| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "global_step": 63575, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "learning_rate": 4.9606763664962646e-05, |
| "loss": 0.6201, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 4.921352732992528e-05, |
| "loss": 0.6142, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 4.882029099488793e-05, |
| "loss": 0.6107, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 4.8427054659850575e-05, |
| "loss": 0.6097, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 4.803381832481321e-05, |
| "loss": 0.6088, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 4.7640581989775855e-05, |
| "loss": 0.6155, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 4.72473456547385e-05, |
| "loss": 0.6084, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 4.685410931970115e-05, |
| "loss": 0.6064, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 4.6460872984663785e-05, |
| "loss": 0.6085, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 4.606763664962643e-05, |
| "loss": 0.6056, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 4.567440031458907e-05, |
| "loss": 0.6066, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 4.528116397955171e-05, |
| "loss": 0.6065, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 4.488792764451436e-05, |
| "loss": 0.6031, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 4.4494691309477e-05, |
| "loss": 0.6049, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.410145497443964e-05, |
| "loss": 0.6031, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 4.370821863940228e-05, |
| "loss": 0.6059, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 4.3314982304364923e-05, |
| "loss": 0.6005, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 4.2921745969327573e-05, |
| "loss": 0.6018, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 4.252850963429021e-05, |
| "loss": 0.6012, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 4.213527329925285e-05, |
| "loss": 0.6037, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 4.1742036964215496e-05, |
| "loss": 0.6056, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 4.134880062917813e-05, |
| "loss": 0.6002, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 4.095556429414078e-05, |
| "loss": 0.5984, |
| "step": 11500 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 4.0562327959103426e-05, |
| "loss": 0.6002, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 4.016909162406606e-05, |
| "loss": 0.5967, |
| "step": 12500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_bleu": 26.593, |
| "eval_bleu_random_subnet": 26.593, |
| "eval_bleu_smallest_subnet": 26.593, |
| "eval_bleu_sum": 79.779, |
| "eval_gen_len": 42.4422, |
| "eval_gen_len_random_subnet": 42.4422, |
| "eval_gen_len_smallest_subnet": 42.4422, |
| "eval_gen_len_sum": 127.3266, |
| "eval_loss": 1.382042407989502, |
| "eval_loss_random_subnet": 1.382042407989502, |
| "eval_loss_smallest_subnet": 1.382042407989502, |
| "eval_loss_sum": 4.146127223968506, |
| "eval_runtime": 58.2627, |
| "eval_samples_per_second": 34.31, |
| "eval_steps_per_second": 0.36, |
| "step": 12715 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 3.9775855289028706e-05, |
| "loss": 0.5909, |
| "step": 13000 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 3.938261895399135e-05, |
| "loss": 0.5852, |
| "step": 13500 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 3.8989382618954e-05, |
| "loss": 0.5861, |
| "step": 14000 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 3.8596146283916635e-05, |
| "loss": 0.5852, |
| "step": 14500 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 3.820290994887928e-05, |
| "loss": 0.5876, |
| "step": 15000 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 3.780967361384192e-05, |
| "loss": 0.5827, |
| "step": 15500 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 3.741643727880456e-05, |
| "loss": 0.5915, |
| "step": 16000 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 3.702320094376721e-05, |
| "loss": 0.5852, |
| "step": 16500 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 3.662996460872985e-05, |
| "loss": 0.5837, |
| "step": 17000 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 3.623672827369249e-05, |
| "loss": 0.583, |
| "step": 17500 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 3.584349193865513e-05, |
| "loss": 0.582, |
| "step": 18000 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 3.5450255603617774e-05, |
| "loss": 0.5879, |
| "step": 18500 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 3.5057019268580424e-05, |
| "loss": 0.5873, |
| "step": 19000 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 3.466378293354306e-05, |
| "loss": 0.578, |
| "step": 19500 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 3.4270546598505704e-05, |
| "loss": 0.5775, |
| "step": 20000 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 3.387731026346835e-05, |
| "loss": 0.5812, |
| "step": 20500 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 3.3484073928430984e-05, |
| "loss": 0.5805, |
| "step": 21000 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 3.3090837593393633e-05, |
| "loss": 0.5819, |
| "step": 21500 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 3.269760125835628e-05, |
| "loss": 0.5816, |
| "step": 22000 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 3.230436492331891e-05, |
| "loss": 0.5809, |
| "step": 22500 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 3.1911128588281556e-05, |
| "loss": 0.5808, |
| "step": 23000 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 3.15178922532442e-05, |
| "loss": 0.5785, |
| "step": 23500 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 3.112465591820685e-05, |
| "loss": 0.5781, |
| "step": 24000 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 3.0731419583169486e-05, |
| "loss": 0.5806, |
| "step": 24500 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 3.033818324813213e-05, |
| "loss": 0.5768, |
| "step": 25000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_bleu": 26.6191, |
| "eval_bleu_random_subnet": 26.6191, |
| "eval_bleu_smallest_subnet": 26.6191, |
| "eval_bleu_sum": 79.8573, |
| "eval_gen_len": 42.6738, |
| "eval_gen_len_random_subnet": 42.6738, |
| "eval_gen_len_smallest_subnet": 42.6738, |
| "eval_gen_len_sum": 128.0214, |
| "eval_loss": 1.3727843761444092, |
| "eval_loss_random_subnet": 1.3727843761444092, |
| "eval_loss_smallest_subnet": 1.3727843761444092, |
| "eval_loss_sum": 4.1183531284332275, |
| "eval_runtime": 58.9438, |
| "eval_samples_per_second": 33.914, |
| "eval_steps_per_second": 0.356, |
| "step": 25430 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 2.9944946913094772e-05, |
| "loss": 0.5748, |
| "step": 25500 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 2.9551710578057412e-05, |
| "loss": 0.5645, |
| "step": 26000 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 2.9158474243020055e-05, |
| "loss": 0.5638, |
| "step": 26500 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 2.8765237907982702e-05, |
| "loss": 0.5676, |
| "step": 27000 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 2.837200157294534e-05, |
| "loss": 0.5698, |
| "step": 27500 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 2.7978765237907985e-05, |
| "loss": 0.5667, |
| "step": 28000 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 2.758552890287063e-05, |
| "loss": 0.5718, |
| "step": 28500 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 2.719229256783327e-05, |
| "loss": 0.5693, |
| "step": 29000 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 2.679905623279591e-05, |
| "loss": 0.5664, |
| "step": 29500 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 2.6405819897758555e-05, |
| "loss": 0.5652, |
| "step": 30000 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 2.6012583562721198e-05, |
| "loss": 0.5721, |
| "step": 30500 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 2.5619347227683838e-05, |
| "loss": 0.5676, |
| "step": 31000 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 2.522611089264648e-05, |
| "loss": 0.5631, |
| "step": 31500 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 2.4832874557609124e-05, |
| "loss": 0.5672, |
| "step": 32000 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 2.4439638222571767e-05, |
| "loss": 0.5653, |
| "step": 32500 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 2.404640188753441e-05, |
| "loss": 0.5691, |
| "step": 33000 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 2.3653165552497054e-05, |
| "loss": 0.5613, |
| "step": 33500 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 2.3259929217459694e-05, |
| "loss": 0.5661, |
| "step": 34000 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 2.2866692882422337e-05, |
| "loss": 0.568, |
| "step": 34500 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 2.247345654738498e-05, |
| "loss": 0.5648, |
| "step": 35000 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 2.2080220212347623e-05, |
| "loss": 0.5654, |
| "step": 35500 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 2.1686983877310266e-05, |
| "loss": 0.5671, |
| "step": 36000 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 2.1293747542272906e-05, |
| "loss": 0.5633, |
| "step": 36500 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 2.090051120723555e-05, |
| "loss": 0.5645, |
| "step": 37000 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 2.0507274872198193e-05, |
| "loss": 0.5667, |
| "step": 37500 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 2.0114038537160836e-05, |
| "loss": 0.5663, |
| "step": 38000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_bleu": 26.9203, |
| "eval_bleu_random_subnet": 26.9203, |
| "eval_bleu_smallest_subnet": 26.9203, |
| "eval_bleu_sum": 80.7609, |
| "eval_gen_len": 42.5298, |
| "eval_gen_len_random_subnet": 42.5298, |
| "eval_gen_len_smallest_subnet": 42.5298, |
| "eval_gen_len_sum": 127.58940000000001, |
| "eval_loss": 1.3616396188735962, |
| "eval_loss_random_subnet": 1.3616396188735962, |
| "eval_loss_smallest_subnet": 1.3616396188735962, |
| "eval_loss_sum": 4.084918856620789, |
| "eval_runtime": 58.6658, |
| "eval_samples_per_second": 34.074, |
| "eval_steps_per_second": 0.358, |
| "step": 38145 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 1.972080220212348e-05, |
| "loss": 0.5601, |
| "step": 38500 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 1.932756586708612e-05, |
| "loss": 0.5545, |
| "step": 39000 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 1.8934329532048762e-05, |
| "loss": 0.5571, |
| "step": 39500 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 1.8541093197011405e-05, |
| "loss": 0.5549, |
| "step": 40000 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 1.814785686197405e-05, |
| "loss": 0.5516, |
| "step": 40500 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 1.7754620526936692e-05, |
| "loss": 0.557, |
| "step": 41000 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 1.736138419189933e-05, |
| "loss": 0.5513, |
| "step": 41500 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 1.6968147856861975e-05, |
| "loss": 0.5557, |
| "step": 42000 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 1.6574911521824618e-05, |
| "loss": 0.5572, |
| "step": 42500 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 1.618167518678726e-05, |
| "loss": 0.5528, |
| "step": 43000 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 1.5788438851749904e-05, |
| "loss": 0.556, |
| "step": 43500 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 1.5395202516712544e-05, |
| "loss": 0.554, |
| "step": 44000 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 1.5001966181675187e-05, |
| "loss": 0.5512, |
| "step": 44500 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 1.460872984663783e-05, |
| "loss": 0.5515, |
| "step": 45000 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 1.4215493511600472e-05, |
| "loss": 0.554, |
| "step": 45500 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 1.3822257176563117e-05, |
| "loss": 0.5542, |
| "step": 46000 |
| }, |
| { |
| "epoch": 3.66, |
| "learning_rate": 1.3429020841525759e-05, |
| "loss": 0.556, |
| "step": 46500 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 1.30357845064884e-05, |
| "loss": 0.5532, |
| "step": 47000 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 1.2642548171451043e-05, |
| "loss": 0.556, |
| "step": 47500 |
| }, |
| { |
| "epoch": 3.78, |
| "learning_rate": 1.2249311836413685e-05, |
| "loss": 0.5547, |
| "step": 48000 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 1.1856075501376328e-05, |
| "loss": 0.5508, |
| "step": 48500 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 1.1462839166338971e-05, |
| "loss": 0.5537, |
| "step": 49000 |
| }, |
| { |
| "epoch": 3.89, |
| "learning_rate": 1.1069602831301613e-05, |
| "loss": 0.5532, |
| "step": 49500 |
| }, |
| { |
| "epoch": 3.93, |
| "learning_rate": 1.0676366496264254e-05, |
| "loss": 0.5548, |
| "step": 50000 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 1.0283130161226898e-05, |
| "loss": 0.5523, |
| "step": 50500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_bleu": 27.0195, |
| "eval_bleu_random_subnet": 27.0195, |
| "eval_bleu_smallest_subnet": 27.0195, |
| "eval_bleu_sum": 81.05850000000001, |
| "eval_gen_len": 42.5203, |
| "eval_gen_len_random_subnet": 42.5203, |
| "eval_gen_len_smallest_subnet": 42.5203, |
| "eval_gen_len_sum": 127.5609, |
| "eval_loss": 1.3569680452346802, |
| "eval_loss_random_subnet": 1.3569680452346802, |
| "eval_loss_smallest_subnet": 1.3569680452346802, |
| "eval_loss_sum": 4.0709041357040405, |
| "eval_runtime": 59.137, |
| "eval_samples_per_second": 33.803, |
| "eval_steps_per_second": 0.355, |
| "step": 50860 |
| }, |
| { |
| "epoch": 4.01, |
| "learning_rate": 9.88989382618954e-06, |
| "loss": 0.5513, |
| "step": 51000 |
| }, |
| { |
| "epoch": 4.05, |
| "learning_rate": 9.496657491152184e-06, |
| "loss": 0.5468, |
| "step": 51500 |
| }, |
| { |
| "epoch": 4.09, |
| "learning_rate": 9.103421156114826e-06, |
| "loss": 0.5486, |
| "step": 52000 |
| }, |
| { |
| "epoch": 4.13, |
| "learning_rate": 8.710184821077467e-06, |
| "loss": 0.5521, |
| "step": 52500 |
| }, |
| { |
| "epoch": 4.17, |
| "learning_rate": 8.31694848604011e-06, |
| "loss": 0.5437, |
| "step": 53000 |
| }, |
| { |
| "epoch": 4.21, |
| "learning_rate": 7.923712151002753e-06, |
| "loss": 0.5455, |
| "step": 53500 |
| }, |
| { |
| "epoch": 4.25, |
| "learning_rate": 7.530475815965396e-06, |
| "loss": 0.5475, |
| "step": 54000 |
| }, |
| { |
| "epoch": 4.29, |
| "learning_rate": 7.137239480928037e-06, |
| "loss": 0.5438, |
| "step": 54500 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 6.7440031458906806e-06, |
| "loss": 0.544, |
| "step": 55000 |
| }, |
| { |
| "epoch": 4.36, |
| "learning_rate": 6.350766810853323e-06, |
| "loss": 0.5418, |
| "step": 55500 |
| }, |
| { |
| "epoch": 4.4, |
| "learning_rate": 5.957530475815966e-06, |
| "loss": 0.5457, |
| "step": 56000 |
| }, |
| { |
| "epoch": 4.44, |
| "learning_rate": 5.564294140778608e-06, |
| "loss": 0.5415, |
| "step": 56500 |
| }, |
| { |
| "epoch": 4.48, |
| "learning_rate": 5.171057805741251e-06, |
| "loss": 0.5415, |
| "step": 57000 |
| }, |
| { |
| "epoch": 4.52, |
| "learning_rate": 4.777821470703893e-06, |
| "loss": 0.5498, |
| "step": 57500 |
| }, |
| { |
| "epoch": 4.56, |
| "learning_rate": 4.384585135666536e-06, |
| "loss": 0.5479, |
| "step": 58000 |
| }, |
| { |
| "epoch": 4.6, |
| "learning_rate": 3.991348800629179e-06, |
| "loss": 0.5449, |
| "step": 58500 |
| }, |
| { |
| "epoch": 4.64, |
| "learning_rate": 3.5981124655918208e-06, |
| "loss": 0.5474, |
| "step": 59000 |
| }, |
| { |
| "epoch": 4.68, |
| "learning_rate": 3.2048761305544636e-06, |
| "loss": 0.5456, |
| "step": 59500 |
| }, |
| { |
| "epoch": 4.72, |
| "learning_rate": 2.811639795517106e-06, |
| "loss": 0.5453, |
| "step": 60000 |
| }, |
| { |
| "epoch": 4.76, |
| "learning_rate": 2.4184034604797483e-06, |
| "loss": 0.5442, |
| "step": 60500 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 2.025167125442391e-06, |
| "loss": 0.5472, |
| "step": 61000 |
| }, |
| { |
| "epoch": 4.84, |
| "learning_rate": 1.6319307904050335e-06, |
| "loss": 0.5453, |
| "step": 61500 |
| }, |
| { |
| "epoch": 4.88, |
| "learning_rate": 1.238694455367676e-06, |
| "loss": 0.5404, |
| "step": 62000 |
| }, |
| { |
| "epoch": 4.92, |
| "learning_rate": 8.454581203303186e-07, |
| "loss": 0.5402, |
| "step": 62500 |
| }, |
| { |
| "epoch": 4.95, |
| "learning_rate": 4.522217852929611e-07, |
| "loss": 0.5429, |
| "step": 63000 |
| }, |
| { |
| "epoch": 4.99, |
| "learning_rate": 5.898545025560362e-08, |
| "loss": 0.5436, |
| "step": 63500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_bleu": 27.1318, |
| "eval_bleu_random_subnet": 27.1318, |
| "eval_bleu_smallest_subnet": 27.1318, |
| "eval_bleu_sum": 81.3954, |
| "eval_gen_len": 42.5798, |
| "eval_gen_len_random_subnet": 42.5798, |
| "eval_gen_len_smallest_subnet": 42.5798, |
| "eval_gen_len_sum": 127.73939999999999, |
| "eval_loss": 1.357446312904358, |
| "eval_loss_random_subnet": 1.357446312904358, |
| "eval_loss_smallest_subnet": 1.357446312904358, |
| "eval_loss_sum": 4.072338938713074, |
| "eval_runtime": 57.2594, |
| "eval_samples_per_second": 34.911, |
| "eval_steps_per_second": 0.367, |
| "step": 63575 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 63575, |
| "total_flos": 5.581813633043661e+16, |
| "train_loss": 0.5707878178196351, |
| "train_runtime": 16495.2684, |
| "train_samples_per_second": 184.999, |
| "train_steps_per_second": 3.854 |
| } |
| ], |
| "max_steps": 63575, |
| "num_train_epochs": 5, |
| "total_flos": 5.581813633043661e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
