| { | |
| "best_metric": 4.228977203369141, | |
| "best_model_checkpoint": "finetuning/output/bart-adapter-finetuned_xe_ey_fae/checkpoint-25000", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 25377, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.804547424833511e-06, | |
| "loss": 7.6974, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.06490582319808594, | |
| "eval_loss": 6.724620819091797, | |
| "eval_runtime": 94.6343, | |
| "eval_samples_per_second": 178.878, | |
| "eval_steps_per_second": 22.36, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.607912676833355e-06, | |
| "loss": 6.8017, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_accuracy": 0.07624003920813896, | |
| "eval_loss": 6.406736373901367, | |
| "eval_runtime": 94.6629, | |
| "eval_samples_per_second": 178.824, | |
| "eval_steps_per_second": 22.353, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.410883871221972e-06, | |
| "loss": 6.5894, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.08208813335328147, | |
| "eval_loss": 6.266135215759277, | |
| "eval_runtime": 94.5601, | |
| "eval_samples_per_second": 179.019, | |
| "eval_steps_per_second": 22.377, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.213855065610593e-06, | |
| "loss": 6.443, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.09051518335536303, | |
| "eval_loss": 6.134974002838135, | |
| "eval_runtime": 94.5786, | |
| "eval_samples_per_second": 178.983, | |
| "eval_steps_per_second": 22.373, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 9.016826259999214e-06, | |
| "loss": 6.3245, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.10075202490707738, | |
| "eval_loss": 6.002374172210693, | |
| "eval_runtime": 94.5343, | |
| "eval_samples_per_second": 179.067, | |
| "eval_steps_per_second": 22.383, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.819797454387831e-06, | |
| "loss": 6.2208, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_accuracy": 0.11453583223288173, | |
| "eval_loss": 5.851789474487305, | |
| "eval_runtime": 94.517, | |
| "eval_samples_per_second": 179.1, | |
| "eval_steps_per_second": 22.388, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.622768648776452e-06, | |
| "loss": 6.097, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.13295434177816914, | |
| "eval_loss": 5.658839225769043, | |
| "eval_runtime": 94.5475, | |
| "eval_samples_per_second": 179.042, | |
| "eval_steps_per_second": 22.38, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 8.425739843165071e-06, | |
| "loss": 5.9862, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_accuracy": 0.15434364158992747, | |
| "eval_loss": 5.464097023010254, | |
| "eval_runtime": 94.6204, | |
| "eval_samples_per_second": 178.904, | |
| "eval_steps_per_second": 22.363, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 8.22871103755369e-06, | |
| "loss": 5.8742, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.17065464547534417, | |
| "eval_loss": 5.319990158081055, | |
| "eval_runtime": 94.6537, | |
| "eval_samples_per_second": 178.841, | |
| "eval_steps_per_second": 22.355, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.03168223194231e-06, | |
| "loss": 5.7716, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.1840178168169571, | |
| "eval_loss": 5.204446315765381, | |
| "eval_runtime": 94.6335, | |
| "eval_samples_per_second": 178.879, | |
| "eval_steps_per_second": 22.36, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 7.83465342633093e-06, | |
| "loss": 5.6952, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.19522825907475083, | |
| "eval_loss": 5.11543607711792, | |
| "eval_runtime": 94.6161, | |
| "eval_samples_per_second": 178.913, | |
| "eval_steps_per_second": 22.364, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 7.63762462071955e-06, | |
| "loss": 5.6209, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.20442877856808384, | |
| "eval_loss": 5.042799949645996, | |
| "eval_runtime": 94.6498, | |
| "eval_samples_per_second": 178.849, | |
| "eval_steps_per_second": 22.356, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.440595815108169e-06, | |
| "loss": 5.5752, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_accuracy": 0.21356098820506358, | |
| "eval_loss": 4.97105598449707, | |
| "eval_runtime": 94.647, | |
| "eval_samples_per_second": 178.854, | |
| "eval_steps_per_second": 22.357, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 7.2435670094967895e-06, | |
| "loss": 5.5091, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.2211917808858752, | |
| "eval_loss": 4.907817363739014, | |
| "eval_runtime": 94.6132, | |
| "eval_samples_per_second": 178.918, | |
| "eval_steps_per_second": 22.365, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 7.0465382038854095e-06, | |
| "loss": 5.4657, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.22866674452100122, | |
| "eval_loss": 4.849499225616455, | |
| "eval_runtime": 94.6751, | |
| "eval_samples_per_second": 178.801, | |
| "eval_steps_per_second": 22.35, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 6.849509398274028e-06, | |
| "loss": 5.4245, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.2359544531397667, | |
| "eval_loss": 4.801201343536377, | |
| "eval_runtime": 94.5944, | |
| "eval_samples_per_second": 178.954, | |
| "eval_steps_per_second": 22.369, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.652480592662648e-06, | |
| "loss": 5.3813, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.24091048075194954, | |
| "eval_loss": 4.756309986114502, | |
| "eval_runtime": 94.6708, | |
| "eval_samples_per_second": 178.809, | |
| "eval_steps_per_second": 22.351, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 6.4554517870512675e-06, | |
| "loss": 5.3501, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.24637192061403781, | |
| "eval_loss": 4.716611862182617, | |
| "eval_runtime": 94.6539, | |
| "eval_samples_per_second": 178.841, | |
| "eval_steps_per_second": 22.355, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.2584229814398866e-06, | |
| "loss": 5.3098, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.2501098972917417, | |
| "eval_loss": 4.683783054351807, | |
| "eval_runtime": 94.7201, | |
| "eval_samples_per_second": 178.716, | |
| "eval_steps_per_second": 22.339, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.0613941758285065e-06, | |
| "loss": 5.2856, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.2551260313174862, | |
| "eval_loss": 4.651512622833252, | |
| "eval_runtime": 94.7148, | |
| "eval_samples_per_second": 178.726, | |
| "eval_steps_per_second": 22.341, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 5.864365370217126e-06, | |
| "loss": 5.2549, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_accuracy": 0.2601890994584574, | |
| "eval_loss": 4.612128257751465, | |
| "eval_runtime": 94.6453, | |
| "eval_samples_per_second": 178.857, | |
| "eval_steps_per_second": 22.357, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 5.6673365646057455e-06, | |
| "loss": 5.2217, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_accuracy": 0.2636951256551434, | |
| "eval_loss": 4.5841240882873535, | |
| "eval_runtime": 94.6678, | |
| "eval_samples_per_second": 178.815, | |
| "eval_steps_per_second": 22.352, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.470701816605588e-06, | |
| "loss": 5.1997, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.267359922045739, | |
| "eval_loss": 4.558795928955078, | |
| "eval_runtime": 94.6574, | |
| "eval_samples_per_second": 178.834, | |
| "eval_steps_per_second": 22.354, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.273673010994208e-06, | |
| "loss": 5.1844, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_accuracy": 0.27077985002194555, | |
| "eval_loss": 4.530928611755371, | |
| "eval_runtime": 94.6472, | |
| "eval_samples_per_second": 178.854, | |
| "eval_steps_per_second": 22.357, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.076644205382827e-06, | |
| "loss": 5.1491, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.27483096084023484, | |
| "eval_loss": 4.499913692474365, | |
| "eval_runtime": 94.5904, | |
| "eval_samples_per_second": 178.961, | |
| "eval_steps_per_second": 22.37, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.879615399771447e-06, | |
| "loss": 5.1244, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_accuracy": 0.27797822970103025, | |
| "eval_loss": 4.47827672958374, | |
| "eval_runtime": 94.6192, | |
| "eval_samples_per_second": 178.907, | |
| "eval_steps_per_second": 22.363, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.6825865941600665e-06, | |
| "loss": 5.1047, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.28116894803558673, | |
| "eval_loss": 4.456052780151367, | |
| "eval_runtime": 94.6508, | |
| "eval_samples_per_second": 178.847, | |
| "eval_steps_per_second": 22.356, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.485557788548686e-06, | |
| "loss": 5.0917, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.28257652944074685, | |
| "eval_loss": 4.440920352935791, | |
| "eval_runtime": 94.6448, | |
| "eval_samples_per_second": 178.858, | |
| "eval_steps_per_second": 22.357, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.2885289829373055e-06, | |
| "loss": 5.0631, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_accuracy": 0.2851284480287185, | |
| "eval_loss": 4.4198174476623535, | |
| "eval_runtime": 94.6157, | |
| "eval_samples_per_second": 178.913, | |
| "eval_steps_per_second": 22.364, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 4.091500177325925e-06, | |
| "loss": 5.0537, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.2881034378022738, | |
| "eval_loss": 4.400303840637207, | |
| "eval_runtime": 94.6637, | |
| "eval_samples_per_second": 178.823, | |
| "eval_steps_per_second": 22.353, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.894865429325768e-06, | |
| "loss": 5.0339, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.2898631699682636, | |
| "eval_loss": 4.385478973388672, | |
| "eval_runtime": 94.7914, | |
| "eval_samples_per_second": 178.582, | |
| "eval_steps_per_second": 22.323, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.6978366237143875e-06, | |
| "loss": 5.0235, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_accuracy": 0.29213215439190976, | |
| "eval_loss": 4.3650221824646, | |
| "eval_runtime": 94.7339, | |
| "eval_samples_per_second": 178.69, | |
| "eval_steps_per_second": 22.336, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.500807818103007e-06, | |
| "loss": 5.0074, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_accuracy": 0.2941743633357399, | |
| "eval_loss": 4.349618911743164, | |
| "eval_runtime": 94.7186, | |
| "eval_samples_per_second": 178.719, | |
| "eval_steps_per_second": 22.34, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.304173070102849e-06, | |
| "loss": 4.9927, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_accuracy": 0.2964732381378149, | |
| "eval_loss": 4.336081027984619, | |
| "eval_runtime": 94.7044, | |
| "eval_samples_per_second": 178.746, | |
| "eval_steps_per_second": 22.343, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.107144264491469e-06, | |
| "loss": 4.9797, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.2981180855432632, | |
| "eval_loss": 4.320304870605469, | |
| "eval_runtime": 94.752, | |
| "eval_samples_per_second": 178.656, | |
| "eval_steps_per_second": 22.332, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.9101154588800883e-06, | |
| "loss": 4.9725, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.2994866192996549, | |
| "eval_loss": 4.311823844909668, | |
| "eval_runtime": 94.7748, | |
| "eval_samples_per_second": 178.613, | |
| "eval_steps_per_second": 22.327, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.713086653268708e-06, | |
| "loss": 4.9552, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.3011751340054841, | |
| "eval_loss": 4.297677516937256, | |
| "eval_runtime": 94.6902, | |
| "eval_samples_per_second": 178.772, | |
| "eval_steps_per_second": 22.347, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.5160578476573277e-06, | |
| "loss": 4.956, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.3018521891702124, | |
| "eval_loss": 4.289434909820557, | |
| "eval_runtime": 94.6916, | |
| "eval_samples_per_second": 178.77, | |
| "eval_steps_per_second": 22.346, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.3190290420459476e-06, | |
| "loss": 4.9427, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.30359935941560284, | |
| "eval_loss": 4.278063774108887, | |
| "eval_runtime": 94.7241, | |
| "eval_samples_per_second": 178.709, | |
| "eval_steps_per_second": 22.339, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.12239429404579e-06, | |
| "loss": 4.9337, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_accuracy": 0.30382226071056156, | |
| "eval_loss": 4.277279853820801, | |
| "eval_runtime": 94.6289, | |
| "eval_samples_per_second": 178.888, | |
| "eval_steps_per_second": 22.361, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.9253654884344093e-06, | |
| "loss": 4.9333, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_accuracy": 0.305628714892609, | |
| "eval_loss": 4.262350559234619, | |
| "eval_runtime": 94.5958, | |
| "eval_samples_per_second": 178.951, | |
| "eval_steps_per_second": 22.369, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1.7283366828230288e-06, | |
| "loss": 4.9173, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_accuracy": 0.30594861364613246, | |
| "eval_loss": 4.26426887512207, | |
| "eval_runtime": 94.6851, | |
| "eval_samples_per_second": 178.782, | |
| "eval_steps_per_second": 22.348, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.5313078772116485e-06, | |
| "loss": 4.915, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_accuracy": 0.3068805715197335, | |
| "eval_loss": 4.253678321838379, | |
| "eval_runtime": 94.5821, | |
| "eval_samples_per_second": 178.977, | |
| "eval_steps_per_second": 22.372, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.3342790716002682e-06, | |
| "loss": 4.9092, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_accuracy": 0.30841780910899225, | |
| "eval_loss": 4.245660781860352, | |
| "eval_runtime": 94.6548, | |
| "eval_samples_per_second": 178.839, | |
| "eval_steps_per_second": 22.355, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.1372502659888877e-06, | |
| "loss": 4.9043, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.3080689795368392, | |
| "eval_loss": 4.245626926422119, | |
| "eval_runtime": 94.7104, | |
| "eval_samples_per_second": 178.734, | |
| "eval_steps_per_second": 22.342, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.402214603775073e-07, | |
| "loss": 4.9014, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.3087008130169778, | |
| "eval_loss": 4.24239444732666, | |
| "eval_runtime": 94.6532, | |
| "eval_samples_per_second": 178.842, | |
| "eval_steps_per_second": 22.355, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 7.431926547661269e-07, | |
| "loss": 4.8889, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_accuracy": 0.3103718452365669, | |
| "eval_loss": 4.2347259521484375, | |
| "eval_runtime": 94.6443, | |
| "eval_samples_per_second": 178.859, | |
| "eval_steps_per_second": 22.357, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5.461638491547465e-07, | |
| "loss": 4.8898, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_accuracy": 0.30947218110795954, | |
| "eval_loss": 4.233951091766357, | |
| "eval_runtime": 94.5592, | |
| "eval_samples_per_second": 179.02, | |
| "eval_steps_per_second": 22.378, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.4952910115458886e-07, | |
| "loss": 4.8814, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_accuracy": 0.31004912351666813, | |
| "eval_loss": 4.2296977043151855, | |
| "eval_runtime": 94.6234, | |
| "eval_samples_per_second": 178.899, | |
| "eval_steps_per_second": 22.362, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 1.5250029554320843e-07, | |
| "loss": 4.8804, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.3095025688930406, | |
| "eval_loss": 4.228977203369141, | |
| "eval_runtime": 94.5894, | |
| "eval_samples_per_second": 178.963, | |
| "eval_steps_per_second": 22.37, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 25377, | |
| "total_flos": 1.2489741444494131e+17, | |
| "train_loss": 5.366477503620405, | |
| "train_runtime": 9239.2947, | |
| "train_samples_per_second": 43.945, | |
| "train_steps_per_second": 2.747 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 25377, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.2489741444494131e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |