|
{ |
|
"best_metric": 1.8420542478561401, |
|
"best_model_checkpoint": "./vit-base-beans/checkpoint-640", |
|
"epoch": 15.0, |
|
"global_step": 2955, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00019932318104906937, |
|
"loss": 3.8192, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00019864636209813877, |
|
"loss": 3.7847, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019796954314720813, |
|
"loss": 3.6849, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019729272419627753, |
|
"loss": 3.6122, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"eval_accuracy": 0.10967741935483871, |
|
"eval_loss": 3.561206340789795, |
|
"eval_runtime": 31.2002, |
|
"eval_samples_per_second": 54.647, |
|
"eval_steps_per_second": 6.859, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00019661590524534686, |
|
"loss": 3.5748, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00019593908629441626, |
|
"loss": 3.491, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00019526226734348562, |
|
"loss": 3.3556, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.000194585448392555, |
|
"loss": 3.4008, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"eval_accuracy": 0.2475073313782991, |
|
"eval_loss": 3.2414700984954834, |
|
"eval_runtime": 30.544, |
|
"eval_samples_per_second": 55.821, |
|
"eval_steps_per_second": 7.006, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00019390862944162438, |
|
"loss": 3.2255, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00019323181049069374, |
|
"loss": 3.1171, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.00019255499153976314, |
|
"loss": 3.1394, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0001918781725888325, |
|
"loss": 3.0872, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"eval_accuracy": 0.2809384164222874, |
|
"eval_loss": 2.9989874362945557, |
|
"eval_runtime": 30.8814, |
|
"eval_samples_per_second": 55.211, |
|
"eval_steps_per_second": 6.93, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.00019120135363790187, |
|
"loss": 2.9773, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.00019052453468697123, |
|
"loss": 2.7993, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.0001898477157360406, |
|
"loss": 2.8672, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.00018917089678511, |
|
"loss": 2.8733, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"eval_accuracy": 0.34252199413489737, |
|
"eval_loss": 2.7833735942840576, |
|
"eval_runtime": 30.3566, |
|
"eval_samples_per_second": 56.166, |
|
"eval_steps_per_second": 7.05, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.00018849407783417936, |
|
"loss": 2.7912, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00018781725888324875, |
|
"loss": 2.7577, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00018714043993231811, |
|
"loss": 2.7865, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.00018646362098138748, |
|
"loss": 2.591, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"eval_accuracy": 0.37360703812316715, |
|
"eval_loss": 2.6250743865966797, |
|
"eval_runtime": 30.4336, |
|
"eval_samples_per_second": 56.024, |
|
"eval_steps_per_second": 7.032, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.00018578680203045687, |
|
"loss": 2.3103, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.00018510998307952624, |
|
"loss": 2.2942, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0001844331641285956, |
|
"loss": 2.3883, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.00018375634517766497, |
|
"loss": 2.1643, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"eval_accuracy": 0.40527859237536656, |
|
"eval_loss": 2.423466920852661, |
|
"eval_runtime": 30.3039, |
|
"eval_samples_per_second": 56.263, |
|
"eval_steps_per_second": 7.062, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.00018307952622673436, |
|
"loss": 2.2077, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00018240270727580373, |
|
"loss": 2.1227, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.0001817258883248731, |
|
"loss": 2.0657, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.00018104906937394248, |
|
"loss": 2.0669, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"eval_accuracy": 0.3882697947214076, |
|
"eval_loss": 2.3226494789123535, |
|
"eval_runtime": 30.2544, |
|
"eval_samples_per_second": 56.355, |
|
"eval_steps_per_second": 7.073, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.00018037225042301185, |
|
"loss": 2.1189, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00017969543147208124, |
|
"loss": 2.1857, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.0001790186125211506, |
|
"loss": 2.272, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.00017834179357021997, |
|
"loss": 1.9717, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"eval_accuracy": 0.40821114369501466, |
|
"eval_loss": 2.2509706020355225, |
|
"eval_runtime": 30.2595, |
|
"eval_samples_per_second": 56.346, |
|
"eval_steps_per_second": 7.072, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00017766497461928934, |
|
"loss": 2.0974, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 0.0001769881556683587, |
|
"loss": 2.1316, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 0.0001763113367174281, |
|
"loss": 2.0845, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 0.00017563451776649746, |
|
"loss": 2.1714, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"eval_accuracy": 0.4351906158357771, |
|
"eval_loss": 2.203674077987671, |
|
"eval_runtime": 30.4099, |
|
"eval_samples_per_second": 56.067, |
|
"eval_steps_per_second": 7.037, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.00017495769881556685, |
|
"loss": 2.0881, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.00017428087986463622, |
|
"loss": 1.9428, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 0.0001736040609137056, |
|
"loss": 1.8203, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 0.00017292724196277498, |
|
"loss": 1.6183, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"eval_accuracy": 0.4533724340175953, |
|
"eval_loss": 2.0731186866760254, |
|
"eval_runtime": 30.3675, |
|
"eval_samples_per_second": 56.146, |
|
"eval_steps_per_second": 7.047, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00017225042301184434, |
|
"loss": 1.3395, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.0001715736040609137, |
|
"loss": 1.4052, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 0.00017089678510998307, |
|
"loss": 1.3804, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 0.00017021996615905247, |
|
"loss": 1.2771, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"eval_accuracy": 0.42052785923753666, |
|
"eval_loss": 2.0928714275360107, |
|
"eval_runtime": 30.2484, |
|
"eval_samples_per_second": 56.367, |
|
"eval_steps_per_second": 7.075, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.00016954314720812183, |
|
"loss": 1.431, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 0.00016886632825719122, |
|
"loss": 1.353, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.0001681895093062606, |
|
"loss": 1.307, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.00016751269035532995, |
|
"loss": 1.2116, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"eval_accuracy": 0.4504398826979472, |
|
"eval_loss": 2.0171947479248047, |
|
"eval_runtime": 30.2989, |
|
"eval_samples_per_second": 56.273, |
|
"eval_steps_per_second": 7.063, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 0.00016683587140439935, |
|
"loss": 1.2762, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 0.0001661590524534687, |
|
"loss": 1.2253, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 0.00016548223350253808, |
|
"loss": 1.238, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.00016480541455160744, |
|
"loss": 1.158, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"eval_accuracy": 0.45689149560117304, |
|
"eval_loss": 1.9670987129211426, |
|
"eval_runtime": 30.2767, |
|
"eval_samples_per_second": 56.314, |
|
"eval_steps_per_second": 7.068, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 0.00016412859560067684, |
|
"loss": 1.1488, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 0.0001634517766497462, |
|
"loss": 1.294, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 0.00016277495769881557, |
|
"loss": 1.0431, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 0.00016209813874788496, |
|
"loss": 1.1864, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"eval_accuracy": 0.4563049853372434, |
|
"eval_loss": 1.9570399522781372, |
|
"eval_runtime": 30.2455, |
|
"eval_samples_per_second": 56.372, |
|
"eval_steps_per_second": 7.075, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 0.00016142131979695432, |
|
"loss": 1.1271, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 0.00016074450084602372, |
|
"loss": 1.1006, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 0.00016006768189509308, |
|
"loss": 1.1867, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 0.00015939086294416242, |
|
"loss": 0.7778, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"eval_accuracy": 0.49560117302052786, |
|
"eval_loss": 1.8706681728363037, |
|
"eval_runtime": 30.3606, |
|
"eval_samples_per_second": 56.158, |
|
"eval_steps_per_second": 7.049, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 0.0001587140439932318, |
|
"loss": 0.6935, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 0.00015803722504230118, |
|
"loss": 0.5692, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.00015736040609137057, |
|
"loss": 0.5985, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 0.00015668358714043994, |
|
"loss": 0.6021, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"eval_accuracy": 0.4950146627565982, |
|
"eval_loss": 1.8420542478561401, |
|
"eval_runtime": 30.3002, |
|
"eval_samples_per_second": 56.27, |
|
"eval_steps_per_second": 7.063, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 0.00015600676818950933, |
|
"loss": 0.5766, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 0.0001553299492385787, |
|
"loss": 0.7232, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 0.00015465313028764806, |
|
"loss": 0.5083, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 0.00015397631133671742, |
|
"loss": 0.5362, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"eval_accuracy": 0.4756598240469208, |
|
"eval_loss": 1.9472501277923584, |
|
"eval_runtime": 30.3609, |
|
"eval_samples_per_second": 56.158, |
|
"eval_steps_per_second": 7.049, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 0.0001532994923857868, |
|
"loss": 0.6784, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 0.00015262267343485618, |
|
"loss": 0.5623, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 0.00015194585448392555, |
|
"loss": 0.5619, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"learning_rate": 0.00015126903553299494, |
|
"loss": 0.5469, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 3.65, |
|
"eval_accuracy": 0.4621700879765396, |
|
"eval_loss": 1.9724935293197632, |
|
"eval_runtime": 30.833, |
|
"eval_samples_per_second": 55.298, |
|
"eval_steps_per_second": 6.941, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 0.0001505922165820643, |
|
"loss": 0.6058, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 0.00014991539763113367, |
|
"loss": 0.5332, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 0.00014923857868020306, |
|
"loss": 0.5891, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 0.00014856175972927243, |
|
"loss": 0.5486, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"eval_accuracy": 0.4744868035190616, |
|
"eval_loss": 1.9740947484970093, |
|
"eval_runtime": 30.1738, |
|
"eval_samples_per_second": 56.506, |
|
"eval_steps_per_second": 7.092, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 0.0001478849407783418, |
|
"loss": 0.624, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 0.00014720812182741116, |
|
"loss": 0.5719, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 0.00014653130287648055, |
|
"loss": 0.6461, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 0.00014585448392554992, |
|
"loss": 0.339, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"eval_accuracy": 0.47038123167155427, |
|
"eval_loss": 1.9945420026779175, |
|
"eval_runtime": 30.3298, |
|
"eval_samples_per_second": 56.215, |
|
"eval_steps_per_second": 7.056, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 0.00014517766497461928, |
|
"loss": 0.2895, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 0.00014450084602368868, |
|
"loss": 0.3324, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 0.00014382402707275804, |
|
"loss": 0.3296, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 0.00014314720812182743, |
|
"loss": 0.2798, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"eval_accuracy": 0.46686217008797654, |
|
"eval_loss": 2.03950572013855, |
|
"eval_runtime": 30.2799, |
|
"eval_samples_per_second": 56.308, |
|
"eval_steps_per_second": 7.067, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 0.0001424703891708968, |
|
"loss": 0.254, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 4.37, |
|
"learning_rate": 0.00014179357021996616, |
|
"loss": 0.2533, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 0.00014111675126903553, |
|
"loss": 0.1897, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 0.0001404399323181049, |
|
"loss": 0.2813, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"eval_accuracy": 0.47390029325513194, |
|
"eval_loss": 2.0258262157440186, |
|
"eval_runtime": 30.5513, |
|
"eval_samples_per_second": 55.808, |
|
"eval_steps_per_second": 7.005, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 0.0001397631133671743, |
|
"loss": 0.3286, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 0.00013908629441624365, |
|
"loss": 0.2575, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 0.00013840947546531305, |
|
"loss": 0.201, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 0.0001377326565143824, |
|
"loss": 0.209, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"eval_accuracy": 0.47624633431085045, |
|
"eval_loss": 2.0693771839141846, |
|
"eval_runtime": 30.3252, |
|
"eval_samples_per_second": 56.224, |
|
"eval_steps_per_second": 7.057, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 0.00013705583756345178, |
|
"loss": 0.2873, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 0.00013637901861252117, |
|
"loss": 0.33, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 0.00013570219966159053, |
|
"loss": 0.2578, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 0.0001350253807106599, |
|
"loss": 0.3733, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"eval_accuracy": 0.4797653958944281, |
|
"eval_loss": 2.0537850856781006, |
|
"eval_runtime": 30.0679, |
|
"eval_samples_per_second": 56.705, |
|
"eval_steps_per_second": 7.117, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 4.92, |
|
"learning_rate": 0.00013434856175972926, |
|
"loss": 0.2922, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 4.97, |
|
"learning_rate": 0.00013367174280879866, |
|
"loss": 0.2236, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 0.00013299492385786802, |
|
"loss": 0.2532, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"learning_rate": 0.0001323181049069374, |
|
"loss": 0.1729, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"eval_accuracy": 0.4563049853372434, |
|
"eval_loss": 2.179201126098633, |
|
"eval_runtime": 30.3122, |
|
"eval_samples_per_second": 56.248, |
|
"eval_steps_per_second": 7.06, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.13, |
|
"learning_rate": 0.00013164128595600678, |
|
"loss": 0.1751, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.18, |
|
"learning_rate": 0.00013096446700507615, |
|
"loss": 0.1609, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 5.23, |
|
"learning_rate": 0.00013028764805414554, |
|
"loss": 0.1254, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"learning_rate": 0.0001296108291032149, |
|
"loss": 0.0891, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"eval_accuracy": 0.4715542521994135, |
|
"eval_loss": 2.140515089035034, |
|
"eval_runtime": 30.4734, |
|
"eval_samples_per_second": 55.95, |
|
"eval_steps_per_second": 7.023, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 5.33, |
|
"learning_rate": 0.00012893401015228427, |
|
"loss": 0.0719, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 5.38, |
|
"learning_rate": 0.00012825719120135363, |
|
"loss": 0.1418, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 0.000127580372250423, |
|
"loss": 0.1633, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 5.48, |
|
"learning_rate": 0.0001269035532994924, |
|
"loss": 0.114, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 5.48, |
|
"eval_accuracy": 0.4774193548387097, |
|
"eval_loss": 2.172985315322876, |
|
"eval_runtime": 30.271, |
|
"eval_samples_per_second": 56.325, |
|
"eval_steps_per_second": 7.069, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 0.00012622673434856176, |
|
"loss": 0.1615, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 5.58, |
|
"learning_rate": 0.00012554991539763115, |
|
"loss": 0.1589, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 5.63, |
|
"learning_rate": 0.00012487309644670052, |
|
"loss": 0.1249, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 0.0001241962774957699, |
|
"loss": 0.207, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"eval_accuracy": 0.4475073313782991, |
|
"eval_loss": 2.32855486869812, |
|
"eval_runtime": 30.3218, |
|
"eval_samples_per_second": 56.23, |
|
"eval_steps_per_second": 7.058, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 5.74, |
|
"learning_rate": 0.00012351945854483927, |
|
"loss": 0.1255, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 0.00012284263959390864, |
|
"loss": 0.0847, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 5.84, |
|
"learning_rate": 0.000122165820642978, |
|
"loss": 0.2418, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"learning_rate": 0.00012148900169204738, |
|
"loss": 0.0984, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"eval_accuracy": 0.4826979472140763, |
|
"eval_loss": 2.280658006668091, |
|
"eval_runtime": 30.3832, |
|
"eval_samples_per_second": 56.116, |
|
"eval_steps_per_second": 7.043, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 5.94, |
|
"learning_rate": 0.00012081218274111676, |
|
"loss": 0.2079, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 5.99, |
|
"learning_rate": 0.00012013536379018613, |
|
"loss": 0.1239, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 0.00011945854483925552, |
|
"loss": 0.1165, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 6.09, |
|
"learning_rate": 0.00011878172588832489, |
|
"loss": 0.0544, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 6.09, |
|
"eval_accuracy": 0.44868035190615835, |
|
"eval_loss": 2.3984222412109375, |
|
"eval_runtime": 30.0364, |
|
"eval_samples_per_second": 56.764, |
|
"eval_steps_per_second": 7.125, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 6.14, |
|
"learning_rate": 0.00011810490693739425, |
|
"loss": 0.1029, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 0.00011742808798646363, |
|
"loss": 0.1151, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 0.000116751269035533, |
|
"loss": 0.0611, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 6.29, |
|
"learning_rate": 0.00011607445008460239, |
|
"loss": 0.1109, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 6.29, |
|
"eval_accuracy": 0.4780058651026393, |
|
"eval_loss": 2.314086437225342, |
|
"eval_runtime": 30.0544, |
|
"eval_samples_per_second": 56.73, |
|
"eval_steps_per_second": 7.12, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 6.35, |
|
"learning_rate": 0.00011539763113367175, |
|
"loss": 0.064, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"learning_rate": 0.00011472081218274113, |
|
"loss": 0.0555, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 6.45, |
|
"learning_rate": 0.0001140439932318105, |
|
"loss": 0.0774, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 6.5, |
|
"learning_rate": 0.00011336717428087986, |
|
"loss": 0.121, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 6.5, |
|
"eval_accuracy": 0.49032258064516127, |
|
"eval_loss": 2.225583791732788, |
|
"eval_runtime": 30.2835, |
|
"eval_samples_per_second": 56.301, |
|
"eval_steps_per_second": 7.067, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 6.55, |
|
"learning_rate": 0.00011269035532994925, |
|
"loss": 0.0801, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 6.6, |
|
"learning_rate": 0.0001120135363790186, |
|
"loss": 0.045, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 6.65, |
|
"learning_rate": 0.000111336717428088, |
|
"loss": 0.0725, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 6.7, |
|
"learning_rate": 0.00011065989847715736, |
|
"loss": 0.0387, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 6.7, |
|
"eval_accuracy": 0.5032258064516129, |
|
"eval_loss": 2.191972494125366, |
|
"eval_runtime": 30.6293, |
|
"eval_samples_per_second": 55.666, |
|
"eval_steps_per_second": 6.987, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 6.75, |
|
"learning_rate": 0.00010998307952622673, |
|
"loss": 0.0376, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 6.8, |
|
"learning_rate": 0.00010930626057529611, |
|
"loss": 0.082, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 6.85, |
|
"learning_rate": 0.00010862944162436547, |
|
"loss": 0.026, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 6.9, |
|
"learning_rate": 0.00010795262267343487, |
|
"loss": 0.0469, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 6.9, |
|
"eval_accuracy": 0.481524926686217, |
|
"eval_loss": 2.3258745670318604, |
|
"eval_runtime": 30.3501, |
|
"eval_samples_per_second": 56.178, |
|
"eval_steps_per_second": 7.051, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 6.95, |
|
"learning_rate": 0.00010727580372250423, |
|
"loss": 0.0221, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 7.01, |
|
"learning_rate": 0.00010659898477157362, |
|
"loss": 0.0234, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 7.06, |
|
"learning_rate": 0.00010592216582064298, |
|
"loss": 0.0536, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"learning_rate": 0.00010524534686971234, |
|
"loss": 0.0269, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"eval_accuracy": 0.49325513196480936, |
|
"eval_loss": 2.3082282543182373, |
|
"eval_runtime": 30.3956, |
|
"eval_samples_per_second": 56.094, |
|
"eval_steps_per_second": 7.04, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 7.16, |
|
"learning_rate": 0.00010456852791878173, |
|
"loss": 0.0626, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 7.21, |
|
"learning_rate": 0.0001038917089678511, |
|
"loss": 0.0338, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 7.26, |
|
"learning_rate": 0.00010321489001692048, |
|
"loss": 0.0534, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 7.31, |
|
"learning_rate": 0.00010253807106598984, |
|
"loss": 0.0482, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 7.31, |
|
"eval_accuracy": 0.47624633431085045, |
|
"eval_loss": 2.3973476886749268, |
|
"eval_runtime": 30.8314, |
|
"eval_samples_per_second": 55.301, |
|
"eval_steps_per_second": 6.941, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 0.00010186125211505924, |
|
"loss": 0.043, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 7.41, |
|
"learning_rate": 0.0001011844331641286, |
|
"loss": 0.0217, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 7.46, |
|
"learning_rate": 0.00010050761421319797, |
|
"loss": 0.0253, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 7.51, |
|
"learning_rate": 9.983079526226735e-05, |
|
"loss": 0.052, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 7.51, |
|
"eval_accuracy": 0.4750733137829912, |
|
"eval_loss": 2.3328230381011963, |
|
"eval_runtime": 30.3845, |
|
"eval_samples_per_second": 56.114, |
|
"eval_steps_per_second": 7.043, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 7.56, |
|
"learning_rate": 9.915397631133673e-05, |
|
"loss": 0.0445, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 7.61, |
|
"learning_rate": 9.847715736040609e-05, |
|
"loss": 0.0927, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 7.66, |
|
"learning_rate": 9.780033840947547e-05, |
|
"loss": 0.0418, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 7.72, |
|
"learning_rate": 9.712351945854485e-05, |
|
"loss": 0.0342, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 7.72, |
|
"eval_accuracy": 0.5020527859237537, |
|
"eval_loss": 2.301551580429077, |
|
"eval_runtime": 31.0377, |
|
"eval_samples_per_second": 54.933, |
|
"eval_steps_per_second": 6.895, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 7.77, |
|
"learning_rate": 9.644670050761421e-05, |
|
"loss": 0.0925, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 7.82, |
|
"learning_rate": 9.576988155668359e-05, |
|
"loss": 0.0187, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 7.87, |
|
"learning_rate": 9.509306260575297e-05, |
|
"loss": 0.0816, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"learning_rate": 9.441624365482235e-05, |
|
"loss": 0.0374, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"eval_accuracy": 0.49736070381231673, |
|
"eval_loss": 2.250404119491577, |
|
"eval_runtime": 31.1263, |
|
"eval_samples_per_second": 54.777, |
|
"eval_steps_per_second": 6.875, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 7.97, |
|
"learning_rate": 9.373942470389172e-05, |
|
"loss": 0.0521, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 9.306260575296108e-05, |
|
"loss": 0.0443, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 8.07, |
|
"learning_rate": 9.238578680203046e-05, |
|
"loss": 0.019, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 8.12, |
|
"learning_rate": 9.170896785109984e-05, |
|
"loss": 0.0169, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 8.12, |
|
"eval_accuracy": 0.48328445747800586, |
|
"eval_loss": 2.3862178325653076, |
|
"eval_runtime": 30.7127, |
|
"eval_samples_per_second": 55.514, |
|
"eval_steps_per_second": 6.968, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 8.17, |
|
"learning_rate": 9.103214890016922e-05, |
|
"loss": 0.0239, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 8.22, |
|
"learning_rate": 9.035532994923858e-05, |
|
"loss": 0.0145, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 8.967851099830795e-05, |
|
"loss": 0.0398, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 8.900169204737733e-05, |
|
"loss": 0.084, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"eval_accuracy": 0.49442815249266864, |
|
"eval_loss": 2.4026331901550293, |
|
"eval_runtime": 30.8185, |
|
"eval_samples_per_second": 55.324, |
|
"eval_steps_per_second": 6.944, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 8.38, |
|
"learning_rate": 8.83248730964467e-05, |
|
"loss": 0.0215, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 8.43, |
|
"learning_rate": 8.764805414551607e-05, |
|
"loss": 0.0115, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 8.48, |
|
"learning_rate": 8.697123519458545e-05, |
|
"loss": 0.0331, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 8.53, |
|
"learning_rate": 8.629441624365483e-05, |
|
"loss": 0.0115, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 8.53, |
|
"eval_accuracy": 0.49149560117302055, |
|
"eval_loss": 2.382765293121338, |
|
"eval_runtime": 30.6052, |
|
"eval_samples_per_second": 55.71, |
|
"eval_steps_per_second": 6.992, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 8.58, |
|
"learning_rate": 8.561759729272421e-05, |
|
"loss": 0.0304, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 8.63, |
|
"learning_rate": 8.494077834179357e-05, |
|
"loss": 0.0108, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 8.68, |
|
"learning_rate": 8.426395939086294e-05, |
|
"loss": 0.0252, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 8.73, |
|
"learning_rate": 8.358714043993232e-05, |
|
"loss": 0.0285, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 8.73, |
|
"eval_accuracy": 0.49560117302052786, |
|
"eval_loss": 2.352389097213745, |
|
"eval_runtime": 30.3007, |
|
"eval_samples_per_second": 56.269, |
|
"eval_steps_per_second": 7.063, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 8.78, |
|
"learning_rate": 8.29103214890017e-05, |
|
"loss": 0.0605, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 8.83, |
|
"learning_rate": 8.223350253807108e-05, |
|
"loss": 0.0314, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 8.88, |
|
"learning_rate": 8.155668358714044e-05, |
|
"loss": 0.0135, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 8.93, |
|
"learning_rate": 8.087986463620981e-05, |
|
"loss": 0.1062, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 8.93, |
|
"eval_accuracy": 0.49149560117302055, |
|
"eval_loss": 2.412898063659668, |
|
"eval_runtime": 30.498, |
|
"eval_samples_per_second": 55.905, |
|
"eval_steps_per_second": 7.017, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 8.98, |
|
"learning_rate": 8.020304568527919e-05, |
|
"loss": 0.025, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 9.04, |
|
"learning_rate": 7.952622673434857e-05, |
|
"loss": 0.0383, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 9.09, |
|
"learning_rate": 7.884940778341794e-05, |
|
"loss": 0.0116, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"learning_rate": 7.817258883248731e-05, |
|
"loss": 0.0113, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"eval_accuracy": 0.49208211143695013, |
|
"eval_loss": 2.3613696098327637, |
|
"eval_runtime": 30.6596, |
|
"eval_samples_per_second": 55.611, |
|
"eval_steps_per_second": 6.98, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 9.19, |
|
"learning_rate": 7.749576988155669e-05, |
|
"loss": 0.0226, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 9.24, |
|
"learning_rate": 7.681895093062607e-05, |
|
"loss": 0.0203, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 9.29, |
|
"learning_rate": 7.614213197969543e-05, |
|
"loss": 0.0354, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 9.34, |
|
"learning_rate": 7.546531302876481e-05, |
|
"loss": 0.0101, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 9.34, |
|
"eval_accuracy": 0.5002932551319648, |
|
"eval_loss": 2.3706891536712646, |
|
"eval_runtime": 30.567, |
|
"eval_samples_per_second": 55.779, |
|
"eval_steps_per_second": 7.001, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"learning_rate": 7.478849407783418e-05, |
|
"loss": 0.0181, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 9.44, |
|
"learning_rate": 7.411167512690356e-05, |
|
"loss": 0.0368, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 9.49, |
|
"learning_rate": 7.343485617597293e-05, |
|
"loss": 0.0082, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 9.54, |
|
"learning_rate": 7.275803722504231e-05, |
|
"loss": 0.028, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 9.54, |
|
"eval_accuracy": 0.4967741935483871, |
|
"eval_loss": 2.414238452911377, |
|
"eval_runtime": 30.6609, |
|
"eval_samples_per_second": 55.608, |
|
"eval_steps_per_second": 6.98, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 7.208121827411168e-05, |
|
"loss": 0.0404, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 9.64, |
|
"learning_rate": 7.140439932318104e-05, |
|
"loss": 0.0486, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 9.7, |
|
"learning_rate": 7.072758037225042e-05, |
|
"loss": 0.0197, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 9.75, |
|
"learning_rate": 7.00507614213198e-05, |
|
"loss": 0.0131, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 9.75, |
|
"eval_accuracy": 0.501466275659824, |
|
"eval_loss": 2.4358253479003906, |
|
"eval_runtime": 30.4732, |
|
"eval_samples_per_second": 55.951, |
|
"eval_steps_per_second": 7.023, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 9.8, |
|
"learning_rate": 6.937394247038918e-05, |
|
"loss": 0.0394, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 9.85, |
|
"learning_rate": 6.869712351945855e-05, |
|
"loss": 0.0402, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 9.9, |
|
"learning_rate": 6.802030456852793e-05, |
|
"loss": 0.0215, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"learning_rate": 6.734348561759729e-05, |
|
"loss": 0.0115, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"eval_accuracy": 0.4997067448680352, |
|
"eval_loss": 2.3999907970428467, |
|
"eval_runtime": 30.5014, |
|
"eval_samples_per_second": 55.899, |
|
"eval_steps_per_second": 7.016, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 6.666666666666667e-05, |
|
"loss": 0.0148, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 10.05, |
|
"learning_rate": 6.598984771573604e-05, |
|
"loss": 0.0075, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 10.1, |
|
"learning_rate": 6.531302876480541e-05, |
|
"loss": 0.0232, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 10.15, |
|
"learning_rate": 6.463620981387479e-05, |
|
"loss": 0.0108, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 10.15, |
|
"eval_accuracy": 0.5043988269794721, |
|
"eval_loss": 2.407888889312744, |
|
"eval_runtime": 30.7257, |
|
"eval_samples_per_second": 55.491, |
|
"eval_steps_per_second": 6.965, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 10.2, |
|
"learning_rate": 6.395939086294417e-05, |
|
"loss": 0.0182, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 10.25, |
|
"learning_rate": 6.328257191201354e-05, |
|
"loss": 0.0219, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 10.3, |
|
"learning_rate": 6.26057529610829e-05, |
|
"loss": 0.0277, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 10.36, |
|
"learning_rate": 6.192893401015228e-05, |
|
"loss": 0.009, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 10.36, |
|
"eval_accuracy": 0.5067448680351906, |
|
"eval_loss": 2.3866255283355713, |
|
"eval_runtime": 30.7008, |
|
"eval_samples_per_second": 55.536, |
|
"eval_steps_per_second": 6.971, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 10.41, |
|
"learning_rate": 6.125211505922166e-05, |
|
"loss": 0.0212, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 10.46, |
|
"learning_rate": 6.057529610829103e-05, |
|
"loss": 0.0065, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 10.51, |
|
"learning_rate": 5.989847715736041e-05, |
|
"loss": 0.0306, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 10.56, |
|
"learning_rate": 5.9221658206429784e-05, |
|
"loss": 0.0112, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 10.56, |
|
"eval_accuracy": 0.5085043988269795, |
|
"eval_loss": 2.3716347217559814, |
|
"eval_runtime": 30.6367, |
|
"eval_samples_per_second": 55.652, |
|
"eval_steps_per_second": 6.985, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 10.61, |
|
"learning_rate": 5.854483925549916e-05, |
|
"loss": 0.0325, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 10.66, |
|
"learning_rate": 5.786802030456853e-05, |
|
"loss": 0.0335, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 10.71, |
|
"learning_rate": 5.71912013536379e-05, |
|
"loss": 0.0209, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 10.76, |
|
"learning_rate": 5.651438240270728e-05, |
|
"loss": 0.0066, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 10.76, |
|
"eval_accuracy": 0.509090909090909, |
|
"eval_loss": 2.3734991550445557, |
|
"eval_runtime": 30.6695, |
|
"eval_samples_per_second": 55.593, |
|
"eval_steps_per_second": 6.978, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 10.81, |
|
"learning_rate": 5.583756345177665e-05, |
|
"loss": 0.0146, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 10.86, |
|
"learning_rate": 5.516074450084603e-05, |
|
"loss": 0.0061, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 10.91, |
|
"learning_rate": 5.44839255499154e-05, |
|
"loss": 0.0163, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 10.96, |
|
"learning_rate": 5.380710659898477e-05, |
|
"loss": 0.0164, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 10.96, |
|
"eval_accuracy": 0.5055718475073314, |
|
"eval_loss": 2.399704694747925, |
|
"eval_runtime": 30.8256, |
|
"eval_samples_per_second": 55.311, |
|
"eval_steps_per_second": 6.942, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 11.02, |
|
"learning_rate": 5.313028764805415e-05, |
|
"loss": 0.017, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 11.07, |
|
"learning_rate": 5.245346869712352e-05, |
|
"loss": 0.0056, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 11.12, |
|
"learning_rate": 5.17766497461929e-05, |
|
"loss": 0.0191, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 11.17, |
|
"learning_rate": 5.109983079526227e-05, |
|
"loss": 0.0126, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 11.17, |
|
"eval_accuracy": 0.5055718475073314, |
|
"eval_loss": 2.4104385375976562, |
|
"eval_runtime": 30.7309, |
|
"eval_samples_per_second": 55.482, |
|
"eval_steps_per_second": 6.964, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 11.22, |
|
"learning_rate": 5.042301184433165e-05, |
|
"loss": 0.0125, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 11.27, |
|
"learning_rate": 4.9746192893401014e-05, |
|
"loss": 0.011, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 11.32, |
|
"learning_rate": 4.906937394247039e-05, |
|
"loss": 0.0305, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 11.37, |
|
"learning_rate": 4.8392554991539766e-05, |
|
"loss": 0.0174, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 11.37, |
|
"eval_accuracy": 0.5026392961876833, |
|
"eval_loss": 2.443206548690796, |
|
"eval_runtime": 30.8601, |
|
"eval_samples_per_second": 55.249, |
|
"eval_steps_per_second": 6.935, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 11.42, |
|
"learning_rate": 4.771573604060914e-05, |
|
"loss": 0.0125, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 11.47, |
|
"learning_rate": 4.7038917089678517e-05, |
|
"loss": 0.0127, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 11.52, |
|
"learning_rate": 4.636209813874789e-05, |
|
"loss": 0.0253, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 11.57, |
|
"learning_rate": 4.568527918781726e-05, |
|
"loss": 0.0241, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 11.57, |
|
"eval_accuracy": 0.5055718475073314, |
|
"eval_loss": 2.4564218521118164, |
|
"eval_runtime": 30.6781, |
|
"eval_samples_per_second": 55.577, |
|
"eval_steps_per_second": 6.976, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 11.62, |
|
"learning_rate": 4.500846023688663e-05, |
|
"loss": 0.0084, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 11.68, |
|
"learning_rate": 4.433164128595601e-05, |
|
"loss": 0.0054, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 11.73, |
|
"learning_rate": 4.365482233502538e-05, |
|
"loss": 0.0055, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 11.78, |
|
"learning_rate": 4.2978003384094756e-05, |
|
"loss": 0.0182, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 11.78, |
|
"eval_accuracy": 0.5038123167155425, |
|
"eval_loss": 2.481368064880371, |
|
"eval_runtime": 30.9495, |
|
"eval_samples_per_second": 55.09, |
|
"eval_steps_per_second": 6.914, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 11.83, |
|
"learning_rate": 4.230118443316413e-05, |
|
"loss": 0.0205, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 11.88, |
|
"learning_rate": 4.162436548223351e-05, |
|
"loss": 0.0053, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 11.93, |
|
"learning_rate": 4.094754653130288e-05, |
|
"loss": 0.0153, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 11.98, |
|
"learning_rate": 4.027072758037225e-05, |
|
"loss": 0.0196, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 11.98, |
|
"eval_accuracy": 0.5032258064516129, |
|
"eval_loss": 2.4746322631835938, |
|
"eval_runtime": 30.3112, |
|
"eval_samples_per_second": 56.25, |
|
"eval_steps_per_second": 7.06, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 12.03, |
|
"learning_rate": 3.959390862944163e-05, |
|
"loss": 0.0114, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 12.08, |
|
"learning_rate": 3.8917089678510996e-05, |
|
"loss": 0.0144, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 12.13, |
|
"learning_rate": 3.8240270727580375e-05, |
|
"loss": 0.0193, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 12.18, |
|
"learning_rate": 3.756345177664975e-05, |
|
"loss": 0.0104, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 12.18, |
|
"eval_accuracy": 0.5079178885630499, |
|
"eval_loss": 2.4812278747558594, |
|
"eval_runtime": 30.7018, |
|
"eval_samples_per_second": 55.534, |
|
"eval_steps_per_second": 6.97, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 12.23, |
|
"learning_rate": 3.688663282571912e-05, |
|
"loss": 0.015, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 12.28, |
|
"learning_rate": 3.62098138747885e-05, |
|
"loss": 0.0115, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 12.34, |
|
"learning_rate": 3.553299492385787e-05, |
|
"loss": 0.0152, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 12.39, |
|
"learning_rate": 3.485617597292725e-05, |
|
"loss": 0.0254, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 12.39, |
|
"eval_accuracy": 0.506158357771261, |
|
"eval_loss": 2.465996265411377, |
|
"eval_runtime": 30.4976, |
|
"eval_samples_per_second": 55.906, |
|
"eval_steps_per_second": 7.017, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 12.44, |
|
"learning_rate": 3.4179357021996615e-05, |
|
"loss": 0.005, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 12.49, |
|
"learning_rate": 3.3502538071065994e-05, |
|
"loss": 0.0046, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 12.54, |
|
"learning_rate": 3.2825719120135366e-05, |
|
"loss": 0.0048, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 12.59, |
|
"learning_rate": 3.214890016920474e-05, |
|
"loss": 0.0057, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 12.59, |
|
"eval_accuracy": 0.5096774193548387, |
|
"eval_loss": 2.4570250511169434, |
|
"eval_runtime": 30.647, |
|
"eval_samples_per_second": 55.634, |
|
"eval_steps_per_second": 6.983, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 12.64, |
|
"learning_rate": 3.147208121827411e-05, |
|
"loss": 0.0159, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 12.69, |
|
"learning_rate": 3.079526226734349e-05, |
|
"loss": 0.0156, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 12.74, |
|
"learning_rate": 3.0118443316412858e-05, |
|
"loss": 0.0089, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 12.79, |
|
"learning_rate": 2.9441624365482233e-05, |
|
"loss": 0.0161, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 12.79, |
|
"eval_accuracy": 0.509090909090909, |
|
"eval_loss": 2.452195644378662, |
|
"eval_runtime": 30.5139, |
|
"eval_samples_per_second": 55.876, |
|
"eval_steps_per_second": 7.013, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 12.84, |
|
"learning_rate": 2.876480541455161e-05, |
|
"loss": 0.0046, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 12.89, |
|
"learning_rate": 2.808798646362098e-05, |
|
"loss": 0.0181, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 12.94, |
|
"learning_rate": 2.7411167512690357e-05, |
|
"loss": 0.0131, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 12.99, |
|
"learning_rate": 2.6734348561759732e-05, |
|
"loss": 0.0237, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 12.99, |
|
"eval_accuracy": 0.506158357771261, |
|
"eval_loss": 2.461273670196533, |
|
"eval_runtime": 30.9259, |
|
"eval_samples_per_second": 55.132, |
|
"eval_steps_per_second": 6.92, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 13.05, |
|
"learning_rate": 2.6057529610829108e-05, |
|
"loss": 0.0098, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 13.1, |
|
"learning_rate": 2.5380710659898476e-05, |
|
"loss": 0.0135, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 13.15, |
|
"learning_rate": 2.4703891708967852e-05, |
|
"loss": 0.009, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 13.2, |
|
"learning_rate": 2.4027072758037224e-05, |
|
"loss": 0.0048, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 13.2, |
|
"eval_accuracy": 0.5055718475073314, |
|
"eval_loss": 2.4772698879241943, |
|
"eval_runtime": 30.4386, |
|
"eval_samples_per_second": 56.014, |
|
"eval_steps_per_second": 7.031, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 13.25, |
|
"learning_rate": 2.33502538071066e-05, |
|
"loss": 0.0138, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 13.3, |
|
"learning_rate": 2.2673434856175975e-05, |
|
"loss": 0.009, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 13.35, |
|
"learning_rate": 2.199661590524535e-05, |
|
"loss": 0.0044, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 13.4, |
|
"learning_rate": 2.1319796954314723e-05, |
|
"loss": 0.0067, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 13.4, |
|
"eval_accuracy": 0.5079178885630499, |
|
"eval_loss": 2.474796772003174, |
|
"eval_runtime": 30.9994, |
|
"eval_samples_per_second": 55.001, |
|
"eval_steps_per_second": 6.903, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 13.45, |
|
"learning_rate": 2.0642978003384095e-05, |
|
"loss": 0.0048, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 13.5, |
|
"learning_rate": 1.996615905245347e-05, |
|
"loss": 0.0201, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 13.55, |
|
"learning_rate": 1.9289340101522843e-05, |
|
"loss": 0.0144, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 13.6, |
|
"learning_rate": 1.8612521150592218e-05, |
|
"loss": 0.0105, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 13.6, |
|
"eval_accuracy": 0.5085043988269795, |
|
"eval_loss": 2.4759089946746826, |
|
"eval_runtime": 30.6746, |
|
"eval_samples_per_second": 55.584, |
|
"eval_steps_per_second": 6.976, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 13.65, |
|
"learning_rate": 1.793570219966159e-05, |
|
"loss": 0.0174, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 13.71, |
|
"learning_rate": 1.7258883248730966e-05, |
|
"loss": 0.0045, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 13.76, |
|
"learning_rate": 1.658206429780034e-05, |
|
"loss": 0.0044, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 13.81, |
|
"learning_rate": 1.5905245346869714e-05, |
|
"loss": 0.0209, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 13.81, |
|
"eval_accuracy": 0.506158357771261, |
|
"eval_loss": 2.4831149578094482, |
|
"eval_runtime": 30.8346, |
|
"eval_samples_per_second": 55.295, |
|
"eval_steps_per_second": 6.94, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 13.86, |
|
"learning_rate": 1.5228426395939088e-05, |
|
"loss": 0.0122, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 13.91, |
|
"learning_rate": 1.4551607445008461e-05, |
|
"loss": 0.0149, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 13.96, |
|
"learning_rate": 1.3874788494077834e-05, |
|
"loss": 0.0225, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"learning_rate": 1.3197969543147209e-05, |
|
"loss": 0.0112, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 14.01, |
|
"eval_accuracy": 0.5085043988269795, |
|
"eval_loss": 2.482898473739624, |
|
"eval_runtime": 30.9465, |
|
"eval_samples_per_second": 55.095, |
|
"eval_steps_per_second": 6.915, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 14.06, |
|
"learning_rate": 1.2521150592216583e-05, |
|
"loss": 0.0084, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 14.11, |
|
"learning_rate": 1.1844331641285957e-05, |
|
"loss": 0.0127, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 14.16, |
|
"learning_rate": 1.116751269035533e-05, |
|
"loss": 0.0097, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 14.21, |
|
"learning_rate": 1.0490693739424704e-05, |
|
"loss": 0.0084, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 14.21, |
|
"eval_accuracy": 0.509090909090909, |
|
"eval_loss": 2.4852123260498047, |
|
"eval_runtime": 30.864, |
|
"eval_samples_per_second": 55.242, |
|
"eval_steps_per_second": 6.934, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 14.26, |
|
"learning_rate": 9.813874788494078e-06, |
|
"loss": 0.0078, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 14.31, |
|
"learning_rate": 9.137055837563452e-06, |
|
"loss": 0.0173, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 14.37, |
|
"learning_rate": 8.460236886632826e-06, |
|
"loss": 0.0145, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 14.42, |
|
"learning_rate": 7.7834179357022e-06, |
|
"loss": 0.0203, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 14.42, |
|
"eval_accuracy": 0.5096774193548387, |
|
"eval_loss": 2.4804649353027344, |
|
"eval_runtime": 30.8958, |
|
"eval_samples_per_second": 55.185, |
|
"eval_steps_per_second": 6.927, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 14.47, |
|
"learning_rate": 7.106598984771575e-06, |
|
"loss": 0.0143, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 14.52, |
|
"learning_rate": 6.429780033840948e-06, |
|
"loss": 0.0094, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 14.57, |
|
"learning_rate": 5.7529610829103214e-06, |
|
"loss": 0.0105, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 14.62, |
|
"learning_rate": 5.076142131979695e-06, |
|
"loss": 0.0086, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 14.62, |
|
"eval_accuracy": 0.5085043988269795, |
|
"eval_loss": 2.480623960494995, |
|
"eval_runtime": 30.8962, |
|
"eval_samples_per_second": 55.185, |
|
"eval_steps_per_second": 6.926, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 14.67, |
|
"learning_rate": 4.39932318104907e-06, |
|
"loss": 0.01, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 14.72, |
|
"learning_rate": 3.7225042301184434e-06, |
|
"loss": 0.0048, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 14.77, |
|
"learning_rate": 3.0456852791878177e-06, |
|
"loss": 0.0087, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 14.82, |
|
"learning_rate": 2.3688663282571915e-06, |
|
"loss": 0.0103, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 14.82, |
|
"eval_accuracy": 0.5085043988269795, |
|
"eval_loss": 2.4825499057769775, |
|
"eval_runtime": 30.9894, |
|
"eval_samples_per_second": 55.019, |
|
"eval_steps_per_second": 6.906, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 14.87, |
|
"learning_rate": 1.6920473773265652e-06, |
|
"loss": 0.0095, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 14.92, |
|
"learning_rate": 1.015228426395939e-06, |
|
"loss": 0.0046, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 14.97, |
|
"learning_rate": 3.38409475465313e-07, |
|
"loss": 0.0113, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"step": 2955, |
|
"total_flos": 3.64901908299393e+18, |
|
"train_loss": 0.5233747142333972, |
|
"train_runtime": 4896.0515, |
|
"train_samples_per_second": 9.614, |
|
"train_steps_per_second": 0.604 |
|
} |
|
], |
|
"max_steps": 2955, |
|
"num_train_epochs": 15, |
|
"total_flos": 3.64901908299393e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|