728406016e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |