|
{ |
|
"best_metric": 0.7445889711380005, |
|
"best_model_checkpoint": "./croupier-creature-classifier/checkpoint-2200", |
|
"epoch": 25.0, |
|
"global_step": 2275, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00019912087912087913, |
|
"loss": 1.3637, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00019824175824175827, |
|
"loss": 1.3785, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00019736263736263738, |
|
"loss": 1.3807, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00019648351648351647, |
|
"loss": 1.3582, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.00019560439560439562, |
|
"loss": 1.2273, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.00019472527472527473, |
|
"loss": 1.3811, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.00019384615384615385, |
|
"loss": 1.3425, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.000192967032967033, |
|
"loss": 1.3062, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0001920879120879121, |
|
"loss": 1.2959, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.00019120879120879122, |
|
"loss": 1.1638, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"eval_accuracy": 0.5470588235294118, |
|
"eval_loss": 1.0563907623291016, |
|
"eval_runtime": 1.5249, |
|
"eval_samples_per_second": 111.483, |
|
"eval_steps_per_second": 14.427, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.00019032967032967034, |
|
"loss": 1.0851, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00018945054945054945, |
|
"loss": 1.1777, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.00018857142857142857, |
|
"loss": 1.1352, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.0001876923076923077, |
|
"loss": 1.0112, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.00018681318681318683, |
|
"loss": 1.0718, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00018593406593406595, |
|
"loss": 0.9871, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.00018505494505494506, |
|
"loss": 1.2279, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.00018417582417582418, |
|
"loss": 1.148, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 0.0001832967032967033, |
|
"loss": 0.8905, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.0001824175824175824, |
|
"loss": 0.8524, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"eval_accuracy": 0.611764705882353, |
|
"eval_loss": 0.9402753114700317, |
|
"eval_runtime": 1.611, |
|
"eval_samples_per_second": 105.524, |
|
"eval_steps_per_second": 13.656, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.31, |
|
"learning_rate": 0.00018153846153846155, |
|
"loss": 0.8388, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 0.00018065934065934067, |
|
"loss": 0.7519, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 0.00017978021978021978, |
|
"loss": 1.0743, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.00017890109890109893, |
|
"loss": 0.8687, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 0.00017802197802197802, |
|
"loss": 0.886, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 0.00017714285714285713, |
|
"loss": 0.8484, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 0.00017626373626373627, |
|
"loss": 0.8394, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 0.0001753846153846154, |
|
"loss": 0.8304, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 0.0001745054945054945, |
|
"loss": 0.6359, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 0.00017362637362637365, |
|
"loss": 0.8231, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"eval_accuracy": 0.7176470588235294, |
|
"eval_loss": 0.8282244801521301, |
|
"eval_runtime": 2.0367, |
|
"eval_samples_per_second": 83.467, |
|
"eval_steps_per_second": 10.802, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 0.00017274725274725276, |
|
"loss": 0.6735, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.00017186813186813185, |
|
"loss": 0.6721, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 0.000170989010989011, |
|
"loss": 0.8183, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 0.0001701098901098901, |
|
"loss": 0.7158, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 0.00016923076923076923, |
|
"loss": 0.796, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 0.00016835164835164837, |
|
"loss": 0.7814, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 0.0001674725274725275, |
|
"loss": 0.6363, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 0.0001665934065934066, |
|
"loss": 0.57, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 0.00016571428571428575, |
|
"loss": 0.5695, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 0.00016483516483516484, |
|
"loss": 0.7398, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"eval_accuracy": 0.6294117647058823, |
|
"eval_loss": 0.9056094884872437, |
|
"eval_runtime": 1.6835, |
|
"eval_samples_per_second": 100.978, |
|
"eval_steps_per_second": 13.068, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 0.00016395604395604395, |
|
"loss": 0.5678, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 0.0001630769230769231, |
|
"loss": 0.5507, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 0.0001621978021978022, |
|
"loss": 0.4983, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 4.84, |
|
"learning_rate": 0.00016131868131868133, |
|
"loss": 0.6078, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 4.95, |
|
"learning_rate": 0.00016043956043956044, |
|
"loss": 0.584, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 5.05, |
|
"learning_rate": 0.00015956043956043958, |
|
"loss": 0.4714, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 5.16, |
|
"learning_rate": 0.00015868131868131867, |
|
"loss": 0.6575, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 5.27, |
|
"learning_rate": 0.00015780219780219782, |
|
"loss": 0.522, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 5.38, |
|
"learning_rate": 0.00015692307692307693, |
|
"loss": 0.5475, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"learning_rate": 0.00015604395604395605, |
|
"loss": 0.41, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"eval_accuracy": 0.6235294117647059, |
|
"eval_loss": 0.8814617991447449, |
|
"eval_runtime": 1.5991, |
|
"eval_samples_per_second": 106.312, |
|
"eval_steps_per_second": 13.758, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.6, |
|
"learning_rate": 0.00015516483516483516, |
|
"loss": 0.4955, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 0.0001542857142857143, |
|
"loss": 0.5234, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 0.00015340659340659342, |
|
"loss": 0.4696, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 5.93, |
|
"learning_rate": 0.00015252747252747254, |
|
"loss": 0.4195, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 0.00015164835164835165, |
|
"loss": 0.5375, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 6.15, |
|
"learning_rate": 0.00015076923076923077, |
|
"loss": 0.3726, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"learning_rate": 0.0001498901098901099, |
|
"loss": 0.3705, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 6.37, |
|
"learning_rate": 0.00014901098901098903, |
|
"loss": 0.3445, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 6.48, |
|
"learning_rate": 0.00014813186813186815, |
|
"loss": 0.4785, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"learning_rate": 0.00014725274725274726, |
|
"loss": 0.4849, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"eval_accuracy": 0.6294117647058823, |
|
"eval_loss": 0.9504889249801636, |
|
"eval_runtime": 1.7834, |
|
"eval_samples_per_second": 95.325, |
|
"eval_steps_per_second": 12.336, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 6.7, |
|
"learning_rate": 0.00014637362637362638, |
|
"loss": 0.5062, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 6.81, |
|
"learning_rate": 0.0001454945054945055, |
|
"loss": 0.4269, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 6.92, |
|
"learning_rate": 0.0001446153846153846, |
|
"loss": 0.3566, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 7.03, |
|
"learning_rate": 0.00014373626373626375, |
|
"loss": 0.3931, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 7.14, |
|
"learning_rate": 0.00014285714285714287, |
|
"loss": 0.3896, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 0.00014197802197802198, |
|
"loss": 0.3306, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 0.00014109890109890113, |
|
"loss": 0.4898, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 7.47, |
|
"learning_rate": 0.00014021978021978022, |
|
"loss": 0.4136, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 7.58, |
|
"learning_rate": 0.00013934065934065933, |
|
"loss": 0.4874, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"learning_rate": 0.00013846153846153847, |
|
"loss": 0.3894, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"eval_accuracy": 0.6882352941176471, |
|
"eval_loss": 0.8051896095275879, |
|
"eval_runtime": 2.0897, |
|
"eval_samples_per_second": 81.352, |
|
"eval_steps_per_second": 10.528, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 7.8, |
|
"learning_rate": 0.0001375824175824176, |
|
"loss": 0.355, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 7.91, |
|
"learning_rate": 0.0001367032967032967, |
|
"loss": 0.4024, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 0.00013582417582417585, |
|
"loss": 0.458, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 8.13, |
|
"learning_rate": 0.00013494505494505497, |
|
"loss": 0.2912, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 8.24, |
|
"learning_rate": 0.00013406593406593405, |
|
"loss": 0.3608, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 8.35, |
|
"learning_rate": 0.0001331868131868132, |
|
"loss": 0.3897, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 8.46, |
|
"learning_rate": 0.0001323076923076923, |
|
"loss": 0.3451, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 8.57, |
|
"learning_rate": 0.00013142857142857143, |
|
"loss": 0.3122, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 8.68, |
|
"learning_rate": 0.00013054945054945057, |
|
"loss": 0.2771, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 8.79, |
|
"learning_rate": 0.0001296703296703297, |
|
"loss": 0.4678, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 8.79, |
|
"eval_accuracy": 0.7058823529411765, |
|
"eval_loss": 0.8423882722854614, |
|
"eval_runtime": 1.8864, |
|
"eval_samples_per_second": 90.118, |
|
"eval_steps_per_second": 11.662, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 8.9, |
|
"learning_rate": 0.0001287912087912088, |
|
"loss": 0.4709, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 0.00012791208791208792, |
|
"loss": 0.3594, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 9.12, |
|
"learning_rate": 0.00012703296703296704, |
|
"loss": 0.3349, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 9.23, |
|
"learning_rate": 0.00012615384615384615, |
|
"loss": 0.4093, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 9.34, |
|
"learning_rate": 0.00012527472527472527, |
|
"loss": 0.2627, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 9.45, |
|
"learning_rate": 0.0001243956043956044, |
|
"loss": 0.2817, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 9.56, |
|
"learning_rate": 0.00012351648351648353, |
|
"loss": 0.3046, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 9.67, |
|
"learning_rate": 0.00012263736263736264, |
|
"loss": 0.5005, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 9.78, |
|
"learning_rate": 0.00012175824175824176, |
|
"loss": 0.1866, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"learning_rate": 0.00012087912087912087, |
|
"loss": 0.4279, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"eval_accuracy": 0.6705882352941176, |
|
"eval_loss": 0.963887095451355, |
|
"eval_runtime": 1.496, |
|
"eval_samples_per_second": 113.639, |
|
"eval_steps_per_second": 14.706, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 0.00012, |
|
"loss": 0.4008, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 10.11, |
|
"learning_rate": 0.00011912087912087912, |
|
"loss": 0.3001, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 10.22, |
|
"learning_rate": 0.00011824175824175825, |
|
"loss": 0.2588, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 10.33, |
|
"learning_rate": 0.00011736263736263738, |
|
"loss": 0.4082, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 10.44, |
|
"learning_rate": 0.0001164835164835165, |
|
"loss": 0.3957, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 10.55, |
|
"learning_rate": 0.0001156043956043956, |
|
"loss": 0.3988, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 10.66, |
|
"learning_rate": 0.00011472527472527473, |
|
"loss": 0.2264, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 10.77, |
|
"learning_rate": 0.00011384615384615384, |
|
"loss": 0.3202, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 10.88, |
|
"learning_rate": 0.00011296703296703297, |
|
"loss": 0.2622, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 10.99, |
|
"learning_rate": 0.0001120879120879121, |
|
"loss": 0.3461, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 10.99, |
|
"eval_accuracy": 0.7058823529411765, |
|
"eval_loss": 0.8496671915054321, |
|
"eval_runtime": 1.4967, |
|
"eval_samples_per_second": 113.586, |
|
"eval_steps_per_second": 14.699, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 11.1, |
|
"learning_rate": 0.00011120879120879122, |
|
"loss": 0.1967, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 11.21, |
|
"learning_rate": 0.00011032967032967035, |
|
"loss": 0.2573, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 11.32, |
|
"learning_rate": 0.00010945054945054946, |
|
"loss": 0.3313, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 11.43, |
|
"learning_rate": 0.00010857142857142856, |
|
"loss": 0.2774, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 11.54, |
|
"learning_rate": 0.0001076923076923077, |
|
"loss": 0.1745, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 11.65, |
|
"learning_rate": 0.00010681318681318682, |
|
"loss": 0.2563, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 11.76, |
|
"learning_rate": 0.00010593406593406594, |
|
"loss": 0.15, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 11.87, |
|
"learning_rate": 0.00010505494505494507, |
|
"loss": 0.346, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 11.98, |
|
"learning_rate": 0.00010417582417582418, |
|
"loss": 0.3187, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 12.09, |
|
"learning_rate": 0.00010329670329670331, |
|
"loss": 0.2741, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 12.09, |
|
"eval_accuracy": 0.7, |
|
"eval_loss": 0.9090209007263184, |
|
"eval_runtime": 1.5007, |
|
"eval_samples_per_second": 113.284, |
|
"eval_steps_per_second": 14.66, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 12.2, |
|
"learning_rate": 0.00010241758241758242, |
|
"loss": 0.2168, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 12.31, |
|
"learning_rate": 0.00010153846153846153, |
|
"loss": 0.1902, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 12.42, |
|
"learning_rate": 0.00010065934065934066, |
|
"loss": 0.2154, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 12.53, |
|
"learning_rate": 9.978021978021979e-05, |
|
"loss": 0.3392, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 12.64, |
|
"learning_rate": 9.89010989010989e-05, |
|
"loss": 0.2567, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 12.75, |
|
"learning_rate": 9.802197802197802e-05, |
|
"loss": 0.3863, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 12.86, |
|
"learning_rate": 9.714285714285715e-05, |
|
"loss": 0.3635, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 12.97, |
|
"learning_rate": 9.626373626373627e-05, |
|
"loss": 0.2915, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 13.08, |
|
"learning_rate": 9.53846153846154e-05, |
|
"loss": 0.3021, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 13.19, |
|
"learning_rate": 9.450549450549451e-05, |
|
"loss": 0.1771, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 13.19, |
|
"eval_accuracy": 0.711764705882353, |
|
"eval_loss": 0.8292282819747925, |
|
"eval_runtime": 1.5182, |
|
"eval_samples_per_second": 111.974, |
|
"eval_steps_per_second": 14.491, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 13.3, |
|
"learning_rate": 9.362637362637363e-05, |
|
"loss": 0.1475, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 13.41, |
|
"learning_rate": 9.274725274725276e-05, |
|
"loss": 0.1051, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 13.52, |
|
"learning_rate": 9.186813186813187e-05, |
|
"loss": 0.1564, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 13.63, |
|
"learning_rate": 9.098901098901099e-05, |
|
"loss": 0.4018, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 13.74, |
|
"learning_rate": 9.010989010989012e-05, |
|
"loss": 0.3191, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 13.85, |
|
"learning_rate": 8.923076923076924e-05, |
|
"loss": 0.2845, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 13.96, |
|
"learning_rate": 8.835164835164835e-05, |
|
"loss": 0.3667, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 14.07, |
|
"learning_rate": 8.747252747252748e-05, |
|
"loss": 0.2433, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 14.18, |
|
"learning_rate": 8.65934065934066e-05, |
|
"loss": 0.1794, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 14.29, |
|
"learning_rate": 8.571428571428571e-05, |
|
"loss": 0.1779, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 14.29, |
|
"eval_accuracy": 0.6294117647058823, |
|
"eval_loss": 1.1313611268997192, |
|
"eval_runtime": 1.4881, |
|
"eval_samples_per_second": 114.237, |
|
"eval_steps_per_second": 14.784, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 14.4, |
|
"learning_rate": 8.483516483516484e-05, |
|
"loss": 0.2517, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 14.51, |
|
"learning_rate": 8.395604395604396e-05, |
|
"loss": 0.2737, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 14.62, |
|
"learning_rate": 8.307692307692309e-05, |
|
"loss": 0.2092, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 14.73, |
|
"learning_rate": 8.21978021978022e-05, |
|
"loss": 0.2281, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 14.84, |
|
"learning_rate": 8.131868131868132e-05, |
|
"loss": 0.2375, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 14.95, |
|
"learning_rate": 8.043956043956045e-05, |
|
"loss": 0.2062, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 15.05, |
|
"learning_rate": 7.956043956043956e-05, |
|
"loss": 0.1698, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 15.16, |
|
"learning_rate": 7.868131868131868e-05, |
|
"loss": 0.1904, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 15.27, |
|
"learning_rate": 7.780219780219781e-05, |
|
"loss": 0.2469, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 15.38, |
|
"learning_rate": 7.692307692307693e-05, |
|
"loss": 0.2044, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 15.38, |
|
"eval_accuracy": 0.7294117647058823, |
|
"eval_loss": 0.8349283337593079, |
|
"eval_runtime": 1.502, |
|
"eval_samples_per_second": 113.184, |
|
"eval_steps_per_second": 14.647, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 15.49, |
|
"learning_rate": 7.604395604395604e-05, |
|
"loss": 0.2405, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 15.6, |
|
"learning_rate": 7.516483516483517e-05, |
|
"loss": 0.1326, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 15.71, |
|
"learning_rate": 7.428571428571429e-05, |
|
"loss": 0.2253, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 15.82, |
|
"learning_rate": 7.34065934065934e-05, |
|
"loss": 0.2029, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 15.93, |
|
"learning_rate": 7.252747252747253e-05, |
|
"loss": 0.1161, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 16.04, |
|
"learning_rate": 7.164835164835165e-05, |
|
"loss": 0.3051, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 16.15, |
|
"learning_rate": 7.076923076923078e-05, |
|
"loss": 0.3765, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 16.26, |
|
"learning_rate": 6.98901098901099e-05, |
|
"loss": 0.1976, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 16.37, |
|
"learning_rate": 6.901098901098901e-05, |
|
"loss": 0.1887, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 16.48, |
|
"learning_rate": 6.813186813186814e-05, |
|
"loss": 0.1543, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 16.48, |
|
"eval_accuracy": 0.6941176470588235, |
|
"eval_loss": 0.8952152132987976, |
|
"eval_runtime": 1.5318, |
|
"eval_samples_per_second": 110.978, |
|
"eval_steps_per_second": 14.362, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 16.59, |
|
"learning_rate": 6.725274725274725e-05, |
|
"loss": 0.2324, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 16.7, |
|
"learning_rate": 6.637362637362637e-05, |
|
"loss": 0.1539, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 16.81, |
|
"learning_rate": 6.54945054945055e-05, |
|
"loss": 0.2305, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 16.92, |
|
"learning_rate": 6.461538461538462e-05, |
|
"loss": 0.1771, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 17.03, |
|
"learning_rate": 6.373626373626373e-05, |
|
"loss": 0.1604, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 17.14, |
|
"learning_rate": 6.285714285714286e-05, |
|
"loss": 0.1297, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 17.25, |
|
"learning_rate": 6.197802197802198e-05, |
|
"loss": 0.1646, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 17.36, |
|
"learning_rate": 6.10989010989011e-05, |
|
"loss": 0.1942, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 17.47, |
|
"learning_rate": 6.021978021978022e-05, |
|
"loss": 0.105, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 17.58, |
|
"learning_rate": 5.9340659340659345e-05, |
|
"loss": 0.1283, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 17.58, |
|
"eval_accuracy": 0.7352941176470589, |
|
"eval_loss": 0.8053585290908813, |
|
"eval_runtime": 1.4888, |
|
"eval_samples_per_second": 114.184, |
|
"eval_steps_per_second": 14.777, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 17.69, |
|
"learning_rate": 5.846153846153847e-05, |
|
"loss": 0.1779, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 17.8, |
|
"learning_rate": 5.7582417582417584e-05, |
|
"loss": 0.1588, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 17.91, |
|
"learning_rate": 5.6703296703296706e-05, |
|
"loss": 0.1868, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 18.02, |
|
"learning_rate": 5.582417582417583e-05, |
|
"loss": 0.1537, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 18.13, |
|
"learning_rate": 5.494505494505495e-05, |
|
"loss": 0.1426, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 18.24, |
|
"learning_rate": 5.406593406593407e-05, |
|
"loss": 0.1759, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 18.35, |
|
"learning_rate": 5.318681318681319e-05, |
|
"loss": 0.1908, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 18.46, |
|
"learning_rate": 5.230769230769231e-05, |
|
"loss": 0.1562, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 18.57, |
|
"learning_rate": 5.142857142857143e-05, |
|
"loss": 0.1137, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 18.68, |
|
"learning_rate": 5.054945054945055e-05, |
|
"loss": 0.1721, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 18.68, |
|
"eval_accuracy": 0.7235294117647059, |
|
"eval_loss": 0.9094342589378357, |
|
"eval_runtime": 1.4871, |
|
"eval_samples_per_second": 114.319, |
|
"eval_steps_per_second": 14.794, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 18.79, |
|
"learning_rate": 4.9670329670329674e-05, |
|
"loss": 0.1623, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 18.9, |
|
"learning_rate": 4.879120879120879e-05, |
|
"loss": 0.1731, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 4.791208791208792e-05, |
|
"loss": 0.1458, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 19.12, |
|
"learning_rate": 4.7032967032967035e-05, |
|
"loss": 0.1717, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 19.23, |
|
"learning_rate": 4.615384615384616e-05, |
|
"loss": 0.1125, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 19.34, |
|
"learning_rate": 4.5274725274725274e-05, |
|
"loss": 0.1776, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 19.45, |
|
"learning_rate": 4.43956043956044e-05, |
|
"loss": 0.1259, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 19.56, |
|
"learning_rate": 4.351648351648352e-05, |
|
"loss": 0.1294, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 19.67, |
|
"learning_rate": 4.2637362637362635e-05, |
|
"loss": 0.2037, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 19.78, |
|
"learning_rate": 4.1758241758241765e-05, |
|
"loss": 0.1509, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 19.78, |
|
"eval_accuracy": 0.7411764705882353, |
|
"eval_loss": 0.9168078303337097, |
|
"eval_runtime": 1.5237, |
|
"eval_samples_per_second": 111.573, |
|
"eval_steps_per_second": 14.439, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 19.89, |
|
"learning_rate": 4.087912087912088e-05, |
|
"loss": 0.0973, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 4e-05, |
|
"loss": 0.2074, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 20.11, |
|
"learning_rate": 3.912087912087912e-05, |
|
"loss": 0.185, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 20.22, |
|
"learning_rate": 3.824175824175824e-05, |
|
"loss": 0.0895, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 20.33, |
|
"learning_rate": 3.7362637362637365e-05, |
|
"loss": 0.1081, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 20.44, |
|
"learning_rate": 3.648351648351648e-05, |
|
"loss": 0.169, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 20.55, |
|
"learning_rate": 3.560439560439561e-05, |
|
"loss": 0.1601, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 20.66, |
|
"learning_rate": 3.4725274725274726e-05, |
|
"loss": 0.0853, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 20.77, |
|
"learning_rate": 3.384615384615385e-05, |
|
"loss": 0.1067, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 20.88, |
|
"learning_rate": 3.296703296703297e-05, |
|
"loss": 0.1257, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 20.88, |
|
"eval_accuracy": 0.7411764705882353, |
|
"eval_loss": 0.939464807510376, |
|
"eval_runtime": 1.4981, |
|
"eval_samples_per_second": 113.476, |
|
"eval_steps_per_second": 14.685, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 20.99, |
|
"learning_rate": 3.2087912087912094e-05, |
|
"loss": 0.2041, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 21.1, |
|
"learning_rate": 3.120879120879121e-05, |
|
"loss": 0.144, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 21.21, |
|
"learning_rate": 3.032967032967033e-05, |
|
"loss": 0.0677, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 21.32, |
|
"learning_rate": 2.945054945054945e-05, |
|
"loss": 0.1195, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 21.43, |
|
"learning_rate": 2.857142857142857e-05, |
|
"loss": 0.1599, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 21.54, |
|
"learning_rate": 2.7692307692307694e-05, |
|
"loss": 0.0681, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 21.65, |
|
"learning_rate": 2.6813186813186813e-05, |
|
"loss": 0.0854, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 21.76, |
|
"learning_rate": 2.593406593406594e-05, |
|
"loss": 0.1481, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 21.87, |
|
"learning_rate": 2.5054945054945055e-05, |
|
"loss": 0.0927, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 21.98, |
|
"learning_rate": 2.4175824175824177e-05, |
|
"loss": 0.1747, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 21.98, |
|
"eval_accuracy": 0.7470588235294118, |
|
"eval_loss": 0.8745805025100708, |
|
"eval_runtime": 1.5068, |
|
"eval_samples_per_second": 112.823, |
|
"eval_steps_per_second": 14.601, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 22.09, |
|
"learning_rate": 2.3296703296703297e-05, |
|
"loss": 0.0698, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 22.2, |
|
"learning_rate": 2.241758241758242e-05, |
|
"loss": 0.0488, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 22.31, |
|
"learning_rate": 2.1538461538461542e-05, |
|
"loss": 0.0583, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 22.42, |
|
"learning_rate": 2.0659340659340658e-05, |
|
"loss": 0.1999, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 22.53, |
|
"learning_rate": 1.978021978021978e-05, |
|
"loss": 0.0723, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 22.64, |
|
"learning_rate": 1.89010989010989e-05, |
|
"loss": 0.1596, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 22.75, |
|
"learning_rate": 1.8021978021978023e-05, |
|
"loss": 0.1527, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 22.86, |
|
"learning_rate": 1.7142857142857145e-05, |
|
"loss": 0.1554, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 22.97, |
|
"learning_rate": 1.6263736263736265e-05, |
|
"loss": 0.1464, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 23.08, |
|
"learning_rate": 1.5384615384615387e-05, |
|
"loss": 0.1506, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 23.08, |
|
"eval_accuracy": 0.7352941176470589, |
|
"eval_loss": 0.7992474436759949, |
|
"eval_runtime": 1.5262, |
|
"eval_samples_per_second": 111.385, |
|
"eval_steps_per_second": 14.415, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 23.19, |
|
"learning_rate": 1.4505494505494508e-05, |
|
"loss": 0.1008, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 23.3, |
|
"learning_rate": 1.3626373626373626e-05, |
|
"loss": 0.0949, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 23.41, |
|
"learning_rate": 1.2747252747252747e-05, |
|
"loss": 0.09, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 23.52, |
|
"learning_rate": 1.1868131868131868e-05, |
|
"loss": 0.1631, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 23.63, |
|
"learning_rate": 1.0989010989010989e-05, |
|
"loss": 0.0929, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 23.74, |
|
"learning_rate": 1.0109890109890111e-05, |
|
"loss": 0.1425, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 23.85, |
|
"learning_rate": 9.230769230769232e-06, |
|
"loss": 0.1187, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 23.96, |
|
"learning_rate": 8.351648351648352e-06, |
|
"loss": 0.1834, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 24.07, |
|
"learning_rate": 7.4725274725274726e-06, |
|
"loss": 0.1157, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 24.18, |
|
"learning_rate": 6.5934065934065935e-06, |
|
"loss": 0.1021, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 24.18, |
|
"eval_accuracy": 0.7705882352941177, |
|
"eval_loss": 0.7445889711380005, |
|
"eval_runtime": 1.5168, |
|
"eval_samples_per_second": 112.082, |
|
"eval_steps_per_second": 14.505, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 24.29, |
|
"learning_rate": 5.7142857142857145e-06, |
|
"loss": 0.1826, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 24.4, |
|
"learning_rate": 4.8351648351648355e-06, |
|
"loss": 0.1807, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 24.51, |
|
"learning_rate": 3.9560439560439565e-06, |
|
"loss": 0.0946, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 24.62, |
|
"learning_rate": 3.0769230769230774e-06, |
|
"loss": 0.1039, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 24.73, |
|
"learning_rate": 2.197802197802198e-06, |
|
"loss": 0.1729, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 24.84, |
|
"learning_rate": 1.3186813186813187e-06, |
|
"loss": 0.1052, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 24.95, |
|
"learning_rate": 4.3956043956043957e-07, |
|
"loss": 0.1003, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"step": 2275, |
|
"total_flos": 2.8110723118700544e+18, |
|
"train_loss": 0.38098634693648786, |
|
"train_runtime": 883.423, |
|
"train_samples_per_second": 41.062, |
|
"train_steps_per_second": 2.575 |
|
} |
|
], |
|
"max_steps": 2275, |
|
"num_train_epochs": 25, |
|
"total_flos": 2.8110723118700544e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|