| { | |
| "best_metric": 1.6703945398330688, | |
| "best_model_checkpoint": "models/models/mbert-3-5e-5/checkpoint-116000", | |
| "epoch": 49.998677383253636, | |
| "eval_steps": 2000, | |
| "global_step": 122850, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8139179977617255, | |
| "grad_norm": 9.055466651916504, | |
| "learning_rate": 4.796499796499796e-05, | |
| "loss": 5.8944, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8139179977617255, | |
| "eval_loss": 5.142313480377197, | |
| "eval_runtime": 73.0566, | |
| "eval_samples_per_second": 136.88, | |
| "eval_steps_per_second": 2.149, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.6275307762742903, | |
| "grad_norm": 14.413078308105469, | |
| "learning_rate": 4.592999592999594e-05, | |
| "loss": 4.8554, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6275307762742903, | |
| "eval_loss": 4.169687747955322, | |
| "eval_runtime": 73.0805, | |
| "eval_samples_per_second": 136.835, | |
| "eval_steps_per_second": 2.148, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.4411435547868554, | |
| "grad_norm": 10.98070240020752, | |
| "learning_rate": 4.38949938949939e-05, | |
| "loss": 3.8936, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.4411435547868554, | |
| "eval_loss": 3.520249605178833, | |
| "eval_runtime": 73.0468, | |
| "eval_samples_per_second": 136.898, | |
| "eval_steps_per_second": 2.149, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.25475633329942, | |
| "grad_norm": 12.734247207641602, | |
| "learning_rate": 4.185999185999186e-05, | |
| "loss": 3.3719, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.25475633329942, | |
| "eval_loss": 3.012561082839966, | |
| "eval_runtime": 73.0351, | |
| "eval_samples_per_second": 136.92, | |
| "eval_steps_per_second": 2.15, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.068369111811985, | |
| "grad_norm": 11.761553764343262, | |
| "learning_rate": 3.9824989824989825e-05, | |
| "loss": 2.9884, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.068369111811985, | |
| "eval_loss": 2.7652907371520996, | |
| "eval_runtime": 73.0559, | |
| "eval_samples_per_second": 136.882, | |
| "eval_steps_per_second": 2.149, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.882287109573711, | |
| "grad_norm": 12.824328422546387, | |
| "learning_rate": 3.778998778998779e-05, | |
| "loss": 2.7846, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.882287109573711, | |
| "eval_loss": 2.616189956665039, | |
| "eval_runtime": 73.0493, | |
| "eval_samples_per_second": 136.894, | |
| "eval_steps_per_second": 2.149, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.6958998880862755, | |
| "grad_norm": 12.507063865661621, | |
| "learning_rate": 3.575498575498576e-05, | |
| "loss": 2.6443, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.6958998880862755, | |
| "eval_loss": 2.491734504699707, | |
| "eval_runtime": 73.0626, | |
| "eval_samples_per_second": 136.869, | |
| "eval_steps_per_second": 2.149, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 6.50951266659884, | |
| "grad_norm": 12.569066047668457, | |
| "learning_rate": 3.371998371998372e-05, | |
| "loss": 2.5361, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.50951266659884, | |
| "eval_loss": 2.402878522872925, | |
| "eval_runtime": 73.0516, | |
| "eval_samples_per_second": 136.89, | |
| "eval_steps_per_second": 2.149, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 7.323125445111405, | |
| "grad_norm": 12.419079780578613, | |
| "learning_rate": 3.168498168498169e-05, | |
| "loss": 2.4558, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 7.323125445111405, | |
| "eval_loss": 2.3287837505340576, | |
| "eval_runtime": 73.0774, | |
| "eval_samples_per_second": 136.841, | |
| "eval_steps_per_second": 2.148, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 8.13673822362397, | |
| "grad_norm": 12.206134796142578, | |
| "learning_rate": 2.9649979649979655e-05, | |
| "loss": 2.3847, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.13673822362397, | |
| "eval_loss": 2.2792084217071533, | |
| "eval_runtime": 73.059, | |
| "eval_samples_per_second": 136.876, | |
| "eval_steps_per_second": 2.149, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.950656221385696, | |
| "grad_norm": 12.273974418640137, | |
| "learning_rate": 2.7614977614977615e-05, | |
| "loss": 2.3293, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 8.950656221385696, | |
| "eval_loss": 2.2214159965515137, | |
| "eval_runtime": 73.07, | |
| "eval_samples_per_second": 136.855, | |
| "eval_steps_per_second": 2.149, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 9.76426899989826, | |
| "grad_norm": 12.672439575195312, | |
| "learning_rate": 2.557997557997558e-05, | |
| "loss": 2.2763, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 9.76426899989826, | |
| "eval_loss": 2.1826987266540527, | |
| "eval_runtime": 73.0461, | |
| "eval_samples_per_second": 136.9, | |
| "eval_steps_per_second": 2.149, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 10.577881778410825, | |
| "grad_norm": 12.514191627502441, | |
| "learning_rate": 2.3544973544973546e-05, | |
| "loss": 2.2361, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 10.577881778410825, | |
| "eval_loss": 2.1435160636901855, | |
| "eval_runtime": 73.0345, | |
| "eval_samples_per_second": 136.922, | |
| "eval_steps_per_second": 2.15, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 11.39149455692339, | |
| "grad_norm": 12.286685943603516, | |
| "learning_rate": 2.150997150997151e-05, | |
| "loss": 2.1973, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 11.39149455692339, | |
| "eval_loss": 2.1050431728363037, | |
| "eval_runtime": 73.0521, | |
| "eval_samples_per_second": 136.889, | |
| "eval_steps_per_second": 2.149, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 12.209990843422526, | |
| "grad_norm": 12.680660247802734, | |
| "learning_rate": 2.9649979649979655e-05, | |
| "loss": 2.1805, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 12.209990843422526, | |
| "eval_loss": 2.0837137699127197, | |
| "eval_runtime": 73.1666, | |
| "eval_samples_per_second": 136.674, | |
| "eval_steps_per_second": 2.146, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 13.02360362193509, | |
| "grad_norm": 12.36361026763916, | |
| "learning_rate": 2.8293311626644965e-05, | |
| "loss": 2.1418, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 13.02360362193509, | |
| "eval_loss": 2.052241802215576, | |
| "eval_runtime": 73.1973, | |
| "eval_samples_per_second": 136.617, | |
| "eval_steps_per_second": 2.145, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 13.837521619696815, | |
| "grad_norm": 12.344305992126465, | |
| "learning_rate": 2.693664360331027e-05, | |
| "loss": 2.1107, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 13.837521619696815, | |
| "eval_loss": 2.0308263301849365, | |
| "eval_runtime": 73.2003, | |
| "eval_samples_per_second": 136.611, | |
| "eval_steps_per_second": 2.145, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 14.651134398209381, | |
| "grad_norm": 12.52969741821289, | |
| "learning_rate": 2.557997557997558e-05, | |
| "loss": 2.0818, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 14.651134398209381, | |
| "eval_loss": 2.0151000022888184, | |
| "eval_runtime": 73.21, | |
| "eval_samples_per_second": 136.593, | |
| "eval_steps_per_second": 2.145, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 15.464747176721945, | |
| "grad_norm": 12.168683052062988, | |
| "learning_rate": 2.4223307556640893e-05, | |
| "loss": 2.0559, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 15.464747176721945, | |
| "eval_loss": 1.9706333875656128, | |
| "eval_runtime": 73.1868, | |
| "eval_samples_per_second": 136.637, | |
| "eval_steps_per_second": 2.145, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 16.27835995523451, | |
| "grad_norm": 12.408997535705566, | |
| "learning_rate": 2.28666395333062e-05, | |
| "loss": 2.0272, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 16.27835995523451, | |
| "eval_loss": 1.9658160209655762, | |
| "eval_runtime": 73.2254, | |
| "eval_samples_per_second": 136.565, | |
| "eval_steps_per_second": 2.144, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 17.091972733747074, | |
| "grad_norm": 13.222212791442871, | |
| "learning_rate": 2.150997150997151e-05, | |
| "loss": 2.0069, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 17.091972733747074, | |
| "eval_loss": 1.9462146759033203, | |
| "eval_runtime": 73.2046, | |
| "eval_samples_per_second": 136.603, | |
| "eval_steps_per_second": 2.145, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 17.9058907315088, | |
| "grad_norm": 12.432639122009277, | |
| "learning_rate": 2.015330348663682e-05, | |
| "loss": 1.9873, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 17.9058907315088, | |
| "eval_loss": 1.9287099838256836, | |
| "eval_runtime": 73.196, | |
| "eval_samples_per_second": 136.619, | |
| "eval_steps_per_second": 2.145, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 18.719503510021365, | |
| "grad_norm": 12.828729629516602, | |
| "learning_rate": 1.879663546330213e-05, | |
| "loss": 1.9696, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 18.719503510021365, | |
| "eval_loss": 1.9102226495742798, | |
| "eval_runtime": 73.1921, | |
| "eval_samples_per_second": 136.627, | |
| "eval_steps_per_second": 2.145, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 19.53311628853393, | |
| "grad_norm": 12.529792785644531, | |
| "learning_rate": 1.743996743996744e-05, | |
| "loss": 1.9506, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 19.53311628853393, | |
| "eval_loss": 1.8978015184402466, | |
| "eval_runtime": 73.2056, | |
| "eval_samples_per_second": 136.602, | |
| "eval_steps_per_second": 2.145, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 20.346729067046496, | |
| "grad_norm": 12.476061820983887, | |
| "learning_rate": 1.6083299416632748e-05, | |
| "loss": 1.937, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 20.346729067046496, | |
| "eval_loss": 1.8884605169296265, | |
| "eval_runtime": 73.211, | |
| "eval_samples_per_second": 136.592, | |
| "eval_steps_per_second": 2.144, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 21.16034184555906, | |
| "grad_norm": 12.546550750732422, | |
| "learning_rate": 1.472663139329806e-05, | |
| "loss": 1.9239, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 21.16034184555906, | |
| "eval_loss": 1.8613293170928955, | |
| "eval_runtime": 73.2024, | |
| "eval_samples_per_second": 136.608, | |
| "eval_steps_per_second": 2.145, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 21.974259843320784, | |
| "grad_norm": 12.588421821594238, | |
| "learning_rate": 1.336996336996337e-05, | |
| "loss": 1.9106, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 21.974259843320784, | |
| "eval_loss": 1.8496237993240356, | |
| "eval_runtime": 73.1844, | |
| "eval_samples_per_second": 136.641, | |
| "eval_steps_per_second": 2.145, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 22.78787262183335, | |
| "grad_norm": 12.508979797363281, | |
| "learning_rate": 1.2013295346628681e-05, | |
| "loss": 1.9004, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 22.78787262183335, | |
| "eval_loss": 1.8513011932373047, | |
| "eval_runtime": 73.1881, | |
| "eval_samples_per_second": 136.634, | |
| "eval_steps_per_second": 2.145, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 23.605961949333604, | |
| "grad_norm": 12.510702133178711, | |
| "learning_rate": 2.0492470492470494e-05, | |
| "loss": 1.8995, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 23.605961949333604, | |
| "eval_loss": 1.8457722663879395, | |
| "eval_runtime": 73.2143, | |
| "eval_samples_per_second": 136.585, | |
| "eval_steps_per_second": 2.144, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 24.419574727846168, | |
| "grad_norm": 12.43933391571045, | |
| "learning_rate": 1.9474969474969477e-05, | |
| "loss": 1.8903, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 24.419574727846168, | |
| "eval_loss": 1.8323436975479126, | |
| "eval_runtime": 73.2612, | |
| "eval_samples_per_second": 136.498, | |
| "eval_steps_per_second": 2.143, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 25.233187506358735, | |
| "grad_norm": 12.256065368652344, | |
| "learning_rate": 1.8457468457468458e-05, | |
| "loss": 1.8754, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 25.233187506358735, | |
| "eval_loss": 1.8291531801223755, | |
| "eval_runtime": 73.2439, | |
| "eval_samples_per_second": 136.53, | |
| "eval_steps_per_second": 2.144, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 26.0468002848713, | |
| "grad_norm": 12.613372802734375, | |
| "learning_rate": 1.743996743996744e-05, | |
| "loss": 1.8644, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 26.0468002848713, | |
| "eval_loss": 1.823506236076355, | |
| "eval_runtime": 73.2487, | |
| "eval_samples_per_second": 136.521, | |
| "eval_steps_per_second": 2.143, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 26.860718282633023, | |
| "grad_norm": 12.547616958618164, | |
| "learning_rate": 1.642246642246642e-05, | |
| "loss": 1.8537, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 26.860718282633023, | |
| "eval_loss": 1.7943871021270752, | |
| "eval_runtime": 73.2466, | |
| "eval_samples_per_second": 136.525, | |
| "eval_steps_per_second": 2.143, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 27.67433106114559, | |
| "grad_norm": 12.599259376525879, | |
| "learning_rate": 1.5404965404965405e-05, | |
| "loss": 1.8426, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 27.67433106114559, | |
| "eval_loss": 1.787021517753601, | |
| "eval_runtime": 73.2491, | |
| "eval_samples_per_second": 136.52, | |
| "eval_steps_per_second": 2.143, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 28.487943839658154, | |
| "grad_norm": 12.874439239501953, | |
| "learning_rate": 1.4387464387464389e-05, | |
| "loss": 1.8307, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 28.487943839658154, | |
| "eval_loss": 1.7922056913375854, | |
| "eval_runtime": 73.2621, | |
| "eval_samples_per_second": 136.496, | |
| "eval_steps_per_second": 2.143, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 29.301556618170718, | |
| "grad_norm": 12.278645515441895, | |
| "learning_rate": 1.336996336996337e-05, | |
| "loss": 1.8235, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 29.301556618170718, | |
| "eval_loss": 1.7722290754318237, | |
| "eval_runtime": 73.2392, | |
| "eval_samples_per_second": 136.539, | |
| "eval_steps_per_second": 2.144, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 30.115169396683285, | |
| "grad_norm": 12.372228622436523, | |
| "learning_rate": 1.2352462352462353e-05, | |
| "loss": 1.8142, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 30.115169396683285, | |
| "eval_loss": 1.7639870643615723, | |
| "eval_runtime": 73.2474, | |
| "eval_samples_per_second": 136.524, | |
| "eval_steps_per_second": 2.143, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 30.92908739444501, | |
| "grad_norm": 13.026344299316406, | |
| "learning_rate": 1.1334961334961336e-05, | |
| "loss": 1.8052, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 30.92908739444501, | |
| "eval_loss": 1.7618211507797241, | |
| "eval_runtime": 73.2535, | |
| "eval_samples_per_second": 136.512, | |
| "eval_steps_per_second": 2.143, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 31.742700172957573, | |
| "grad_norm": 12.346455574035645, | |
| "learning_rate": 1.0317460317460318e-05, | |
| "loss": 1.7968, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 31.742700172957573, | |
| "eval_loss": 1.7621996402740479, | |
| "eval_runtime": 73.2566, | |
| "eval_samples_per_second": 136.506, | |
| "eval_steps_per_second": 2.143, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 32.55631295147014, | |
| "grad_norm": 12.404403686523438, | |
| "learning_rate": 9.2999592999593e-06, | |
| "loss": 1.7906, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 32.55631295147014, | |
| "eval_loss": 1.7546992301940918, | |
| "eval_runtime": 73.2436, | |
| "eval_samples_per_second": 136.531, | |
| "eval_steps_per_second": 2.144, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 33.369925729982704, | |
| "grad_norm": 13.407048225402832, | |
| "learning_rate": 8.282458282458284e-06, | |
| "loss": 1.7831, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 33.369925729982704, | |
| "eval_loss": 1.7637808322906494, | |
| "eval_runtime": 73.252, | |
| "eval_samples_per_second": 136.515, | |
| "eval_steps_per_second": 2.143, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 34.18353850849527, | |
| "grad_norm": 12.677322387695312, | |
| "learning_rate": 7.264957264957266e-06, | |
| "loss": 1.7781, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 34.18353850849527, | |
| "eval_loss": 1.7423206567764282, | |
| "eval_runtime": 73.2424, | |
| "eval_samples_per_second": 136.533, | |
| "eval_steps_per_second": 2.144, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 35.0020347949944, | |
| "grad_norm": 12.919666290283203, | |
| "learning_rate": 1.4997964997965e-05, | |
| "loss": 1.7839, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 35.0020347949944, | |
| "eval_loss": 1.7404271364212036, | |
| "eval_runtime": 73.1021, | |
| "eval_samples_per_second": 136.795, | |
| "eval_steps_per_second": 2.148, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 35.81595279275613, | |
| "grad_norm": 13.499661445617676, | |
| "learning_rate": 1.4183964183964185e-05, | |
| "loss": 1.7779, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 35.81595279275613, | |
| "eval_loss": 1.7452839612960815, | |
| "eval_runtime": 73.1263, | |
| "eval_samples_per_second": 136.75, | |
| "eval_steps_per_second": 2.147, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 36.62956557126869, | |
| "grad_norm": 12.777277946472168, | |
| "learning_rate": 1.336996336996337e-05, | |
| "loss": 1.7694, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 36.62956557126869, | |
| "eval_loss": 1.7361302375793457, | |
| "eval_runtime": 73.1394, | |
| "eval_samples_per_second": 136.725, | |
| "eval_steps_per_second": 2.147, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 37.443178349781256, | |
| "grad_norm": 12.409318923950195, | |
| "learning_rate": 1.2555962555962556e-05, | |
| "loss": 1.7634, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 37.443178349781256, | |
| "eval_loss": 1.7353118658065796, | |
| "eval_runtime": 73.1692, | |
| "eval_samples_per_second": 136.669, | |
| "eval_steps_per_second": 2.146, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 38.25679112829383, | |
| "grad_norm": 13.48429012298584, | |
| "learning_rate": 1.1741961741961743e-05, | |
| "loss": 1.7593, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 38.25679112829383, | |
| "eval_loss": 1.7299132347106934, | |
| "eval_runtime": 73.1218, | |
| "eval_samples_per_second": 136.758, | |
| "eval_steps_per_second": 2.147, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 39.07040390680639, | |
| "grad_norm": 12.476696014404297, | |
| "learning_rate": 1.0927960927960928e-05, | |
| "loss": 1.7498, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 39.07040390680639, | |
| "eval_loss": 1.7091785669326782, | |
| "eval_runtime": 73.0912, | |
| "eval_samples_per_second": 136.815, | |
| "eval_steps_per_second": 2.148, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 39.88432190456812, | |
| "grad_norm": 13.220356941223145, | |
| "learning_rate": 1.0113960113960115e-05, | |
| "loss": 1.7446, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 39.88432190456812, | |
| "eval_loss": 1.7064162492752075, | |
| "eval_runtime": 73.1495, | |
| "eval_samples_per_second": 136.706, | |
| "eval_steps_per_second": 2.146, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 40.69793468308068, | |
| "grad_norm": 13.10384750366211, | |
| "learning_rate": 9.2999592999593e-06, | |
| "loss": 1.7376, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 40.69793468308068, | |
| "eval_loss": 1.7068718671798706, | |
| "eval_runtime": 73.1342, | |
| "eval_samples_per_second": 136.735, | |
| "eval_steps_per_second": 2.147, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 41.511547461593246, | |
| "grad_norm": 13.384297370910645, | |
| "learning_rate": 8.485958485958487e-06, | |
| "loss": 1.732, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 41.511547461593246, | |
| "eval_loss": 1.7083535194396973, | |
| "eval_runtime": 73.1173, | |
| "eval_samples_per_second": 136.767, | |
| "eval_steps_per_second": 2.147, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 42.32516024010581, | |
| "grad_norm": 12.881793022155762, | |
| "learning_rate": 7.671957671957672e-06, | |
| "loss": 1.7282, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 42.32516024010581, | |
| "eval_loss": 1.7061749696731567, | |
| "eval_runtime": 73.1059, | |
| "eval_samples_per_second": 136.788, | |
| "eval_steps_per_second": 2.148, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 43.13877301861837, | |
| "grad_norm": 13.3131685256958, | |
| "learning_rate": 6.857956857956858e-06, | |
| "loss": 1.7218, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 43.13877301861837, | |
| "eval_loss": 1.6910033226013184, | |
| "eval_runtime": 73.0946, | |
| "eval_samples_per_second": 136.809, | |
| "eval_steps_per_second": 2.148, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 43.9526910163801, | |
| "grad_norm": 12.788925170898438, | |
| "learning_rate": 6.043956043956044e-06, | |
| "loss": 1.7205, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 43.9526910163801, | |
| "eval_loss": 1.6898643970489502, | |
| "eval_runtime": 73.1074, | |
| "eval_samples_per_second": 136.785, | |
| "eval_steps_per_second": 2.148, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 44.766303794892664, | |
| "grad_norm": 12.509169578552246, | |
| "learning_rate": 5.22995522995523e-06, | |
| "loss": 1.7151, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 44.766303794892664, | |
| "eval_loss": 1.6873972415924072, | |
| "eval_runtime": 73.1077, | |
| "eval_samples_per_second": 136.784, | |
| "eval_steps_per_second": 2.148, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 45.57991657340523, | |
| "grad_norm": 12.945860862731934, | |
| "learning_rate": 4.415954415954416e-06, | |
| "loss": 1.7109, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 45.57991657340523, | |
| "eval_loss": 1.677456021308899, | |
| "eval_runtime": 73.1203, | |
| "eval_samples_per_second": 136.761, | |
| "eval_steps_per_second": 2.147, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 46.39800590090548, | |
| "grad_norm": 12.642820358276367, | |
| "learning_rate": 3.6019536019536017e-06, | |
| "loss": 1.7058, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 46.39800590090548, | |
| "eval_loss": 1.6775144338607788, | |
| "eval_runtime": 73.1275, | |
| "eval_samples_per_second": 136.747, | |
| "eval_steps_per_second": 2.147, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 47.21161867941805, | |
| "grad_norm": 13.197073936462402, | |
| "learning_rate": 2.787952787952788e-06, | |
| "loss": 1.7048, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 47.21161867941805, | |
| "eval_loss": 1.6703945398330688, | |
| "eval_runtime": 73.1574, | |
| "eval_samples_per_second": 136.691, | |
| "eval_steps_per_second": 2.146, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 48.025231457930616, | |
| "grad_norm": 12.470918655395508, | |
| "learning_rate": 1.9739519739519742e-06, | |
| "loss": 1.7037, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 48.025231457930616, | |
| "eval_loss": 1.6824976205825806, | |
| "eval_runtime": 73.1867, | |
| "eval_samples_per_second": 136.637, | |
| "eval_steps_per_second": 2.145, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 48.839149455692336, | |
| "grad_norm": 12.579526901245117, | |
| "learning_rate": 1.15995115995116e-06, | |
| "loss": 1.6999, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 48.839149455692336, | |
| "eval_loss": 1.678907871246338, | |
| "eval_runtime": 73.1871, | |
| "eval_samples_per_second": 136.636, | |
| "eval_steps_per_second": 2.145, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 49.65276223420491, | |
| "grad_norm": 13.10560131072998, | |
| "learning_rate": 3.4595034595034596e-07, | |
| "loss": 1.6969, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 49.65276223420491, | |
| "eval_loss": 1.6780418157577515, | |
| "eval_runtime": 73.1913, | |
| "eval_samples_per_second": 136.628, | |
| "eval_steps_per_second": 2.145, | |
| "step": 122000 | |
| } | |
| ], | |
| "logging_steps": 2000, | |
| "max_steps": 122850, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.275195636696166e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |