diff --git "a/checkpoint-2900160/trainer_state.json" "b/checkpoint-2900160/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2900160/trainer_state.json" @@ -0,0 +1,34313 @@ +{ + "best_metric": 3.8415467739105225, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/transformer/1/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2900160, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.974, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8153, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1834, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.97, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8132, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7086, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6021, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5349, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4463, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3944, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3494, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3162, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2631, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2043, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1752, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1243, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1035, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0788, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0407, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0161, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0012, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9747, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9468, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9276, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9187, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8818, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8675, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8592, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8292, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8116, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7994, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7931, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7811, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7635, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7539, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7476, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7295, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7017, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6987, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6724, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6824, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6688, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6683, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6457, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6475, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6328, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6266, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6291, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5892, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5974, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5991, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5925, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5698, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5606, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5526, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.547, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5609, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5242, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5391, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5323, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5116, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5196, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.4955, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.492, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.492, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.501, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4713, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4749, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4563, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4691, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.472, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4693, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4493, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4591, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4653, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4404, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4347, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4284, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4209, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4297, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4104, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4293, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4215, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4064, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3896, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3993, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3981, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4007, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3863, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3893, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3806, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3693, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3668, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922041807879253e-05, + "loss": 4.373, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921203213128201e-05, + "loss": 4.3676, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3682, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3527, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3524, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3583, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.357, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.349, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3451, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914497730880531e-05, + "loss": 4.3366, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913659136129479e-05, + "loss": 4.333, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.3366, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.3121, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111449897566966e-05, + "loss": 4.3243, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103063950056446e-05, + "loss": 4.3271, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094678002545926e-05, + "loss": 4.3254, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086292055035406e-05, + "loss": 4.3133, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.9077922486328615e-05, + "loss": 4.3214, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069536538818095e-05, + "loss": 4.3009, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061150591307575e-05, + "loss": 4.3254, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052764643797055e-05, + "loss": 4.295, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044378696286535e-05, + "loss": 4.3072, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9036009127579744e-05, + "loss": 4.3054, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027623180069224e-05, + "loss": 4.311, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901925361136244e-05, + "loss": 4.3006, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901086766385192e-05, + "loss": 4.2913, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024817163414e-05, + "loss": 4.2952, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899409576883088e-05, + "loss": 4.2969, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898570982132036e-05, + "loss": 4.2833, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897732387380984e-05, + "loss": 4.2829, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896893792629932e-05, + "loss": 4.2796, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.89605519787888e-05, + "loss": 4.2949, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895216603127827e-05, + "loss": 4.2655, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2705, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.2703, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892702456755045e-05, + "loss": 4.2727, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.2633, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2803, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2684, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2632, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2545, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2671, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2617, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2648, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2499, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2623, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834811902542186e-05, + "loss": 4.2535, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2572, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2385, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2581, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880128449130384e-05, + "loss": 4.2381, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2221, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2543, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2372, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2377, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2374, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2239, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.193942070007324, + "eval_runtime": 322.1087, + "eval_samples_per_second": 1184.665, + "eval_steps_per_second": 37.022, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.2036, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2116, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2304, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.87174577738061e-05, + "loss": 4.2168, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870907182629558e-05, + "loss": 4.2205, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870068587878506e-05, + "loss": 4.2112, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2052, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.1993, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.205, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2029, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2163, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2105, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642033382622614e-05, + "loss": 4.1943, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633647435112094e-05, + "loss": 4.1863, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625261487601574e-05, + "loss": 4.1803, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616875540091054e-05, + "loss": 4.1793, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608489592580534e-05, + "loss": 4.1916, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600103645070014e-05, + "loss": 4.1807, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591717697559493e-05, + "loss": 4.1762, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858333175004898e-05, + "loss": 4.1956, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857496218134219e-05, + "loss": 4.1822, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856657623383167e-05, + "loss": 4.1777, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855819028632115e-05, + "loss": 4.1804, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854980433881063e-05, + "loss": 4.1905, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854143477010384e-05, + "loss": 4.1627, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853304882259332e-05, + "loss": 4.1674, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.85246628750828e-05, + "loss": 4.1768, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851627692757228e-05, + "loss": 4.1657, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850790735886549e-05, + "loss": 4.1553, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849952141135497e-05, + "loss": 4.1544, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849115184264818e-05, + "loss": 4.1685, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848276589513766e-05, + "loss": 4.1648, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847437994762714e-05, + "loss": 4.16, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846599400011662e-05, + "loss": 4.1605, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.84576080526061e-05, + "loss": 4.1617, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844922210509558e-05, + "loss": 4.1602, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440836157585056e-05, + "loss": 4.1439, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432450210074536e-05, + "loss": 4.1464, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842408064136775e-05, + "loss": 4.1332, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415694693857225e-05, + "loss": 4.1448, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407308746346705e-05, + "loss": 4.1412, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398922798836185e-05, + "loss": 4.1523, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.83905532301294e-05, + "loss": 4.1376, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838216728261888e-05, + "loss": 4.1437, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837378133510836e-05, + "loss": 4.1385, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836539538759784e-05, + "loss": 4.1411, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8357025818891057e-05, + "loss": 4.1469, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834863987138053e-05, + "loss": 4.1161, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340270302673746e-05, + "loss": 4.1265, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331884355163226e-05, + "loss": 4.1414, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.83234984076527e-05, + "loss": 4.1349, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831511246014218e-05, + "loss": 4.1233, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306742891435395e-05, + "loss": 4.1172, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298356943924875e-05, + "loss": 4.1177, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289970996414354e-05, + "loss": 4.1075, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281585048903834e-05, + "loss": 4.1304, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273199101393314e-05, + "loss": 4.1068, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264813153882794e-05, + "loss": 4.125, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256427206372274e-05, + "loss": 4.1177, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248041258861754e-05, + "loss": 4.1059, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823967169015496e-05, + "loss": 4.1131, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823128574264444e-05, + "loss": 4.1031, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822289979513392e-05, + "loss": 4.1001, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.82145138476234e-05, + "loss": 4.1044, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820614427891661e-05, + "loss": 4.1208, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819775833140609e-05, + "loss": 4.0917, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818937238389558e-05, + "loss": 4.1001, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818098643638506e-05, + "loss": 4.0832, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817261686767827e-05, + "loss": 4.0996, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816423092016775e-05, + "loss": 4.1138, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815584497265723e-05, + "loss": 4.106, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814745902514671e-05, + "loss": 4.0971, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813908945643992e-05, + "loss": 4.1046, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81307035089294e-05, + "loss": 4.1107, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812231756141888e-05, + "loss": 4.0926, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.091, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105562045201566e-05, + "loss": 4.0918, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097176097691046e-05, + "loss": 4.0881, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808879015018053e-05, + "loss": 4.0911, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808040420267001e-05, + "loss": 4.0838, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807203463396322e-05, + "loss": 4.0974, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.80636486864527e-05, + "loss": 4.0922, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805526273894218e-05, + "loss": 4.0875, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804687679143166e-05, + "loss": 4.0692, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803850722272487e-05, + "loss": 4.0781, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803012127521435e-05, + "loss": 4.0863, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802173532770383e-05, + "loss": 4.0863, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801334938019331e-05, + "loss": 4.0828, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800497981148652e-05, + "loss": 4.0799, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996593863976e-05, + "loss": 4.0813, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988207916465486e-05, + "loss": 4.0694, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979821968954966e-05, + "loss": 4.0655, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971452400248175e-05, + "loss": 4.0809, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963082831541385e-05, + "loss": 4.0717, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954696884030864e-05, + "loss": 4.0773, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946310936520344e-05, + "loss": 4.0691, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937924989009824e-05, + "loss": 4.0613, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929539041499304e-05, + "loss": 4.0743, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921153093988784e-05, + "loss": 4.0789, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912767146478264e-05, + "loss": 4.0695, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790439757777147e-05, + "loss": 4.0663, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789601163026095e-05, + "loss": 4.0576, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788762568275043e-05, + "loss": 4.0619, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787923973523992e-05, + "loss": 4.0696, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787087016653313e-05, + "loss": 4.0477, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.055, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0607, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.065, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783734275529478e-05, + "loss": 4.0502, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782897318658799e-05, + "loss": 4.0578, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782058723907747e-05, + "loss": 4.0455, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781220129156695e-05, + "loss": 4.0666, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780381534405643e-05, + "loss": 4.0448, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779542939654591e-05, + "loss": 4.0532, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778704344903539e-05, + "loss": 4.0594, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778657501524874e-05, + "loss": 4.0584, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777028793281808e-05, + "loss": 4.0552, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776190198530756e-05, + "loss": 4.0413, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775351603779704e-05, + "loss": 4.0501, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774513009028652e-05, + "loss": 4.0539, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736744142776e-05, + "loss": 4.04, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772835819526548e-05, + "loss": 4.0447, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719972247754956e-05, + "loss": 4.0388, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711586300244436e-05, + "loss": 4.0563, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770321673153765e-05, + "loss": 4.0295, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769483078402713e-05, + "loss": 4.0401, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768644483651661e-05, + "loss": 4.0371, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767805888900609e-05, + "loss": 4.041, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766968932029931e-05, + "loss": 4.0332, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766130337278878e-05, + "loss": 4.0515, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765291742527826e-05, + "loss": 4.0445, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.7644547856571476e-05, + "loss": 4.0355, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636161909060956e-05, + "loss": 4.0293, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762777596155043e-05, + "loss": 4.0439, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761939001403991e-05, + "loss": 4.0399, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761100406652939e-05, + "loss": 4.0494, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760261811901887e-05, + "loss": 4.0236, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759423217150835e-05, + "loss": 4.045, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0364, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577476655291045e-05, + "loss": 4.0456, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569107086584254e-05, + "loss": 4.025, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560721139073734e-05, + "loss": 4.039, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552335191563214e-05, + "loss": 4.0294, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543949244052694e-05, + "loss": 4.0173, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535563296542174e-05, + "loss": 4.0402, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527177349031654e-05, + "loss": 4.0333, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518791401521134e-05, + "loss": 4.0291, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510405454010614e-05, + "loss": 4.0246, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750203588530382e-05, + "loss": 4.0217, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.023805618286133, + "eval_runtime": 322.2873, + "eval_samples_per_second": 1184.009, + "eval_steps_per_second": 37.001, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.74936499377933e-05, + "loss": 4.0001, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748526399028278e-05, + "loss": 4.009, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747687804277226e-05, + "loss": 4.0302, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746849209526175e-05, + "loss": 4.0202, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746010614775123e-05, + "loss": 4.0263, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745172020024071e-05, + "loss": 4.0095, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744333425273019e-05, + "loss": 4.0115, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743494830521967e-05, + "loss": 4.0042, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742656235770914e-05, + "loss": 4.0102, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.015, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.74097904626881e-05, + "loss": 4.0194, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740142089398132e-05, + "loss": 4.0214, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739305132527453e-05, + "loss": 4.007, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738466537776401e-05, + "loss": 3.9987, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737627943025349e-05, + "loss": 3.9988, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736789348274297e-05, + "loss": 3.9916, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735950753523245e-05, + "loss": 4.005, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735112158772193e-05, + "loss": 3.9988, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734275201901514e-05, + "loss": 3.9971, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334366071504616e-05, + "loss": 4.0186, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325980123994096e-05, + "loss": 3.9993, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317594176483576e-05, + "loss": 4.0022, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309208228973056e-05, + "loss": 4.0044, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300838660266265e-05, + "loss": 4.013, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292452712755745e-05, + "loss": 3.9837, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284066765245225e-05, + "loss": 3.9941, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275680817734705e-05, + "loss": 4.0021, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726731124902792e-05, + "loss": 3.9951, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.72589253015174e-05, + "loss": 3.9846, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725053935400688e-05, + "loss": 3.9813, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724215340649636e-05, + "loss": 4.0004, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723376745898584e-05, + "loss": 3.9985, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722538151147532e-05, + "loss": 3.9888, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.72169955639648e-05, + "loss": 3.9948, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720860961645428e-05, + "loss": 3.9923, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720025642655122e-05, + "loss": 3.99, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.71918704790407e-05, + "loss": 3.9789, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718348453153018e-05, + "loss": 3.9868, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717509858401966e-05, + "loss": 3.9666, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716671263650914e-05, + "loss": 3.9834, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715832668899862e-05, + "loss": 3.9813, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149940741488105e-05, + "loss": 3.9916, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141571172781314e-05, + "loss": 3.98, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133185225270794e-05, + "loss": 3.9817, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124799277760274e-05, + "loss": 3.9862, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116413330249754e-05, + "loss": 3.9779, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108027382739234e-05, + "loss": 3.99, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.9589, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709127186652192e-05, + "loss": 3.9744, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.70828859190114e-05, + "loss": 3.9837, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707449997150088e-05, + "loss": 3.9829, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706611402399036e-05, + "loss": 3.9702, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705774445528357e-05, + "loss": 3.964, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704935850777306e-05, + "loss": 3.9683, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704097256026254e-05, + "loss": 3.9532, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703258661275202e-05, + "loss": 3.9827, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.70242006652415e-05, + "loss": 3.9619, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701583109653471e-05, + "loss": 3.972, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700744514902419e-05, + "loss": 3.9707, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699905920151367e-05, + "loss": 3.9586, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699067325400315e-05, + "loss": 3.9652, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9551, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9562, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696553179027532e-05, + "loss": 3.9541, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69571458427648e-05, + "loss": 3.975, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694875989525428e-05, + "loss": 3.9526, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694037394774376e-05, + "loss": 3.9555, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693200437903697e-05, + "loss": 3.9436, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692361843152645e-05, + "loss": 3.9569, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9664, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.969, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689847696779862e-05, + "loss": 3.957, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890091020288095e-05, + "loss": 3.9644, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881705072777575e-05, + "loss": 3.9731, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.9549, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686494955656027e-05, + "loss": 3.9477, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685656360904975e-05, + "loss": 3.9588, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684817766153923e-05, + "loss": 3.9511, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683979171402871e-05, + "loss": 3.9538, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831422145321926e-05, + "loss": 3.9464, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.68230361978114e-05, + "loss": 3.9604, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681465025030088e-05, + "loss": 3.9627, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680626430279036e-05, + "loss": 3.9515, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679787835527984e-05, + "loss": 3.9366, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678950878657305e-05, + "loss": 3.9428, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678112283906253e-05, + "loss": 3.9506, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677273689155201e-05, + "loss": 3.9571, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676435094404149e-05, + "loss": 3.9498, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675596499653097e-05, + "loss": 3.9523, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674757904902045e-05, + "loss": 3.9493, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.9404, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9384, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722437585292624e-05, + "loss": 3.9443, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671406801658583e-05, + "loss": 3.9463, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670568206907531e-05, + "loss": 3.9511, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669729612156479e-05, + "loss": 3.9453, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668891017405427e-05, + "loss": 3.9308, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668054060534748e-05, + "loss": 3.9485, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667215465783696e-05, + "loss": 3.9542, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666376871032644e-05, + "loss": 3.9408, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665538276281592e-05, + "loss": 3.9432, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664701319410914e-05, + "loss": 3.9303, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663862724659862e-05, + "loss": 3.9371, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66302412990881e-05, + "loss": 3.946, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662185535157758e-05, + "loss": 3.9246, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661346940406706e-05, + "loss": 3.9332, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660509983536027e-05, + "loss": 3.9419, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659671388784975e-05, + "loss": 3.9387, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658832794033923e-05, + "loss": 3.9276, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579941992828707e-05, + "loss": 3.9386, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571572424121916e-05, + "loss": 3.9252, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563186476611396e-05, + "loss": 3.9446, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554800529100876e-05, + "loss": 3.9295, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546414581590356e-05, + "loss": 3.9278, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653804501288357e-05, + "loss": 3.9414, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652965906537305e-05, + "loss": 3.9415, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652127311786253e-05, + "loss": 3.9361, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651288717035201e-05, + "loss": 3.9277, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650450122284149e-05, + "loss": 3.9303, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.64961316541347e-05, + "loss": 3.9333, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648774570662418e-05, + "loss": 3.9264, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647935975911366e-05, + "loss": 3.9306, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647097381160314e-05, + "loss": 3.9205, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646260424289635e-05, + "loss": 3.9347, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645421829538583e-05, + "loss": 3.9243, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644583234787531e-05, + "loss": 3.925, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643744640036479e-05, + "loss": 3.918, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429076831658005e-05, + "loss": 3.9289, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420690884147485e-05, + "loss": 3.9154, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412304936636965e-05, + "loss": 3.939, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403918989126445e-05, + "loss": 3.9333, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395533041615925e-05, + "loss": 3.9252, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387163472909134e-05, + "loss": 3.9138, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378777525398614e-05, + "loss": 3.9337, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370391577888094e-05, + "loss": 3.9282, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6362005630377574e-05, + "loss": 3.9334, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635363606167078e-05, + "loss": 3.916, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634525011416026e-05, + "loss": 3.9299, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633686416664974e-05, + "loss": 3.9302, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632847821913923e-05, + "loss": 3.9361, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632010865043244e-05, + "loss": 3.9189, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631172270292192e-05, + "loss": 3.9264, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.63033367554114e-05, + "loss": 3.9223, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629495080790088e-05, + "loss": 3.9088, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628656486039035e-05, + "loss": 3.9329, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627819529168357e-05, + "loss": 3.9301, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626980934417305e-05, + "loss": 3.917, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626142339666253e-05, + "loss": 3.9179, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6253037449152e-05, + "loss": 3.9118, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.949960708618164, + "eval_runtime": 322.2009, + "eval_samples_per_second": 1184.326, + "eval_steps_per_second": 37.011, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244667880445217e-05, + "loss": 3.9056, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236281932934697e-05, + "loss": 3.9026, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227895985424176e-05, + "loss": 3.9245, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219510037913656e-05, + "loss": 3.913, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6211124090403136e-05, + "loss": 3.9247, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620275452169635e-05, + "loss": 3.9061, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194368574185825e-05, + "loss": 3.9096, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185982626675305e-05, + "loss": 3.8958, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177596679164785e-05, + "loss": 3.9101, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169227110458e-05, + "loss": 3.9091, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160841162947474e-05, + "loss": 3.9186, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152455215436954e-05, + "loss": 3.9155, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614408564673017e-05, + "loss": 3.9047, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613569969921965e-05, + "loss": 3.9003, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612731375170913e-05, + "loss": 3.8995, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611892780419861e-05, + "loss": 3.893, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611054185668809e-05, + "loss": 3.8993, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610215590917757e-05, + "loss": 3.8984, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609376996166705e-05, + "loss": 3.8951, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608538401415653e-05, + "loss": 3.9225, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607701444544974e-05, + "loss": 3.9013, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606862849793922e-05, + "loss": 3.9006, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.60602425504287e-05, + "loss": 3.9071, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605185660291818e-05, + "loss": 3.9113, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604347065540766e-05, + "loss": 3.889, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035101086700875e-05, + "loss": 3.8954, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026715139190355e-05, + "loss": 3.9042, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018329191679835e-05, + "loss": 3.9002, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009943244169315e-05, + "loss": 3.8857, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001557296658795e-05, + "loss": 3.8846, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993187727952004e-05, + "loss": 3.9021, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984801780441484e-05, + "loss": 3.9046, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976415832930964e-05, + "loss": 3.8959, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5968029885420443e-05, + "loss": 3.8987, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595966031671365e-05, + "loss": 3.8949, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595127436920313e-05, + "loss": 3.8977, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594288842169261e-05, + "loss": 3.8826, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593450247418209e-05, + "loss": 3.8966, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592611652667157e-05, + "loss": 3.8744, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591774695796479e-05, + "loss": 3.8886, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590936101045427e-05, + "loss": 3.8868, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590097506294375e-05, + "loss": 3.9019, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589258911543323e-05, + "loss": 3.8903, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588420316792271e-05, + "loss": 3.8874, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587581722041219e-05, + "loss": 3.8927, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.58674476517054e-05, + "loss": 3.8896, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585906170419488e-05, + "loss": 3.8946, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585067575668436e-05, + "loss": 3.8692, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584228980917384e-05, + "loss": 3.8807, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833920240467046e-05, + "loss": 3.8944, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825534292956526e-05, + "loss": 3.89, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817148345446006e-05, + "loss": 3.8808, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808762397935486e-05, + "loss": 3.8762, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.58003928292287e-05, + "loss": 3.8768, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579200688171818e-05, + "loss": 3.8649, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578362093420766e-05, + "loss": 3.8908, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5775234986697135e-05, + "loss": 3.8702, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576686541799035e-05, + "loss": 3.8832, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575847947047983e-05, + "loss": 3.8847, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575009352296931e-05, + "loss": 3.8708, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741707575458784e-05, + "loss": 3.8737, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733321627948264e-05, + "loss": 3.8706, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724935680437744e-05, + "loss": 3.8661, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571656611173096e-05, + "loss": 3.8723, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570818016422044e-05, + "loss": 3.8834, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569979421670992e-05, + "loss": 3.8664, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691424648003135e-05, + "loss": 3.8695, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568303870049261e-05, + "loss": 3.8593, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567465275298209e-05, + "loss": 3.8689, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566626680547157e-05, + "loss": 3.878, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565789723676478e-05, + "loss": 3.887, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564951128925426e-05, + "loss": 3.8696, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564112534174374e-05, + "loss": 3.8783, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563273939423322e-05, + "loss": 3.8832, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243534467227e-05, + "loss": 3.8788, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561598387801591e-05, + "loss": 3.8569, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560759793050539e-05, + "loss": 3.8783, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559921198299487e-05, + "loss": 3.8708, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559082603548435e-05, + "loss": 3.8627, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558245646677756e-05, + "loss": 3.8716, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557407051926704e-05, + "loss": 3.8719, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556568457175652e-05, + "loss": 3.8794, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557298624246e-05, + "loss": 3.8681, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554891267673548e-05, + "loss": 3.8532, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554054310802869e-05, + "loss": 3.8639, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553215716051817e-05, + "loss": 3.8624, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552377121300765e-05, + "loss": 3.8731, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551538526549714e-05, + "loss": 3.8716, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550699931798662e-05, + "loss": 3.8659, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549862974927983e-05, + "loss": 3.8703, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549024380176931e-05, + "loss": 3.8575, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548185785425879e-05, + "loss": 3.8581, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547347190674827e-05, + "loss": 3.8621, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546508595923775e-05, + "loss": 3.8666, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456716390530956e-05, + "loss": 3.8685, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448330443020436e-05, + "loss": 3.8728, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439944495509916e-05, + "loss": 3.8466, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431558547999396e-05, + "loss": 3.8701, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423188979292605e-05, + "loss": 3.8738, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541480303178209e-05, + "loss": 3.8641, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540641708427157e-05, + "loss": 3.8629, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539803113676105e-05, + "loss": 3.8513, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538964518925053e-05, + "loss": 3.8619, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538127562054374e-05, + "loss": 3.8648, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537288967303322e-05, + "loss": 3.8463, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.53645037255227e-05, + "loss": 3.8564, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535611777801218e-05, + "loss": 3.8591, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534774820930539e-05, + "loss": 3.8622, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533936226179487e-05, + "loss": 3.8464, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533097631428435e-05, + "loss": 3.8668, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532259036677383e-05, + "loss": 3.8434, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531420441926331e-05, + "loss": 3.8683, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305834850556525e-05, + "loss": 3.8553, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297448903046005e-05, + "loss": 3.8491, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289062955535485e-05, + "loss": 3.865, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280677008024965e-05, + "loss": 3.8665, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272307439318174e-05, + "loss": 3.8566, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263921491807654e-05, + "loss": 3.8529, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255535544297134e-05, + "loss": 3.8571, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247149596786614e-05, + "loss": 3.8558, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523878002807982e-05, + "loss": 3.8484, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52303940805693e-05, + "loss": 3.8548, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522200813305878e-05, + "loss": 3.8509, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521362218554826e-05, + "loss": 3.853, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520525261684148e-05, + "loss": 3.8521, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.853, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518848072182044e-05, + "loss": 3.8375, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518009477430992e-05, + "loss": 3.8534, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517170882679939e-05, + "loss": 3.8466, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8609, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515495331058209e-05, + "loss": 3.8581, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514656736307156e-05, + "loss": 3.8536, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513818141556104e-05, + "loss": 3.8387, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512981184685426e-05, + "loss": 3.858, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512142589934374e-05, + "loss": 3.8533, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511303995183322e-05, + "loss": 3.8604, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104654004322697e-05, + "loss": 3.8404, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509628443561591e-05, + "loss": 3.8593, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508789848810539e-05, + "loss": 3.8571, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079512540594866e-05, + "loss": 3.863, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5071126593084346e-05, + "loss": 3.8405, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506275702437756e-05, + "loss": 3.8538, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054371076867035e-05, + "loss": 3.8494, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045985129356515e-05, + "loss": 3.8407, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037599181845995e-05, + "loss": 3.8551, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502922961313921e-05, + "loss": 3.8582, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020843665628684e-05, + "loss": 3.8477, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501245771811817e-05, + "loss": 3.843, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500407177060765e-05, + "loss": 3.8448, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.909270763397217, + "eval_runtime": 319.717, + "eval_samples_per_second": 1193.527, + "eval_steps_per_second": 37.299, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499568582309713e-05, + "loss": 3.8272, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498729987558661e-05, + "loss": 3.8316, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497891392807609e-05, + "loss": 3.849, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497052798056557e-05, + "loss": 3.8428, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496214203305505e-05, + "loss": 3.8535, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495375608554453e-05, + "loss": 3.8382, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494537013803401e-05, + "loss": 3.839, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493698419052349e-05, + "loss": 3.8244, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.49286146218167e-05, + "loss": 3.843, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492022867430618e-05, + "loss": 3.8419, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491184272679566e-05, + "loss": 3.8425, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490345677928514e-05, + "loss": 3.8482, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895087210578355e-05, + "loss": 3.8327, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886701263067835e-05, + "loss": 3.8339, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878315315557315e-05, + "loss": 3.8277, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869929368046795e-05, + "loss": 3.8242, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861559799340004e-05, + "loss": 3.8327, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853173851829484e-05, + "loss": 3.8315, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844787904318964e-05, + "loss": 3.8282, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836401956808444e-05, + "loss": 3.8519, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482803238810165e-05, + "loss": 3.8329, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481964644059113e-05, + "loss": 3.8321, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481126049308061e-05, + "loss": 3.8399, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480287454557009e-05, + "loss": 3.8418, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479448859805957e-05, + "loss": 3.8232, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478611902935279e-05, + "loss": 3.8305, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477773308184227e-05, + "loss": 3.8348, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476934713433175e-05, + "loss": 3.8326, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476096118682122e-05, + "loss": 3.8172, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475259161811444e-05, + "loss": 3.8188, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474420567060392e-05, + "loss": 3.836, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47358197230934e-05, + "loss": 3.8359, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472743377558287e-05, + "loss": 3.8305, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719064206876086e-05, + "loss": 3.8357, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710678259365566e-05, + "loss": 3.8257, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702292311855046e-05, + "loss": 3.8343, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693906364344526e-05, + "loss": 3.819, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468553679563774e-05, + "loss": 3.8262, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467715084812722e-05, + "loss": 3.8092, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668764900616695e-05, + "loss": 3.8221, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660378953106175e-05, + "loss": 3.8205, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651993005595655e-05, + "loss": 3.8381, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464362343688887e-05, + "loss": 3.8259, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635237489378344e-05, + "loss": 3.8215, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626851541867824e-05, + "loss": 3.8267, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618465594357304e-05, + "loss": 3.8275, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461009602565052e-05, + "loss": 3.8295, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460171007814e-05, + "loss": 3.8085, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459332413062948e-05, + "loss": 3.8133, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458493818311896e-05, + "loss": 3.8321, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457656861441217e-05, + "loss": 3.8266, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456818266690165e-05, + "loss": 3.8136, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455979671939113e-05, + "loss": 3.8122, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455141077188061e-05, + "loss": 3.8177, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.804, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.45346552556633e-05, + "loss": 3.8231, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452626930815278e-05, + "loss": 3.8096, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451788336064226e-05, + "loss": 3.8193, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450949741313174e-05, + "loss": 3.8197, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.8134, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492741896914433e-05, + "loss": 3.8067, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484355949403913e-05, + "loss": 3.8118, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475970001893393e-05, + "loss": 3.8034, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.8104, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445921448567608e-05, + "loss": 3.8206, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445082853816556e-05, + "loss": 3.8063, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444244259065504e-05, + "loss": 3.8069, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443405664314452e-05, + "loss": 3.7972, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.804, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8188, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440891517941669e-05, + "loss": 3.8217, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440052923190617e-05, + "loss": 3.8114, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439214328439565e-05, + "loss": 3.8177, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.8242, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8164, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436700182066783e-05, + "loss": 3.7984, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435861587315731e-05, + "loss": 3.8159, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435022992564679e-05, + "loss": 3.8118, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.8038, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333474409429476e-05, + "loss": 3.8084, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.814, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8234, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8066, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299946998191125e-05, + "loss": 3.7905, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291561050680605e-05, + "loss": 3.8058, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283175103170085e-05, + "loss": 3.8065, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.8075, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.8114, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425803363944226e-05, + "loss": 3.8091, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424964769193174e-05, + "loss": 3.8115, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424126174442122e-05, + "loss": 3.8002, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.7978, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422448984940018e-05, + "loss": 3.8019, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421612028069339e-05, + "loss": 3.811, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420773433318287e-05, + "loss": 3.8099, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.814, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419096243816182e-05, + "loss": 3.7914, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418259286945504e-05, + "loss": 3.807, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174206921944525e-05, + "loss": 3.813, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165820974434005e-05, + "loss": 3.8096, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415743502692348e-05, + "loss": 3.8029, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149065458216694e-05, + "loss": 3.7963, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140679510706174e-05, + "loss": 3.8022, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132293563195654e-05, + "loss": 3.8098, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412390761568513e-05, + "loss": 3.7878, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411553804697834e-05, + "loss": 3.8019, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410715209946782e-05, + "loss": 3.8006, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098766151957296e-05, + "loss": 3.805, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090380204446776e-05, + "loss": 3.7892, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408201063573999e-05, + "loss": 3.8077, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407362468822948e-05, + "loss": 3.7957, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406523874071895e-05, + "loss": 3.8067, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405685279320843e-05, + "loss": 3.7984, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404848322450165e-05, + "loss": 3.7911, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404009727699113e-05, + "loss": 3.8064, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.8097, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402332538197008e-05, + "loss": 3.8026, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149558132633e-05, + "loss": 3.7934, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400656986575277e-05, + "loss": 3.7998, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.8011, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398979797073173e-05, + "loss": 3.7898, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981428402024946e-05, + "loss": 3.8, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3973042454514426e-05, + "loss": 3.7933, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964656507003906e-05, + "loss": 3.797, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956270559493386e-05, + "loss": 3.797, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.39479009907866e-05, + "loss": 3.8006, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939515043276075e-05, + "loss": 3.7822, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931129095765555e-05, + "loss": 3.7953, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922743148255035e-05, + "loss": 3.7945, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914357200744515e-05, + "loss": 3.8075, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905987632037724e-05, + "loss": 3.7978, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897601684527204e-05, + "loss": 3.8022, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889215737016684e-05, + "loss": 3.7832, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388082978950617e-05, + "loss": 3.8043, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387244384199565e-05, + "loss": 3.8014, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386407427328886e-05, + "loss": 3.8047, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385568832577834e-05, + "loss": 3.7861, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384730237826782e-05, + "loss": 3.8035, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.8005, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383054686205051e-05, + "loss": 3.8152, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382216091453999e-05, + "loss": 3.7851, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381377496702947e-05, + "loss": 3.8001, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.7959, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379701945081216e-05, + "loss": 3.7857, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378863350330164e-05, + "loss": 3.8017, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780247555791124e-05, + "loss": 3.8027, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.7977, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376349203957381e-05, + "loss": 3.7871, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375510609206329e-05, + "loss": 3.7955, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8844587802886963, + "eval_runtime": 306.1862, + "eval_samples_per_second": 1246.271, + "eval_steps_per_second": 38.947, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374672014455277e-05, + "loss": 3.7819, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373833419704225e-05, + "loss": 3.7747, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372994824953173e-05, + "loss": 3.794, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372157868082494e-05, + "loss": 3.7926, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371319273331442e-05, + "loss": 3.7975, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.37048067858039e-05, + "loss": 3.7889, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369642083829338e-05, + "loss": 3.7842, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368805126958659e-05, + "loss": 3.7747, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367966532207607e-05, + "loss": 3.7884, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367127937456556e-05, + "loss": 3.7876, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366289342705504e-05, + "loss": 3.789, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365452385834825e-05, + "loss": 3.7941, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3646154289641456e-05, + "loss": 3.7805, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637768342130936e-05, + "loss": 3.7811, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629382394620416e-05, + "loss": 3.7793, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620996447109896e-05, + "loss": 3.7708, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612610499599376e-05, + "loss": 3.7809, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604224552088856e-05, + "loss": 3.7785, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595838604578336e-05, + "loss": 3.7746, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587452657067816e-05, + "loss": 3.7974, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579083088361025e-05, + "loss": 3.786, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357069714085051e-05, + "loss": 3.7837, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356231119333999e-05, + "loss": 3.7884, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355392524582947e-05, + "loss": 3.7918, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354555567712268e-05, + "loss": 3.769, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353716972961216e-05, + "loss": 3.7805, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352878378210164e-05, + "loss": 3.7882, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352039783459112e-05, + "loss": 3.7761, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351202826588433e-05, + "loss": 3.7677, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350364231837381e-05, + "loss": 3.7682, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349525637086329e-05, + "loss": 3.7862, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348687042335277e-05, + "loss": 3.7847, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347850085464598e-05, + "loss": 3.7816, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470114907135465e-05, + "loss": 3.7848, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461728959624945e-05, + "loss": 3.7764, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453343012114425e-05, + "loss": 3.7787, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444973443407634e-05, + "loss": 3.7733, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436587495897114e-05, + "loss": 3.7752, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428201548386594e-05, + "loss": 3.7621, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419815600876074e-05, + "loss": 3.7704, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341144603216928e-05, + "loss": 3.7716, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340306008465876e-05, + "loss": 3.7872, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339467413714824e-05, + "loss": 3.7771, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338628818963772e-05, + "loss": 3.7742, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.33779022421272e-05, + "loss": 3.7803, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336953267342042e-05, + "loss": 3.7724, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.33611467259099e-05, + "loss": 3.7819, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335276077839938e-05, + "loss": 3.7642, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334439120969259e-05, + "loss": 3.7612, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333600526218207e-05, + "loss": 3.7799, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332761931467155e-05, + "loss": 3.7772, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331923336716103e-05, + "loss": 3.7661, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.33108474196505e-05, + "loss": 3.7658, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302477850943717e-05, + "loss": 3.7692, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294091903433197e-05, + "loss": 3.7533, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285705955922677e-05, + "loss": 3.7756, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277320008412156e-05, + "loss": 3.7619, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.7656, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.7761, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252178544684325e-05, + "loss": 3.764, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243792597173805e-05, + "loss": 3.7622, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.7631, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.32270370809565e-05, + "loss": 3.7567, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218651133445974e-05, + "loss": 3.7593, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321028156473919e-05, + "loss": 3.7727, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.7628, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.7559, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185123722207623e-05, + "loss": 3.7534, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317673777469711e-05, + "loss": 3.7557, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168368205990326e-05, + "loss": 3.7673, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.773, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315159631096928e-05, + "loss": 3.7668, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314321036345876e-05, + "loss": 3.771, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134840794751975e-05, + "loss": 3.7741, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.776, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311806889973093e-05, + "loss": 3.7505, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310968295222041e-05, + "loss": 3.7668, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310131338351362e-05, + "loss": 3.768, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30929274360031e-05, + "loss": 3.7516, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308454148849258e-05, + "loss": 3.7685, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076155540982064e-05, + "loss": 3.7625, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306778597227527e-05, + "loss": 3.7746, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305940002476475e-05, + "loss": 3.7626, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305101407725423e-05, + "loss": 3.7447, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304262812974371e-05, + "loss": 3.7593, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303425856103692e-05, + "loss": 3.7603, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.30258726135264e-05, + "loss": 3.7644, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301748666601588e-05, + "loss": 3.7612, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300910071850536e-05, + "loss": 3.7654, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300073114979857e-05, + "loss": 3.7648, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299234520228805e-05, + "loss": 3.7553, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298395925477753e-05, + "loss": 3.7492, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297557330726702e-05, + "loss": 3.7566, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967203738560227e-05, + "loss": 3.7672, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958817791049707e-05, + "loss": 3.7629, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950431843539186e-05, + "loss": 3.7669, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2942045896028666e-05, + "loss": 3.7485, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933676327321876e-05, + "loss": 3.7611, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925290379811355e-05, + "loss": 3.7657, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916904432300835e-05, + "loss": 3.7654, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908518484790315e-05, + "loss": 3.7549, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.7543, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891762968573004e-05, + "loss": 3.756, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883377021062484e-05, + "loss": 3.7646, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287499107355197e-05, + "loss": 3.7417, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.757, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285823555733466e-05, + "loss": 3.7493, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284984960982414e-05, + "loss": 3.7611, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284146366231362e-05, + "loss": 3.7426, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283309409360683e-05, + "loss": 3.7681, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282470814609631e-05, + "loss": 3.7497, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281632219858579e-05, + "loss": 3.763, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280793625107527e-05, + "loss": 3.7554, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279956668236848e-05, + "loss": 3.7481, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279118073485796e-05, + "loss": 3.7598, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278279478734744e-05, + "loss": 3.7676, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277440883983692e-05, + "loss": 3.7574, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.7481, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7563, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.7585, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740881428598574e-05, + "loss": 3.7471, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.7565, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.7447, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271573996487074e-05, + "loss": 3.7526, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270735401736022e-05, + "loss": 3.754, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269898444865343e-05, + "loss": 3.7578, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7376, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.7536, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267382660612187e-05, + "loss": 3.7471, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266544065861136e-05, + "loss": 3.762, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265707108990457e-05, + "loss": 3.7557, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7588, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264029919488353e-05, + "loss": 3.7387, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631929626176737e-05, + "loss": 3.7596, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623543678666216e-05, + "loss": 3.7574, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7579, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606771783645176e-05, + "loss": 3.747, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598402214938386e-05, + "loss": 3.757, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2590016267427865e-05, + "loss": 3.7596, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7677, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573244372406825e-05, + "loss": 3.7447, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256487480370004e-05, + "loss": 3.7571, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255648885618952e-05, + "loss": 3.7545, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548102908679e-05, + "loss": 3.7433, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253971696116848e-05, + "loss": 3.759, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253134739246169e-05, + "loss": 3.7563, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252296144495117e-05, + "loss": 3.7611, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251457549744065e-05, + "loss": 3.7425, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250618954993013e-05, + "loss": 3.7518, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8680803775787354, + "eval_runtime": 306.2514, + "eval_samples_per_second": 1246.006, + "eval_steps_per_second": 38.939, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249780360241961e-05, + "loss": 3.7384, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248941765490909e-05, + "loss": 3.73, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248103170739857e-05, + "loss": 3.7519, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247264575988805e-05, + "loss": 3.7514, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246425981237753e-05, + "loss": 3.755, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245587386486701e-05, + "loss": 3.7463, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244748791735649e-05, + "loss": 3.7356, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243910196984597e-05, + "loss": 3.7361, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243073240113918e-05, + "loss": 3.7445, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242234645362866e-05, + "loss": 3.7447, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241396050611814e-05, + "loss": 3.748, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7545, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397221368704564e-05, + "loss": 3.7404, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388835421194044e-05, + "loss": 3.737, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380449473683524e-05, + "loss": 3.7401, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2372063526173004e-05, + "loss": 3.7278, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363677578662484e-05, + "loss": 3.7405, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355291631151963e-05, + "loss": 3.7389, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346905683641443e-05, + "loss": 3.733, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.755, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233015016742413e-05, + "loss": 3.7462, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232176421991361e-05, + "loss": 3.7457, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231337827240309e-05, + "loss": 3.7444, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230499232489257e-05, + "loss": 3.7501, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.731, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228823680867526e-05, + "loss": 3.7428, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227985086116474e-05, + "loss": 3.7426, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227146491365422e-05, + "loss": 3.7354, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7328, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7258, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22463234499264e-05, + "loss": 3.7462, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223793750241588e-05, + "loss": 3.743, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229567933709086e-05, + "loss": 3.7412, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221181986198566e-05, + "loss": 3.7457, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212796038688046e-05, + "loss": 3.7338, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204410091177526e-05, + "loss": 3.7399, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7362, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7297, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179268627449695e-05, + "loss": 3.7214, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.7282, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216251311123239e-05, + "loss": 3.7312, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7479, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7354, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.7309, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212898569999404e-05, + "loss": 3.7446, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212059975248352e-05, + "loss": 3.7329, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112213804973e-05, + "loss": 3.7396, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.7271, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.7186, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.7412, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207868639373465e-05, + "loss": 3.7372, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207030044622413e-05, + "loss": 3.7303, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061930877517345e-05, + "loss": 3.7236, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053544930006824e-05, + "loss": 3.7322, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045158982496304e-05, + "loss": 3.7119, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036773034985784e-05, + "loss": 3.736, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028403466278993e-05, + "loss": 3.7248, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020017518768473e-05, + "loss": 3.7243, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011631571257953e-05, + "loss": 3.7391, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200324562374743e-05, + "loss": 3.7258, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199487605504064e-05, + "loss": 3.7228, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198649010753012e-05, + "loss": 3.7291, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781041600196e-05, + "loss": 3.7148, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196971821250908e-05, + "loss": 3.7228, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19613486438023e-05, + "loss": 3.7334, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7257, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.718, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193619080127074e-05, + "loss": 3.717, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192782123256395e-05, + "loss": 3.715, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191943528505343e-05, + "loss": 3.7262, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7349, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190266339003239e-05, + "loss": 3.7276, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894293821325596e-05, + "loss": 3.7352, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885907873815076e-05, + "loss": 3.7322, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877521926304556e-05, + "loss": 3.7396, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869135978794036e-05, + "loss": 3.7145, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186076641008725e-05, + "loss": 3.7319, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185238046257673e-05, + "loss": 3.7305, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184399451506621e-05, + "loss": 3.7108, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183560856755569e-05, + "loss": 3.7335, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.18272389988489e-05, + "loss": 3.7278, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181885305133838e-05, + "loss": 3.734, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181046710382786e-05, + "loss": 3.7262, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180208115631734e-05, + "loss": 3.7088, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179371158761055e-05, + "loss": 3.7181, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178532564010003e-05, + "loss": 3.7223, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177693969258951e-05, + "loss": 3.727, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176855374507899e-05, + "loss": 3.7238, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760184176372206e-05, + "loss": 3.7302, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751798228861685e-05, + "loss": 3.7251, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743412281351165e-05, + "loss": 3.7208, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735026333840645e-05, + "loss": 3.7136, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726656765133854e-05, + "loss": 3.7173, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718270817623334e-05, + "loss": 3.7309, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709884870112814e-05, + "loss": 3.7281, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701498922602294e-05, + "loss": 3.7283, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693129353895503e-05, + "loss": 3.7116, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684743406384983e-05, + "loss": 3.7234, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167635745887446e-05, + "loss": 3.7278, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166797151136394e-05, + "loss": 3.7266, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165960194265716e-05, + "loss": 3.7208, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165121599514664e-05, + "loss": 3.7182, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164283004763612e-05, + "loss": 3.7194, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163446047892933e-05, + "loss": 3.726, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162607453141881e-05, + "loss": 3.7058, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161768858390829e-05, + "loss": 3.7175, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160930263639777e-05, + "loss": 3.7134, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160093306769098e-05, + "loss": 3.7236, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159254712018046e-05, + "loss": 3.7123, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158416117266994e-05, + "loss": 3.7273, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157577522515942e-05, + "loss": 3.7153, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567405656452626e-05, + "loss": 3.7231, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155901970894211e-05, + "loss": 3.7237, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155063376143159e-05, + "loss": 3.7095, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154224781392107e-05, + "loss": 3.7212, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153387824521428e-05, + "loss": 3.7324, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152549229770376e-05, + "loss": 3.7178, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151710635019324e-05, + "loss": 3.7181, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150872040268272e-05, + "loss": 3.7137, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150035083397593e-05, + "loss": 3.7217, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149196488646541e-05, + "loss": 3.7166, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148357893895489e-05, + "loss": 3.7173, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147519299144437e-05, + "loss": 3.7082, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146682342273758e-05, + "loss": 3.7162, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458437475227067e-05, + "loss": 3.7195, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1450051527716546e-05, + "loss": 3.7182, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441665580206026e-05, + "loss": 3.7032, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433296011499236e-05, + "loss": 3.7196, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424910063988715e-05, + "loss": 3.7098, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416524116478195e-05, + "loss": 3.7298, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140813816896767e-05, + "loss": 3.7172, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399768600260884e-05, + "loss": 3.7244, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391382652750364e-05, + "loss": 3.7034, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382996705239844e-05, + "loss": 3.7248, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137461075772932e-05, + "loss": 3.7199, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366241189022533e-05, + "loss": 3.7253, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135785524151202e-05, + "loss": 3.7071, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.13494692940015e-05, + "loss": 3.7217, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134108334649097e-05, + "loss": 3.7238, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133271377778419e-05, + "loss": 3.7297, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132432783027367e-05, + "loss": 3.7112, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131594188276314e-05, + "loss": 3.7199, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130755593525262e-05, + "loss": 3.7203, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129918636654584e-05, + "loss": 3.7115, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129080041903532e-05, + "loss": 3.7185, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128241447152479e-05, + "loss": 3.7217, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127402852401427e-05, + "loss": 3.7237, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126565895530749e-05, + "loss": 3.7104, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125727300779697e-05, + "loss": 3.7165, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.857938289642334, + "eval_runtime": 306.6295, + "eval_samples_per_second": 1244.469, + "eval_steps_per_second": 38.891, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124888706028645e-05, + "loss": 3.7087, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124050111277593e-05, + "loss": 3.6949, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123213154406914e-05, + "loss": 3.7155, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223745596558616e-05, + "loss": 3.7172, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215359649048096e-05, + "loss": 3.7181, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206973701537576e-05, + "loss": 3.7124, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119860413283079e-05, + "loss": 3.704, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190218185320265e-05, + "loss": 3.7021, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181832237809745e-05, + "loss": 3.7106, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173446290299225e-05, + "loss": 3.7081, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116507672159244e-05, + "loss": 3.7141, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115669077408192e-05, + "loss": 3.7159, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114832120537514e-05, + "loss": 3.7086, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139935257864617e-05, + "loss": 3.705, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113154931035409e-05, + "loss": 3.703, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112316336284357e-05, + "loss": 3.6906, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111477741533305e-05, + "loss": 3.7075, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110639146782253e-05, + "loss": 3.7039, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109800552031201e-05, + "loss": 3.7027, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108961957280149e-05, + "loss": 3.7157, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.10812500040947e-05, + "loss": 3.7162, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107286405658418e-05, + "loss": 3.7073, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106447810907366e-05, + "loss": 3.7106, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056092161563145e-05, + "loss": 3.7131, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047722592856354e-05, + "loss": 3.6976, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039336645345834e-05, + "loss": 3.7108, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030950697835314e-05, + "loss": 3.7088, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1022564750324794e-05, + "loss": 3.7019, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014195181618e-05, + "loss": 3.6958, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100580923410748e-05, + "loss": 3.6975, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099742328659696e-05, + "loss": 3.7074, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098903733908644e-05, + "loss": 3.7141, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098066777037965e-05, + "loss": 3.7057, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097228182286913e-05, + "loss": 3.7103, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096389587535861e-05, + "loss": 3.698, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095552630665183e-05, + "loss": 3.7074, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094714035914131e-05, + "loss": 3.7073, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093875441163079e-05, + "loss": 3.6914, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093036846412027e-05, + "loss": 3.6925, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092199889541348e-05, + "loss": 3.6944, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091361294790296e-05, + "loss": 3.6969, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090522700039244e-05, + "loss": 3.7154, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089684105288192e-05, + "loss": 3.7004, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888471484175126e-05, + "loss": 3.6958, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0880085536664606e-05, + "loss": 3.7139, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871699589154086e-05, + "loss": 3.7021, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863313641643566e-05, + "loss": 3.7052, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085494407293678e-05, + "loss": 3.6936, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084655812542626e-05, + "loss": 3.6854, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083817217791574e-05, + "loss": 3.7121, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082978623040522e-05, + "loss": 3.7017, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082141666169843e-05, + "loss": 3.6979, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081303071418791e-05, + "loss": 3.6945, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080464476667739e-05, + "loss": 3.6912, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079625881916687e-05, + "loss": 3.6851, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078788925046008e-05, + "loss": 3.6979, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077950330294956e-05, + "loss": 3.694, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077111735543904e-05, + "loss": 3.6954, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076273140792852e-05, + "loss": 3.7055, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754361839221735e-05, + "loss": 3.6929, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745975891711215e-05, + "loss": 3.6884, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737589944200695e-05, + "loss": 3.6997, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0729203996690175e-05, + "loss": 3.68, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720834427983384e-05, + "loss": 3.6903, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712448480472864e-05, + "loss": 3.6973, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0704062532962344e-05, + "loss": 3.6937, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695676585451824e-05, + "loss": 3.6861, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068730701674503e-05, + "loss": 3.6859, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067892106923451e-05, + "loss": 3.6801, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067053512172399e-05, + "loss": 3.6951, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066214917421347e-05, + "loss": 3.701, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065377960550669e-05, + "loss": 3.6976, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064539365799617e-05, + "loss": 3.6989, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063700771048565e-05, + "loss": 3.7006, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062862176297513e-05, + "loss": 3.7084, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062025219426834e-05, + "loss": 3.6798, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061186624675782e-05, + "loss": 3.7007, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.06034802992473e-05, + "loss": 3.6994, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059509435173678e-05, + "loss": 3.674, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058672478302999e-05, + "loss": 3.7048, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057833883551947e-05, + "loss": 3.6916, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056995288800895e-05, + "loss": 3.703, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056156694049843e-05, + "loss": 3.6958, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055319737179164e-05, + "loss": 3.6776, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054481142428112e-05, + "loss": 3.6833, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.05364254767706e-05, + "loss": 3.6927, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052803952926008e-05, + "loss": 3.6933, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051966996055329e-05, + "loss": 3.6902, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051128401304277e-05, + "loss": 3.6977, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050289806553225e-05, + "loss": 3.6926, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049452849682546e-05, + "loss": 3.6868, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048614254931494e-05, + "loss": 3.6863, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047775660180442e-05, + "loss": 3.6844, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.04693706542939e-05, + "loss": 3.6962, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0461001085587116e-05, + "loss": 3.6954, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452615138076596e-05, + "loss": 3.702, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0444245569369806e-05, + "loss": 3.677, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435859621859285e-05, + "loss": 3.6913, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427473674348765e-05, + "loss": 3.6981, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0419087726838245e-05, + "loss": 3.6964, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410701779327725e-05, + "loss": 3.6882, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402315831817205e-05, + "loss": 3.6856, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393929884306685e-05, + "loss": 3.688, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0385543936796165e-05, + "loss": 3.6933, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0377190746893103e-05, + "loss": 3.6741, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036880479938259e-05, + "loss": 3.6915, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036041885187207e-05, + "loss": 3.679, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035203290436155e-05, + "loss": 3.6957, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034364695685103e-05, + "loss": 3.6804, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033527738814424e-05, + "loss": 3.6904, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032689144063372e-05, + "loss": 3.6864, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.03185054931232e-05, + "loss": 3.6945, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.031011954561268e-05, + "loss": 3.6906, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030173359810216e-05, + "loss": 3.6774, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029334765059164e-05, + "loss": 3.6892, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028496170308111e-05, + "loss": 3.6997, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027657575557059e-05, + "loss": 3.6872, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026820618686381e-05, + "loss": 3.6915, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025982023935329e-05, + "loss": 3.6795, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025143429184277e-05, + "loss": 3.6889, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024304834433225e-05, + "loss": 3.69, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023469515442919e-05, + "loss": 3.6816, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022630920691867e-05, + "loss": 3.6834, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021792325940815e-05, + "loss": 3.6851, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020953731189763e-05, + "loss": 3.6903, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020115136438711e-05, + "loss": 3.6879, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192765416876586e-05, + "loss": 3.6714, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184379469366066e-05, + "loss": 3.6906, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175993521855546e-05, + "loss": 3.6755, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016762395314876e-05, + "loss": 3.697, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015923800563824e-05, + "loss": 3.6887, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015085205812772e-05, + "loss": 3.6926, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.01424661106172e-05, + "loss": 3.6718, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013409654191041e-05, + "loss": 3.6955, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012571059439989e-05, + "loss": 3.6881, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011732464688937e-05, + "loss": 3.6918, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010893869937885e-05, + "loss": 3.6807, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010056913067206e-05, + "loss": 3.6867, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009218318316154e-05, + "loss": 3.6923, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008379723565102e-05, + "loss": 3.7038, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.00754112881405e-05, + "loss": 3.6816, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0067041719433715e-05, + "loss": 3.6887, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0058655771923195e-05, + "loss": 3.6923, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005028620321641e-05, + "loss": 3.6816, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041900255705884e-05, + "loss": 3.6833, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033514308195364e-05, + "loss": 3.6926, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0025128360684844e-05, + "loss": 3.6927, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016742413174324e-05, + "loss": 3.6801, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008356465663804e-05, + "loss": 3.6877, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.851024627685547, + "eval_runtime": 305.9845, + "eval_samples_per_second": 1247.093, + "eval_steps_per_second": 38.973, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999970518153284e-05, + "loss": 3.6727, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991584570642764e-05, + "loss": 3.6675, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983198623132244e-05, + "loss": 3.6837, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974812675621724e-05, + "loss": 3.685, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966426728111204e-05, + "loss": 3.6939, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9958040780600684e-05, + "loss": 3.6811, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949654833090164e-05, + "loss": 3.6785, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941268885579644e-05, + "loss": 3.6767, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993289931687286e-05, + "loss": 3.677, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992451336936234e-05, + "loss": 3.6812, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991612742185182e-05, + "loss": 3.6825, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99077414743413e-05, + "loss": 3.6841, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989938828443824e-05, + "loss": 3.6785, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989100233692772e-05, + "loss": 3.6762, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.98826163894172e-05, + "loss": 3.6759, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987423044190668e-05, + "loss": 3.6615, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986584449439616e-05, + "loss": 3.6722, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985745854688564e-05, + "loss": 3.6745, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984907259937512e-05, + "loss": 3.6766, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98406866518646e-05, + "loss": 3.6818, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983231708315781e-05, + "loss": 3.6879, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982394751445102e-05, + "loss": 3.6826, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.98155615669405e-05, + "loss": 3.681, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980717561942998e-05, + "loss": 3.6818, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979878967191946e-05, + "loss": 3.6699, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979040372440894e-05, + "loss": 3.6787, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978201777689842e-05, + "loss": 3.6802, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773631829387895e-05, + "loss": 3.6743, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765245881877375e-05, + "loss": 3.6737, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975687631317059e-05, + "loss": 3.6648, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974849036566007e-05, + "loss": 3.6752, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974010441814955e-05, + "loss": 3.6876, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973171847063903e-05, + "loss": 3.6789, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972334890193225e-05, + "loss": 3.6763, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971496295442172e-05, + "loss": 3.6685, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.97065770069112e-05, + "loss": 3.6814, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969819105940068e-05, + "loss": 3.6765, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689821490693896e-05, + "loss": 3.6665, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968143554318337e-05, + "loss": 3.6657, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967304959567285e-05, + "loss": 3.6637, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966466364816233e-05, + "loss": 3.6651, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9656294079455545e-05, + "loss": 3.6857, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647908131945025e-05, + "loss": 3.674, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639522184434505e-05, + "loss": 3.67, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631136236923985e-05, + "loss": 3.6813, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622766668217194e-05, + "loss": 3.6716, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614380720706674e-05, + "loss": 3.6812, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605994773196154e-05, + "loss": 3.6693, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959762520448937e-05, + "loss": 3.6495, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958923925697884e-05, + "loss": 3.687, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958085330946832e-05, + "loss": 3.6717, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95724673619578e-05, + "loss": 3.673, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956409779325101e-05, + "loss": 3.6656, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955572822454423e-05, + "loss": 3.6603, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547342277033714e-05, + "loss": 3.6606, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538956329523194e-05, + "loss": 3.6689, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953057038201267e-05, + "loss": 3.6662, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952218443450215e-05, + "loss": 3.6639, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951379848699163e-05, + "loss": 3.6799, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950541253948111e-05, + "loss": 3.6638, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949702659197059e-05, + "loss": 3.659, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488657023263796e-05, + "loss": 3.6736, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480271075753276e-05, + "loss": 3.6502, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471885128242756e-05, + "loss": 3.6581, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463499180732236e-05, + "loss": 3.6734, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945512961202545e-05, + "loss": 3.6665, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944674366451493e-05, + "loss": 3.6548, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943837409580814e-05, + "loss": 3.662, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942998814829762e-05, + "loss": 3.6546, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.94216022007871e-05, + "loss": 3.668, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941321625327658e-05, + "loss": 3.672, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940483030576606e-05, + "loss": 3.6685, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939644435825554e-05, + "loss": 3.669, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938805841074502e-05, + "loss": 3.6747, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.93796724632345e-05, + "loss": 3.6788, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937130289452771e-05, + "loss": 3.6555, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936291694701719e-05, + "loss": 3.6766, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935453099950667e-05, + "loss": 3.667, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934614505199615e-05, + "loss": 3.6499, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337775483289366e-05, + "loss": 3.6745, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329389535778846e-05, + "loss": 3.6669, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9321019967072055e-05, + "loss": 3.6775, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312634019561535e-05, + "loss": 3.6665, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304248072051015e-05, + "loss": 3.6506, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295862124540495e-05, + "loss": 3.6547, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287476177029975e-05, + "loss": 3.6663, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9279106608323184e-05, + "loss": 3.6643, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270720660812664e-05, + "loss": 3.6678, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9262334713302144e-05, + "loss": 3.6665, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9253948765791624e-05, + "loss": 3.663, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245562818281104e-05, + "loss": 3.664, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237176870770583e-05, + "loss": 3.6574, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922879092326007e-05, + "loss": 3.6578, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922040497574955e-05, + "loss": 3.6685, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921203540704276e-05, + "loss": 3.6667, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920364945953224e-05, + "loss": 3.6744, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919527989082545e-05, + "loss": 3.6515, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918689394331493e-05, + "loss": 3.6627, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917850799580441e-05, + "loss": 3.6692, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917012204829389e-05, + "loss": 3.6675, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916173610078337e-05, + "loss": 3.6612, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915335015327285e-05, + "loss": 3.6604, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914496420576232e-05, + "loss": 3.6624, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913657825825181e-05, + "loss": 3.6631, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912822506834875e-05, + "loss": 3.653, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911983912083823e-05, + "loss": 3.6613, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911145317332771e-05, + "loss": 3.6531, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910306722581719e-05, + "loss": 3.6694, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909468127830667e-05, + "loss": 3.6532, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908631170959988e-05, + "loss": 3.6616, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907792576208936e-05, + "loss": 3.6562, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906953981457884e-05, + "loss": 3.6701, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906115386706832e-05, + "loss": 3.6615, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052767919557795e-05, + "loss": 3.6517, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044381972047275e-05, + "loss": 3.6652, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903599602453676e-05, + "loss": 3.6724, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902761007702624e-05, + "loss": 3.6619, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901924050831945e-05, + "loss": 3.6615, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010870939612667e-05, + "loss": 3.6533, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002484992102147e-05, + "loss": 3.6604, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899409904459162e-05, + "loss": 3.6622, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.89857130970811e-05, + "loss": 3.6541, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897732714957058e-05, + "loss": 3.655, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896894120206006e-05, + "loss": 3.6608, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896055525454954e-05, + "loss": 3.6657, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895216930703902e-05, + "loss": 3.6607, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894379973833223e-05, + "loss": 3.6475, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935413790821715e-05, + "loss": 3.662, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8927027843311195e-05, + "loss": 3.6509, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918641895800675e-05, + "loss": 3.6696, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910272327093884e-05, + "loss": 3.6655, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901886379583364e-05, + "loss": 3.6666, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893500432072844e-05, + "loss": 3.6456, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8885114484562324e-05, + "loss": 3.6696, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887674491585553e-05, + "loss": 3.6599, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886835896834501e-05, + "loss": 3.6677, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885997302083449e-05, + "loss": 3.6553, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885158707332397e-05, + "loss": 3.6573, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884321750461718e-05, + "loss": 3.6624, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883483155710667e-05, + "loss": 3.6792, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882644560959615e-05, + "loss": 3.6544, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881805966208563e-05, + "loss": 3.6638, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880969009337884e-05, + "loss": 3.6675, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880132052467205e-05, + "loss": 3.6529, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879293457716153e-05, + "loss": 3.6581, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878454862965101e-05, + "loss": 3.6661, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877616268214049e-05, + "loss": 3.6677, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876777673462997e-05, + "loss": 3.657, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875939078711945e-05, + "loss": 3.6604, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.846804141998291, + "eval_runtime": 303.4911, + "eval_samples_per_second": 1257.338, + "eval_steps_per_second": 39.293, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875100483960893e-05, + "loss": 3.6499, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874261889209841e-05, + "loss": 3.6406, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734249323391616e-05, + "loss": 3.6578, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.87258633758811e-05, + "loss": 3.6617, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871747742837058e-05, + "loss": 3.6653, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870909148086006e-05, + "loss": 3.6516, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870072191215327e-05, + "loss": 3.6555, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869233596464275e-05, + "loss": 3.6487, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868395001713223e-05, + "loss": 3.649, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867556406962171e-05, + "loss": 3.6575, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866719450091492e-05, + "loss": 3.6567, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86588085534044e-05, + "loss": 3.6548, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865043898469761e-05, + "loss": 3.6614, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864205303718709e-05, + "loss": 3.6449, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863366708967657e-05, + "loss": 3.6484, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625281142166056e-05, + "loss": 3.6377, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616895194655536e-05, + "loss": 3.6487, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608509247145016e-05, + "loss": 3.651, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8600123299634496e-05, + "loss": 3.6456, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591737352123976e-05, + "loss": 3.6558, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583367783417185e-05, + "loss": 3.6648, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574981835906665e-05, + "loss": 3.6581, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566595888396145e-05, + "loss": 3.6556, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558226319689354e-05, + "loss": 3.6538, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549840372178834e-05, + "loss": 3.6468, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541454424668314e-05, + "loss": 3.6541, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.8533068477157794e-05, + "loss": 3.6535, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.8524682529647274e-05, + "loss": 3.6526, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516296582136754e-05, + "loss": 3.6426, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507910634626234e-05, + "loss": 3.6433, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849954106591945e-05, + "loss": 3.6455, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849115511840893e-05, + "loss": 3.6601, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84827691708984e-05, + "loss": 3.6557, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847438322338788e-05, + "loss": 3.6531, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.84660136546811e-05, + "loss": 3.6435, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845762770717058e-05, + "loss": 3.6511, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844924175966005e-05, + "loss": 3.6552, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844087219095327e-05, + "loss": 3.6405, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843248624344275e-05, + "loss": 3.6409, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842410029593223e-05, + "loss": 3.6349, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841571434842171e-05, + "loss": 3.6411, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840732840091119e-05, + "loss": 3.6583, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839894245340067e-05, + "loss": 3.6518, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839055650589015e-05, + "loss": 3.6435, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838217055837963e-05, + "loss": 3.6557, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373800989672837e-05, + "loss": 3.6457, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365415042162317e-05, + "loss": 3.6518, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8357045473455526e-05, + "loss": 3.6486, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348659525945006e-05, + "loss": 3.6212, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340273578434486e-05, + "loss": 3.6643, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331887630923966e-05, + "loss": 3.6452, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323501683413445e-05, + "loss": 3.6526, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831511573590293e-05, + "loss": 3.6371, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830674616719614e-05, + "loss": 3.6405, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829836021968562e-05, + "loss": 3.6316, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.82899742721751e-05, + "loss": 3.643, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828158832466458e-05, + "loss": 3.6406, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827320237715406e-05, + "loss": 3.6381, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826481642964354e-05, + "loss": 3.6576, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825644686093675e-05, + "loss": 3.6399, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824806091342623e-05, + "loss": 3.6333, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823967496591571e-05, + "loss": 3.6492, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823128901840519e-05, + "loss": 3.6281, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822290307089467e-05, + "loss": 3.631, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821451712338415e-05, + "loss": 3.6495, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820613117587363e-05, + "loss": 3.6417, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197761607166846e-05, + "loss": 3.634, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189375659656326e-05, + "loss": 3.6321, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180989712145806e-05, + "loss": 3.6332, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172603764635286e-05, + "loss": 3.6419, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164234195928495e-05, + "loss": 3.6476, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155848248417975e-05, + "loss": 3.6415, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147462300907455e-05, + "loss": 3.6456, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8139092732200664e-05, + "loss": 3.6484, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8130706784690144e-05, + "loss": 3.6566, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8122320837179624e-05, + "loss": 3.6282, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113934889669104e-05, + "loss": 3.6517, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.8105548942158584e-05, + "loss": 3.6382, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.80971793734518e-05, + "loss": 3.6272, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808879342594128e-05, + "loss": 3.6447, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808040747843076e-05, + "loss": 3.6518, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807202153092024e-05, + "loss": 3.6493, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806363558340971e-05, + "loss": 3.6489, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805526601470293e-05, + "loss": 3.6241, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804688006719241e-05, + "loss": 3.6262, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803849411968189e-05, + "loss": 3.6419, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803010817217136e-05, + "loss": 3.6393, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802172222466084e-05, + "loss": 3.6404, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801333627715032e-05, + "loss": 3.6477, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.80049503296398e-05, + "loss": 3.6382, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799658076093302e-05, + "loss": 3.6392, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.79881948134225e-05, + "loss": 3.6362, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797980886591198e-05, + "loss": 3.6323, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797142291840146e-05, + "loss": 3.6444, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796303697089094e-05, + "loss": 3.6446, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795465102338042e-05, + "loss": 3.6461, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946281454673626e-05, + "loss": 3.6336, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937895507163106e-05, + "loss": 3.6326, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929509559652586e-05, + "loss": 3.646, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7921123612142066e-05, + "loss": 3.6442, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912737664631546e-05, + "loss": 3.6373, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904351717121026e-05, + "loss": 3.6396, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895965769610506e-05, + "loss": 3.6344, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887579822099986e-05, + "loss": 3.6345, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.78792102533932e-05, + "loss": 3.6356, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787084068468641e-05, + "loss": 3.6358, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786245473717589e-05, + "loss": 3.6284, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785406878966537e-05, + "loss": 3.6474, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784568284215485e-05, + "loss": 3.6299, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783729689464433e-05, + "loss": 3.6366, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782892732593754e-05, + "loss": 3.6316, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782054137842702e-05, + "loss": 3.6451, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.78121554309165e-05, + "loss": 3.6408, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780376948340598e-05, + "loss": 3.629, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779538353589546e-05, + "loss": 3.6433, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7787013967188675e-05, + "loss": 3.6474, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778628019678155e-05, + "loss": 3.6376, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7770242072167635e-05, + "loss": 3.6353, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761856124657115e-05, + "loss": 3.6341, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753470177146595e-05, + "loss": 3.6351, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7745084229636075e-05, + "loss": 3.6395, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736714660929284e-05, + "loss": 3.6313, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728328713418764e-05, + "loss": 3.6323, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719942765908244e-05, + "loss": 3.637, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771155681839772e-05, + "loss": 3.6407, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.77031708708872e-05, + "loss": 3.6351, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769478492337668e-05, + "loss": 3.6266, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686398975866164e-05, + "loss": 3.6416, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7678013028355644e-05, + "loss": 3.6246, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766964345964885e-05, + "loss": 3.6456, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766125751213833e-05, + "loss": 3.639, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765287156462781e-05, + "loss": 3.6466, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764450199592102e-05, + "loss": 3.6187, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.76361160484105e-05, + "loss": 3.6485, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762773010089998e-05, + "loss": 3.6319, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761934415338946e-05, + "loss": 3.6444, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761097458468267e-05, + "loss": 3.6342, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760258863717215e-05, + "loss": 3.6284, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759420268966163e-05, + "loss": 3.6455, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758581674215112e-05, + "loss": 3.6537, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.75774307946406e-05, + "loss": 3.6358, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756904484713008e-05, + "loss": 3.6382, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756065889961956e-05, + "loss": 3.6433, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7552289330912767e-05, + "loss": 3.6311, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543903383402247e-05, + "loss": 3.6348, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535517435891726e-05, + "loss": 3.6434, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7527131488381206e-05, + "loss": 3.6402, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518761919674416e-05, + "loss": 3.638, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510375972163895e-05, + "loss": 3.6352, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.844243288040161, + "eval_runtime": 303.6171, + "eval_samples_per_second": 1256.816, + "eval_steps_per_second": 39.276, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501990024653375e-05, + "loss": 3.6185, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493604077142855e-05, + "loss": 3.6161, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485218129632335e-05, + "loss": 3.6322, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476832182121815e-05, + "loss": 3.6374, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746846261341503e-05, + "loss": 3.6406, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.746007666590451e-05, + "loss": 3.6303, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745169071839399e-05, + "loss": 3.632, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744330477088347e-05, + "loss": 3.624, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743491882337295e-05, + "loss": 3.6295, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742653287586243e-05, + "loss": 3.631, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418146928351904e-05, + "loss": 3.6318, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740977735964512e-05, + "loss": 3.6335, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.74013914121346e-05, + "loss": 3.6425, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739300546462408e-05, + "loss": 3.621, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738461951711355e-05, + "loss": 3.628, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737623356960303e-05, + "loss": 3.6106, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736784762209252e-05, + "loss": 3.6266, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359478053385736e-05, + "loss": 3.6257, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735109210587521e-05, + "loss": 3.6233, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734270615836469e-05, + "loss": 3.6326, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733432021085417e-05, + "loss": 3.6381, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732595064214738e-05, + "loss": 3.639, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731756469463686e-05, + "loss": 3.6346, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730917874712634e-05, + "loss": 3.6292, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730079279961582e-05, + "loss": 3.626, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.72924068521053e-05, + "loss": 3.6312, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728403728339851e-05, + "loss": 3.6301, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727565133588799e-05, + "loss": 3.6313, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267265388377473e-05, + "loss": 3.6188, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258879440866953e-05, + "loss": 3.6194, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725049349335643e-05, + "loss": 3.6192, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724212392464964e-05, + "loss": 3.6403, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723373797713912e-05, + "loss": 3.6358, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.72253520296286e-05, + "loss": 3.6247, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721696608211808e-05, + "loss": 3.6238, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720858013460756e-05, + "loss": 3.6217, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720021056590077e-05, + "loss": 3.6361, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719182461839025e-05, + "loss": 3.62, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718343867087973e-05, + "loss": 3.6186, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717505272336921e-05, + "loss": 3.6141, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716666677585869e-05, + "loss": 3.6198, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715828082834817e-05, + "loss": 3.63, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714989488083766e-05, + "loss": 3.6304, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714152531213087e-05, + "loss": 3.623, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713313936462035e-05, + "loss": 3.6325, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712475341710983e-05, + "loss": 3.6223, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711636746959931e-05, + "loss": 3.6292, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107997900892516e-05, + "loss": 3.626, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099611953381996e-05, + "loss": 3.6005, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7091226005871476e-05, + "loss": 3.6385, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082840058360956e-05, + "loss": 3.6215, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074454110850436e-05, + "loss": 3.6307, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7066068163339916e-05, + "loss": 3.6178, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057698594633125e-05, + "loss": 3.6171, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704931264712261e-05, + "loss": 3.6082, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704092669961209e-05, + "loss": 3.6194, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703254075210157e-05, + "loss": 3.6203, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024154804591045e-05, + "loss": 3.6134, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701578523588426e-05, + "loss": 3.6354, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700739928837374e-05, + "loss": 3.623, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6999013340863214e-05, + "loss": 3.6053, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990627393352694e-05, + "loss": 3.6287, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698225782464591e-05, + "loss": 3.6097, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697387187713539e-05, + "loss": 3.6082, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696548592962486e-05, + "loss": 3.6259, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695709998211435e-05, + "loss": 3.62, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694871403460383e-05, + "loss": 3.611, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694032808709331e-05, + "loss": 3.6097, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693194213958279e-05, + "loss": 3.6124, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923572570876e-05, + "loss": 3.6205, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691518662336548e-05, + "loss": 3.6254, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690680067585496e-05, + "loss": 3.6217, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689841472834444e-05, + "loss": 3.6248, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689004515963765e-05, + "loss": 3.6252, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688165921212713e-05, + "loss": 3.6314, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687327326461661e-05, + "loss": 3.6129, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686488731710609e-05, + "loss": 3.6257, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685650136959557e-05, + "loss": 3.6159, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684813180088878e-05, + "loss": 3.6075, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683974585337826e-05, + "loss": 3.6213, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683135990586774e-05, + "loss": 3.63, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682297395835722e-05, + "loss": 3.6261, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.68145880108467e-05, + "loss": 3.63, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680621844213991e-05, + "loss": 3.5987, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679783249462939e-05, + "loss": 3.6124, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678944654711887e-05, + "loss": 3.6183, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678106059960835e-05, + "loss": 3.6208, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677267465209783e-05, + "loss": 3.6122, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676430508339104e-05, + "loss": 3.6269, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675591913588052e-05, + "loss": 3.6181, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674753318837e-05, + "loss": 3.6204, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673914724085948e-05, + "loss": 3.6075, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730777672152697e-05, + "loss": 3.6115, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722391724642177e-05, + "loss": 3.6226, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6714005777131656e-05, + "loss": 3.619, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6705619829621136e-05, + "loss": 3.6276, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6697233882110616e-05, + "loss": 3.614, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688864313403825e-05, + "loss": 3.6078, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680478365893305e-05, + "loss": 3.6233, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672092418382785e-05, + "loss": 3.6229, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663706470872265e-05, + "loss": 3.618, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655320523361745e-05, + "loss": 3.6157, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646934575851225e-05, + "loss": 3.613, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638548628340705e-05, + "loss": 3.6143, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663017905963392e-05, + "loss": 3.6169, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.66217931121234e-05, + "loss": 3.6115, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613407164612874e-05, + "loss": 3.611, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6605021217102354e-05, + "loss": 3.6186, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659665164839557e-05, + "loss": 3.6172, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658826570088505e-05, + "loss": 3.608, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657987975337452e-05, + "loss": 3.6147, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571493805864e-05, + "loss": 3.6177, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656310785835348e-05, + "loss": 3.6197, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.65547382896467e-05, + "loss": 3.6065, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654635234213617e-05, + "loss": 3.6205, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653796639462566e-05, + "loss": 3.6264, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652958044711514e-05, + "loss": 3.6202, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652121087840835e-05, + "loss": 3.6116, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651282493089783e-05, + "loss": 3.6127, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650443898338731e-05, + "loss": 3.6147, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649605303587679e-05, + "loss": 3.6219, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648768346717e-05, + "loss": 3.6099, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647929751965948e-05, + "loss": 3.6117, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647091157214896e-05, + "loss": 3.6101, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646252562463844e-05, + "loss": 3.6214, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645413967712792e-05, + "loss": 3.6142, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445770108421126e-05, + "loss": 3.6011, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643738416091061e-05, + "loss": 3.6184, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642899821340009e-05, + "loss": 3.6067, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642061226588957e-05, + "loss": 3.6253, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641222631837905e-05, + "loss": 3.6168, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640384037086853e-05, + "loss": 3.6227, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639545442335801e-05, + "loss": 3.5999, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638708485465122e-05, + "loss": 3.621, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.63786989071407e-05, + "loss": 3.6148, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637031295963018e-05, + "loss": 3.6193, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636192701211966e-05, + "loss": 3.616, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635355744341287e-05, + "loss": 3.6074, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634517149590235e-05, + "loss": 3.6276, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633678554839183e-05, + "loss": 3.6243, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632839960088131e-05, + "loss": 3.6179, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6320030032174526e-05, + "loss": 3.6175, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311644084664006e-05, + "loss": 3.6211, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303258137153486e-05, + "loss": 3.6144, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294872189642966e-05, + "loss": 3.6094, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286486242132446e-05, + "loss": 3.6234, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278100294621926e-05, + "loss": 3.6179, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269730725915135e-05, + "loss": 3.6211, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261344778404615e-05, + "loss": 3.6113, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.842008590698242, + "eval_runtime": 306.6227, + "eval_samples_per_second": 1244.497, + "eval_steps_per_second": 38.891, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252958830894095e-05, + "loss": 3.6047, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244572883383575e-05, + "loss": 3.5969, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236203314676784e-05, + "loss": 3.6128, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227817367166264e-05, + "loss": 3.6168, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219431419655744e-05, + "loss": 3.6244, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621104547214523e-05, + "loss": 3.609, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620265952463471e-05, + "loss": 3.6111, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194273577124184e-05, + "loss": 3.6075, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.61859040084174e-05, + "loss": 3.6076, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617751806090688e-05, + "loss": 3.6064, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616913211339636e-05, + "loss": 3.6131, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616074616588583e-05, + "loss": 3.6157, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615237659717905e-05, + "loss": 3.6188, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614399064966853e-05, + "loss": 3.5993, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135604702158e-05, + "loss": 3.6058, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612721875464748e-05, + "loss": 3.5876, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611883280713697e-05, + "loss": 3.6089, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110463238430184e-05, + "loss": 3.6093, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610207729091966e-05, + "loss": 3.6007, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609369134340914e-05, + "loss": 3.6104, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608530539589862e-05, + "loss": 3.6183, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607693582719183e-05, + "loss": 3.6137, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068549879681306e-05, + "loss": 3.6181, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060163932170786e-05, + "loss": 3.609, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051777984660266e-05, + "loss": 3.6088, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043392037149746e-05, + "loss": 3.607, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035022468442955e-05, + "loss": 3.6058, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026636520932435e-05, + "loss": 3.6137, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601825057342192e-05, + "loss": 3.6021, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.60098646259114e-05, + "loss": 3.5983, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600147867840088e-05, + "loss": 3.6001, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599310910969409e-05, + "loss": 3.6149, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598472316218357e-05, + "loss": 3.6136, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597633721467305e-05, + "loss": 3.6111, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596795126716253e-05, + "loss": 3.6021, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595958169845574e-05, + "loss": 3.6049, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595119575094522e-05, + "loss": 3.6148, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.59428098034347e-05, + "loss": 3.5963, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593442385592418e-05, + "loss": 3.5989, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592603790841366e-05, + "loss": 3.5979, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917668339706876e-05, + "loss": 3.5976, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909282392196356e-05, + "loss": 3.6107, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900896444685836e-05, + "loss": 3.6049, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892510497175316e-05, + "loss": 3.6076, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884124549664796e-05, + "loss": 3.6091, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875754980958005e-05, + "loss": 3.6082, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867369033447485e-05, + "loss": 3.6059, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858983085936965e-05, + "loss": 3.6092, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850597138426445e-05, + "loss": 3.5793, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842211190915924e-05, + "loss": 3.6149, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833841622209134e-05, + "loss": 3.6029, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825455674698614e-05, + "loss": 3.612, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817069727188093e-05, + "loss": 3.5989, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808683779677573e-05, + "loss": 3.5985, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580031421097079e-05, + "loss": 3.5862, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579192826346027e-05, + "loss": 3.5996, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578354231594975e-05, + "loss": 3.605, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577515636843923e-05, + "loss": 3.5883, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576678679973244e-05, + "loss": 3.6156, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575840085222192e-05, + "loss": 3.6037, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.57500149047114e-05, + "loss": 3.5852, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574162895720088e-05, + "loss": 3.6055, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573325938849409e-05, + "loss": 3.5924, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572487344098357e-05, + "loss": 3.5881, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571648749347305e-05, + "loss": 3.6041, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570810154596253e-05, + "loss": 3.6026, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569971559845201e-05, + "loss": 3.5903, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569134602974522e-05, + "loss": 3.5913, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.56829600822347e-05, + "loss": 3.5893, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567457413472418e-05, + "loss": 3.6011, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566618818721366e-05, + "loss": 3.6048, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565781861850687e-05, + "loss": 3.5991, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564943267099635e-05, + "loss": 3.6072, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564104672348583e-05, + "loss": 3.6031, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563266077597531e-05, + "loss": 3.6117, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562429120726852e-05, + "loss": 3.5958, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615905259758e-05, + "loss": 3.6089, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560751931224748e-05, + "loss": 3.5927, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559913336473696e-05, + "loss": 3.5891, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559074741722644e-05, + "loss": 3.6017, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582377848519657e-05, + "loss": 3.6075, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573991901009137e-05, + "loss": 3.608, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556560595349861e-05, + "loss": 3.6102, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555722000598809e-05, + "loss": 3.5767, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554883405847757e-05, + "loss": 3.5913, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540464489770785e-05, + "loss": 3.6005, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553207854226026e-05, + "loss": 3.6029, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552369259474974e-05, + "loss": 3.5924, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551530664723922e-05, + "loss": 3.6047, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506937078532434e-05, + "loss": 3.6013, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498551131021914e-05, + "loss": 3.5973, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490165183511394e-05, + "loss": 3.5922, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481779236000874e-05, + "loss": 3.5925, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473393288490354e-05, + "loss": 3.6036, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546502371978356e-05, + "loss": 3.6031, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545663777227304e-05, + "loss": 3.6057, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544825182476252e-05, + "loss": 3.5961, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439865877252e-05, + "loss": 3.5913, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543149630854521e-05, + "loss": 3.6025, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542311036103469e-05, + "loss": 3.603, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541472441352417e-05, + "loss": 3.5936, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540633846601365e-05, + "loss": 3.596, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539795251850314e-05, + "loss": 3.5934, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538956657099262e-05, + "loss": 3.5985, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538119700228583e-05, + "loss": 3.5924, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537281105477531e-05, + "loss": 3.5936, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536442510726479e-05, + "loss": 3.5909, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535603915975427e-05, + "loss": 3.6014, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534766959104748e-05, + "loss": 3.5938, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533928364353696e-05, + "loss": 3.5923, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533089769602644e-05, + "loss": 3.5893, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532251174851592e-05, + "loss": 3.5971, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314142179809126e-05, + "loss": 3.6041, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305756232298606e-05, + "loss": 3.5915, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529737028478809e-05, + "loss": 3.5953, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528898433727757e-05, + "loss": 3.6054, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528059838976705e-05, + "loss": 3.6031, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527221244225653e-05, + "loss": 3.5945, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526384287354974e-05, + "loss": 3.5962, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525545692603922e-05, + "loss": 3.5926, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.52470709785287e-05, + "loss": 3.6038, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523868503101818e-05, + "loss": 3.5912, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523031546231139e-05, + "loss": 3.5903, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522192951480087e-05, + "loss": 3.5906, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521354356729035e-05, + "loss": 3.6004, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520515761977983e-05, + "loss": 3.5992, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196788051073046e-05, + "loss": 3.5869, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188402103562526e-05, + "loss": 3.595, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5180016156052006e-05, + "loss": 3.5847, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171630208541486e-05, + "loss": 3.6041, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163260639834695e-05, + "loss": 3.6021, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154874692324175e-05, + "loss": 3.6039, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146488744813655e-05, + "loss": 3.5824, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138102797303135e-05, + "loss": 3.6001, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129716849792615e-05, + "loss": 3.5991, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121347281085824e-05, + "loss": 3.5971, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5112961333575304e-05, + "loss": 3.5951, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104575386064784e-05, + "loss": 3.5869, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096189438554264e-05, + "loss": 3.6102, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508781986984748e-05, + "loss": 3.6047, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507943392233696e-05, + "loss": 3.6007, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507104797482644e-05, + "loss": 3.5972, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506266202731592e-05, + "loss": 3.602, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505429245860913e-05, + "loss": 3.5935, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504590651109861e-05, + "loss": 3.5905, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503752056358809e-05, + "loss": 3.6071, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502913461607757e-05, + "loss": 3.5974, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502076504737078e-05, + "loss": 3.6037, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501237909986026e-05, + "loss": 3.592, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8417367935180664, + "eval_runtime": 305.008, + "eval_samples_per_second": 1251.085, + "eval_steps_per_second": 39.097, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500399315234974e-05, + "loss": 3.5953, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499560720483922e-05, + "loss": 3.5706, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.49872212573287e-05, + "loss": 3.5953, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497883530981818e-05, + "loss": 3.5988, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970465741111393e-05, + "loss": 3.5997, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496207979360087e-05, + "loss": 3.5894, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953693846090347e-05, + "loss": 3.5979, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945307898579827e-05, + "loss": 3.5856, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493693832987304e-05, + "loss": 3.5855, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928552382362516e-05, + "loss": 3.5843, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920166434851996e-05, + "loss": 3.6, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911780487341476e-05, + "loss": 3.5959, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490341091863469e-05, + "loss": 3.6002, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489502497112417e-05, + "loss": 3.5824, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488663902361365e-05, + "loss": 3.5892, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487825307610313e-05, + "loss": 3.5693, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486986712859261e-05, + "loss": 3.589, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486149755988582e-05, + "loss": 3.5895, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.48531116123753e-05, + "loss": 3.5818, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484472566486478e-05, + "loss": 3.5923, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483633971735426e-05, + "loss": 3.5979, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482797014864747e-05, + "loss": 3.5942, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481958420113695e-05, + "loss": 3.6, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481119825362643e-05, + "loss": 3.5893, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480281230611591e-05, + "loss": 3.5922, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794442737409125e-05, + "loss": 3.5889, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786056789898605e-05, + "loss": 3.5867, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777670842388085e-05, + "loss": 3.596, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769284894877565e-05, + "loss": 3.5831, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760898947367045e-05, + "loss": 3.5761, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752529378660254e-05, + "loss": 3.5847, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744143431149734e-05, + "loss": 3.5936, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735757483639214e-05, + "loss": 3.5913, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727371536128694e-05, + "loss": 3.5939, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718985588618174e-05, + "loss": 3.5844, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471061601991138e-05, + "loss": 3.5849, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470223007240086e-05, + "loss": 3.5965, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469384412489034e-05, + "loss": 3.5772, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468545817737982e-05, + "loss": 3.5801, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467708860867304e-05, + "loss": 3.5784, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466870266116252e-05, + "loss": 3.5816, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660316713652e-05, + "loss": 3.5867, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465193076614148e-05, + "loss": 3.5901, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464354481863096e-05, + "loss": 3.59, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463517524992417e-05, + "loss": 3.5888, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462678930241365e-05, + "loss": 3.5868, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461840335490313e-05, + "loss": 3.5878, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461001740739261e-05, + "loss": 3.5949, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601647838685816e-05, + "loss": 3.561, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593261891175296e-05, + "loss": 3.5968, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584875943664776e-05, + "loss": 3.5843, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457648999615426e-05, + "loss": 3.5889, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456810404864374e-05, + "loss": 3.5818, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455973447993695e-05, + "loss": 3.5789, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455134853242643e-05, + "loss": 3.5695, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454296258491591e-05, + "loss": 3.5791, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453457663740539e-05, + "loss": 3.5885, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.45262070686986e-05, + "loss": 3.5722, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451782112118808e-05, + "loss": 3.5979, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450943517367756e-05, + "loss": 3.5853, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450104922616704e-05, + "loss": 3.5661, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449266327865652e-05, + "loss": 3.5881, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448429370994973e-05, + "loss": 3.5714, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447590776243922e-05, + "loss": 3.5706, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.44675218149287e-05, + "loss": 3.5835, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445913586741818e-05, + "loss": 3.5845, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450766298711386e-05, + "loss": 3.571, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442380351200866e-05, + "loss": 3.5779, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433994403690346e-05, + "loss": 3.5714, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425608456179826e-05, + "loss": 3.5778, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.44172225086693e-05, + "loss": 3.5863, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408852939962515e-05, + "loss": 3.5824, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400466992451995e-05, + "loss": 3.5872, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439208104494147e-05, + "loss": 3.5853, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383695097430955e-05, + "loss": 3.5935, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437532552872417e-05, + "loss": 3.5799, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436693958121365e-05, + "loss": 3.589, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358553633703124e-05, + "loss": 3.5746, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4350167686192604e-05, + "loss": 3.5706, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434179811748582e-05, + "loss": 3.5849, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433341216997529e-05, + "loss": 3.5874, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432502622246477e-05, + "loss": 3.5931, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431664027495425e-05, + "loss": 3.5909, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430827070624747e-05, + "loss": 3.5657, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429988475873694e-05, + "loss": 3.5713, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429149881122642e-05, + "loss": 3.5791, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428311286371591e-05, + "loss": 3.5842, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427472691620539e-05, + "loss": 3.5758, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42663573474986e-05, + "loss": 3.587, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425797139998808e-05, + "loss": 3.59, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424958545247756e-05, + "loss": 3.5739, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424119950496704e-05, + "loss": 3.5737, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232829936260246e-05, + "loss": 3.5761, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224443988749726e-05, + "loss": 3.5811, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4216058041239206e-05, + "loss": 3.5867, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207672093728686e-05, + "loss": 3.5861, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199302525021895e-05, + "loss": 3.5778, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190916577511375e-05, + "loss": 3.57, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418253063000086e-05, + "loss": 3.5889, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417414468249034e-05, + "loss": 3.5837, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416577511378355e-05, + "loss": 3.5804, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415738916627303e-05, + "loss": 3.5759, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414900321876251e-05, + "loss": 3.5766, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414061727125199e-05, + "loss": 3.5791, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413223132374147e-05, + "loss": 3.5751, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412386175503468e-05, + "loss": 3.5778, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411547580752416e-05, + "loss": 3.5727, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410708986001364e-05, + "loss": 3.579, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409870391250312e-05, + "loss": 3.5824, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409033434379633e-05, + "loss": 3.5701, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408194839628581e-05, + "loss": 3.5746, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073562448775296e-05, + "loss": 3.5772, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065176501264775e-05, + "loss": 3.5874, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056806932557985e-05, + "loss": 3.5703, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048420985047465e-05, + "loss": 3.5814, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040035037536944e-05, + "loss": 3.5806, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031649090026424e-05, + "loss": 3.5881, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023279521319634e-05, + "loss": 3.5775, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014893573809113e-05, + "loss": 3.5774, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006507626298593e-05, + "loss": 3.5782, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998121678788073e-05, + "loss": 3.5837, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398975211008128e-05, + "loss": 3.5714, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398136616257076e-05, + "loss": 3.5763, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397298021506025e-05, + "loss": 3.573, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396459426754973e-05, + "loss": 3.5801, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395622469884294e-05, + "loss": 3.5759, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394783875133242e-05, + "loss": 3.572, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.39394528038219e-05, + "loss": 3.5753, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393106685631138e-05, + "loss": 3.572, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392269728760459e-05, + "loss": 3.5896, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391431134009407e-05, + "loss": 3.5774, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390592539258355e-05, + "loss": 3.5879, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389753944507303e-05, + "loss": 3.5637, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3889169876366236e-05, + "loss": 3.5836, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880783928855716e-05, + "loss": 3.5815, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.38723979813452e-05, + "loss": 3.5801, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386401203383468e-05, + "loss": 3.5755, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385562608632416e-05, + "loss": 3.5678, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384725651761737e-05, + "loss": 3.5938, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383887057010685e-05, + "loss": 3.5843, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383048462259633e-05, + "loss": 3.585, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382209867508581e-05, + "loss": 3.5781, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381372910637902e-05, + "loss": 3.5864, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.38053431588685e-05, + "loss": 3.5777, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379695721135798e-05, + "loss": 3.568, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378857126384746e-05, + "loss": 3.5931, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378020169514067e-05, + "loss": 3.5758, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771815747630157e-05, + "loss": 3.5883, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763429800119636e-05, + "loss": 3.5744, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8415467739105225, + "eval_runtime": 333.1108, + "eval_samples_per_second": 1145.538, + "eval_steps_per_second": 35.799, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3755043852609116e-05, + "loss": 3.5739, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746674283902326e-05, + "loss": 3.5526, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738288336391805e-05, + "loss": 3.5738, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729902388881285e-05, + "loss": 3.5862, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721516441370765e-05, + "loss": 3.5805, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713146872663974e-05, + "loss": 3.5762, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704760925153454e-05, + "loss": 3.5783, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696374977642934e-05, + "loss": 3.5701, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687989030132414e-05, + "loss": 3.567, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679603082621894e-05, + "loss": 3.5694, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671217135111374e-05, + "loss": 3.5805, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366284756640459e-05, + "loss": 3.5763, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365446161889407e-05, + "loss": 3.5896, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364607567138355e-05, + "loss": 3.562, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363768972387302e-05, + "loss": 3.565, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362932015516624e-05, + "loss": 3.5558, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362093420765572e-05, + "loss": 3.569, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.36125482601452e-05, + "loss": 3.5732, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360416231263467e-05, + "loss": 3.5682, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359577636512415e-05, + "loss": 3.5683, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358740679641737e-05, + "loss": 3.5863, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357902084890685e-05, + "loss": 3.5767, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357063490139633e-05, + "loss": 3.5817, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356224895388581e-05, + "loss": 3.5728, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553879385179024e-05, + "loss": 3.5767, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.35454934376685e-05, + "loss": 3.5687, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353710749015798e-05, + "loss": 3.5702, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352872154264746e-05, + "loss": 3.5799, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352035197394067e-05, + "loss": 3.5683, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511966026430146e-05, + "loss": 3.5556, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503580078919626e-05, + "loss": 3.5691, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495194131409106e-05, + "loss": 3.5752, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486824562702315e-05, + "loss": 3.5765, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.34784386151918e-05, + "loss": 3.5726, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347005266768128e-05, + "loss": 3.5704, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346166672017076e-05, + "loss": 3.57, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345329715146397e-05, + "loss": 3.5788, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344491120395345e-05, + "loss": 3.5561, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343652525644293e-05, + "loss": 3.5656, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342813930893241e-05, + "loss": 3.5599, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341976974022562e-05, + "loss": 3.5609, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.34113837927151e-05, + "loss": 3.5741, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340299784520458e-05, + "loss": 3.5763, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339461189769406e-05, + "loss": 3.5709, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338624232898727e-05, + "loss": 3.5704, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377856381476755e-05, + "loss": 3.5676, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369470433966235e-05, + "loss": 3.5719, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3361084486455715e-05, + "loss": 3.5741, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352714917748924e-05, + "loss": 3.5472, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344328970238404e-05, + "loss": 3.5762, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335943022727884e-05, + "loss": 3.5711, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3327557075217364e-05, + "loss": 3.5711, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331918750651057e-05, + "loss": 3.5633, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331080155900005e-05, + "loss": 3.5612, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330241561148953e-05, + "loss": 3.5563, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329402966397901e-05, + "loss": 3.5607, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328566009527222e-05, + "loss": 3.5709, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327727414776171e-05, + "loss": 3.5558, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326888820025119e-05, + "loss": 3.5816, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326050225274067e-05, + "loss": 3.5663, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325213268403388e-05, + "loss": 3.5498, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324374673652336e-05, + "loss": 3.5718, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323536078901284e-05, + "loss": 3.5533, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322697484150232e-05, + "loss": 3.5575, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321860527279553e-05, + "loss": 3.5628, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321021932528501e-05, + "loss": 3.5696, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320183337777449e-05, + "loss": 3.5517, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319344743026397e-05, + "loss": 3.5651, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3185077861557176e-05, + "loss": 3.5513, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176691914046656e-05, + "loss": 3.5628, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316830596653614e-05, + "loss": 3.5725, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315992001902562e-05, + "loss": 3.5622, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315155045031883e-05, + "loss": 3.5741, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314316450280831e-05, + "loss": 3.5652, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313477855529779e-05, + "loss": 3.5805, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312639260778727e-05, + "loss": 3.5613, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311802303908048e-05, + "loss": 3.5717, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310963709156996e-05, + "loss": 3.5592, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310125114405944e-05, + "loss": 3.5542, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309286519654892e-05, + "loss": 3.5672, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308449562784213e-05, + "loss": 3.5649, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307610968033161e-05, + "loss": 3.5736, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067723732821096e-05, + "loss": 3.5763, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059337785310576e-05, + "loss": 3.5546, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050951837800056e-05, + "loss": 3.5513, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042582269093265e-05, + "loss": 3.5612, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034196321582745e-05, + "loss": 3.5656, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025810374072225e-05, + "loss": 3.5635, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017424426561705e-05, + "loss": 3.5652, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3009054857854914e-05, + "loss": 3.5713, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000668910344394e-05, + "loss": 3.5594, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992282962833874e-05, + "loss": 3.5601, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2983897015323354e-05, + "loss": 3.554, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975511067812834e-05, + "loss": 3.5717, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296714149910605e-05, + "loss": 3.5683, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295875555159553e-05, + "loss": 3.5705, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295036960408501e-05, + "loss": 3.5608, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294198365657449e-05, + "loss": 3.555, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.29336140878677e-05, + "loss": 3.5718, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292522814035718e-05, + "loss": 3.5673, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291684219284666e-05, + "loss": 3.562, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290845624533614e-05, + "loss": 3.5621, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290008667662935e-05, + "loss": 3.5569, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289170072911883e-05, + "loss": 3.5653, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288331478160831e-05, + "loss": 3.5599, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287492883409779e-05, + "loss": 3.5547, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866559265391004e-05, + "loss": 3.5588, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2858173317880484e-05, + "loss": 3.5618, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2849787370369964e-05, + "loss": 3.5684, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841401422859443e-05, + "loss": 3.5496, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283303185415265e-05, + "loss": 3.561, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282464590664213e-05, + "loss": 3.5569, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281625995913161e-05, + "loss": 3.575, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280787401162109e-05, + "loss": 3.5578, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.27995044429143e-05, + "loss": 3.5579, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279111849540378e-05, + "loss": 3.5669, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278273254789326e-05, + "loss": 3.5722, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277434660038274e-05, + "loss": 3.5578, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276597703167596e-05, + "loss": 3.5606, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275759108416544e-05, + "loss": 3.5621, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274920513665492e-05, + "loss": 3.5631, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.27408191891444e-05, + "loss": 3.5551, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732449620437606e-05, + "loss": 3.5597, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724063672927086e-05, + "loss": 3.5567, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715677725416566e-05, + "loss": 3.5656, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707291777906046e-05, + "loss": 3.5604, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269890583039552e-05, + "loss": 3.556, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690536261688735e-05, + "loss": 3.5586, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682150314178215e-05, + "loss": 3.5546, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673764366667695e-05, + "loss": 3.5686, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266539479796091e-05, + "loss": 3.5629, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265700885045039e-05, + "loss": 3.571, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264862290293987e-05, + "loss": 3.5497, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640236955429344e-05, + "loss": 3.5645, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263186738672256e-05, + "loss": 3.5651, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262348143921204e-05, + "loss": 3.5605, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261509549170152e-05, + "loss": 3.5596, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260670954419099e-05, + "loss": 3.5526, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259833997548421e-05, + "loss": 3.5767, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258995402797369e-05, + "loss": 3.5692, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258156808046317e-05, + "loss": 3.5683, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257318213295265e-05, + "loss": 3.5604, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2564812564245865e-05, + "loss": 3.5729, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.2556426616735345e-05, + "loss": 3.5596, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254804066922482e-05, + "loss": 3.5515, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.25396547217143e-05, + "loss": 3.5766, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253126877420378e-05, + "loss": 3.5598, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522899205496994e-05, + "loss": 3.5751, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251451325798647e-05, + "loss": 3.553, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.842904806137085, + "eval_runtime": 332.1175, + "eval_samples_per_second": 1148.964, + "eval_steps_per_second": 35.906, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250612731047595e-05, + "loss": 3.5568, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249774136296543e-05, + "loss": 3.5395, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489355415454907e-05, + "loss": 3.5559, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480969467944387e-05, + "loss": 3.5673, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.24725998992376e-05, + "loss": 3.5669, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246421395172708e-05, + "loss": 3.5596, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245582800421656e-05, + "loss": 3.5569, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244744205670604e-05, + "loss": 3.5539, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243907248799925e-05, + "loss": 3.5512, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243068654048873e-05, + "loss": 3.5564, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242230059297821e-05, + "loss": 3.5602, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241391464546769e-05, + "loss": 3.5657, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.24055450767609e-05, + "loss": 3.5696, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239715912925038e-05, + "loss": 3.5463, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238877318173986e-05, + "loss": 3.5534, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238038723422934e-05, + "loss": 3.5371, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237201766552255e-05, + "loss": 3.5547, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363631718012036e-05, + "loss": 3.5523, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355245770501516e-05, + "loss": 3.5554, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346859822990996e-05, + "loss": 3.5481, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338473875480476e-05, + "loss": 3.5729, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330104306773685e-05, + "loss": 3.5588, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321718359263165e-05, + "loss": 3.5638, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313332411752645e-05, + "loss": 3.5549, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304946464242125e-05, + "loss": 3.5666, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2296576895535334e-05, + "loss": 3.5485, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2288190948024814e-05, + "loss": 3.5529, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279805000514294e-05, + "loss": 3.5655, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271419053003774e-05, + "loss": 3.5502, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226304948429699e-05, + "loss": 3.542, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225466353678647e-05, + "loss": 3.5523, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224627758927595e-05, + "loss": 3.5572, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223789164176543e-05, + "loss": 3.5621, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222952207305864e-05, + "loss": 3.5567, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222113612554812e-05, + "loss": 3.5514, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.22127501780376e-05, + "loss": 3.5567, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220436423052708e-05, + "loss": 3.5633, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219599466182029e-05, + "loss": 3.5396, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218760871430977e-05, + "loss": 3.5507, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217922276679925e-05, + "loss": 3.5432, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217083681928873e-05, + "loss": 3.5439, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216246725058194e-05, + "loss": 3.5583, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215408130307142e-05, + "loss": 3.5627, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.21456953555609e-05, + "loss": 3.5528, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213730940805038e-05, + "loss": 3.5567, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212892346053986e-05, + "loss": 3.5561, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212055389183307e-05, + "loss": 3.5515, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211216794432255e-05, + "loss": 3.5586, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210378199681203e-05, + "loss": 3.5328, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209539604930151e-05, + "loss": 3.558, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208702648059472e-05, + "loss": 3.5566, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.20786405330842e-05, + "loss": 3.5588, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207025458557368e-05, + "loss": 3.549, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206186863806316e-05, + "loss": 3.5432, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205349906935638e-05, + "loss": 3.5395, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204511312184586e-05, + "loss": 3.5416, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203672717433534e-05, + "loss": 3.5535, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028357605628546e-05, + "loss": 3.5401, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019971658118026e-05, + "loss": 3.5656, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011585710607506e-05, + "loss": 3.5502, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2003199763096986e-05, + "loss": 3.5405, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994830194390195e-05, + "loss": 3.5527, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986444246879675e-05, + "loss": 3.5351, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1978058299369155e-05, + "loss": 3.5419, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969672351858635e-05, + "loss": 3.5475, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196130278315185e-05, + "loss": 3.5562, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195291683564133e-05, + "loss": 3.5368, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194453088813081e-05, + "loss": 3.5471, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193614494062029e-05, + "loss": 3.5351, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.19277753719135e-05, + "loss": 3.5474, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191938942440298e-05, + "loss": 3.5533, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191100347689246e-05, + "loss": 3.5518, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190261752938194e-05, + "loss": 3.5533, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189424796067515e-05, + "loss": 3.5512, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188586201316463e-05, + "loss": 3.5638, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187747606565411e-05, + "loss": 3.5457, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186909011814359e-05, + "loss": 3.5533, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860720549436804e-05, + "loss": 3.545, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852334601926284e-05, + "loss": 3.5436, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843948654415764e-05, + "loss": 3.5504, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835562706905244e-05, + "loss": 3.5494, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182719313819845e-05, + "loss": 3.5588, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181880719068793e-05, + "loss": 3.5586, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181042124317741e-05, + "loss": 3.5467, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180203529566689e-05, + "loss": 3.5326, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.17936657269601e-05, + "loss": 3.5448, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178527977944958e-05, + "loss": 3.5473, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177689383193906e-05, + "loss": 3.5493, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176850788442854e-05, + "loss": 3.5516, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176013831572176e-05, + "loss": 3.5513, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175175236821124e-05, + "loss": 3.547, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174336642070072e-05, + "loss": 3.5417, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173498047319019e-05, + "loss": 3.544, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172661090448341e-05, + "loss": 3.5489, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171822495697289e-05, + "loss": 3.5551, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170983900946237e-05, + "loss": 3.553, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170145306195184e-05, + "loss": 3.5449, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1693083493245056e-05, + "loss": 3.5388, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684697545734536e-05, + "loss": 3.5537, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676311598224016e-05, + "loss": 3.552, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667925650713496e-05, + "loss": 3.5449, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165955608200671e-05, + "loss": 3.5484, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165117013449619e-05, + "loss": 3.5372, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642784186985665e-05, + "loss": 3.5501, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634398239475145e-05, + "loss": 3.547, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162602867076836e-05, + "loss": 3.5402, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161764272325784e-05, + "loss": 3.5454, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1609256775747314e-05, + "loss": 3.5434, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600870828236794e-05, + "loss": 3.5543, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159250125953001e-05, + "loss": 3.5335, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158411531201949e-05, + "loss": 3.5482, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157572936450896e-05, + "loss": 3.537, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156734341699845e-05, + "loss": 3.5593, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155897384829166e-05, + "loss": 3.5416, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155058790078114e-05, + "loss": 3.5439, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154220195327062e-05, + "loss": 3.5528, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.15338160057601e-05, + "loss": 3.559, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525446437053314e-05, + "loss": 3.542, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151706048954279e-05, + "loss": 3.5411, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150867454203227e-05, + "loss": 3.5517, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150028859452175e-05, + "loss": 3.5491, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149191902581496e-05, + "loss": 3.5364, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483533078304436e-05, + "loss": 3.5432, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1475147130793916e-05, + "loss": 3.543, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466761183283396e-05, + "loss": 3.5503, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145839161457661e-05, + "loss": 3.5454, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145000566706609e-05, + "loss": 3.537, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144161971955557e-05, + "loss": 3.5458, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143323377204505e-05, + "loss": 3.539, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142486420333826e-05, + "loss": 3.5496, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141647825582774e-05, + "loss": 3.5512, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140809230831722e-05, + "loss": 3.549, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.13997063608067e-05, + "loss": 3.5396, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139133679209991e-05, + "loss": 3.5427, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138295084458939e-05, + "loss": 3.5516, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137456489707887e-05, + "loss": 3.5462, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136617894956835e-05, + "loss": 3.5462, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357809380861566e-05, + "loss": 3.5362, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349423433351046e-05, + "loss": 3.5654, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341037485840526e-05, + "loss": 3.5495, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332651538330006e-05, + "loss": 3.5562, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324281969623215e-05, + "loss": 3.5447, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315896022112695e-05, + "loss": 3.5535, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307510074602175e-05, + "loss": 3.5424, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299124127091655e-05, + "loss": 3.5342, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290754558384864e-05, + "loss": 3.5613, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282368610874344e-05, + "loss": 3.5452, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273982663363824e-05, + "loss": 3.558, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265596715853304e-05, + "loss": 3.5374, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8429811000823975, + "eval_runtime": 308.1411, + "eval_samples_per_second": 1238.364, + "eval_steps_per_second": 38.7, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125722714714652e-05, + "loss": 3.5409, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248841199636e-05, + "loss": 3.5288, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124045525212548e-05, + "loss": 3.5384, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123206930461496e-05, + "loss": 3.5521, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122369973590817e-05, + "loss": 3.5505, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121531378839765e-05, + "loss": 3.5473, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120692784088713e-05, + "loss": 3.5396, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119854189337661e-05, + "loss": 3.5387, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119017232466982e-05, + "loss": 3.5375, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11817863771593e-05, + "loss": 3.5421, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117340042964878e-05, + "loss": 3.5431, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116501448213826e-05, + "loss": 3.5487, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115666129223521e-05, + "loss": 3.5555, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114827534472468e-05, + "loss": 3.532, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113988939721416e-05, + "loss": 3.538, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113150344970364e-05, + "loss": 3.5228, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112311750219312e-05, + "loss": 3.5398, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11147315546826e-05, + "loss": 3.5356, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110634560717208e-05, + "loss": 3.5392, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109795965966156e-05, + "loss": 3.5357, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108959009095477e-05, + "loss": 3.5554, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108120414344425e-05, + "loss": 3.5468, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107281819593373e-05, + "loss": 3.5454, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106443224842321e-05, + "loss": 3.543, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105606267971643e-05, + "loss": 3.5533, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104767673220591e-05, + "loss": 3.533, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103929078469539e-05, + "loss": 3.536, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103090483718487e-05, + "loss": 3.5514, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022535268478076e-05, + "loss": 3.5316, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1014149320967556e-05, + "loss": 3.5254, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005763373457036e-05, + "loss": 3.5356, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997377425946516e-05, + "loss": 3.5425, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0989007857239725e-05, + "loss": 3.5459, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980621909729205e-05, + "loss": 3.542, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972235962218685e-05, + "loss": 3.5402, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963850014708165e-05, + "loss": 3.5414, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095548044600138e-05, + "loss": 3.5451, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094709449849086e-05, + "loss": 3.5272, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093870855098034e-05, + "loss": 3.5411, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093032260346982e-05, + "loss": 3.5247, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092195303476303e-05, + "loss": 3.5334, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091356708725251e-05, + "loss": 3.5369, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090518113974199e-05, + "loss": 3.549, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089679519223147e-05, + "loss": 3.5407, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088842562352468e-05, + "loss": 3.5378, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088003967601416e-05, + "loss": 3.5403, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087165372850364e-05, + "loss": 3.5359, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086326778099312e-05, + "loss": 3.5447, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854898212286334e-05, + "loss": 3.5162, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846512264775814e-05, + "loss": 3.5426, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0838126317265294e-05, + "loss": 3.5418, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829740369754774e-05, + "loss": 3.5436, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082137080104798e-05, + "loss": 3.5339, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081298485353746e-05, + "loss": 3.529, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080459890602694e-05, + "loss": 3.5188, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079621295851642e-05, + "loss": 3.524, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078784338980963e-05, + "loss": 3.5445, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077945744229911e-05, + "loss": 3.526, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077107149478859e-05, + "loss": 3.5454, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076268554727807e-05, + "loss": 3.5385, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075431597857129e-05, + "loss": 3.5258, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074593003106077e-05, + "loss": 3.538, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073754408355025e-05, + "loss": 3.5202, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072915813603973e-05, + "loss": 3.5277, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072078856733294e-05, + "loss": 3.5298, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071240261982242e-05, + "loss": 3.5451, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.07040166723119e-05, + "loss": 3.52, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069563072480138e-05, + "loss": 3.5281, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0687261156094586e-05, + "loss": 3.5199, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678875208584066e-05, + "loss": 3.5316, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670489261073546e-05, + "loss": 3.5391, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0662103313563026e-05, + "loss": 3.5399, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653717366052506e-05, + "loss": 3.5344, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064534779734572e-05, + "loss": 3.5391, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06369618498352e-05, + "loss": 3.5471, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062857590232468e-05, + "loss": 3.5322, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062018995481416e-05, + "loss": 3.5343, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061182038610737e-05, + "loss": 3.532, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060343443859685e-05, + "loss": 3.5277, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059504849108633e-05, + "loss": 3.5377, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058667892237954e-05, + "loss": 3.533, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057829297486902e-05, + "loss": 3.5444, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.05699070273585e-05, + "loss": 3.5413, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056152107984798e-05, + "loss": 3.5324, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553151511141195e-05, + "loss": 3.516, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544765563630675e-05, + "loss": 3.529, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536379616120155e-05, + "loss": 3.5329, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527993668609635e-05, + "loss": 3.5349, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0519624099902844e-05, + "loss": 3.5356, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511238152392324e-05, + "loss": 3.5405, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502852204881804e-05, + "loss": 3.5328, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494466257371284e-05, + "loss": 3.5247, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486096688664497e-05, + "loss": 3.5276, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477710741153977e-05, + "loss": 3.5372, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469324793643456e-05, + "loss": 3.5386, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460938846132936e-05, + "loss": 3.5392, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452569277426146e-05, + "loss": 3.5269, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444183329915625e-05, + "loss": 3.5277, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435797382405105e-05, + "loss": 3.5381, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427411434894582e-05, + "loss": 3.5389, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419041866187798e-05, + "loss": 3.5329, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410655918677278e-05, + "loss": 3.5265, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402269971166758e-05, + "loss": 3.5251, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393884023656234e-05, + "loss": 3.5387, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038551445494945e-05, + "loss": 3.5331, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037712850743893e-05, + "loss": 3.524, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368742559928403e-05, + "loss": 3.5279, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360356612417883e-05, + "loss": 3.5319, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.03519870437111e-05, + "loss": 3.5346, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034360109620058e-05, + "loss": 3.5237, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335215148690056e-05, + "loss": 3.5373, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326829201179536e-05, + "loss": 3.5181, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031845963247275e-05, + "loss": 3.5478, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.031007368496223e-05, + "loss": 3.5241, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301687737451705e-05, + "loss": 3.5324, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293301789941188e-05, + "loss": 3.5376, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284932221234404e-05, + "loss": 3.5433, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276546273723877e-05, + "loss": 3.5268, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268160326213357e-05, + "loss": 3.527, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259774378702837e-05, + "loss": 3.5345, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251388431192317e-05, + "loss": 3.5329, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024301886248553e-05, + "loss": 3.5239, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023463291497501e-05, + "loss": 3.5286, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022624696746449e-05, + "loss": 3.5277, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021786101995397e-05, + "loss": 3.5393, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020949145124718e-05, + "loss": 3.527, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020110550373666e-05, + "loss": 3.5241, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192719556226142e-05, + "loss": 3.5309, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018433360871562e-05, + "loss": 3.5268, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017596404000883e-05, + "loss": 3.526, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016757809249831e-05, + "loss": 3.5404, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015919214498779e-05, + "loss": 3.5398, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015080619747727e-05, + "loss": 3.5211, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142436628770483e-05, + "loss": 3.5272, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134050681259963e-05, + "loss": 3.5382, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125664733749443e-05, + "loss": 3.5324, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117278786238923e-05, + "loss": 3.5322, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108909217532132e-05, + "loss": 3.5256, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100523270021612e-05, + "loss": 3.5459, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092137322511092e-05, + "loss": 3.5345, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083751375000575e-05, + "loss": 3.5421, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075381806293784e-05, + "loss": 3.5302, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066995858783264e-05, + "loss": 3.5413, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058609911272744e-05, + "loss": 3.5273, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050223963762224e-05, + "loss": 3.521, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041854395055437e-05, + "loss": 3.5464, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033468447544917e-05, + "loss": 3.5333, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025082500034397e-05, + "loss": 3.5434, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016696552523877e-05, + "loss": 3.5268, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008326983817086e-05, + "loss": 3.527, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8430335521698, + "eval_runtime": 309.7749, + "eval_samples_per_second": 1231.833, + "eval_steps_per_second": 38.496, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999941036306566e-05, + "loss": 3.5136, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991555088796046e-05, + "loss": 3.5222, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998316914128553e-05, + "loss": 3.539, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974799572578738e-05, + "loss": 3.5347, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966413625068218e-05, + "loss": 3.5353, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958027677557698e-05, + "loss": 3.5255, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949641730047178e-05, + "loss": 3.5225, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994127216134039e-05, + "loss": 3.5187, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993288621382987e-05, + "loss": 3.5313, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992450026631935e-05, + "loss": 3.5235, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991611431880883e-05, + "loss": 3.539, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990774475010204e-05, + "loss": 3.5404, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989935880259152e-05, + "loss": 3.5193, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890972855081e-05, + "loss": 3.5208, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882603286374212e-05, + "loss": 3.5118, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874217338863692e-05, + "loss": 3.5188, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865831391353172e-05, + "loss": 3.5258, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985744544384265e-05, + "loss": 3.5229, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984905949633213e-05, + "loss": 3.5215, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984067354882161e-05, + "loss": 3.5403, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983228760131109e-05, + "loss": 3.5318, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823901653800575e-05, + "loss": 3.5305, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815532085093784e-05, + "loss": 3.5295, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807146137583264e-05, + "loss": 3.5418, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798760190072744e-05, + "loss": 3.5141, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790374242562224e-05, + "loss": 3.524, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782004673855436e-05, + "loss": 3.5365, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773618726344916e-05, + "loss": 3.5151, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765232778834396e-05, + "loss": 3.5165, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756846831323876e-05, + "loss": 3.5185, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748477262617085e-05, + "loss": 3.5279, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740091315106565e-05, + "loss": 3.5308, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731705367596045e-05, + "loss": 3.5252, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.972331942008553e-05, + "loss": 3.5242, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714949851378738e-05, + "loss": 3.5267, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706563903868218e-05, + "loss": 3.5292, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698177956357698e-05, + "loss": 3.517, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689792008847177e-05, + "loss": 3.5257, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968142244014039e-05, + "loss": 3.5064, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967303649262987e-05, + "loss": 3.5222, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966465054511935e-05, + "loss": 3.5219, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965626459760883e-05, + "loss": 3.5349, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964789502890204e-05, + "loss": 3.5267, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963950908139152e-05, + "loss": 3.5247, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631123133881e-05, + "loss": 3.5276, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622737186370482e-05, + "loss": 3.5228, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961436761766369e-05, + "loss": 3.53, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960598167015317e-05, + "loss": 3.5006, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959759572264265e-05, + "loss": 3.5255, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958920977513213e-05, + "loss": 3.5304, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580840206425344e-05, + "loss": 3.5291, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572454258914824e-05, + "loss": 3.518, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564068311404304e-05, + "loss": 3.5148, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555682363893784e-05, + "loss": 3.5084, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547312795186993e-05, + "loss": 3.5096, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538926847676473e-05, + "loss": 3.5304, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530540900165953e-05, + "loss": 3.5111, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952215495265543e-05, + "loss": 3.5286, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513785383948645e-05, + "loss": 3.5261, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505399436438125e-05, + "loss": 3.5102, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497013488927605e-05, + "loss": 3.5237, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948862754141708e-05, + "loss": 3.5085, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480257972710297e-05, + "loss": 3.5137, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471872025199777e-05, + "loss": 3.5146, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463486077689257e-05, + "loss": 3.5314, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945510013017873e-05, + "loss": 3.5082, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446730561471946e-05, + "loss": 3.5127, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438344613961426e-05, + "loss": 3.5057, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429958666450903e-05, + "loss": 3.5185, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421572718940383e-05, + "loss": 3.5205, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.94132031502336e-05, + "loss": 3.5264, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940481720272308e-05, + "loss": 3.5192, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396431255212552e-05, + "loss": 3.5287, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388045307702035e-05, + "loss": 3.5325, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379675738995248e-05, + "loss": 3.5192, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937128979148473e-05, + "loss": 3.5186, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362903843974204e-05, + "loss": 3.5155, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354517896463684e-05, + "loss": 3.5175, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.93461483277569e-05, + "loss": 3.5238, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337762380246377e-05, + "loss": 3.512, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329376432735856e-05, + "loss": 3.5327, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320990485225336e-05, + "loss": 3.5306, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312620916518552e-05, + "loss": 3.5157, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304234969008025e-05, + "loss": 3.5024, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295849021497505e-05, + "loss": 3.5142, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287463073986985e-05, + "loss": 3.5203, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.92790935052802e-05, + "loss": 3.5245, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270707557769678e-05, + "loss": 3.5182, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262321610259158e-05, + "loss": 3.5265, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253935662748638e-05, + "loss": 3.5208, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924556609404185e-05, + "loss": 3.5082, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923718014653133e-05, + "loss": 3.5124, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922879419902081e-05, + "loss": 3.5234, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922040825151029e-05, + "loss": 3.5208, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.92120386828035e-05, + "loss": 3.529, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920365273529298e-05, + "loss": 3.5126, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919526678778246e-05, + "loss": 3.5134, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918688084027194e-05, + "loss": 3.5258, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917851127156515e-05, + "loss": 3.5262, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.917012532405463e-05, + "loss": 3.5159, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916173937654411e-05, + "loss": 3.5171, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915335342903359e-05, + "loss": 3.5112, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.91449838603268e-05, + "loss": 3.519, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136597912816284e-05, + "loss": 3.5238, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128211965305764e-05, + "loss": 3.5062, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119826017795244e-05, + "loss": 3.5156, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111456449088453e-05, + "loss": 3.5202, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103070501577933e-05, + "loss": 3.5204, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094684554067413e-05, + "loss": 3.5058, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086314985360625e-05, + "loss": 3.5239, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077929037850105e-05, + "loss": 3.5056, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069543090339585e-05, + "loss": 3.5342, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061157142829065e-05, + "loss": 3.5074, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052771195318545e-05, + "loss": 3.5183, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044401626611754e-05, + "loss": 3.5228, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9036015679101238e-05, + "loss": 3.5321, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027629731590717e-05, + "loss": 3.5149, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9019243784080197e-05, + "loss": 3.5172, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010874215373407e-05, + "loss": 3.519, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002488267862886e-05, + "loss": 3.5167, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994102320352366e-05, + "loss": 3.5123, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898573275164558e-05, + "loss": 3.5147, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897734680413506e-05, + "loss": 3.5106, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896896085662454e-05, + "loss": 3.5303, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896057490911402e-05, + "loss": 3.5077, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952205340407228e-05, + "loss": 3.5122, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943819392896708e-05, + "loss": 3.5145, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893543344538619e-05, + "loss": 3.5146, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892704749787567e-05, + "loss": 3.5111, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891867792916888e-05, + "loss": 3.5272, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891029198165836e-05, + "loss": 3.5247, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890190603414784e-05, + "loss": 3.516, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889352008663732e-05, + "loss": 3.5094, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885150517930533e-05, + "loss": 3.5194, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876764570420013e-05, + "loss": 3.5209, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868378622909493e-05, + "loss": 3.5221, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859992675398972e-05, + "loss": 3.5097, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885162310669218e-05, + "loss": 3.531, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884323715918166e-05, + "loss": 3.5199, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834851211671145e-05, + "loss": 3.5302, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826465264160625e-05, + "loss": 3.5138, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818095695453834e-05, + "loss": 3.5304, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809709747943314e-05, + "loss": 3.5169, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801323800432794e-05, + "loss": 3.5016, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792937852922274e-05, + "loss": 3.5369, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784568284215486e-05, + "loss": 3.5186, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776182336704966e-05, + "loss": 3.5257, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767796389194446e-05, + "loss": 3.516, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759410441683926e-05, + "loss": 3.5111, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8449554443359375, + "eval_runtime": 303.4951, + "eval_samples_per_second": 1257.322, + "eval_steps_per_second": 39.292, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751040872977135e-05, + "loss": 3.5014, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742654925466615e-05, + "loss": 3.5079, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.87342689779561e-05, + "loss": 3.5253, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872588303044558e-05, + "loss": 3.5154, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717513461738788e-05, + "loss": 3.523, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709127514228268e-05, + "loss": 3.5131, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700741566717747e-05, + "loss": 3.5082, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692355619207227e-05, + "loss": 3.5063, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868398605050044e-05, + "loss": 3.5163, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867560010298992e-05, + "loss": 3.5122, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.86672141554794e-05, + "loss": 3.5241, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865882820796888e-05, + "loss": 3.5252, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865045863926209e-05, + "loss": 3.511, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864207269175157e-05, + "loss": 3.5048, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863370312304478e-05, + "loss": 3.501, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862531717553426e-05, + "loss": 3.5022, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861693122802374e-05, + "loss": 3.5127, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860854528051322e-05, + "loss": 3.5108, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.86001593330027e-05, + "loss": 3.5032, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859177338549218e-05, + "loss": 3.5292, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858338743798166e-05, + "loss": 3.5167, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575001490471144e-05, + "loss": 3.5145, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566631921764354e-05, + "loss": 3.5153, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558245974253833e-05, + "loss": 3.5294, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549860026743313e-05, + "loss": 3.5013, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541474079232793e-05, + "loss": 3.5103, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533104510526006e-05, + "loss": 3.5192, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524718563015486e-05, + "loss": 3.5089, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516332615504966e-05, + "loss": 3.5002, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507946667994446e-05, + "loss": 3.503, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499577099287655e-05, + "loss": 3.5188, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491191151777135e-05, + "loss": 3.514, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482805204266615e-05, + "loss": 3.5132, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474419256756095e-05, + "loss": 3.5135, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466049688049307e-05, + "loss": 3.5129, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457663740538787e-05, + "loss": 3.5149, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449277793028267e-05, + "loss": 3.5059, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440891845517747e-05, + "loss": 3.5092, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432522276810956e-05, + "loss": 3.4949, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842413632930044e-05, + "loss": 3.5064, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841575038178992e-05, + "loss": 3.5073, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.84073644342794e-05, + "loss": 3.5222, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839899486557261e-05, + "loss": 3.509, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839060891806209e-05, + "loss": 3.5143, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838222297055157e-05, + "loss": 3.5117, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837383702304105e-05, + "loss": 3.5114, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836546745433426e-05, + "loss": 3.5182, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835708150682374e-05, + "loss": 3.4908, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834869555931322e-05, + "loss": 3.5073, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340309611802694e-05, + "loss": 3.5198, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833194004309591e-05, + "loss": 3.5149, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323554095585393e-05, + "loss": 3.5043, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315168148074873e-05, + "loss": 3.4976, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306782200564346e-05, + "loss": 3.5001, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298412631857562e-05, + "loss": 3.4906, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8290026684347042e-05, + "loss": 3.5188, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281640736836522e-05, + "loss": 3.4991, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273254789326e-05, + "loss": 3.5161, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264885220619215e-05, + "loss": 3.5093, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256499273108694e-05, + "loss": 3.4983, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248113325598168e-05, + "loss": 3.5077, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239727378087648e-05, + "loss": 3.4965, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231357809380863e-05, + "loss": 3.5, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222971861870347e-05, + "loss": 3.5012, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821458591435982e-05, + "loss": 3.5194, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.82061999668493e-05, + "loss": 3.4936, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197830398142516e-05, + "loss": 3.4997, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189444450631996e-05, + "loss": 3.4923, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8181058503121472e-05, + "loss": 3.5027, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172672555610952e-05, + "loss": 3.514, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164302986904168e-05, + "loss": 3.5105, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815591703939364e-05, + "loss": 3.5074, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814753109188312e-05, + "loss": 3.5127, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81391451443726e-05, + "loss": 3.5182, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130775575665817e-05, + "loss": 3.5068, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122389628155294e-05, + "loss": 3.5043, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8114003680644774e-05, + "loss": 3.505, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105617733134254e-05, + "loss": 3.505, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809724816442747e-05, + "loss": 3.508, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088862216916946e-05, + "loss": 3.5031, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080476269406426e-05, + "loss": 3.5151, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072090321895906e-05, + "loss": 3.5128, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063720753189115e-05, + "loss": 3.5061, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055334805678595e-05, + "loss": 3.4894, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046948858168075e-05, + "loss": 3.4986, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038562910657555e-05, + "loss": 3.5104, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030193341950767e-05, + "loss": 3.5092, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021807394440247e-05, + "loss": 3.5108, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013421446929727e-05, + "loss": 3.5069, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005035499419207e-05, + "loss": 3.51, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996665930712416e-05, + "loss": 3.4975, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.79882799832019e-05, + "loss": 3.4968, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797989403569138e-05, + "loss": 3.5127, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797150808818086e-05, + "loss": 3.5051, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796313851947407e-05, + "loss": 3.5117, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795475257196355e-05, + "loss": 3.5051, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946383003256765e-05, + "loss": 3.498, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793799705574624e-05, + "loss": 3.5119, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792961110823572e-05, + "loss": 3.5136, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.79212251607252e-05, + "loss": 3.505, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791283921321468e-05, + "loss": 3.5036, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790445326570416e-05, + "loss": 3.4931, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789606731819364e-05, + "loss": 3.5059, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887697749486853e-05, + "loss": 3.5125, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879311801976333e-05, + "loss": 3.4941, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870925854465813e-05, + "loss": 3.5022, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862539906955293e-05, + "loss": 3.5032, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7854170338248502e-05, + "loss": 3.5105, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845784390737982e-05, + "loss": 3.492, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837398443227462e-05, + "loss": 3.5072, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7829012495716946e-05, + "loss": 3.4961, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820626548206426e-05, + "loss": 3.517, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812256979499635e-05, + "loss": 3.4983, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803871031989115e-05, + "loss": 3.5032, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795485084478595e-05, + "loss": 3.5128, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787099136968075e-05, + "loss": 3.5144, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778729568261287e-05, + "loss": 3.5032, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770343620750767e-05, + "loss": 3.5007, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761957673240247e-05, + "loss": 3.5064, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753571725729727e-05, + "loss": 3.5042, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745202157022936e-05, + "loss": 3.4976, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736816209512416e-05, + "loss": 3.5024, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.77284302620019e-05, + "loss": 3.4996, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.772004431449138e-05, + "loss": 3.516, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771167474578459e-05, + "loss": 3.4923, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703288798274068e-05, + "loss": 3.5028, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694902850763548e-05, + "loss": 3.5003, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686516903253028e-05, + "loss": 3.5009, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767814733454624e-05, + "loss": 3.4971, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766976138703572e-05, + "loss": 3.5154, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.76613754395252e-05, + "loss": 3.513, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765298949201468e-05, + "loss": 3.5013, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764461992330789e-05, + "loss": 3.4946, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763623397579737e-05, + "loss": 3.5084, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627848028286853e-05, + "loss": 3.506, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619462080776333e-05, + "loss": 3.5144, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611092512069542e-05, + "loss": 3.4897, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602706564559022e-05, + "loss": 3.5166, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594320617048502e-05, + "loss": 3.5048, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585934669537982e-05, + "loss": 3.5184, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577565100831194e-05, + "loss": 3.5056, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569179153320674e-05, + "loss": 3.5135, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560793205810154e-05, + "loss": 3.5048, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552407258299634e-05, + "loss": 3.4928, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7544037689592843e-05, + "loss": 3.5169, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535651742082323e-05, + "loss": 3.5093, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527265794571803e-05, + "loss": 3.5093, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518879847061287e-05, + "loss": 3.4995, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510510278354496e-05, + "loss": 3.497, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.846972703933716, + "eval_runtime": 303.6736, + "eval_samples_per_second": 1256.583, + "eval_steps_per_second": 39.269, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502124330843976e-05, + "loss": 3.4863, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493738383333456e-05, + "loss": 3.4941, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485352435822936e-05, + "loss": 3.512, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476966488312415e-05, + "loss": 3.5034, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468596919605628e-05, + "loss": 3.5122, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460210972095108e-05, + "loss": 3.4952, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451825024584588e-05, + "loss": 3.4978, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443439077074068e-05, + "loss": 3.4951, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435069508367277e-05, + "loss": 3.5011, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426683560856757e-05, + "loss": 3.5038, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.741829761334624e-05, + "loss": 3.5052, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740991166583572e-05, + "loss": 3.5114, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.740154209712893e-05, + "loss": 3.4982, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739315614961841e-05, + "loss": 3.4911, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738478658091162e-05, + "loss": 3.4946, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.73764006334011e-05, + "loss": 3.4874, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736801468589058e-05, + "loss": 3.4966, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735962873838006e-05, + "loss": 3.4956, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735124279086954e-05, + "loss": 3.4919, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734285684335902e-05, + "loss": 3.5188, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334470895848495e-05, + "loss": 3.5023, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326084948337978e-05, + "loss": 3.5023, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317715379631194e-05, + "loss": 3.5061, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309329432120667e-05, + "loss": 3.5157, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300943484610147e-05, + "loss": 3.4855, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292557537099627e-05, + "loss": 3.4992, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284187968392843e-05, + "loss": 3.5062, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727580202088232e-05, + "loss": 3.4977, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.72674160733718e-05, + "loss": 3.4917, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725903012586128e-05, + "loss": 3.4857, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250660557154495e-05, + "loss": 3.5059, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724227460964397e-05, + "loss": 3.5029, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723388866213345e-05, + "loss": 3.498, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722550271462293e-05, + "loss": 3.5029, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721713314591614e-05, + "loss": 3.4988, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720874719840562e-05, + "loss": 3.4956, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.72003612508951e-05, + "loss": 3.492, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719197530338458e-05, + "loss": 3.5014, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183605734677793e-05, + "loss": 3.4792, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175219787167273e-05, + "loss": 3.4947, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166833839656753e-05, + "loss": 3.4971, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158447892146233e-05, + "loss": 3.5072, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7150078323439442e-05, + "loss": 3.4987, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141692375928922e-05, + "loss": 3.4982, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133306428418402e-05, + "loss": 3.5029, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124920480907885e-05, + "loss": 3.495, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116550912201094e-05, + "loss": 3.5057, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108164964690574e-05, + "loss": 3.4775, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099779017180054e-05, + "loss": 3.4982, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091409448473263e-05, + "loss": 3.5018, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7083023500962747e-05, + "loss": 3.5059, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074637553452227e-05, + "loss": 3.4914, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066251605941707e-05, + "loss": 3.484, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057882037234916e-05, + "loss": 3.492, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049496089724396e-05, + "loss": 3.4762, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7041110142213876e-05, + "loss": 3.5076, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032724194703356e-05, + "loss": 3.489, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024354625996568e-05, + "loss": 3.4969, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015968678486048e-05, + "loss": 3.4985, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007582730975528e-05, + "loss": 3.4873, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999196783465008e-05, + "loss": 3.4947, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990827214758217e-05, + "loss": 3.4843, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.69824412672477e-05, + "loss": 3.4896, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697405531973718e-05, + "loss": 3.4837, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696566937222666e-05, + "loss": 3.505, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695729980351987e-05, + "loss": 3.4842, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694891385600935e-05, + "loss": 3.4877, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694052790849883e-05, + "loss": 3.4802, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693214196098831e-05, + "loss": 3.4897, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923772392281522e-05, + "loss": 3.4982, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915386444771002e-05, + "loss": 3.5016, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6907000497260482e-05, + "loss": 3.4939, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898614549749962e-05, + "loss": 3.5015, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689024498104317e-05, + "loss": 3.5074, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881859033532654e-05, + "loss": 3.4964, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873473086022134e-05, + "loss": 3.4833, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6865087138511614e-05, + "loss": 3.4981, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856717569804823e-05, + "loss": 3.4907, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848331622294303e-05, + "loss": 3.494, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839945674783783e-05, + "loss": 3.4886, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831559727273263e-05, + "loss": 3.5003, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6823190158566475e-05, + "loss": 3.5057, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814804211055955e-05, + "loss": 3.4903, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806418263545435e-05, + "loss": 3.4786, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6798032316034915e-05, + "loss": 3.4836, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789662747328124e-05, + "loss": 3.4959, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781293178621337e-05, + "loss": 3.4993, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772907231110817e-05, + "loss": 3.4941, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764521283600297e-05, + "loss": 3.4993, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756135336089777e-05, + "loss": 3.4962, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747749388579257e-05, + "loss": 3.4867, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739363441068737e-05, + "loss": 3.4866, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730977493558217e-05, + "loss": 3.4922, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722591546047697e-05, + "loss": 3.4971, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671422197734091e-05, + "loss": 3.4983, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670583602983039e-05, + "loss": 3.4965, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669745008231987e-05, + "loss": 3.482, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668906413480935e-05, + "loss": 3.5001, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668069456610256e-05, + "loss": 3.4994, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667230861859204e-05, + "loss": 3.4909, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666392267108152e-05, + "loss": 3.4955, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655536723571e-05, + "loss": 3.4817, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664716715486421e-05, + "loss": 3.4939, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663878120735369e-05, + "loss": 3.5003, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663039525984317e-05, + "loss": 3.4803, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662200931233265e-05, + "loss": 3.4892, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613639743625863e-05, + "loss": 3.4941, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605253796115343e-05, + "loss": 3.4921, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596867848604823e-05, + "loss": 3.4805, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588481901094303e-05, + "loss": 3.4975, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6580112332387512e-05, + "loss": 3.4813, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571726384876995e-05, + "loss": 3.5031, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563340437366475e-05, + "loss": 3.4859, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554954489855955e-05, + "loss": 3.4875, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546584921149164e-05, + "loss": 3.5015, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538198973638644e-05, + "loss": 3.5039, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529813026128124e-05, + "loss": 3.4912, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521443457421336e-05, + "loss": 3.4888, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6513057509910816e-05, + "loss": 3.492, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504671562400296e-05, + "loss": 3.4887, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496285614889776e-05, + "loss": 3.4896, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487916046182985e-05, + "loss": 3.4921, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479530098672465e-05, + "loss": 3.4837, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647114415116195e-05, + "loss": 3.4968, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646275820365143e-05, + "loss": 3.4875, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645437225614091e-05, + "loss": 3.4892, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644598630863039e-05, + "loss": 3.4852, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643760036111987e-05, + "loss": 3.4894, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429214413609342e-05, + "loss": 3.4813, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420844844902558e-05, + "loss": 3.5033, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641245889739204e-05, + "loss": 3.5003, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404072949881514e-05, + "loss": 3.4904, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395687002370994e-05, + "loss": 3.4803, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638731743366421e-05, + "loss": 3.497, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637893148615369e-05, + "loss": 3.4929, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370545538643167e-05, + "loss": 3.497, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362159591132646e-05, + "loss": 3.4844, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353790022425862e-05, + "loss": 3.4982, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345404074915342e-05, + "loss": 3.4958, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6337018127404815e-05, + "loss": 3.5054, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328632179894295e-05, + "loss": 3.4957, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.632026261118751e-05, + "loss": 3.4961, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311876663676988e-05, + "loss": 3.4946, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303507094970204e-05, + "loss": 3.4785, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295121147459684e-05, + "loss": 3.5054, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286735199949164e-05, + "loss": 3.5015, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627834925243864e-05, + "loss": 3.4955, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626996330492812e-05, + "loss": 3.4897, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.62615773574176e-05, + "loss": 3.4839, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.847775459289551, + "eval_runtime": 303.8184, + "eval_samples_per_second": 1255.984, + "eval_steps_per_second": 39.25, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625319140990708e-05, + "loss": 3.4827, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624480546239656e-05, + "loss": 3.4808, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623643589368977e-05, + "loss": 3.4998, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622804994617925e-05, + "loss": 3.4897, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219663998668732e-05, + "loss": 3.5036, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6211278051158212e-05, + "loss": 3.4838, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620290848245142e-05, + "loss": 3.4879, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.61945225349409e-05, + "loss": 3.4779, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618613658743038e-05, + "loss": 3.4899, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617775063991986e-05, + "loss": 3.4871, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169381071213074e-05, + "loss": 3.4956, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160995123702554e-05, + "loss": 3.4968, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152609176192034e-05, + "loss": 3.4843, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144223228681514e-05, + "loss": 3.4801, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613587003877846e-05, + "loss": 3.482, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127484091267935e-05, + "loss": 3.4772, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6119098143757415e-05, + "loss": 3.4825, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110712196246895e-05, + "loss": 3.4829, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102326248736375e-05, + "loss": 3.4776, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093940301225855e-05, + "loss": 3.5082, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085554353715335e-05, + "loss": 3.4897, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077168406204815e-05, + "loss": 3.4912, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068798837498028e-05, + "loss": 3.4943, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060412889987507e-05, + "loss": 3.4982, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6052026942476987e-05, + "loss": 3.477, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043640994966467e-05, + "loss": 3.4862, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035271426259676e-05, + "loss": 3.4933, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026885478749156e-05, + "loss": 3.4886, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601849953123864e-05, + "loss": 3.4733, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.601011358372812e-05, + "loss": 3.4748, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600174401502133e-05, + "loss": 3.4912, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599335806751081e-05, + "loss": 3.4925, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598497212000029e-05, + "loss": 3.4879, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597658617248977e-05, + "loss": 3.4896, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596821660378298e-05, + "loss": 3.4828, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595983065627246e-05, + "loss": 3.4861, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595144470876194e-05, + "loss": 3.4772, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594305876125142e-05, + "loss": 3.492, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593468919254463e-05, + "loss": 3.4702, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592630324503411e-05, + "loss": 3.4817, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917917297523593e-05, + "loss": 3.4781, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909531350013073e-05, + "loss": 3.4977, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5901161781306282e-05, + "loss": 3.4885, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892775833795762e-05, + "loss": 3.4837, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884389886285242e-05, + "loss": 3.4891, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5876003938774722e-05, + "loss": 3.4855, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867634370067935e-05, + "loss": 3.4918, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859248422557415e-05, + "loss": 3.4668, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850862475046895e-05, + "loss": 3.4801, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842476527536375e-05, + "loss": 3.4912, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5834106958829584e-05, + "loss": 3.491, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825721011319064e-05, + "loss": 3.4802, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817335063808544e-05, + "loss": 3.4745, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808965495101756e-05, + "loss": 3.4791, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800579547591236e-05, + "loss": 3.4662, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792193600080716e-05, + "loss": 3.492, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783807652570196e-05, + "loss": 3.4758, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775438083863405e-05, + "loss": 3.4862, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576705213635289e-05, + "loss": 3.4875, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575866618884237e-05, + "loss": 3.4758, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.575028024133185e-05, + "loss": 3.4796, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741910672625058e-05, + "loss": 3.4731, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733524725114537e-05, + "loss": 3.475, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725138777604017e-05, + "loss": 3.4766, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716752830093497e-05, + "loss": 3.4883, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570838326138671e-05, + "loss": 3.475, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569999731387619e-05, + "loss": 3.4753, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569161136636567e-05, + "loss": 3.4685, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568322541885515e-05, + "loss": 3.4774, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567485585014836e-05, + "loss": 3.4807, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666469902637842e-05, + "loss": 3.4924, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658083955127322e-05, + "loss": 3.4789, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649698007616802e-05, + "loss": 3.4894, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564132843891001e-05, + "loss": 3.4927, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563294249139949e-05, + "loss": 3.4916, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.562455654388897e-05, + "loss": 3.467, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561617059637845e-05, + "loss": 3.4869, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607801027671664e-05, + "loss": 3.4819, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599415080161143e-05, + "loss": 3.4751, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5591029132650623e-05, + "loss": 3.486, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582643185140103e-05, + "loss": 3.4849, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574273616433313e-05, + "loss": 3.4941, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565887668922796e-05, + "loss": 3.478, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557501721412276e-05, + "loss": 3.4679, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5549115773901756e-05, + "loss": 3.4741, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540746205194965e-05, + "loss": 3.4791, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532376636488174e-05, + "loss": 3.4859, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523990688977657e-05, + "loss": 3.486, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515604741467137e-05, + "loss": 3.4817, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507218793956617e-05, + "loss": 3.4857, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498832846446097e-05, + "loss": 3.4697, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490446898935577e-05, + "loss": 3.4757, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5482060951425057e-05, + "loss": 3.4785, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473675003914537e-05, + "loss": 3.4847, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546530543520775e-05, + "loss": 3.4813, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545691948769723e-05, + "loss": 3.4916, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544854991899044e-05, + "loss": 3.4651, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.544016397147992e-05, + "loss": 3.4876, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.54317780239694e-05, + "loss": 3.4902, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542339207645888e-05, + "loss": 3.481, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541500612894836e-05, + "loss": 3.4809, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406620181437842e-05, + "loss": 3.4715, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398234233927315e-05, + "loss": 3.4828, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389848286416795e-05, + "loss": 3.4843, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538149509651374e-05, + "loss": 3.4699, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537310914900322e-05, + "loss": 3.4799, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364723201492703e-05, + "loss": 3.477, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356337253982183e-05, + "loss": 3.4832, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347951306471663e-05, + "loss": 3.4654, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339565358961136e-05, + "loss": 3.4903, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331179411450616e-05, + "loss": 3.4646, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322793463940096e-05, + "loss": 3.4906, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314423895233312e-05, + "loss": 3.4787, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530603794772279e-05, + "loss": 3.4716, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529765200021227e-05, + "loss": 3.4898, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528926605270175e-05, + "loss": 3.4922, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280896483994958e-05, + "loss": 3.4776, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527251053648444e-05, + "loss": 3.4783, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526412458897392e-05, + "loss": 3.4818, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.52557386414634e-05, + "loss": 3.4779, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524736907275661e-05, + "loss": 3.4729, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523898312524609e-05, + "loss": 3.4784, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523059717773557e-05, + "loss": 3.4761, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522221123022505e-05, + "loss": 3.483, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213841661518262e-05, + "loss": 3.4779, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205455714007742e-05, + "loss": 3.4812, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5197069766497222e-05, + "loss": 3.4673, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188683818986702e-05, + "loss": 3.4787, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.518031425027991e-05, + "loss": 3.4753, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171928302769395e-05, + "loss": 3.4879, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163542355258875e-05, + "loss": 3.4886, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155156407748355e-05, + "loss": 3.4812, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146786839041564e-05, + "loss": 3.4695, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138400891531044e-05, + "loss": 3.4832, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5130014944020524e-05, + "loss": 3.479, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121628996510004e-05, + "loss": 3.4862, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113259427803216e-05, + "loss": 3.4717, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104873480292696e-05, + "loss": 3.4884, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096487532782176e-05, + "loss": 3.4864, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088101585271656e-05, + "loss": 3.4943, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079732016564865e-05, + "loss": 3.4769, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507134606905435e-05, + "loss": 3.4853, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062960121543828e-05, + "loss": 3.4823, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054590552837037e-05, + "loss": 3.4709, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5046204605326517e-05, + "loss": 3.4862, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037818657815997e-05, + "loss": 3.4926, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029432710305477e-05, + "loss": 3.4827, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5021046762794957e-05, + "loss": 3.4758, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012660815284437e-05, + "loss": 3.4754, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8492884635925293, + "eval_runtime": 303.4579, + "eval_samples_per_second": 1257.476, + "eval_steps_per_second": 39.297, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500427486777392e-05, + "loss": 3.4623, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.49958889202634e-05, + "loss": 3.4695, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498750297275288e-05, + "loss": 3.4831, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979117025242357e-05, + "loss": 3.4807, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497074745653557e-05, + "loss": 3.4887, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496236150902505e-05, + "loss": 3.4738, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495397556151453e-05, + "loss": 3.4757, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494558961400401e-05, + "loss": 3.4609, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937220045297222e-05, + "loss": 3.4806, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928834097786702e-05, + "loss": 3.4772, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492044815027618e-05, + "loss": 3.4782, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4912062202765658e-05, + "loss": 3.4855, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903709012862603e-05, + "loss": 3.4724, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895323065352083e-05, + "loss": 3.4717, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886937117841563e-05, + "loss": 3.4679, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878551170331043e-05, + "loss": 3.4657, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4870165222820523e-05, + "loss": 3.4719, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861779275310003e-05, + "loss": 3.4712, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853393327799483e-05, + "loss": 3.4702, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845007380288963e-05, + "loss": 3.4915, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836637811582175e-05, + "loss": 3.4773, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828251864071652e-05, + "loss": 3.4772, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819865916561132e-05, + "loss": 3.4859, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811496347854344e-05, + "loss": 3.4844, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803110400343828e-05, + "loss": 3.4662, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794724452833304e-05, + "loss": 3.4762, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786338505322784e-05, + "loss": 3.4774, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777968936615997e-05, + "loss": 3.4744, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769582989105473e-05, + "loss": 3.4596, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761197041594957e-05, + "loss": 3.4655, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752811094084437e-05, + "loss": 3.4787, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474444152537765e-05, + "loss": 3.4792, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736055577867126e-05, + "loss": 3.4762, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727669630356606e-05, + "loss": 3.4831, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719283682846086e-05, + "loss": 3.4669, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710914114139298e-05, + "loss": 3.4763, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702528166628778e-05, + "loss": 3.468, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694142219118258e-05, + "loss": 3.4759, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685756271607738e-05, + "loss": 3.457, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677386702900947e-05, + "loss": 3.4691, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669000755390427e-05, + "loss": 3.4669, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466061480787991e-05, + "loss": 3.4878, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465222886036939e-05, + "loss": 3.478, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.46438592916626e-05, + "loss": 3.473, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463547334415208e-05, + "loss": 3.4773, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462708739664156e-05, + "loss": 3.4753, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461870144913104e-05, + "loss": 3.4806, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610331880424252e-05, + "loss": 3.4585, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601945932913732e-05, + "loss": 3.4671, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593559985403212e-05, + "loss": 3.481, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458517403789269e-05, + "loss": 3.4798, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.45768044691859e-05, + "loss": 3.4655, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456841852167538e-05, + "loss": 3.4619, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456003257416486e-05, + "loss": 3.4703, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551646626654344e-05, + "loss": 3.4565, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543277057947553e-05, + "loss": 3.4763, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534891110437033e-05, + "loss": 3.464, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526505162926513e-05, + "loss": 3.4733, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518119215415993e-05, + "loss": 3.4744, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509749646709205e-05, + "loss": 3.47, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501363699198685e-05, + "loss": 3.4633, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492977751688165e-05, + "loss": 3.4637, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484591804177645e-05, + "loss": 3.4611, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476222235470854e-05, + "loss": 3.4667, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467836287960334e-05, + "loss": 3.4742, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459450340449814e-05, + "loss": 3.464, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4451064392939298e-05, + "loss": 3.463, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442694824232507e-05, + "loss": 3.4553, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434308876721987e-05, + "loss": 3.4629, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425922929211467e-05, + "loss": 3.47, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417536981700947e-05, + "loss": 3.4769, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440916741299416e-05, + "loss": 3.4692, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440078146548364e-05, + "loss": 3.4765, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439239551797312e-05, + "loss": 3.4801, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.43840095704626e-05, + "loss": 3.4785, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375640001755808e-05, + "loss": 3.456, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367254054245288e-05, + "loss": 3.4738, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358868106734768e-05, + "loss": 3.4727, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435049853802798e-05, + "loss": 3.4616, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434211259051746e-05, + "loss": 3.472, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433374302181067e-05, + "loss": 3.4742, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432535707430015e-05, + "loss": 3.4845, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431697112678963e-05, + "loss": 3.4646, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308585179279113e-05, + "loss": 3.4505, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300199231768593e-05, + "loss": 3.4657, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291813284258073e-05, + "loss": 3.4689, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283443715551282e-05, + "loss": 3.4718, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4275057768040762e-05, + "loss": 3.4724, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266671820530242e-05, + "loss": 3.474, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.425828587301972e-05, + "loss": 3.472, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.42498999255092e-05, + "loss": 3.4596, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424151397799868e-05, + "loss": 3.4596, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423312803048816e-05, + "loss": 3.4655, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422474208297764e-05, + "loss": 3.4761, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421637251427085e-05, + "loss": 3.471, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207986566760334e-05, + "loss": 3.4797, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199616998053546e-05, + "loss": 3.4578, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191231050543023e-05, + "loss": 3.4736, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182845103032503e-05, + "loss": 3.4739, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174459155521983e-05, + "loss": 3.4721, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166073208011463e-05, + "loss": 3.4671, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157687260500943e-05, + "loss": 3.4625, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149301312990423e-05, + "loss": 3.47, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140915365479906e-05, + "loss": 3.4724, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132562175576844e-05, + "loss": 3.4545, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124176228066324e-05, + "loss": 3.4708, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115790280555804e-05, + "loss": 3.4638, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107404333045284e-05, + "loss": 3.4709, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4099018385534768e-05, + "loss": 3.4534, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090632438024248e-05, + "loss": 3.4768, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082246490513727e-05, + "loss": 3.4634, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073860543003204e-05, + "loss": 3.4747, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065490974296417e-05, + "loss": 3.4685, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057105026785896e-05, + "loss": 3.459, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048719079275376e-05, + "loss": 3.4767, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040333131764856e-05, + "loss": 3.48, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403196356305807e-05, + "loss": 3.4697, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.402357761554755e-05, + "loss": 3.4617, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015191668037025e-05, + "loss": 3.4731, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006805720526505e-05, + "loss": 3.4675, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399843615181972e-05, + "loss": 3.4597, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.399006658311293e-05, + "loss": 3.4696, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398168063560241e-05, + "loss": 3.4636, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397329468809189e-05, + "loss": 3.4702, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396490874058137e-05, + "loss": 3.4671, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395652279307085e-05, + "loss": 3.4686, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394813684556033e-05, + "loss": 3.4562, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393975089804981e-05, + "loss": 3.4664, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393136495053929e-05, + "loss": 3.4655, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.39229953818325e-05, + "loss": 3.4752, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391460943432198e-05, + "loss": 3.468, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.390622348681146e-05, + "loss": 3.4741, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897837539300942e-05, + "loss": 3.4565, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388946797059415e-05, + "loss": 3.4707, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388108202308363e-05, + "loss": 3.4719, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387269607557311e-05, + "loss": 3.473, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386431012806259e-05, + "loss": 3.4573, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855940559355804e-05, + "loss": 3.4743, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847554611845284e-05, + "loss": 3.473, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839168664334764e-05, + "loss": 3.4873, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830782716824244e-05, + "loss": 3.464, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822413148117453e-05, + "loss": 3.4723, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814027200606933e-05, + "loss": 3.472, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805657631900145e-05, + "loss": 3.4604, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797271684389625e-05, + "loss": 3.4757, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788885736879105e-05, + "loss": 3.4808, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780499789368585e-05, + "loss": 3.4741, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772113841858065e-05, + "loss": 3.46, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763727894347545e-05, + "loss": 3.4673, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8499767780303955, + "eval_runtime": 313.8561, + "eval_samples_per_second": 1215.815, + "eval_steps_per_second": 37.995, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755341946837025e-05, + "loss": 3.457, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746955999326505e-05, + "loss": 3.4549, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738586430619717e-05, + "loss": 3.472, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730200483109197e-05, + "loss": 3.4714, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721814535598677e-05, + "loss": 3.475, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713428588088154e-05, + "loss": 3.4651, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3705059019381366e-05, + "loss": 3.4619, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696673071870846e-05, + "loss": 3.4542, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368828712436033e-05, + "loss": 3.4656, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679901176849806e-05, + "loss": 3.4671, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367153160814302e-05, + "loss": 3.4671, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.36631456606325e-05, + "loss": 3.473, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654759713121975e-05, + "loss": 3.462, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364639014441519e-05, + "loss": 3.4606, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363800419690467e-05, + "loss": 3.4587, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362961824939415e-05, + "loss": 3.4533, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3621232301883628e-05, + "loss": 3.4622, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612846354373108e-05, + "loss": 3.4615, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604460406862587e-05, + "loss": 3.4541, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3596074459352067e-05, + "loss": 3.4794, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358768851184155e-05, + "loss": 3.4694, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357931894313476e-05, + "loss": 3.4684, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357093299562424e-05, + "loss": 3.4699, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356254704811372e-05, + "loss": 3.4752, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.35541611006032e-05, + "loss": 3.4534, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545791531896412e-05, + "loss": 3.4648, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537405584385892e-05, + "loss": 3.4729, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3529019636875372e-05, + "loss": 3.4589, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520633689364852e-05, + "loss": 3.4498, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351226412065806e-05, + "loss": 3.4543, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350387817314754e-05, + "loss": 3.4659, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349549222563702e-05, + "loss": 3.4684, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3487106278126504e-05, + "loss": 3.4653, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478736709419714e-05, + "loss": 3.4683, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470350761909194e-05, + "loss": 3.4573, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461964814398673e-05, + "loss": 3.4614, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453578866888153e-05, + "loss": 3.4583, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3445209298181366e-05, + "loss": 3.4641, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436823350670846e-05, + "loss": 3.446, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428437403160326e-05, + "loss": 3.4543, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3420067834453535e-05, + "loss": 3.458, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411681886943015e-05, + "loss": 3.4742, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403295939432495e-05, + "loss": 3.4649, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394909991921975e-05, + "loss": 3.4599, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386540423215187e-05, + "loss": 3.4701, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3378154475704667e-05, + "loss": 3.4599, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369768528194147e-05, + "loss": 3.4674, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361382580683627e-05, + "loss": 3.4508, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3353013011976836e-05, + "loss": 3.4527, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344627064466316e-05, + "loss": 3.4672, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.33362411169558e-05, + "loss": 3.4641, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332785516944528e-05, + "loss": 3.4545, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331948560073849e-05, + "loss": 3.4523, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3311116032031698e-05, + "loss": 3.4609, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330273008452118e-05, + "loss": 3.4433, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329434413701066e-05, + "loss": 3.4646, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328595818950014e-05, + "loss": 3.4541, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327757224198962e-05, + "loss": 3.4553, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.32691862944791e-05, + "loss": 3.4691, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260800346968577e-05, + "loss": 3.4557, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252414399458057e-05, + "loss": 3.4549, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.324404483075127e-05, + "loss": 3.453, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235658883240753e-05, + "loss": 3.4508, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322727293573023e-05, + "loss": 3.4535, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321888698821971e-05, + "loss": 3.4635, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210517419512922e-05, + "loss": 3.4555, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.32021314720024e-05, + "loss": 3.4515, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193745524491882e-05, + "loss": 3.4472, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185359576981362e-05, + "loss": 3.4476, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176990008274575e-05, + "loss": 3.4562, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316860406076405e-05, + "loss": 3.4639, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.316021811325353e-05, + "loss": 3.4603, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315183216574301e-05, + "loss": 3.4644, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143462597036224e-05, + "loss": 3.466, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3135076649525703e-05, + "loss": 3.4705, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126690702015183e-05, + "loss": 3.445, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118321133308396e-05, + "loss": 3.4601, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109935185797872e-05, + "loss": 3.463, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101549238287352e-05, + "loss": 3.4462, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3093163290776836e-05, + "loss": 3.4654, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084793722070048e-05, + "loss": 3.4581, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076407774559525e-05, + "loss": 3.4737, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3068021827049005e-05, + "loss": 3.4576, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059635879538485e-05, + "loss": 3.4401, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051266310831697e-05, + "loss": 3.4526, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042880363321177e-05, + "loss": 3.458, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303451079461439e-05, + "loss": 3.4622, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.302612484710387e-05, + "loss": 3.4591, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017738899593346e-05, + "loss": 3.4644, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009352952082826e-05, + "loss": 3.4609, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000967004572306e-05, + "loss": 3.4514, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299258105706179e-05, + "loss": 3.4475, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298419510955127e-05, + "loss": 3.4538, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297580916204075e-05, + "loss": 3.4651, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296743959333396e-05, + "loss": 3.4613, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295905364582344e-05, + "loss": 3.4666, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295068407711665e-05, + "loss": 3.449, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.294229812960613e-05, + "loss": 3.462, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293391218209561e-05, + "loss": 3.4633, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292552623458509e-05, + "loss": 3.4631, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291714028707457e-05, + "loss": 3.4532, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.290875433956405e-05, + "loss": 3.4545, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900368392053527e-05, + "loss": 3.4575, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891982444543007e-05, + "loss": 3.4619, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883612875836223e-05, + "loss": 3.4416, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875226928325703e-05, + "loss": 3.4616, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286684098081518e-05, + "loss": 3.4484, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285845503330466e-05, + "loss": 3.4617, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2850085464597872e-05, + "loss": 3.4421, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841699517087352e-05, + "loss": 3.4676, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833313569576832e-05, + "loss": 3.4506, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824927622066312e-05, + "loss": 3.4629, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816558053359524e-05, + "loss": 3.4551, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2808172105849e-05, + "loss": 3.4503, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279978615833848e-05, + "loss": 3.4617, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279140021082796e-05, + "loss": 3.4715, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2783030642121177e-05, + "loss": 3.458, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774644694610653e-05, + "loss": 3.4502, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766275125903866e-05, + "loss": 3.4585, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757889178393346e-05, + "loss": 3.4579, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749503230882826e-05, + "loss": 3.4484, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2741117283372306e-05, + "loss": 3.4587, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732731335861786e-05, + "loss": 3.4481, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724345388351266e-05, + "loss": 3.456, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715959440840746e-05, + "loss": 3.4562, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707573493330225e-05, + "loss": 3.4588, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699203924623435e-05, + "loss": 3.4432, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690817977112915e-05, + "loss": 3.4541, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682432029602398e-05, + "loss": 3.4523, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2674046082091878e-05, + "loss": 3.4624, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665676513385087e-05, + "loss": 3.4581, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657290565874567e-05, + "loss": 3.4645, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648904618364047e-05, + "loss": 3.4456, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640518670853527e-05, + "loss": 3.4596, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263214910214674e-05, + "loss": 3.4591, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262376315463622e-05, + "loss": 3.4616, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.26153772071257e-05, + "loss": 3.4494, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.260699125961518e-05, + "loss": 3.462, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598621690908388e-05, + "loss": 3.4625, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590235743397868e-05, + "loss": 3.4719, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581849795887348e-05, + "loss": 3.451, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257346384837683e-05, + "loss": 3.4634, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256509427967004e-05, + "loss": 3.4588, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255672471096325e-05, + "loss": 3.451, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.254833876345273e-05, + "loss": 3.464, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539952815942213e-05, + "loss": 3.4638, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531566868431693e-05, + "loss": 3.4682, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523180920921173e-05, + "loss": 3.4466, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514794973410653e-05, + "loss": 3.4558, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.851921319961548, + "eval_runtime": 313.6105, + "eval_samples_per_second": 1216.767, + "eval_steps_per_second": 38.025, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250640902590013e-05, + "loss": 3.4468, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249802307838961e-05, + "loss": 3.439, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248963713087909e-05, + "loss": 3.4602, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248125118336857e-05, + "loss": 3.4604, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472881614661782e-05, + "loss": 3.4646, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464495667151262e-05, + "loss": 3.4538, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2456109719640742e-05, + "loss": 3.4455, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244772377213022e-05, + "loss": 3.4472, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243935420342343e-05, + "loss": 3.4565, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430968255912914e-05, + "loss": 3.4551, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422582308402394e-05, + "loss": 3.4573, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414196360891874e-05, + "loss": 3.4632, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405826792185083e-05, + "loss": 3.4524, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397457223478296e-05, + "loss": 3.4454, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2389071275967776e-05, + "loss": 3.4502, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380685328457255e-05, + "loss": 3.438, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372299380946735e-05, + "loss": 3.4495, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363913433436215e-05, + "loss": 3.4485, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355527485925695e-05, + "loss": 3.4453, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347141538415175e-05, + "loss": 3.4656, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338755590904655e-05, + "loss": 3.4597, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330386022197868e-05, + "loss": 3.4576, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322000074687348e-05, + "loss": 3.4584, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313614127176828e-05, + "loss": 3.463, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305228179666308e-05, + "loss": 3.4444, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296858610959517e-05, + "loss": 3.457, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288472663448997e-05, + "loss": 3.4537, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280086715938477e-05, + "loss": 3.4487, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271700768427957e-05, + "loss": 3.4435, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226333119972117e-05, + "loss": 3.4402, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225494525221065e-05, + "loss": 3.4585, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224655930470013e-05, + "loss": 3.4543, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238173357189606e-05, + "loss": 3.4549, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222980378848282e-05, + "loss": 3.4586, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.22214178409723e-05, + "loss": 3.4465, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221303189346178e-05, + "loss": 3.4506, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204645945951258e-05, + "loss": 3.4507, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219627637724447e-05, + "loss": 3.4475, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.218789042973395e-05, + "loss": 3.4379, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217950448222343e-05, + "loss": 3.4443, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171134913516643e-05, + "loss": 3.4451, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162748966006123e-05, + "loss": 3.4636, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154363018495603e-05, + "loss": 3.4527, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214597707098508e-05, + "loss": 3.4466, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137607502278292e-05, + "loss": 3.4618, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129221554767772e-05, + "loss": 3.4494, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120835607257255e-05, + "loss": 3.4575, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211244965974673e-05, + "loss": 3.4426, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2104080091039944e-05, + "loss": 3.4365, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095710522333153e-05, + "loss": 3.4578, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087324574822633e-05, + "loss": 3.4557, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078938627312116e-05, + "loss": 3.4478, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070552679801596e-05, + "loss": 3.4379, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062166732291076e-05, + "loss": 3.4491, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053797163584286e-05, + "loss": 3.4291, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045411216073765e-05, + "loss": 3.4517, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2037025268563245e-05, + "loss": 3.4435, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028639321052725e-05, + "loss": 3.4431, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020253373542205e-05, + "loss": 3.4567, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011867426031685e-05, + "loss": 3.444, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003481478521165e-05, + "loss": 3.4431, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995095531010645e-05, + "loss": 3.4455, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986725962303854e-05, + "loss": 3.4369, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978340014793338e-05, + "loss": 3.4438, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969954067282818e-05, + "loss": 3.4507, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961568119772298e-05, + "loss": 3.4467, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953198551065507e-05, + "loss": 3.4408, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944812603554987e-05, + "loss": 3.4364, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936426656044467e-05, + "loss": 3.4364, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928040708533947e-05, + "loss": 3.4438, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191967113982716e-05, + "loss": 3.4521, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191128519231664e-05, + "loss": 3.4494, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190289924480612e-05, + "loss": 3.4545, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894529676099328e-05, + "loss": 3.4537, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886143728588808e-05, + "loss": 3.4613, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187775778107829e-05, + "loss": 3.4378, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186937183356777e-05, + "loss": 3.4503, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186100226486098e-05, + "loss": 3.4499, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185261631735046e-05, + "loss": 3.4321, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184423036983994e-05, + "loss": 3.4555, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183584442232942e-05, + "loss": 3.4512, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827474853622633e-05, + "loss": 3.4563, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819088906112113e-05, + "loss": 3.4468, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810702958601593e-05, + "loss": 3.43, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802317011091073e-05, + "loss": 3.4402, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793931063580553e-05, + "loss": 3.446, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178556149487376e-05, + "loss": 3.4502, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777175547363245e-05, + "loss": 3.4469, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768789599852725e-05, + "loss": 3.4534, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760403652342205e-05, + "loss": 3.4481, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175201770483168e-05, + "loss": 3.443, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174363175732116e-05, + "loss": 3.4362, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173524580981064e-05, + "loss": 3.4404, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172685986230012e-05, + "loss": 3.4568, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718490293593334e-05, + "loss": 3.4518, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1710104346082814e-05, + "loss": 3.4528, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701734777376026e-05, + "loss": 3.4364, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693348829865503e-05, + "loss": 3.4472, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684962882354983e-05, + "loss": 3.4524, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676576934844463e-05, + "loss": 3.45, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668190987333946e-05, + "loss": 3.4445, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659805039823426e-05, + "loss": 3.4434, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651419092312906e-05, + "loss": 3.4448, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643033144802386e-05, + "loss": 3.4508, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634679954899328e-05, + "loss": 3.434, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626294007388808e-05, + "loss": 3.446, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617908059878287e-05, + "loss": 3.4366, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609522112367767e-05, + "loss": 3.4503, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601136164857247e-05, + "loss": 3.4342, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592750217346727e-05, + "loss": 3.4538, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584364269836207e-05, + "loss": 3.4401, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575978322325684e-05, + "loss": 3.4507, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.15676087536189e-05, + "loss": 3.452, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155922280610838e-05, + "loss": 3.4366, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155083685859786e-05, + "loss": 3.4476, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542450911087336e-05, + "loss": 3.4599, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153408134238055e-05, + "loss": 3.4451, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152569539487003e-05, + "loss": 3.4459, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151732582616324e-05, + "loss": 3.44, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150893987865272e-05, + "loss": 3.4497, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.15005539311422e-05, + "loss": 3.444, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149216798363168e-05, + "loss": 3.4429, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483782036121158e-05, + "loss": 3.4374, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475396088610638e-05, + "loss": 3.4447, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1467010141100117e-05, + "loss": 3.4471, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.14586241935896e-05, + "loss": 3.4469, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145025462488281e-05, + "loss": 3.4316, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144186867737229e-05, + "loss": 3.4466, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143348272986177e-05, + "loss": 3.4387, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142509678235125e-05, + "loss": 3.4529, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416727213644462e-05, + "loss": 3.4448, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408341266133942e-05, + "loss": 3.4531, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399955318623422e-05, + "loss": 3.4337, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391569371112902e-05, + "loss": 3.4502, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138319980240611e-05, + "loss": 3.4458, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137481385489559e-05, + "loss": 3.4515, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136642790738507e-05, + "loss": 3.4334, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358041959874554e-05, + "loss": 3.4519, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349672391167764e-05, + "loss": 3.4518, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341286443657244e-05, + "loss": 3.4582, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332900496146723e-05, + "loss": 3.4432, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324514548636203e-05, + "loss": 3.4488, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316144979929416e-05, + "loss": 3.4508, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130777541122263e-05, + "loss": 3.4427, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299389463712105e-05, + "loss": 3.4477, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1291003516201585e-05, + "loss": 3.4524, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282617568691065e-05, + "loss": 3.4542, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274231621180545e-05, + "loss": 3.4381, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265845673670025e-05, + "loss": 3.4446, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8528542518615723, + "eval_runtime": 342.1041, + "eval_samples_per_second": 1115.424, + "eval_steps_per_second": 34.858, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257459726159508e-05, + "loss": 3.4406, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1249073778648988e-05, + "loss": 3.4314, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240704209942197e-05, + "loss": 3.4464, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232318262431677e-05, + "loss": 3.4486, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223932314921157e-05, + "loss": 3.4513, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215546367410634e-05, + "loss": 3.4457, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120717679870385e-05, + "loss": 3.4367, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119879085119333e-05, + "loss": 3.435, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119040490368281e-05, + "loss": 3.445, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1182018956172286e-05, + "loss": 3.4402, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.11736493874655e-05, + "loss": 3.4464, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116526343995498e-05, + "loss": 3.4504, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1156877492444462e-05, + "loss": 3.4425, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114850792373767e-05, + "loss": 3.4359, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.114012197622715e-05, + "loss": 3.4386, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113173602871663e-05, + "loss": 3.4244, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123350081206107e-05, + "loss": 3.4386, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114964133695587e-05, + "loss": 3.4385, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110657818618507e-05, + "loss": 3.4374, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109819223867455e-05, + "loss": 3.4479, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108980629116403e-05, + "loss": 3.452, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108143672245724e-05, + "loss": 3.4444, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107305077494672e-05, + "loss": 3.4461, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.10646648274362e-05, + "loss": 3.4485, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.105627887992568e-05, + "loss": 3.4355, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047909311218892e-05, + "loss": 3.4494, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039523363708372e-05, + "loss": 3.4451, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031137416197852e-05, + "loss": 3.4367, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022751468687332e-05, + "loss": 3.4291, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101438189998054e-05, + "loss": 3.4338, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005995952470024e-05, + "loss": 3.4424, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997610004959504e-05, + "loss": 3.4474, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989224057448984e-05, + "loss": 3.4435, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980854488742193e-05, + "loss": 3.447, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972468541231673e-05, + "loss": 3.4324, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0964082593721153e-05, + "loss": 3.4416, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955696646210633e-05, + "loss": 3.4439, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947327077503846e-05, + "loss": 3.433, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938941129993326e-05, + "loss": 3.4311, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930555182482806e-05, + "loss": 3.4313, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922169234972286e-05, + "loss": 3.4339, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913799666265495e-05, + "loss": 3.4523, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905413718754978e-05, + "loss": 3.4403, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0897027771244458e-05, + "loss": 3.4336, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888658202537667e-05, + "loss": 3.4515, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880272255027147e-05, + "loss": 3.4412, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871886307516627e-05, + "loss": 3.4436, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086351673880984e-05, + "loss": 3.4308, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085513079129932e-05, + "loss": 3.4252, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.08467448437888e-05, + "loss": 3.4514, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083835889627828e-05, + "loss": 3.4414, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082997294876776e-05, + "loss": 3.4367, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821587001257236e-05, + "loss": 3.432, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081321743255045e-05, + "loss": 3.4306, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804831485039932e-05, + "loss": 3.4244, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079644553752941e-05, + "loss": 3.4365, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0788059590018888e-05, + "loss": 3.4356, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.07796900213121e-05, + "loss": 3.4345, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077130407380158e-05, + "loss": 3.4452, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762918126291057e-05, + "loss": 3.434, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075453217878054e-05, + "loss": 3.4301, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074614623127002e-05, + "loss": 3.439, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.07377602837595e-05, + "loss": 3.4236, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072937433624898e-05, + "loss": 3.4315, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072098838873846e-05, + "loss": 3.435, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071261882003167e-05, + "loss": 3.4334, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.070423287252115e-05, + "loss": 3.4276, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695846925010633e-05, + "loss": 3.4291, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687460977500113e-05, + "loss": 3.4239, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0679091408793322e-05, + "loss": 3.4357, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670705461282802e-05, + "loss": 3.4415, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662319513772282e-05, + "loss": 3.4395, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653933566261762e-05, + "loss": 3.4406, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645563997554974e-05, + "loss": 3.4424, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637178050044454e-05, + "loss": 3.452, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628792102533934e-05, + "loss": 3.424, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620406155023414e-05, + "loss": 3.441, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0612036586316623e-05, + "loss": 3.4409, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603650638806103e-05, + "loss": 3.4189, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595264691295586e-05, + "loss": 3.4472, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586895122588796e-05, + "loss": 3.4371, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578509175078276e-05, + "loss": 3.4471, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0570123227567755e-05, + "loss": 3.4388, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561737280057235e-05, + "loss": 3.4219, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0553351332546712e-05, + "loss": 3.4263, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544965385036195e-05, + "loss": 3.4359, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536595816329408e-05, + "loss": 3.4383, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528209868818888e-05, + "loss": 3.436, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519823921308364e-05, + "loss": 3.442, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511437973797844e-05, + "loss": 3.4356, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0503052026287324e-05, + "loss": 3.4332, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0494666078776804e-05, + "loss": 3.4304, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0486280131266288e-05, + "loss": 3.4285, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477894183755768e-05, + "loss": 3.4425, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469524615048977e-05, + "loss": 3.4399, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461138667538457e-05, + "loss": 3.4479, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0452752720027937e-05, + "loss": 3.4236, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444366772517416e-05, + "loss": 3.4359, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435980825006896e-05, + "loss": 3.4413, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0427594877496376e-05, + "loss": 3.4401, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0419208929985856e-05, + "loss": 3.4315, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.041083936127907e-05, + "loss": 3.432, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402453413768545e-05, + "loss": 3.4343, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394067466258025e-05, + "loss": 3.4385, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038569789755124e-05, + "loss": 3.422, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037731195004072e-05, + "loss": 3.4402, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368926002530198e-05, + "loss": 3.4237, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360540055019678e-05, + "loss": 3.4415, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352154107509158e-05, + "loss": 3.4239, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343768159998638e-05, + "loss": 3.4362, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335382212488118e-05, + "loss": 3.4308, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326996264977598e-05, + "loss": 3.4409, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031862669627081e-05, + "loss": 3.4381, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.031024074876029e-05, + "loss": 3.4253, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.030185480124977e-05, + "loss": 3.4384, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.029346885373925e-05, + "loss": 3.4478, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.028509928503246e-05, + "loss": 3.4353, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276713337521942e-05, + "loss": 3.4359, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026834376881515e-05, + "loss": 3.4293, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.025995782130463e-05, + "loss": 3.4374, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025157187379411e-05, + "loss": 3.4364, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024318592628359e-05, + "loss": 3.4274, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023479997877307e-05, + "loss": 3.4323, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022641403126255e-05, + "loss": 3.4344, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021802808375203e-05, + "loss": 3.4362, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020964213624151e-05, + "loss": 3.437, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0201272567534724e-05, + "loss": 3.4221, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.01928866200242e-05, + "loss": 3.4337, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018450067251368e-05, + "loss": 3.4253, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0176114725003163e-05, + "loss": 3.4422, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167745156296373e-05, + "loss": 3.4378, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159359208785852e-05, + "loss": 3.443, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150973261275332e-05, + "loss": 3.4189, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142587313764812e-05, + "loss": 3.4427, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0134217745058025e-05, + "loss": 3.4328, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125831797547505e-05, + "loss": 3.4389, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117445850036985e-05, + "loss": 3.4281, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109059902526465e-05, + "loss": 3.435, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100690333819674e-05, + "loss": 3.439, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092304386309154e-05, + "loss": 3.4521, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083918438798634e-05, + "loss": 3.4321, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075532491288114e-05, + "loss": 3.4401, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067162922581326e-05, + "loss": 3.4444, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005879335387454e-05, + "loss": 3.4326, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.005040740636402e-05, + "loss": 3.4312, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0042021458853495e-05, + "loss": 3.4436, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.003363551134298e-05, + "loss": 3.4424, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002524956383246e-05, + "loss": 3.4284, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001686361632194e-05, + "loss": 3.4357, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8546640872955322, + "eval_runtime": 307.3745, + "eval_samples_per_second": 1241.453, + "eval_steps_per_second": 38.796, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.000847766881142e-05, + "loss": 3.4237, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.00000917213009e-05, + "loss": 3.4212, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.999170577379038e-05, + "loss": 3.434, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983319826279855e-05, + "loss": 3.4352, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974950257573067e-05, + "loss": 3.4452, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996656431006255e-05, + "loss": 3.4312, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9958178362552027e-05, + "loss": 3.4287, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949792415041507e-05, + "loss": 3.4283, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.994142284633472e-05, + "loss": 3.4278, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.99330368988242e-05, + "loss": 3.4313, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992465095131368e-05, + "loss": 3.4342, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991626500380316e-05, + "loss": 3.4384, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907895435096372e-05, + "loss": 3.4301, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989952586638958e-05, + "loss": 3.4273, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.989113991887906e-05, + "loss": 3.4301, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.988275397136854e-05, + "loss": 3.4149, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987436802385802e-05, + "loss": 3.425, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.98659820763475e-05, + "loss": 3.4273, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985759612883698e-05, + "loss": 3.4277, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984921018132646e-05, + "loss": 3.4356, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.984082423381594e-05, + "loss": 3.4422, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.983245466510915e-05, + "loss": 3.436, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9824068717598633e-05, + "loss": 3.4349, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815682770088113e-05, + "loss": 3.435, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807296822577593e-05, + "loss": 3.4253, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798927253870802e-05, + "loss": 3.4349, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9790541306360282e-05, + "loss": 3.4323, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9782155358849762e-05, + "loss": 3.4281, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9773769411339242e-05, + "loss": 3.4243, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765399842632455e-05, + "loss": 3.4209, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9757013895121935e-05, + "loss": 3.429, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748627947611415e-05, + "loss": 3.4385, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740242000100895e-05, + "loss": 3.4326, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9731872431394104e-05, + "loss": 3.4331, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723486483883587e-05, + "loss": 3.4209, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9715100536373067e-05, + "loss": 3.4324, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706714588862547e-05, + "loss": 3.431, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698345020155756e-05, + "loss": 3.4243, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689959072645236e-05, + "loss": 3.421, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681573125134716e-05, + "loss": 3.4169, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673187177624196e-05, + "loss": 3.4211, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966481760891741e-05, + "loss": 3.4424, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656431661406888e-05, + "loss": 3.4331, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9648045713896368e-05, + "loss": 3.4248, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639659766385848e-05, + "loss": 3.4383, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631290197679057e-05, + "loss": 3.4269, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622904250168537e-05, + "loss": 3.4387, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961451830265802e-05, + "loss": 3.4265, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.96061323551475e-05, + "loss": 3.4076, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597779165244442e-05, + "loss": 3.4444, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958939321773392e-05, + "loss": 3.4303, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9581007270223402e-05, + "loss": 3.4288, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572621322712882e-05, + "loss": 3.4192, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564235375202362e-05, + "loss": 3.4188, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955586580649557e-05, + "loss": 3.4167, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954747985898505e-05, + "loss": 3.4244, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953909391147453e-05, + "loss": 3.4234, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953070796396401e-05, + "loss": 3.4234, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.952232201645349e-05, + "loss": 3.4347, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513936068942974e-05, + "loss": 3.4221, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950555012143245e-05, + "loss": 3.4173, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949716417392193e-05, + "loss": 3.4318, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488794605215143e-05, + "loss": 3.411, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480408657704623e-05, + "loss": 3.4166, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9472022710194103e-05, + "loss": 3.4268, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463636762683583e-05, + "loss": 3.4254, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455267193976796e-05, + "loss": 3.4159, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446881246466276e-05, + "loss": 3.4193, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438495298955752e-05, + "loss": 3.4153, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9430109351445232e-05, + "loss": 3.4236, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421739782738445e-05, + "loss": 3.4303, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413353835227925e-05, + "loss": 3.4273, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404967887717405e-05, + "loss": 3.4286, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396581940206884e-05, + "loss": 3.4344, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388212371500097e-05, + "loss": 3.439, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379826423989574e-05, + "loss": 3.4155, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371440476479057e-05, + "loss": 3.4311, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936307090777227e-05, + "loss": 3.4246, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.935468496026175e-05, + "loss": 3.4088, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346299012751226e-05, + "loss": 3.4359, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933792944404444e-05, + "loss": 3.4271, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932954349653392e-05, + "loss": 3.4382, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321157549023398e-05, + "loss": 3.4284, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312771601512878e-05, + "loss": 3.4114, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9304385654002358e-05, + "loss": 3.4133, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295999706491838e-05, + "loss": 3.4267, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287630137785047e-05, + "loss": 3.4256, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279244190274527e-05, + "loss": 3.4295, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.927085824276401e-05, + "loss": 3.4292, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926247229525349e-05, + "loss": 3.422, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925408634774297e-05, + "loss": 3.426, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924570040023245e-05, + "loss": 3.4177, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923731445272193e-05, + "loss": 3.4192, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228928505211407e-05, + "loss": 3.4319, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.922055893650462e-05, + "loss": 3.427, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.92121729889941e-05, + "loss": 3.4379, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920378704148358e-05, + "loss": 3.4143, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919540109397306e-05, + "loss": 3.4264, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9187031525266272e-05, + "loss": 3.4307, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178645577755752e-05, + "loss": 3.4285, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9170259630245228e-05, + "loss": 3.4203, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.916187368273471e-05, + "loss": 3.4239, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915348773522419e-05, + "loss": 3.4246, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914510178771367e-05, + "loss": 3.4237, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913673221900688e-05, + "loss": 3.4173, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912834627149636e-05, + "loss": 3.4253, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911996032398584e-05, + "loss": 3.4135, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911157437647532e-05, + "loss": 3.4295, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103188428964804e-05, + "loss": 3.4134, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094802481454284e-05, + "loss": 3.4253, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908641653394376e-05, + "loss": 3.4174, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.907803058643324e-05, + "loss": 3.4339, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069661017726453e-05, + "loss": 3.4254, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061275070215933e-05, + "loss": 3.4143, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052889122705413e-05, + "loss": 3.4284, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044503175194893e-05, + "loss": 3.4385, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036133606488105e-05, + "loss": 3.425, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027747658977585e-05, + "loss": 3.424, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019378090270794e-05, + "loss": 3.4197, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010992142760274e-05, + "loss": 3.4249, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002606195249758e-05, + "loss": 3.4251, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994220247739234e-05, + "loss": 3.4185, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985834300228714e-05, + "loss": 3.4191, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977448352718194e-05, + "loss": 3.4264, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8969062405207674e-05, + "loss": 3.4272, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8960676457697154e-05, + "loss": 3.4258, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8952306888990366e-05, + "loss": 3.4135, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943920941479846e-05, + "loss": 3.4216, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935534993969326e-05, + "loss": 3.4175, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927149046458806e-05, + "loss": 3.4296, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918779477752015e-05, + "loss": 3.4292, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910393530241495e-05, + "loss": 3.4323, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8902007582730975e-05, + "loss": 3.4106, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889362163522046e-05, + "loss": 3.4334, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8885252066513668e-05, + "loss": 3.4218, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876866119003148e-05, + "loss": 3.4319, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868496550296357e-05, + "loss": 3.4184, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8860110602785837e-05, + "loss": 3.4218, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885172465527532e-05, + "loss": 3.4284, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.88433387077648e-05, + "loss": 3.4427, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883495276025428e-05, + "loss": 3.4195, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882656681274376e-05, + "loss": 3.4296, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8818180865233236e-05, + "loss": 3.4341, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.880981129652645e-05, + "loss": 3.4188, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.880142534901593e-05, + "loss": 3.422, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793039401505412e-05, + "loss": 3.4317, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878465345399489e-05, + "loss": 3.4328, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877626750648437e-05, + "loss": 3.4221, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876788155897385e-05, + "loss": 3.4233, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.85634183883667, + "eval_runtime": 305.9431, + "eval_samples_per_second": 1247.261, + "eval_steps_per_second": 38.978, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875949561146333e-05, + "loss": 3.4126, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8751126042756538e-05, + "loss": 3.409, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.874274009524602e-05, + "loss": 3.4234, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.87343541477355e-05, + "loss": 3.4272, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.872596820022498e-05, + "loss": 3.4324, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.871758225271446e-05, + "loss": 3.4199, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.870919630520394e-05, + "loss": 3.4233, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700810357693418e-05, + "loss": 3.4152, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.869244078898663e-05, + "loss": 3.4158, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8684054841476113e-05, + "loss": 3.4247, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675668893965593e-05, + "loss": 3.4236, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866728294645507e-05, + "loss": 3.4226, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658913377748282e-05, + "loss": 3.4275, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.865054380904149e-05, + "loss": 3.4129, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8642157861530975e-05, + "loss": 3.416, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633771914020455e-05, + "loss": 3.4033, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625385966509935e-05, + "loss": 3.415, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8617000018999415e-05, + "loss": 3.4205, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860861407148889e-05, + "loss": 3.4126, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.860022812397837e-05, + "loss": 3.4243, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.859184217646785e-05, + "loss": 3.4332, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583472607761067e-05, + "loss": 3.4274, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8575086660250544e-05, + "loss": 3.4252, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566700712740024e-05, + "loss": 3.4226, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558314765229504e-05, + "loss": 3.4167, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.8549945196522716e-05, + "loss": 3.4254, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541559249012193e-05, + "loss": 3.4228, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8533173301501676e-05, + "loss": 3.4197, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524787353991156e-05, + "loss": 3.4094, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516417785284365e-05, + "loss": 3.4124, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8508031837773845e-05, + "loss": 3.4135, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499645890263325e-05, + "loss": 3.4268, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.8491259942752805e-05, + "loss": 3.4253, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8482890374046017e-05, + "loss": 3.4227, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8474504426535497e-05, + "loss": 3.4095, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8466118479024977e-05, + "loss": 3.4182, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457732531514457e-05, + "loss": 3.4264, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8449362962807666e-05, + "loss": 3.4122, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440977015297146e-05, + "loss": 3.4132, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843259106778663e-05, + "loss": 3.4053, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842422149907984e-05, + "loss": 3.4106, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.841583555156932e-05, + "loss": 3.4285, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.84074496040588e-05, + "loss": 3.4251, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839906365654828e-05, + "loss": 3.4154, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839067770903776e-05, + "loss": 3.4278, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838229176152724e-05, + "loss": 3.4177, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8373905814016722e-05, + "loss": 3.4226, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.83655198665062e-05, + "loss": 3.4202, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835715029779941e-05, + "loss": 3.3925, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834876435028889e-05, + "loss": 3.4361, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.83403947815821e-05, + "loss": 3.4149, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8332008834071583e-05, + "loss": 3.4222, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323622886561063e-05, + "loss": 3.4065, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315236939050543e-05, + "loss": 3.4138, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830685099154002e-05, + "loss": 3.4028, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.82984650440295e-05, + "loss": 3.4126, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.829007909651898e-05, + "loss": 3.4117, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281709527812192e-05, + "loss": 3.4113, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273323580301672e-05, + "loss": 3.4292, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264937632791152e-05, + "loss": 3.4112, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256551685280632e-05, + "loss": 3.4045, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8248165737770112e-05, + "loss": 3.4211, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239779790259592e-05, + "loss": 3.4046, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231393842749072e-05, + "loss": 3.4043, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8223007895238552e-05, + "loss": 3.4197, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214638326531764e-05, + "loss": 3.4131, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206252379021244e-05, + "loss": 3.4088, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197866431510724e-05, + "loss": 3.4057, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.81894804840002e-05, + "loss": 3.4073, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8181110915293413e-05, + "loss": 3.4108, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172724967782893e-05, + "loss": 3.4206, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164339020272377e-05, + "loss": 3.4149, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155953072761853e-05, + "loss": 3.4182, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8147583504055066e-05, + "loss": 3.4228, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.8139197556544546e-05, + "loss": 3.4301, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8130811609034022e-05, + "loss": 3.4027, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122425661523505e-05, + "loss": 3.422, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8114056092816718e-05, + "loss": 3.4103, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105670145306198e-05, + "loss": 3.3992, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097284197795674e-05, + "loss": 3.4179, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088914629088887e-05, + "loss": 3.4263, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080528681578367e-05, + "loss": 3.4231, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8072142734067847e-05, + "loss": 3.424, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8063756786557327e-05, + "loss": 3.3974, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055370839046807e-05, + "loss": 3.4007, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046984891536287e-05, + "loss": 3.4177, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038615322829496e-05, + "loss": 3.4147, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8030229375318976e-05, + "loss": 3.4153, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802184342780846e-05, + "loss": 3.4207, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801345748029794e-05, + "loss": 3.4136, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.800507153278742e-05, + "loss": 3.4147, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.79966855852769e-05, + "loss": 3.4096, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.798829963776638e-05, + "loss": 3.4086, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979913690255856e-05, + "loss": 3.4212, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971544121549068e-05, + "loss": 3.4186, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7963158174038548e-05, + "loss": 3.4231, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795477222652803e-05, + "loss": 3.4073, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946386279017508e-05, + "loss": 3.4095, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.793801671031072e-05, + "loss": 3.4217, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.79296307628002e-05, + "loss": 3.4174, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921244815289677e-05, + "loss": 3.4115, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.791285886777916e-05, + "loss": 3.4164, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.790447292026864e-05, + "loss": 3.4115, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.789608697275812e-05, + "loss": 3.4107, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788771740405133e-05, + "loss": 3.412, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.787933145654081e-05, + "loss": 3.4116, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.787094550903029e-05, + "loss": 3.404, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.786255956151977e-05, + "loss": 3.424, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7854173614009252e-05, + "loss": 3.4058, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845787666498732e-05, + "loss": 3.4122, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837401718988212e-05, + "loss": 3.4066, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782901577147769e-05, + "loss": 3.4207, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.78206462027709e-05, + "loss": 3.417, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812276634064114e-05, + "loss": 3.4039, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803890686553594e-05, + "loss": 3.421, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795504739043074e-05, + "loss": 3.4249, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7787118791532554e-05, + "loss": 3.4155, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7778732844022034e-05, + "loss": 3.4128, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7770363275315243e-05, + "loss": 3.412, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761977327804723e-05, + "loss": 3.412, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.7753591380294206e-05, + "loss": 3.4149, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7745205432783686e-05, + "loss": 3.4078, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736819485273163e-05, + "loss": 3.4112, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.7728433537762643e-05, + "loss": 3.4149, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7720047590252123e-05, + "loss": 3.4148, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7711661642741602e-05, + "loss": 3.4131, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7703292074034815e-05, + "loss": 3.4048, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694906126524295e-05, + "loss": 3.4144, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686520179013775e-05, + "loss": 3.4033, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7678134231503255e-05, + "loss": 3.421, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669764662796464e-05, + "loss": 3.4151, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.7661378715285944e-05, + "loss": 3.4245, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7652992767775424e-05, + "loss": 3.397, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644606820264907e-05, + "loss": 3.4237, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763625363036185e-05, + "loss": 3.4078, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762786768285133e-05, + "loss": 3.4208, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619481735340805e-05, + "loss": 3.4117, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7611095787830285e-05, + "loss": 3.4038, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.760270984031977e-05, + "loss": 3.4222, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759432389280925e-05, + "loss": 3.4312, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.758593794529873e-05, + "loss": 3.4149, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.757755199778821e-05, + "loss": 3.4171, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569182429081418e-05, + "loss": 3.4228, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.756081286037463e-05, + "loss": 3.4082, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.755242691286411e-05, + "loss": 3.4111, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.754404096535359e-05, + "loss": 3.4221, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.753565501784307e-05, + "loss": 3.4191, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.752726907033255e-05, + "loss": 3.4172, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.751888312282203e-05, + "loss": 3.4091, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.857896089553833, + "eval_runtime": 315.3621, + "eval_samples_per_second": 1210.009, + "eval_steps_per_second": 37.814, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.751049717531151e-05, + "loss": 3.3992, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7502127606604722e-05, + "loss": 3.3987, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493741659094202e-05, + "loss": 3.4124, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485355711583682e-05, + "loss": 3.4183, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476969764073162e-05, + "loss": 3.4211, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.746858381656264e-05, + "loss": 3.4091, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.746019786905212e-05, + "loss": 3.4112, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.74518119215416e-05, + "loss": 3.406, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7443458731638544e-05, + "loss": 3.408, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7435072784128024e-05, + "loss": 3.4103, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7426686836617504e-05, + "loss": 3.4128, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7418300889106984e-05, + "loss": 3.4131, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.740991494159646e-05, + "loss": 3.4224, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401545372889676e-05, + "loss": 3.3991, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7393159425379156e-05, + "loss": 3.409, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384773477868636e-05, + "loss": 3.3914, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376387530358112e-05, + "loss": 3.4044, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7368001582847592e-05, + "loss": 3.408, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7359615635337072e-05, + "loss": 3.4059, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7351229687826552e-05, + "loss": 3.4138, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342843740316032e-05, + "loss": 3.4204, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334490550412977e-05, + "loss": 3.4191, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7326104602902457e-05, + "loss": 3.4161, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317718655391934e-05, + "loss": 3.4096, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7309332707881414e-05, + "loss": 3.4102, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7300946760370894e-05, + "loss": 3.4158, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292560812860377e-05, + "loss": 3.4092, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7284174865349857e-05, + "loss": 3.4123, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275788917839337e-05, + "loss": 3.3975, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267419349132546e-05, + "loss": 3.4025, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7259033401622026e-05, + "loss": 3.4003, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.725066383291524e-05, + "loss": 3.4179, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724227788540472e-05, + "loss": 3.4173, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.72338919378942e-05, + "loss": 3.4086, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.722550599038368e-05, + "loss": 3.4038, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721712004287316e-05, + "loss": 3.4001, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208734095362638e-05, + "loss": 3.4175, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200348147852115e-05, + "loss": 3.4067, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.719197857914533e-05, + "loss": 3.4013, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718359263163481e-05, + "loss": 3.3954, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.717522306292802e-05, + "loss": 3.4033, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.71668371154175e-05, + "loss": 3.4132, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715845116790698e-05, + "loss": 3.4144, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.715006522039646e-05, + "loss": 3.4066, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.714167927288594e-05, + "loss": 3.4142, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713329332537542e-05, + "loss": 3.406, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.71249073778649e-05, + "loss": 3.4124, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116537809158112e-05, + "loss": 3.4102, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710815186164759e-05, + "loss": 3.3827, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709976591413707e-05, + "loss": 3.4232, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.709137996662655e-05, + "loss": 3.4055, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7082994019116032e-05, + "loss": 3.414, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074608071605512e-05, + "loss": 3.4007, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.706623850289872e-05, + "loss": 3.3993, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.70578525553882e-05, + "loss": 3.3942, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704946660787768e-05, + "loss": 3.4026, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.704108066036716e-05, + "loss": 3.4039, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.703269471285664e-05, + "loss": 3.398, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024325144149853e-05, + "loss": 3.4192, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7015939196639333e-05, + "loss": 3.4078, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7007553249128813e-05, + "loss": 3.3885, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6999167301618293e-05, + "loss": 3.4117, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990797732911502e-05, + "loss": 3.3962, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982411785400986e-05, + "loss": 3.3935, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6974025837890465e-05, + "loss": 3.4087, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965639890379942e-05, + "loss": 3.4034, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6957253942869422e-05, + "loss": 3.3974, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948867995358902e-05, + "loss": 3.3947, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6940482047848382e-05, + "loss": 3.3989, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6932096100337862e-05, + "loss": 3.403, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923726531631074e-05, + "loss": 3.4092, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915340584120554e-05, + "loss": 3.4059, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906954636610034e-05, + "loss": 3.4115, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898585067903243e-05, + "loss": 3.4103, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890199120392723e-05, + "loss": 3.4167, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881813172882203e-05, + "loss": 3.3997, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873427225371687e-05, + "loss": 3.41, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6865041277861167e-05, + "loss": 3.4002, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856655330350647e-05, + "loss": 3.3937, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848269382840123e-05, + "loss": 3.4075, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839899814133336e-05, + "loss": 3.4158, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6831513866622816e-05, + "loss": 3.4117, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6823127919112295e-05, + "loss": 3.415, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814741971601775e-05, + "loss": 3.3841, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806356024091255e-05, + "loss": 3.3961, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797970076580735e-05, + "loss": 3.4049, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789600507873948e-05, + "loss": 3.4076, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6781214560363424e-05, + "loss": 3.4014, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772828612852908e-05, + "loss": 3.4112, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764442665342388e-05, + "loss": 3.4033, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6756056717831868e-05, + "loss": 3.408, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747670770321348e-05, + "loss": 3.3946, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739284822810828e-05, + "loss": 3.3978, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730898875300304e-05, + "loss": 3.413, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722529306593517e-05, + "loss": 3.4051, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6714143359082997e-05, + "loss": 3.4145, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670575741157248e-05, + "loss": 3.401, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6697371464061956e-05, + "loss": 3.3961, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668900189535517e-05, + "loss": 3.4114, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.668061594784465e-05, + "loss": 3.4095, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.667223000033413e-05, + "loss": 3.4027, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.666384405282361e-05, + "loss": 3.4046, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665545810531309e-05, + "loss": 3.4021, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.664707215780257e-05, + "loss": 3.4019, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638702589095778e-05, + "loss": 3.4054, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6630316641585258e-05, + "loss": 3.3997, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621930694074738e-05, + "loss": 3.3967, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613544746564218e-05, + "loss": 3.4046, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.66051587990537e-05, + "loss": 3.403, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.659677285154318e-05, + "loss": 3.3941, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658838690403266e-05, + "loss": 3.4022, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6580000956522138e-05, + "loss": 3.406, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657163138781535e-05, + "loss": 3.407, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563261819108562e-05, + "loss": 3.3938, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554875871598042e-05, + "loss": 3.4092, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546489924087522e-05, + "loss": 3.416, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6538103976577002e-05, + "loss": 3.4091, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529718029066482e-05, + "loss": 3.3995, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652134846035969e-05, + "loss": 3.4027, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651296251284917e-05, + "loss": 3.4031, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504576565338655e-05, + "loss": 3.4091, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496190617828135e-05, + "loss": 3.3983, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.648780467031761e-05, + "loss": 3.3995, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647941872280709e-05, + "loss": 3.4012, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.647103277529657e-05, + "loss": 3.4091, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.646264682778605e-05, + "loss": 3.4027, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454277259079264e-05, + "loss": 3.3924, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445891311568744e-05, + "loss": 3.4042, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437505364058223e-05, + "loss": 3.3942, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429119416547703e-05, + "loss": 3.41, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420749847840913e-05, + "loss": 3.4056, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6412363900330393e-05, + "loss": 3.4148, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6403994331623605e-05, + "loss": 3.3899, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395608384113085e-05, + "loss": 3.4102, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387222436602565e-05, + "loss": 3.4013, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378836489092045e-05, + "loss": 3.408, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370450541581525e-05, + "loss": 3.4041, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6362080972874734e-05, + "loss": 3.3941, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353695025364217e-05, + "loss": 3.4154, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345309077853697e-05, + "loss": 3.4126, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336923130343177e-05, + "loss": 3.407, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328537182832657e-05, + "loss": 3.4056, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6320151235322137e-05, + "loss": 3.411, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311781666615346e-05, + "loss": 3.404, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6303395719104826e-05, + "loss": 3.3971, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629500977159431e-05, + "loss": 3.4119, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628662382408379e-05, + "loss": 3.4082, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6278237876573266e-05, + "loss": 3.4109, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269851929062746e-05, + "loss": 3.3997, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8585195541381836, + "eval_runtime": 305.6193, + "eval_samples_per_second": 1248.583, + "eval_steps_per_second": 39.019, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626148236035596e-05, + "loss": 3.3866, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253096412845435e-05, + "loss": 3.3885, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.624471046533492e-05, + "loss": 3.4054, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236324517824398e-05, + "loss": 3.4033, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622795494911761e-05, + "loss": 3.4137, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219569001607087e-05, + "loss": 3.3989, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211183054096567e-05, + "loss": 3.4011, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202797106586047e-05, + "loss": 3.3975, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194411159075527e-05, + "loss": 3.397, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618602521156501e-05, + "loss": 3.3971, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617763926405449e-05, + "loss": 3.4034, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616925331654397e-05, + "loss": 3.4086, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616088374783718e-05, + "loss": 3.4067, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615251417913039e-05, + "loss": 3.3891, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144128231619872e-05, + "loss": 3.3973, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135742284109352e-05, + "loss": 3.3805, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127356336598832e-05, + "loss": 3.398, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6118970389088312e-05, + "loss": 3.4011, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110584441577792e-05, + "loss": 3.3911, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610219849406727e-05, + "loss": 3.4025, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609381254655675e-05, + "loss": 3.4095, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085459356653693e-05, + "loss": 3.4039, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077073409143173e-05, + "loss": 3.4098, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068687461632653e-05, + "loss": 3.4012, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060301514122133e-05, + "loss": 3.402, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051915566611613e-05, + "loss": 3.4028, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604352961910109e-05, + "loss": 3.3981, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035143671590573e-05, + "loss": 3.4034, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026757724080053e-05, + "loss": 3.3913, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018388155373266e-05, + "loss": 3.3901, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010002207862742e-05, + "loss": 3.3922, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001616260352222e-05, + "loss": 3.4038, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993230312841702e-05, + "loss": 3.4051, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5984860744134918e-05, + "loss": 3.4043, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976474796624394e-05, + "loss": 3.3936, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968105227917607e-05, + "loss": 3.3955, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959719280407087e-05, + "loss": 3.4051, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951333332896563e-05, + "loss": 3.3886, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5942947385386043e-05, + "loss": 3.3935, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934561437875527e-05, + "loss": 3.3908, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592619186916874e-05, + "loss": 3.3877, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5917805921658216e-05, + "loss": 3.4027, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909419974147696e-05, + "loss": 3.3996, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901034026637176e-05, + "loss": 3.4038, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892648079126656e-05, + "loss": 3.4012, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884262131616136e-05, + "loss": 3.4014, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587587618410562e-05, + "loss": 3.3985, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867506615398828e-05, + "loss": 3.4034, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859120667888308e-05, + "loss": 3.3702, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850734720377788e-05, + "loss": 3.4087, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842348772867268e-05, + "loss": 3.397, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5833962825356748e-05, + "loss": 3.4035, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825576877846228e-05, + "loss": 3.3908, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581720730913944e-05, + "loss": 3.392, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580882136162892e-05, + "loss": 3.3806, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800435414118397e-05, + "loss": 3.3915, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792049466607877e-05, + "loss": 3.3986, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783663519097357e-05, + "loss": 3.3845, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577529395039057e-05, + "loss": 3.4078, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576690800288005e-05, + "loss": 3.3985, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575852205536953e-05, + "loss": 3.3805, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575013610785901e-05, + "loss": 3.4012, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741766539152218e-05, + "loss": 3.389, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733380591641698e-05, + "loss": 3.3853, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.572499464413118e-05, + "loss": 3.3965, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571660869662066e-05, + "loss": 3.3942, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.570822274911014e-05, + "loss": 3.3839, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.569985318040335e-05, + "loss": 3.3861, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569146723289283e-05, + "loss": 3.3858, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568308128538231e-05, + "loss": 3.3925, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567469533787179e-05, + "loss": 3.3999, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666309390361274e-05, + "loss": 3.394, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565792344285075e-05, + "loss": 3.4013, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649553874143963e-05, + "loss": 3.3984, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641167926633443e-05, + "loss": 3.4054, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632781979122923e-05, + "loss": 3.3913, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624396031612403e-05, + "loss": 3.4026, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616010084101883e-05, + "loss": 3.3864, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607624136591363e-05, + "loss": 3.3829, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599238189080843e-05, + "loss": 3.3964, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.559086862037405e-05, + "loss": 3.4036, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.558248267286353e-05, + "loss": 3.4029, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557409672535301e-05, + "loss": 3.4044, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565710777842495e-05, + "loss": 3.372, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557324830331975e-05, + "loss": 3.387, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548938882821455e-05, + "loss": 3.3959, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540569314114664e-05, + "loss": 3.3992, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532183366604144e-05, + "loss": 3.391, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5523797419093624e-05, + "loss": 3.3995, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515411471583104e-05, + "loss": 3.3985, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507025524072584e-05, + "loss": 3.3916, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498639576562064e-05, + "loss": 3.3867, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490253629051544e-05, + "loss": 3.3873, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5481867681541024e-05, + "loss": 3.4005, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473498112834233e-05, + "loss": 3.3978, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465112165323713e-05, + "loss": 3.4, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5456726217813196e-05, + "loss": 3.3906, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448340270302676e-05, + "loss": 3.3884, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5439970701595885e-05, + "loss": 3.3986, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431584754085365e-05, + "loss": 3.3998, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423198806574845e-05, + "loss": 3.3904, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5414812859064325e-05, + "loss": 3.3946, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406426911553805e-05, + "loss": 3.3923, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398040964043288e-05, + "loss": 3.3947, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389655016532765e-05, + "loss": 3.3905, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381285447825977e-05, + "loss": 3.3913, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5372899500315457e-05, + "loss": 3.3892, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364513552804937e-05, + "loss": 3.3953, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356127605294414e-05, + "loss": 3.3904, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534775803658763e-05, + "loss": 3.3868, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.533937208907711e-05, + "loss": 3.386, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5330986141566586e-05, + "loss": 3.3943, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322600194056066e-05, + "loss": 3.4025, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314214246545546e-05, + "loss": 3.3876, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5305828299035026e-05, + "loss": 3.3917, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.529745873032824e-05, + "loss": 3.4042, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528907278281772e-05, + "loss": 3.4006, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.52806868353072e-05, + "loss": 3.3913, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527230088779668e-05, + "loss": 3.3938, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263931319089887e-05, + "loss": 3.3928, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255545371579369e-05, + "loss": 3.4007, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247159424068849e-05, + "loss": 3.3891, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238773476558329e-05, + "loss": 3.3877, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523038752904781e-05, + "loss": 3.3894, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.522200158153729e-05, + "loss": 3.3964, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213615634026767e-05, + "loss": 3.3962, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205229686516249e-05, + "loss": 3.3838, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196860117809461e-05, + "loss": 3.3913, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188474170298941e-05, + "loss": 3.3834, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.518008822278842e-05, + "loss": 3.4006, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.51717022752779e-05, + "loss": 3.3983, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163332706571112e-05, + "loss": 3.4011, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5154963137864323e-05, + "loss": 3.3806, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146577190353803e-05, + "loss": 3.3973, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138191242843283e-05, + "loss": 3.3939, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129805295332764e-05, + "loss": 3.3929, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121419347822241e-05, + "loss": 3.3938, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113049779115453e-05, + "loss": 3.3835, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104663831604935e-05, + "loss": 3.4067, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096277884094415e-05, + "loss": 3.4031, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087891936583892e-05, + "loss": 3.3993, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079505989073373e-05, + "loss": 3.395, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071120041562853e-05, + "loss": 3.4025, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062734094052333e-05, + "loss": 3.3917, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054364525345544e-05, + "loss": 3.3894, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5045978577835024e-05, + "loss": 3.4021, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037592630324504e-05, + "loss": 3.3954, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029206682813984e-05, + "loss": 3.4013, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020820735303465e-05, + "loss": 3.3889, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.860530138015747, + "eval_runtime": 303.7931, + "eval_samples_per_second": 1256.088, + "eval_steps_per_second": 39.254, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012434787792945e-05, + "loss": 3.3871, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004065219086154e-05, + "loss": 3.3743, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995679271575636e-05, + "loss": 3.3943, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987293324065116e-05, + "loss": 3.3971, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4978907376554596e-05, + "loss": 3.399, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970521429044074e-05, + "loss": 3.3905, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962135481533554e-05, + "loss": 3.3978, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4953749534023034e-05, + "loss": 3.3863, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945363586512514e-05, + "loss": 3.3847, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937010396609457e-05, + "loss": 3.3878, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928624449098937e-05, + "loss": 3.396, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920238501588419e-05, + "loss": 3.3955, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4911852554077896e-05, + "loss": 3.3974, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903482985371108e-05, + "loss": 3.3819, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.489509703786059e-05, + "loss": 3.3879, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.488671109035007e-05, + "loss": 3.3694, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878325142839546e-05, + "loss": 3.3874, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4869939195329028e-05, + "loss": 3.3889, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861553247818508e-05, + "loss": 3.3804, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853167300307988e-05, + "loss": 3.3946, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844781352797468e-05, + "loss": 3.3984, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836428162894411e-05, + "loss": 3.3958, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828042215383891e-05, + "loss": 3.3993, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.481965626787337e-05, + "loss": 3.3872, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.481127032036285e-05, + "loss": 3.3962, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.480288437285233e-05, + "loss": 3.3914, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794498425341811e-05, + "loss": 3.387, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786112477831291e-05, + "loss": 3.3963, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.477772653032077e-05, + "loss": 3.3832, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769356961613982e-05, + "loss": 3.3793, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4760971014103462e-05, + "loss": 3.3842, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752601445396672e-05, + "loss": 3.3924, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744215497886152e-05, + "loss": 3.392, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735829550375632e-05, + "loss": 3.3948, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727443602865112e-05, + "loss": 3.385, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719057655354592e-05, + "loss": 3.3845, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710671707844074e-05, + "loss": 3.3975, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.470228576033355e-05, + "loss": 3.379, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.469389981282303e-05, + "loss": 3.3839, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685530244116245e-05, + "loss": 3.3795, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677160675409454e-05, + "loss": 3.3814, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668774727898935e-05, + "loss": 3.3897, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660388780388415e-05, + "loss": 3.3933, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652002832877895e-05, + "loss": 3.3927, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643616885367373e-05, + "loss": 3.3902, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635230937856853e-05, + "loss": 3.3885, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4626861369150066e-05, + "loss": 3.3886, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618475421639546e-05, + "loss": 3.3998, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610089474129024e-05, + "loss": 3.3617, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601703526618504e-05, + "loss": 3.3995, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593333957911717e-05, + "loss": 3.3865, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4584948010401195e-05, + "loss": 3.3913, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576562062890675e-05, + "loss": 3.3835, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568176115380155e-05, + "loss": 3.3809, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559806546673369e-05, + "loss": 3.3739, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551420599162845e-05, + "loss": 3.3804, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543034651652327e-05, + "loss": 3.3879, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534648704141807e-05, + "loss": 3.3744, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526262756631287e-05, + "loss": 3.399, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4517876809120767e-05, + "loss": 3.3877, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509490861610247e-05, + "loss": 3.3693, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501104914099729e-05, + "loss": 3.3907, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492735345392938e-05, + "loss": 3.3776, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.448434939788242e-05, + "loss": 3.3768, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.44759634503719e-05, + "loss": 3.3834, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467577502861376e-05, + "loss": 3.3853, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.445920793415459e-05, + "loss": 3.3752, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.445082198664407e-05, + "loss": 3.3811, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.444243603913355e-05, + "loss": 3.374, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.443406647042676e-05, + "loss": 3.3799, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.442568052291624e-05, + "loss": 3.3894, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.441729457540572e-05, + "loss": 3.3872, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.44089086278952e-05, + "loss": 3.3916, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400522680384679e-05, + "loss": 3.3881, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392153111677891e-05, + "loss": 3.3945, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4383767164167371e-05, + "loss": 3.3836, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.437538121665685e-05, + "loss": 3.3928, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.436699526914633e-05, + "loss": 3.3746, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.435860932163581e-05, + "loss": 3.3721, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350223374125291e-05, + "loss": 3.3867, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.43418538054185e-05, + "loss": 3.3894, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333467857907982e-05, + "loss": 3.3951, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325081910397462e-05, + "loss": 3.3919, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316695962886942e-05, + "loss": 3.369, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308310015376422e-05, + "loss": 3.3752, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299924067865902e-05, + "loss": 3.3832, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291554499159112e-05, + "loss": 3.387, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283168551648592e-05, + "loss": 3.3793, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274782604138074e-05, + "loss": 3.3904, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266396656627554e-05, + "loss": 3.392, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425801070911703e-05, + "loss": 3.3795, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249641140410245e-05, + "loss": 3.3775, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241255192899725e-05, + "loss": 3.3813, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232869245389205e-05, + "loss": 3.3853, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224483297878683e-05, + "loss": 3.3911, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216113729171895e-05, + "loss": 3.3901, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4207727781661375e-05, + "loss": 3.3811, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199341834150855e-05, + "loss": 3.3754, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4190955886640334e-05, + "loss": 3.3944, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4182569939129814e-05, + "loss": 3.3886, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174200370423028e-05, + "loss": 3.3848, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4165814422912504e-05, + "loss": 3.3822, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157428475401984e-05, + "loss": 3.3821, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149042527891466e-05, + "loss": 3.3828, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140672959184678e-05, + "loss": 3.3815, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132287011674155e-05, + "loss": 3.3823, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123901064163637e-05, + "loss": 3.3773, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115515116653117e-05, + "loss": 3.3836, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107129169142597e-05, + "loss": 3.3855, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4098759600435807e-05, + "loss": 3.3729, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090373652925287e-05, + "loss": 3.3785, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4081987705414767e-05, + "loss": 3.3824, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073601757904247e-05, + "loss": 3.3932, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065232189197458e-05, + "loss": 3.3778, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056846241686938e-05, + "loss": 3.3877, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048460294176418e-05, + "loss": 3.3865, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.40400743466659e-05, + "loss": 3.3949, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403168839915538e-05, + "loss": 3.3815, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402330245164486e-05, + "loss": 3.3812, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401493288293807e-05, + "loss": 3.3859, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400654693542755e-05, + "loss": 3.3863, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399816098791703e-05, + "loss": 3.3768, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989775040406508e-05, + "loss": 3.3822, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981389092895988e-05, + "loss": 3.3805, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973003145385468e-05, + "loss": 3.384, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964617197874948e-05, + "loss": 3.3823, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956247629168159e-05, + "loss": 3.3761, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947861681657639e-05, + "loss": 3.3783, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.393947573414712e-05, + "loss": 3.3763, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.39310897866366e-05, + "loss": 3.3936, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.392272021792981e-05, + "loss": 3.3845, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914334270419291e-05, + "loss": 3.3933, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905964701712504e-05, + "loss": 3.3705, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897578754201982e-05, + "loss": 3.3887, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889192806691462e-05, + "loss": 3.3852, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880806859180942e-05, + "loss": 3.3853, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872420911670422e-05, + "loss": 3.381, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864051342963633e-05, + "loss": 3.3734, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855665395453113e-05, + "loss": 3.4003, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847279447942593e-05, + "loss": 3.391, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838893500432074e-05, + "loss": 3.39, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830507552921554e-05, + "loss": 3.3837, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822121605411034e-05, + "loss": 3.3935, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813735657900514e-05, + "loss": 3.3824, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805366089193725e-05, + "loss": 3.3746, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3796980141683205e-05, + "loss": 3.3984, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788594194172685e-05, + "loss": 3.3828, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780208246662163e-05, + "loss": 3.3928, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771838677955376e-05, + "loss": 3.3795, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8612494468688965, + "eval_runtime": 303.8413, + "eval_samples_per_second": 1255.889, + "eval_steps_per_second": 39.247, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763452730444856e-05, + "loss": 3.3908, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755083161738066e-05, + "loss": 3.3644, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3746697214227546e-05, + "loss": 3.381, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738311266717026e-05, + "loss": 3.3926, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3729925319206508e-05, + "loss": 3.3866, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721539371695988e-05, + "loss": 3.3841, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713153424185465e-05, + "loss": 3.3857, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704767476674946e-05, + "loss": 3.3776, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696381529164426e-05, + "loss": 3.3738, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688011960457637e-05, + "loss": 3.378, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679626012947117e-05, + "loss": 3.3865, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671240065436597e-05, + "loss": 3.3837, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3662854117926077e-05, + "loss": 3.395, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.365450092802302e-05, + "loss": 3.3692, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.36461149805125e-05, + "loss": 3.3725, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.363772903300198e-05, + "loss": 3.3647, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629343085491462e-05, + "loss": 3.374, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3620957137980938e-05, + "loss": 3.3806, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612571190470418e-05, + "loss": 3.374, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.36041852429599e-05, + "loss": 3.3757, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359579929544938e-05, + "loss": 3.3927, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587446105546323e-05, + "loss": 3.3859, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579060158035803e-05, + "loss": 3.3879, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3570674210525283e-05, + "loss": 3.3801, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562288263014761e-05, + "loss": 3.3879, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3553902315504241e-05, + "loss": 3.3799, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545516367993721e-05, + "loss": 3.3767, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537130420483201e-05, + "loss": 3.3857, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528744472972683e-05, + "loss": 3.374, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520374904265892e-05, + "loss": 3.3657, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3511988956755372e-05, + "loss": 3.3775, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503619388048583e-05, + "loss": 3.3807, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495233440538063e-05, + "loss": 3.3834, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486847493027544e-05, + "loss": 3.3826, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478461545517024e-05, + "loss": 3.3772, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470091976810233e-05, + "loss": 3.3769, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461706029299715e-05, + "loss": 3.3858, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453320081789195e-05, + "loss": 3.366, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3444934134278675e-05, + "loss": 3.3737, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436548186768155e-05, + "loss": 3.3707, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428178618061366e-05, + "loss": 3.3693, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419792670550846e-05, + "loss": 3.385, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411406723040326e-05, + "loss": 3.3879, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403020775529807e-05, + "loss": 3.3818, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394634828019287e-05, + "loss": 3.3796, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386248880508764e-05, + "loss": 3.3778, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377862932998245e-05, + "loss": 3.3787, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369476985487725e-05, + "loss": 3.3861, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361107416780938e-05, + "loss": 3.3555, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3352721469270416e-05, + "loss": 3.3878, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344351900563629e-05, + "loss": 3.3806, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3335965953053108e-05, + "loss": 3.3809, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327580005542587e-05, + "loss": 3.3709, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319194058032067e-05, + "loss": 3.3697, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.331082448932528e-05, + "loss": 3.3647, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330243854181476e-05, + "loss": 3.3688, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294052594304237e-05, + "loss": 3.3813, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285666646793717e-05, + "loss": 3.3652, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277280699283199e-05, + "loss": 3.3913, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268894751772679e-05, + "loss": 3.3748, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260508804262159e-05, + "loss": 3.3594, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252122856751639e-05, + "loss": 3.3803, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243769666848582e-05, + "loss": 3.3646, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.323538371933806e-05, + "loss": 3.3703, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.322699777182754e-05, + "loss": 3.372, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.321861182431702e-05, + "loss": 3.3781, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.32102258768065e-05, + "loss": 3.3627, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.320183992929598e-05, + "loss": 3.3745, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193470360589191e-05, + "loss": 3.3618, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185084413078671e-05, + "loss": 3.3701, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176698465568153e-05, + "loss": 3.3826, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168312518057633e-05, + "loss": 3.3729, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3159926570547113e-05, + "loss": 3.3823, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151540623036593e-05, + "loss": 3.3757, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143171054329803e-05, + "loss": 3.3898, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134785106819283e-05, + "loss": 3.3725, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126399159308763e-05, + "loss": 3.3814, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118013211798241e-05, + "loss": 3.3673, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109627264287721e-05, + "loss": 3.363, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101241316777201e-05, + "loss": 3.3801, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092871748070416e-05, + "loss": 3.3752, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084485800559892e-05, + "loss": 3.3842, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076099853049372e-05, + "loss": 3.3853, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067713905538854e-05, + "loss": 3.3659, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059327958028334e-05, + "loss": 3.3617, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3050942010517814e-05, + "loss": 3.372, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042572441811024e-05, + "loss": 3.3777, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034186494300504e-05, + "loss": 3.3739, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025800546789984e-05, + "loss": 3.3761, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017414599279464e-05, + "loss": 3.3811, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009028651768946e-05, + "loss": 3.3721, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3000642704258423e-05, + "loss": 3.3694, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992256756747903e-05, + "loss": 3.366, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2983887188041117e-05, + "loss": 3.3819, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975501240530597e-05, + "loss": 3.3799, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967115293020073e-05, + "loss": 3.382, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958729345509555e-05, + "loss": 3.3688, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950359776802767e-05, + "loss": 3.3681, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2941973829292247e-05, + "loss": 3.3827, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933587881781726e-05, + "loss": 3.3773, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925201934271206e-05, + "loss": 3.3736, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2916815986760685e-05, + "loss": 3.3729, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908430039250165e-05, + "loss": 3.3685, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900044091739647e-05, + "loss": 3.377, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891674523032856e-05, + "loss": 3.3706, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883288575522338e-05, + "loss": 3.3693, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874902628011818e-05, + "loss": 3.3705, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866516680501298e-05, + "loss": 3.3717, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858130732990778e-05, + "loss": 3.3792, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849761164283988e-05, + "loss": 3.3602, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841375216773468e-05, + "loss": 3.3735, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2832989269262948e-05, + "loss": 3.3666, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824603321752427e-05, + "loss": 3.3869, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816217374241907e-05, + "loss": 3.3706, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807831426731387e-05, + "loss": 3.3704, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.27994618580246e-05, + "loss": 3.3826, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791075910514077e-05, + "loss": 3.3859, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782689963003557e-05, + "loss": 3.3702, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774304015493039e-05, + "loss": 3.3726, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2765934446786251e-05, + "loss": 3.3779, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.275754849927573e-05, + "loss": 3.3755, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.274916255176521e-05, + "loss": 3.3678, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274077660425469e-05, + "loss": 3.3719, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.273239065674417e-05, + "loss": 3.3693, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.272400470923365e-05, + "loss": 3.3759, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715618761723131e-05, + "loss": 3.3732, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707232814212608e-05, + "loss": 3.3662, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.269886324550582e-05, + "loss": 3.3701, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690477297995302e-05, + "loss": 3.3656, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682091350484782e-05, + "loss": 3.3806, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2673705402974258e-05, + "loss": 3.3757, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665335834267473e-05, + "loss": 3.3848, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2656966265560682e-05, + "loss": 3.3636, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648580318050163e-05, + "loss": 3.3773, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640194370539643e-05, + "loss": 3.3771, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631808423029123e-05, + "loss": 3.373, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623422475518603e-05, + "loss": 3.3729, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615052906811814e-05, + "loss": 3.365, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606666959301294e-05, + "loss": 3.3899, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598281011790774e-05, + "loss": 3.3795, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2589895064280255e-05, + "loss": 3.3802, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581509116769732e-05, + "loss": 3.3734, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573123169259212e-05, + "loss": 3.3844, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564737221748694e-05, + "loss": 3.3715, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556367653041906e-05, + "loss": 3.3663, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2547981705531384e-05, + "loss": 3.3899, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539595758020864e-05, + "loss": 3.3744, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531209810510344e-05, + "loss": 3.3879, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2522840241803555e-05, + "loss": 3.3641, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8621857166290283, + "eval_runtime": 307.8123, + "eval_samples_per_second": 1239.687, + "eval_steps_per_second": 38.741, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514454294293035e-05, + "loss": 3.369, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506068346782515e-05, + "loss": 3.3571, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497682399271995e-05, + "loss": 3.3712, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489312830565207e-05, + "loss": 3.381, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2480926883054687e-05, + "loss": 3.3809, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472540935544166e-05, + "loss": 3.3746, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464154988033647e-05, + "loss": 3.3696, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455769040523127e-05, + "loss": 3.3673, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447399471816338e-05, + "loss": 3.3638, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439013524305818e-05, + "loss": 3.3711, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430627576795298e-05, + "loss": 3.3728, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422241629284778e-05, + "loss": 3.3783, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2413855681774258e-05, + "loss": 3.3815, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2405486113067469e-05, + "loss": 3.3631, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397100165556949e-05, + "loss": 3.3682, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388714218046429e-05, + "loss": 3.3531, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380328270535909e-05, + "loss": 3.3664, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371942323025389e-05, + "loss": 3.3669, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363556375514868e-05, + "loss": 3.3689, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355170428004348e-05, + "loss": 3.3617, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2346784480493828e-05, + "loss": 3.3839, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338431290590772e-05, + "loss": 3.3745, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330045343080252e-05, + "loss": 3.3776, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.232165939556973e-05, + "loss": 3.3712, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313273448059212e-05, + "loss": 3.3824, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304887500548692e-05, + "loss": 3.3645, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.229650155303817e-05, + "loss": 3.3681, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.228811560552765e-05, + "loss": 3.3803, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279729658017131e-05, + "loss": 3.3634, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271360089310342e-05, + "loss": 3.3588, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.226297414179982e-05, + "loss": 3.3658, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254604573093033e-05, + "loss": 3.3683, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246218625582513e-05, + "loss": 3.3767, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2237832678071993e-05, + "loss": 3.3721, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229446730561473e-05, + "loss": 3.3662, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221060783050953e-05, + "loss": 3.3709, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212691214344164e-05, + "loss": 3.3765, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204305266833644e-05, + "loss": 3.3571, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2195919319323123e-05, + "loss": 3.3661, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187533371812603e-05, + "loss": 3.3596, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179163803105814e-05, + "loss": 3.359, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170777855595294e-05, + "loss": 3.3728, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162391908084774e-05, + "loss": 3.3781, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154005960574256e-05, + "loss": 3.3686, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145620013063734e-05, + "loss": 3.372, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137234065553214e-05, + "loss": 3.3717, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2128864496846426e-05, + "loss": 3.3655, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2120478549335905e-05, + "loss": 3.3728, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112092601825385e-05, + "loss": 3.3466, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103706654314866e-05, + "loss": 3.3762, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095337085608077e-05, + "loss": 3.3709, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2086951138097555e-05, + "loss": 3.3736, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078565190587037e-05, + "loss": 3.3632, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070179243076517e-05, + "loss": 3.362, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2061809674369728e-05, + "loss": 3.3547, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053423726859208e-05, + "loss": 3.3576, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045037779348688e-05, + "loss": 3.3695, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036651831838168e-05, + "loss": 3.3558, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028265884327648e-05, + "loss": 3.3824, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2019879936817128e-05, + "loss": 3.3661, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011493989306608e-05, + "loss": 3.359, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003108041796086e-05, + "loss": 3.3665, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994738473089298e-05, + "loss": 3.3552, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986352525578778e-05, + "loss": 3.3606, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1977966578068258e-05, + "loss": 3.3606, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969597009361469e-05, + "loss": 3.3715, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961211061850949e-05, + "loss": 3.3528, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952825114340429e-05, + "loss": 3.3643, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.194443916682991e-05, + "loss": 3.353, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936053219319389e-05, + "loss": 3.3611, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927667271808869e-05, + "loss": 3.3701, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919297703102081e-05, + "loss": 3.3673, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.191091175559156e-05, + "loss": 3.3708, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.190252580808104e-05, + "loss": 3.3684, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894139860570521e-05, + "loss": 3.3793, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885753913060001e-05, + "loss": 3.3636, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.187736796554948e-05, + "loss": 3.3689, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1868998396842692e-05, + "loss": 3.3598, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860612449332172e-05, + "loss": 3.3582, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.185222650182165e-05, + "loss": 3.368, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1843840554311132e-05, + "loss": 3.3651, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835454606800612e-05, + "loss": 3.3756, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827085038093822e-05, + "loss": 3.376, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818699090583302e-05, + "loss": 3.3616, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810313143072782e-05, + "loss": 3.3493, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801927195562262e-05, + "loss": 3.3632, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793557626855475e-05, + "loss": 3.3644, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785171679344953e-05, + "loss": 3.3667, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1776785731834433e-05, + "loss": 3.3677, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768399784323913e-05, + "loss": 3.3675, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760013836813393e-05, + "loss": 3.3632, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751627889302873e-05, + "loss": 3.3575, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743241941792353e-05, + "loss": 3.3632, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1734855994281833e-05, + "loss": 3.366, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1726486425575044e-05, + "loss": 3.3717, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718100478064523e-05, + "loss": 3.3679, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1709714530554005e-05, + "loss": 3.3609, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701328583043483e-05, + "loss": 3.3578, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1692959014336694e-05, + "loss": 3.3732, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1684573066826176e-05, + "loss": 3.3705, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676187119315656e-05, + "loss": 3.3623, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1667801171805134e-05, + "loss": 3.366, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1659415224294614e-05, + "loss": 3.3573, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651045655587827e-05, + "loss": 3.3677, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1642659708077305e-05, + "loss": 3.3655, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634273760566786e-05, + "loss": 3.3591, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1625887813056266e-05, + "loss": 3.3642, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1617518244349477e-05, + "loss": 3.3611, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609132296838957e-05, + "loss": 3.3725, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1600746349328437e-05, + "loss": 3.3507, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592360401817917e-05, + "loss": 3.3661, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1583974454307395e-05, + "loss": 3.3534, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1575604885600608e-05, + "loss": 3.3778, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567218938090088e-05, + "loss": 3.359, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1558832990579568e-05, + "loss": 3.3633, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1550447043069048e-05, + "loss": 3.3732, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542061095558528e-05, + "loss": 3.3768, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533675148048008e-05, + "loss": 3.3608, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525289200537488e-05, + "loss": 3.3594, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516919631830698e-05, + "loss": 3.3727, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508533684320178e-05, + "loss": 3.3667, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.150014773680966e-05, + "loss": 3.3538, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1491761789299138e-05, + "loss": 3.3604, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483375841788618e-05, + "loss": 3.3616, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1474989894278098e-05, + "loss": 3.3679, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466620325571309e-05, + "loss": 3.3645, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458234378060789e-05, + "loss": 3.3557, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449848430550269e-05, + "loss": 3.3643, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.144146248303975e-05, + "loss": 3.357, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433076535529229e-05, + "loss": 3.3663, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424690588018709e-05, + "loss": 3.3691, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416304640508189e-05, + "loss": 3.3692, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.14079350718014e-05, + "loss": 3.3582, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.139954912429088e-05, + "loss": 3.3628, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391163176780361e-05, + "loss": 3.3707, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1382777229269841e-05, + "loss": 3.3632, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.137439128175932e-05, + "loss": 3.3632, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366021713052532e-05, + "loss": 3.3555, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1357635765542012e-05, + "loss": 3.3829, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.134924981803149e-05, + "loss": 3.3658, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1340863870520972e-05, + "loss": 3.3735, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1332477923010452e-05, + "loss": 3.3649, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324091975499931e-05, + "loss": 3.3736, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131570602798941e-05, + "loss": 3.3639, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1307336459282622e-05, + "loss": 3.3556, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1298950511772102e-05, + "loss": 3.3799, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129056456426158e-05, + "loss": 3.3646, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1282178616751062e-05, + "loss": 3.3775, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1273809048044273e-05, + "loss": 3.3563, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.862339973449707, + "eval_runtime": 305.2942, + "eval_samples_per_second": 1249.912, + "eval_steps_per_second": 39.061, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1265423100533753e-05, + "loss": 3.3345, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257053531826964e-05, + "loss": 3.3504, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1248667584316444e-05, + "loss": 3.3605, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1240281636805924e-05, + "loss": 3.3716, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1231895689295405e-05, + "loss": 3.3685, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1223509741784883e-05, + "loss": 3.3664, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1215140173078096e-05, + "loss": 3.3592, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1206754225567576e-05, + "loss": 3.3583, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198368278057054e-05, + "loss": 3.3582, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1189982330546534e-05, + "loss": 3.3616, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1181596383036016e-05, + "loss": 3.3607, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173210435525496e-05, + "loss": 3.3677, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1164824488014974e-05, + "loss": 3.3732, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1156454919308186e-05, + "loss": 3.3515, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148068971797666e-05, + "loss": 3.3584, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1139683024287145e-05, + "loss": 3.3453, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131297076776626e-05, + "loss": 3.3589, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1122927508069837e-05, + "loss": 3.3564, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114541560559317e-05, + "loss": 3.3594, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106155613048797e-05, + "loss": 3.3555, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1097769665538277e-05, + "loss": 3.3742, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089400096831488e-05, + "loss": 3.3664, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.108101414932097e-05, + "loss": 3.3633, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1072628201810448e-05, + "loss": 3.3632, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064242254299928e-05, + "loss": 3.3744, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.105587268559314e-05, + "loss": 3.3533, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1047486738082618e-05, + "loss": 3.3566, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039100790572098e-05, + "loss": 3.3718, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.103071484306158e-05, + "loss": 3.3513, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.102234527435479e-05, + "loss": 3.3477, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1013959326844269e-05, + "loss": 3.3571, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.100557337933375e-05, + "loss": 3.36, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.099718743182323e-05, + "loss": 3.3668, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0988801484312709e-05, + "loss": 3.3639, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980415536802189e-05, + "loss": 3.361, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.097202958929167e-05, + "loss": 3.3622, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963643641781149e-05, + "loss": 3.3639, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0955290451878092e-05, + "loss": 3.3499, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0946904504367572e-05, + "loss": 3.3616, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0938518556857052e-05, + "loss": 3.3455, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930132609346532e-05, + "loss": 3.3541, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0921746661836012e-05, + "loss": 3.3596, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0913377093129223e-05, + "loss": 3.3704, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0904991145618704e-05, + "loss": 3.3626, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0896605198108183e-05, + "loss": 3.3587, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888219250597663e-05, + "loss": 3.3639, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0879833303087143e-05, + "loss": 3.3578, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0871463734380355e-05, + "loss": 3.3664, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863077786869833e-05, + "loss": 3.3371, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0854691839359315e-05, + "loss": 3.3624, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846305891848795e-05, + "loss": 3.3631, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0837919944338273e-05, + "loss": 3.3656, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0829533996827753e-05, + "loss": 3.3547, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0821148049317235e-05, + "loss": 3.3513, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0812778480610446e-05, + "loss": 3.3418, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0804392533099924e-05, + "loss": 3.3455, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796006585589405e-05, + "loss": 3.3645, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0787620638078885e-05, + "loss": 3.3487, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779251069372096e-05, + "loss": 3.3659, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0770865121861576e-05, + "loss": 3.3581, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0762479174351056e-05, + "loss": 3.35, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754093226840536e-05, + "loss": 3.3596, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0745723658133747e-05, + "loss": 3.3458, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737337710623227e-05, + "loss": 3.351, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0728951763112707e-05, + "loss": 3.3487, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720565815602187e-05, + "loss": 3.3644, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712179868091667e-05, + "loss": 3.3433, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703810299384877e-05, + "loss": 3.3503, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695424351874359e-05, + "loss": 3.3437, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687038404363837e-05, + "loss": 3.3536, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0678652456853317e-05, + "loss": 3.3614, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670266509342797e-05, + "loss": 3.3616, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0661880561832277e-05, + "loss": 3.3585, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0653510993125488e-05, + "loss": 3.3628, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.064512504561497e-05, + "loss": 3.3686, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.063673909810445e-05, + "loss": 3.3547, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0628353150593928e-05, + "loss": 3.3568, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0619967203083408e-05, + "loss": 3.3529, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061159763437662e-05, + "loss": 3.349, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.06032116868661e-05, + "loss": 3.359, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.059482573935558e-05, + "loss": 3.3552, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.058643979184506e-05, + "loss": 3.3677, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.057805384433454e-05, + "loss": 3.3651, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0569667896824018e-05, + "loss": 3.3536, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.05612819493135e-05, + "loss": 3.3382, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.055289600180298e-05, + "loss": 3.3511, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0544542811899923e-05, + "loss": 3.3576, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0536156864389402e-05, + "loss": 3.3586, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0527770916878882e-05, + "loss": 3.3568, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0519384969368362e-05, + "loss": 3.3621, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0510999021857841e-05, + "loss": 3.3536, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502613074347321e-05, + "loss": 3.345, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494227126836801e-05, + "loss": 3.3528, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0485841179326281e-05, + "loss": 3.359, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0477471610619492e-05, + "loss": 3.3614, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469085663108972e-05, + "loss": 3.3624, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0460699715598454e-05, + "loss": 3.3483, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452313768087932e-05, + "loss": 3.3522, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0443927820577412e-05, + "loss": 3.3611, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435558251870624e-05, + "loss": 3.3617, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427172304360104e-05, + "loss": 3.3566, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0418786356849583e-05, + "loss": 3.3494, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0410400409339063e-05, + "loss": 3.3492, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402030840632275e-05, + "loss": 3.3598, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0393644893121755e-05, + "loss": 3.3572, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0385258945611235e-05, + "loss": 3.3459, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0376872998100715e-05, + "loss": 3.352, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0368487050590195e-05, + "loss": 3.3547, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360101103079673e-05, + "loss": 3.357, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0351731534372886e-05, + "loss": 3.3458, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0343345586862366e-05, + "loss": 3.3602, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0334959639351844e-05, + "loss": 3.34, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326573691841326e-05, + "loss": 3.3692, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0318187744330806e-05, + "loss": 3.3475, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0309801796820285e-05, + "loss": 3.3566, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0301415849309764e-05, + "loss": 3.362, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293029901799245e-05, + "loss": 3.3697, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0284660333092456e-05, + "loss": 3.3492, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0276274385581936e-05, + "loss": 3.352, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0267904816875147e-05, + "loss": 3.3583, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0259518869364627e-05, + "loss": 3.3564, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251132921854109e-05, + "loss": 3.3474, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0242746974343587e-05, + "loss": 3.3525, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0234361026833067e-05, + "loss": 3.3531, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0225975079322547e-05, + "loss": 3.3606, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0217589131812027e-05, + "loss": 3.3493, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209203184301507e-05, + "loss": 3.3478, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0200833615594717e-05, + "loss": 3.3532, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0192447668084199e-05, + "loss": 3.3505, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184061720573677e-05, + "loss": 3.3502, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0175675773063157e-05, + "loss": 3.3613, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.01673225831601e-05, + "loss": 3.3655, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.015893663564958e-05, + "loss": 3.3448, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.015055068813906e-05, + "loss": 3.3517, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.014216474062854e-05, + "loss": 3.3611, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.013377879311802e-05, + "loss": 3.3557, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125409224411233e-05, + "loss": 3.3568, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117023276900711e-05, + "loss": 3.3474, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0108637329390191e-05, + "loss": 3.3689, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100251381879671e-05, + "loss": 3.3563, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0091865434369151e-05, + "loss": 3.3648, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0083479486858631e-05, + "loss": 3.3537, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075093539348111e-05, + "loss": 3.3667, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0066707591837591e-05, + "loss": 3.3532, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0058354401934533e-05, + "loss": 3.3444, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0049968454424014e-05, + "loss": 3.3708, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0041582506913494e-05, + "loss": 3.3544, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033196559402972e-05, + "loss": 3.3656, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0024826990696185e-05, + "loss": 3.3485, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0016441043185665e-05, + "loss": 3.3489, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.862997531890869, + "eval_runtime": 310.1513, + "eval_samples_per_second": 1230.338, + "eval_steps_per_second": 38.449, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008055095675145e-05, + "loss": 3.341, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.999669148164625e-06, + "loss": 3.3465, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.991299579457836e-06, + "loss": 3.3613, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.982913631947315e-06, + "loss": 3.358, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.974527684436797e-06, + "loss": 3.3606, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966141736926275e-06, + "loss": 3.3491, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.957755789415755e-06, + "loss": 3.3501, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.949386220708968e-06, + "loss": 3.3435, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.941000273198446e-06, + "loss": 3.356, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.932614325687926e-06, + "loss": 3.3506, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.924228378177406e-06, + "loss": 3.3649, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.915842430666888e-06, + "loss": 3.3649, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.907472861960097e-06, + "loss": 3.3448, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.899086914449578e-06, + "loss": 3.3451, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.890700966939058e-06, + "loss": 3.338, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.882315019428537e-06, + "loss": 3.3449, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.873945450721749e-06, + "loss": 3.3497, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.865559503211229e-06, + "loss": 3.3492, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857173555700709e-06, + "loss": 3.3455, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.848787608190187e-06, + "loss": 3.3647, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.8404180394834e-06, + "loss": 3.3568, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.83203209197288e-06, + "loss": 3.3558, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.82364614446236e-06, + "loss": 3.3545, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81526019695184e-06, + "loss": 3.367, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.80687424944132e-06, + "loss": 3.3429, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.7984883019308e-06, + "loss": 3.3487, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.79010235442028e-06, + "loss": 3.3629, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.78171640690976e-06, + "loss": 3.3391, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.77334683820297e-06, + "loss": 3.3431, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.76496089069245e-06, + "loss": 3.3435, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.756591321985661e-06, + "loss": 3.3549, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748205374475141e-06, + "loss": 3.3546, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.739819426964623e-06, + "loss": 3.3526, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.7314334794541e-06, + "loss": 3.3518, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.72304753194358e-06, + "loss": 3.3526, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.71466158443306e-06, + "loss": 3.352, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.706292015726273e-06, + "loss": 3.344, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.697906068215751e-06, + "loss": 3.3505, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.689520120705233e-06, + "loss": 3.3338, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681134173194713e-06, + "loss": 3.3481, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.672748225684191e-06, + "loss": 3.3472, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.664362278173671e-06, + "loss": 3.3612, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.655976330663153e-06, + "loss": 3.3523, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.647590383152631e-06, + "loss": 3.351, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.639220814445844e-06, + "loss": 3.3546, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.630851245739055e-06, + "loss": 3.3497, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.622465298228534e-06, + "loss": 3.3572, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614079350718014e-06, + "loss": 3.326, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.605693403207494e-06, + "loss": 3.3537, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.597323834500705e-06, + "loss": 3.3578, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.588937886990187e-06, + "loss": 3.3558, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.580551939479665e-06, + "loss": 3.3435, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572165991969145e-06, + "loss": 3.3421, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.563796423262358e-06, + "loss": 3.3353, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.555410475751837e-06, + "loss": 3.3353, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.547024528241316e-06, + "loss": 3.3556, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.538638580730796e-06, + "loss": 3.3377, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.530252633220277e-06, + "loss": 3.3559, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.521866685709756e-06, + "loss": 3.3501, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.513480738199236e-06, + "loss": 3.3381, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.505094790688717e-06, + "loss": 3.3472, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.496741600785659e-06, + "loss": 3.3385, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.488355653275139e-06, + "loss": 3.3417, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.479969705764619e-06, + "loss": 3.3389, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.471583758254099e-06, + "loss": 3.3566, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.463197810743579e-06, + "loss": 3.3344, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.454811863233059e-06, + "loss": 3.3405, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.44644229452627e-06, + "loss": 3.3341, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.43805634701575e-06, + "loss": 3.344, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.42967039950523e-06, + "loss": 3.3461, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.42128445199471e-06, + "loss": 3.3532, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.41289850448419e-06, + "loss": 3.3466, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.404528935777402e-06, + "loss": 3.3532, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.39614298826688e-06, + "loss": 3.359, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.38775704075636e-06, + "loss": 3.3453, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.379371093245842e-06, + "loss": 3.3475, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.37098514573532e-06, + "loss": 3.3419, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.3625991982248e-06, + "loss": 3.3443, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.354229629518012e-06, + "loss": 3.3497, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.345843682007492e-06, + "loss": 3.3396, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.33745773449697e-06, + "loss": 3.3609, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329071786986452e-06, + "loss": 3.3583, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.320685839475932e-06, + "loss": 3.3421, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.31229989196541e-06, + "loss": 3.3299, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.303930323258623e-06, + "loss": 3.3412, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.295544375748103e-06, + "loss": 3.3469, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287158428237583e-06, + "loss": 3.3529, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.278772480727061e-06, + "loss": 3.3464, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.270386533216543e-06, + "loss": 3.3545, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262000585706023e-06, + "loss": 3.348, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.253631016999233e-06, + "loss": 3.3346, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.245245069488713e-06, + "loss": 3.341, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.236859121978193e-06, + "loss": 3.3509, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.228473174467673e-06, + "loss": 3.3499, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220103605760884e-06, + "loss": 3.3568, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.211717658250364e-06, + "loss": 3.3383, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.203331710739844e-06, + "loss": 3.3429, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.194945763229324e-06, + "loss": 3.3532, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.186559815718804e-06, + "loss": 3.3531, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.178173868208284e-06, + "loss": 3.3424, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.169787920697764e-06, + "loss": 3.3454, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.161401973187244e-06, + "loss": 3.3386, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153032404480455e-06, + "loss": 3.3464, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.144646456969935e-06, + "loss": 3.3507, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.136260509459414e-06, + "loss": 3.334, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.127874561948894e-06, + "loss": 3.3422, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.119488614438374e-06, + "loss": 3.3489, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.111102666927854e-06, + "loss": 3.3485, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.102733098221065e-06, + "loss": 3.3304, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.094347150710545e-06, + "loss": 3.3515, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.085961203200027e-06, + "loss": 3.3336, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.077575255689505e-06, + "loss": 3.3639, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.069205686982716e-06, + "loss": 3.3354, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.060819739472197e-06, + "loss": 3.3473, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.052433791961677e-06, + "loss": 3.3499, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044047844451156e-06, + "loss": 3.3614, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.035661896940637e-06, + "loss": 3.3422, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.027292328233848e-06, + "loss": 3.3431, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.018906380723326e-06, + "loss": 3.3484, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.010520433212808e-06, + "loss": 3.3428, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002134485702288e-06, + "loss": 3.3394, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.993748538191768e-06, + "loss": 3.3429, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.985378969484979e-06, + "loss": 3.3395, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.976993021974459e-06, + "loss": 3.3571, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.968607074463939e-06, + "loss": 3.3361, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.960221126953419e-06, + "loss": 3.341, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.951835179442899e-06, + "loss": 3.3416, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.943449231932378e-06, + "loss": 3.3436, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.935063284421858e-06, + "loss": 3.3403, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.92669371571507e-06, + "loss": 3.3555, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.91830776820455e-06, + "loss": 3.3539, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.909938199497762e-06, + "loss": 3.3444, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.901552251987242e-06, + "loss": 3.337, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.89316630447672e-06, + "loss": 3.3464, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.8847803569662e-06, + "loss": 3.3489, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.876394409455681e-06, + "loss": 3.3486, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.86802484074889e-06, + "loss": 3.3371, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.859638893238372e-06, + "loss": 3.3587, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.851252945727852e-06, + "loss": 3.3458, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.842866998217332e-06, + "loss": 3.3576, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.83448105070681e-06, + "loss": 3.3432, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826095103196292e-06, + "loss": 3.3585, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.817709155685772e-06, + "loss": 3.3475, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.809339586978981e-06, + "loss": 3.328, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.800953639468463e-06, + "loss": 3.3635, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.792567691957943e-06, + "loss": 3.3477, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.784181744447423e-06, + "loss": 3.3542, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.775812175740633e-06, + "loss": 3.3427, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.767426228230113e-06, + "loss": 3.3375, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8639118671417236, + "eval_runtime": 310.9275, + "eval_samples_per_second": 1227.267, + "eval_steps_per_second": 38.353, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.759056659523326e-06, + "loss": 3.3318, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.750670712012806e-06, + "loss": 3.3397, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.742284764502284e-06, + "loss": 3.3555, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.733898816991764e-06, + "loss": 3.3424, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.725512869481246e-06, + "loss": 3.354, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.717126921970724e-06, + "loss": 3.3432, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.708740974460204e-06, + "loss": 3.3406, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.700371405753416e-06, + "loss": 3.3359, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.691985458242896e-06, + "loss": 3.3447, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.683599510732375e-06, + "loss": 3.3404, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.675213563221855e-06, + "loss": 3.354, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.666827615711336e-06, + "loss": 3.3529, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.658441668200815e-06, + "loss": 3.3389, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.650072099494027e-06, + "loss": 3.3333, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.641686151983507e-06, + "loss": 3.3314, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.633300204472987e-06, + "loss": 3.3323, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.624914256962465e-06, + "loss": 3.3421, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.616528309451947e-06, + "loss": 3.3413, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.608142361941427e-06, + "loss": 3.3328, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.599756414430905e-06, + "loss": 3.3572, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.591386845724118e-06, + "loss": 3.3481, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.583000898213597e-06, + "loss": 3.3453, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.574614950703077e-06, + "loss": 3.3467, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.566229003192557e-06, + "loss": 3.3596, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.557843055682037e-06, + "loss": 3.3309, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.549457108171517e-06, + "loss": 3.341, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.541071160660996e-06, + "loss": 3.3486, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.532685213150477e-06, + "loss": 3.3365, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.524315644443688e-06, + "loss": 3.3315, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.515929696933166e-06, + "loss": 3.3332, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.507543749422648e-06, + "loss": 3.3459, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.499157801912128e-06, + "loss": 3.3444, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.490771854401608e-06, + "loss": 3.3443, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.482385906891086e-06, + "loss": 3.3427, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.473999959380568e-06, + "loss": 3.3435, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.465630390673779e-06, + "loss": 3.3418, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.457244443163258e-06, + "loss": 3.3378, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.448858495652738e-06, + "loss": 3.3418, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.440472548142218e-06, + "loss": 3.3269, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.432086600631698e-06, + "loss": 3.3347, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.423717031924909e-06, + "loss": 3.3376, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.415331084414389e-06, + "loss": 3.3549, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.406945136903869e-06, + "loss": 3.3401, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.398559189393349e-06, + "loss": 3.3454, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.390173241882829e-06, + "loss": 3.3425, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.38180367317604e-06, + "loss": 3.3426, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.373417725665521e-06, + "loss": 3.3481, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.365031778155e-06, + "loss": 3.3194, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.35664583064448e-06, + "loss": 3.3368, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.348276261937692e-06, + "loss": 3.3519, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.339890314427172e-06, + "loss": 3.3445, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.33150436691665e-06, + "loss": 3.335, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.323118419406132e-06, + "loss": 3.3294, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.314748850699343e-06, + "loss": 3.333, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.306362903188821e-06, + "loss": 3.323, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.297976955678303e-06, + "loss": 3.347, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.289591008167783e-06, + "loss": 3.3294, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.281205060657263e-06, + "loss": 3.3479, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.272819113146743e-06, + "loss": 3.3397, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.264433165636222e-06, + "loss": 3.3309, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.256047218125702e-06, + "loss": 3.3364, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.247677649418913e-06, + "loss": 3.3307, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.239308080712124e-06, + "loss": 3.3333, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.230922133201604e-06, + "loss": 3.3298, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.222536185691086e-06, + "loss": 3.3479, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.214150238180564e-06, + "loss": 3.3251, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.205780669473775e-06, + "loss": 3.3302, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.197394721963256e-06, + "loss": 3.3245, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.189008774452736e-06, + "loss": 3.3337, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.180622826942215e-06, + "loss": 3.3437, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.172253258235427e-06, + "loss": 3.3387, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.163867310724907e-06, + "loss": 3.3385, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.155481363214385e-06, + "loss": 3.3446, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.147095415703867e-06, + "loss": 3.3494, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.138709468193347e-06, + "loss": 3.3369, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.130323520682827e-06, + "loss": 3.3361, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.121953951976038e-06, + "loss": 3.3336, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.113568004465518e-06, + "loss": 3.3367, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.105182056954998e-06, + "loss": 3.3375, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.096796109444477e-06, + "loss": 3.3348, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.088426540737688e-06, + "loss": 3.3499, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.080040593227168e-06, + "loss": 3.3442, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.071654645716648e-06, + "loss": 3.3355, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.063268698206128e-06, + "loss": 3.322, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.054882750695608e-06, + "loss": 3.3293, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.046496803185088e-06, + "loss": 3.3433, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.0381272344783e-06, + "loss": 3.3425, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.029741286967779e-06, + "loss": 3.3415, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.021355339457259e-06, + "loss": 3.3381, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.01296939194674e-06, + "loss": 3.3415, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.00459982323995e-06, + "loss": 3.3274, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.99621387572943e-06, + "loss": 3.3299, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.987827928218911e-06, + "loss": 3.3425, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.979441980708391e-06, + "loss": 3.3368, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.971072412001602e-06, + "loss": 3.3433, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.962686464491082e-06, + "loss": 3.3352, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.954300516980562e-06, + "loss": 3.33, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.94591456947004e-06, + "loss": 3.3449, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.937528621959522e-06, + "loss": 3.3455, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.929142674449002e-06, + "loss": 3.3347, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.92075672693848e-06, + "loss": 3.3357, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.91237077942796e-06, + "loss": 3.3267, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.904001210721172e-06, + "loss": 3.3392, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.895615263210652e-06, + "loss": 3.342, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.887229315700132e-06, + "loss": 3.3275, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.878843368189612e-06, + "loss": 3.3341, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.870457420679092e-06, + "loss": 3.3358, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.862087851972303e-06, + "loss": 3.3416, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.853701904461783e-06, + "loss": 3.3225, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.845315956951263e-06, + "loss": 3.3396, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.836930009440743e-06, + "loss": 3.3268, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.828560440733954e-06, + "loss": 3.3464, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.820174493223434e-06, + "loss": 3.331, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.811788545712913e-06, + "loss": 3.3349, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.803402598202395e-06, + "loss": 3.3469, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.795033029495604e-06, + "loss": 3.3489, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.786647081985086e-06, + "loss": 3.3361, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.778261134474566e-06, + "loss": 3.3311, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.769875186964044e-06, + "loss": 3.3409, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.761489239453524e-06, + "loss": 3.3372, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.753103291943006e-06, + "loss": 3.3307, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.744733723236217e-06, + "loss": 3.3336, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.736347775725695e-06, + "loss": 3.3321, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.727961828215176e-06, + "loss": 3.3464, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.719575880704656e-06, + "loss": 3.3244, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.711189933194135e-06, + "loss": 3.3341, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.702803985683615e-06, + "loss": 3.3331, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.694434416976827e-06, + "loss": 3.3332, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.686048469466307e-06, + "loss": 3.3298, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.677662521955787e-06, + "loss": 3.3476, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.669276574445267e-06, + "loss": 3.3455, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.660907005738478e-06, + "loss": 3.3354, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.65252105822796e-06, + "loss": 3.3279, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.644135110717438e-06, + "loss": 3.3372, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.635749163206918e-06, + "loss": 3.3387, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.627363215696398e-06, + "loss": 3.3443, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.618993646989608e-06, + "loss": 3.3234, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.610607699479088e-06, + "loss": 3.3504, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.602221751968569e-06, + "loss": 3.3355, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.593835804458049e-06, + "loss": 3.348, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.585449856947528e-06, + "loss": 3.3366, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.577063909437009e-06, + "loss": 3.3464, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.568677961926489e-06, + "loss": 3.339, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.560308393219699e-06, + "loss": 3.3264, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.55192244570918e-06, + "loss": 3.3497, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.54353649819866e-06, + "loss": 3.3428, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.5351505506881404e-06, + "loss": 3.3421, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.52678098198135e-06, + "loss": 3.3312, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.51839503447083e-06, + "loss": 3.329, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.864245891571045, + "eval_runtime": 316.4561, + "eval_samples_per_second": 1205.826, + "eval_steps_per_second": 37.683, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.510009086960311e-06, + "loss": 3.3251, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.50162313944979e-06, + "loss": 3.3287, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.49323719193927e-06, + "loss": 3.3444, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.48485124442875e-06, + "loss": 3.3365, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.476465296918231e-06, + "loss": 3.3462, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.468095728211441e-06, + "loss": 3.3302, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.459709780700922e-06, + "loss": 3.3319, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.451323833190402e-06, + "loss": 3.3286, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.442937885679881e-06, + "loss": 3.3329, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.434551938169361e-06, + "loss": 3.336, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.4261659906588415e-06, + "loss": 3.3372, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.4177800431483215e-06, + "loss": 3.3444, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.409410474441532e-06, + "loss": 3.3311, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.401024526931012e-06, + "loss": 3.3246, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.392638579420492e-06, + "loss": 3.3268, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.384252631909971e-06, + "loss": 3.319, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.375883063203183e-06, + "loss": 3.3298, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.367497115692664e-06, + "loss": 3.3312, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.359111168182144e-06, + "loss": 3.3251, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.350725220671623e-06, + "loss": 3.353, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.3423556519648344e-06, + "loss": 3.3365, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.333969704454314e-06, + "loss": 3.3382, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.3255837569437935e-06, + "loss": 3.3378, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.3171978094332734e-06, + "loss": 3.3484, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.308811861922754e-06, + "loss": 3.3214, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.300442293215966e-06, + "loss": 3.3338, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.292056345705445e-06, + "loss": 3.3389, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.283670398194925e-06, + "loss": 3.3286, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.275284450684406e-06, + "loss": 3.3248, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.266898503173884e-06, + "loss": 3.3205, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.258528934467096e-06, + "loss": 3.3388, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.2501429869565765e-06, + "loss": 3.3355, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.241757039446056e-06, + "loss": 3.3316, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.2333710919355355e-06, + "loss": 3.3391, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.2249851444250155e-06, + "loss": 3.3312, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.216599196914496e-06, + "loss": 3.3308, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.208229628207708e-06, + "loss": 3.3267, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.199843680697187e-06, + "loss": 3.3363, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.191457733186667e-06, + "loss": 3.3139, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.183071785676147e-06, + "loss": 3.3266, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.174685838165626e-06, + "loss": 3.3305, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.166299890655107e-06, + "loss": 3.343, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.157913943144587e-06, + "loss": 3.3327, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.149527995634066e-06, + "loss": 3.3324, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.1411584269272776e-06, + "loss": 3.338, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.1327724794167575e-06, + "loss": 3.3296, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.124386531906238e-06, + "loss": 3.3405, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.1160005843957166e-06, + "loss": 3.3108, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.107614636885197e-06, + "loss": 3.3339, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.099245068178409e-06, + "loss": 3.3361, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.090859120667889e-06, + "loss": 3.3383, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.082473173157368e-06, + "loss": 3.3257, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.074087225646849e-06, + "loss": 3.3173, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.0657176569400605e-06, + "loss": 3.3254, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.057331709429539e-06, + "loss": 3.3124, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.04894576191902e-06, + "loss": 3.3405, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.0405598144084995e-06, + "loss": 3.3233, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.03217386689798e-06, + "loss": 3.3326, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.023787919387459e-06, + "loss": 3.3318, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.015401971876939e-06, + "loss": 3.3218, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.007016024366419e-06, + "loss": 3.3271, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.99864645565963e-06, + "loss": 3.3205, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.990276886952842e-06, + "loss": 3.3255, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.981890939442322e-06, + "loss": 3.3179, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.9735049919318025e-06, + "loss": 3.3376, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.965119044421281e-06, + "loss": 3.3211, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.9567494757144924e-06, + "loss": 3.3229, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.948363528203973e-06, + "loss": 3.3153, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.939977580693453e-06, + "loss": 3.324, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.931591633182932e-06, + "loss": 3.3325, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.923222064476144e-06, + "loss": 3.3345, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.914836116965624e-06, + "loss": 3.3276, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.906450169455103e-06, + "loss": 3.3355, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.898064221944584e-06, + "loss": 3.3417, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.889678274434064e-06, + "loss": 3.3309, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.881308705727275e-06, + "loss": 3.3194, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.8729227582167545e-06, + "loss": 3.3319, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.8645368107062345e-06, + "loss": 3.3269, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.856150863195715e-06, + "loss": 3.3285, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.847781294488927e-06, + "loss": 3.3261, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.839395346978405e-06, + "loss": 3.3363, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.831009399467886e-06, + "loss": 3.3409, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.822623451957366e-06, + "loss": 3.3253, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.814237504446845e-06, + "loss": 3.3115, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.805851556936326e-06, + "loss": 3.318, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.797465609425806e-06, + "loss": 3.331, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.7890960407190174e-06, + "loss": 3.3355, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.7807100932084965e-06, + "loss": 3.3288, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.7723241456979765e-06, + "loss": 3.3337, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.763938198187457e-06, + "loss": 3.3302, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.755568629480667e-06, + "loss": 3.3209, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.747182681970147e-06, + "loss": 3.3224, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.738796734459628e-06, + "loss": 3.3264, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.730410786949107e-06, + "loss": 3.3337, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.722024839438587e-06, + "loss": 3.3336, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.713655270731799e-06, + "loss": 3.3311, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.705269323221279e-06, + "loss": 3.3183, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.696883375710758e-06, + "loss": 3.3364, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.6884974282002386e-06, + "loss": 3.3374, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.6801114806897185e-06, + "loss": 3.3255, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.67174191198293e-06, + "loss": 3.3283, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.663355964472409e-06, + "loss": 3.3192, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.654970016961889e-06, + "loss": 3.3285, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.64658406945137e-06, + "loss": 3.3347, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.63821450074458e-06, + "loss": 3.316, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.629828553234061e-06, + "loss": 3.327, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.621442605723541e-06, + "loss": 3.3282, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.613056658213021e-06, + "loss": 3.3289, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.6046870895062315e-06, + "loss": 3.3154, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.5963011419957114e-06, + "loss": 3.3341, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.587915194485192e-06, + "loss": 3.3164, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.5795292469746705e-06, + "loss": 3.3396, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.571159678267882e-06, + "loss": 3.3229, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.562773730757363e-06, + "loss": 3.3208, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.554387783246843e-06, + "loss": 3.3364, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.546001835736322e-06, + "loss": 3.342, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.537615888225802e-06, + "loss": 3.328, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.529229940715283e-06, + "loss": 3.3225, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.520860372008494e-06, + "loss": 3.3288, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.5124744244979735e-06, + "loss": 3.3253, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.5040884769874535e-06, + "loss": 3.3248, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.495702529476934e-06, + "loss": 3.3279, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.4873165819664125e-06, + "loss": 3.3201, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.478930634455893e-06, + "loss": 3.3326, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.470561065749105e-06, + "loss": 3.3242, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.462175118238585e-06, + "loss": 3.3256, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.453789170728064e-06, + "loss": 3.3201, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.445403223217544e-06, + "loss": 3.3234, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.437017275707025e-06, + "loss": 3.32, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.428631328196504e-06, + "loss": 3.3383, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.4202617594897155e-06, + "loss": 3.3375, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.4118758119791955e-06, + "loss": 3.327, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.4034898644686755e-06, + "loss": 3.3181, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.3951039169581546e-06, + "loss": 3.331, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.386717969447635e-06, + "loss": 3.3294, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.378332021937115e-06, + "loss": 3.3319, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.369962453230325e-06, + "loss": 3.3196, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.361576505719806e-06, + "loss": 3.3346, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.353190558209286e-06, + "loss": 3.3322, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.344804610698767e-06, + "loss": 3.3403, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.336418663188246e-06, + "loss": 3.3304, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.328032715677726e-06, + "loss": 3.3335, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.3196631469709375e-06, + "loss": 3.3295, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.311277199460417e-06, + "loss": 3.316, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.302891251949897e-06, + "loss": 3.3383, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.294505304439377e-06, + "loss": 3.3397, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.286135735732589e-06, + "loss": 3.329, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.277749788222067e-06, + "loss": 3.3258, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.269363840711548e-06, + "loss": 3.3166, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.8645806312561035, + "eval_runtime": 316.8223, + "eval_samples_per_second": 1204.432, + "eval_steps_per_second": 37.639, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.260977893201028e-06, + "loss": 3.3148, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.252591945690507e-06, + "loss": 3.3189, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.244222376983719e-06, + "loss": 3.3326, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.235836429473199e-06, + "loss": 3.3261, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.227450481962679e-06, + "loss": 3.339, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.219064534452159e-06, + "loss": 3.3225, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.210678586941639e-06, + "loss": 3.3242, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.20230901823485e-06, + "loss": 3.3143, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.19392307072433e-06, + "loss": 3.3264, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.185537123213809e-06, + "loss": 3.3252, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.17715117570329e-06, + "loss": 3.3301, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.168765228192769e-06, + "loss": 3.3341, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.160395659485981e-06, + "loss": 3.3208, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.152009711975461e-06, + "loss": 3.3175, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.143623764464941e-06, + "loss": 3.3203, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.135237816954421e-06, + "loss": 3.3141, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.126868248247632e-06, + "loss": 3.319, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.118482300737112e-06, + "loss": 3.3211, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.1100963532265914e-06, + "loss": 3.3156, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.101710405716072e-06, + "loss": 3.3463, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.093340837009283e-06, + "loss": 3.3287, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.084954889498763e-06, + "loss": 3.329, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.076568941988243e-06, + "loss": 3.3304, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.068182994477723e-06, + "loss": 3.3347, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.059797046967203e-06, + "loss": 3.3146, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.051411099456682e-06, + "loss": 3.3241, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.043041530749894e-06, + "loss": 3.3304, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.0346555832393736e-06, + "loss": 3.3245, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.026269635728854e-06, + "loss": 3.3123, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.0178836882183335e-06, + "loss": 3.3126, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.009514119511545e-06, + "loss": 3.328, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.001128172001025e-06, + "loss": 3.3268, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.992742224490505e-06, + "loss": 3.327, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.984356276979985e-06, + "loss": 3.3273, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.975970329469464e-06, + "loss": 3.3208, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.967600760762676e-06, + "loss": 3.324, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.959214813252156e-06, + "loss": 3.3154, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.950828865741636e-06, + "loss": 3.3294, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.942442918231116e-06, + "loss": 3.308, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.9340569707205955e-06, + "loss": 3.3174, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.925687402013807e-06, + "loss": 3.3193, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.917301454503287e-06, + "loss": 3.3357, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.908915506992767e-06, + "loss": 3.3263, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.900529559482246e-06, + "loss": 3.3225, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.892143611971727e-06, + "loss": 3.3282, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.883774043264938e-06, + "loss": 3.3243, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.875388095754418e-06, + "loss": 3.3315, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.867002148243898e-06, + "loss": 3.3043, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.858616200733378e-06, + "loss": 3.3195, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.850246632026589e-06, + "loss": 3.3315, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.841860684516069e-06, + "loss": 3.3277, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.833474737005549e-06, + "loss": 3.316, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.825088789495028e-06, + "loss": 3.3118, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.816702841984509e-06, + "loss": 3.3191, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.80833327327772e-06, + "loss": 3.3043, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.7999473257672e-06, + "loss": 3.3269, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.79156137825668e-06, + "loss": 3.3128, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.783175430746159e-06, + "loss": 3.3256, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.77478948323564e-06, + "loss": 3.3256, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.766403535725119e-06, + "loss": 3.3138, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.7580175882146e-06, + "loss": 3.3153, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.7496480195078104e-06, + "loss": 3.3116, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.741278450801022e-06, + "loss": 3.3149, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.732892503290502e-06, + "loss": 3.3148, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.724506555779982e-06, + "loss": 3.3234, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.716120608269462e-06, + "loss": 3.3144, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.707734660758941e-06, + "loss": 3.314, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.699365092052153e-06, + "loss": 3.3045, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.690979144541633e-06, + "loss": 3.3146, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.682593197031113e-06, + "loss": 3.3185, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.6742072495205925e-06, + "loss": 3.33, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.665837680813804e-06, + "loss": 3.3171, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.657451733303284e-06, + "loss": 3.3281, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.649065785792764e-06, + "loss": 3.3302, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.640679838282244e-06, + "loss": 3.3297, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.632293890771723e-06, + "loss": 3.306, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.623924322064935e-06, + "loss": 3.3257, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.615538374554415e-06, + "loss": 3.322, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.607152427043895e-06, + "loss": 3.3122, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.598766479533375e-06, + "loss": 3.3247, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.590396910826586e-06, + "loss": 3.3233, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.582010963316065e-06, + "loss": 3.3319, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.573625015805546e-06, + "loss": 3.3183, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.565239068295026e-06, + "loss": 3.3036, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.556853120784505e-06, + "loss": 3.313, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.548467173273986e-06, + "loss": 3.3179, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.540097604567197e-06, + "loss": 3.3249, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.531711657056677e-06, + "loss": 3.3241, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.523325709546157e-06, + "loss": 3.3225, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.514939762035637e-06, + "loss": 3.3225, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.5065701933288475e-06, + "loss": 3.31, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.498184245818328e-06, + "loss": 3.3151, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.4897982983078074e-06, + "loss": 3.3158, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.481412350797287e-06, + "loss": 3.3243, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.473026403286767e-06, + "loss": 3.3218, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.464656834579979e-06, + "loss": 3.3303, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.456270887069459e-06, + "loss": 3.3049, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.447884939558939e-06, + "loss": 3.3272, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.439498992048419e-06, + "loss": 3.3269, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.43112942334163e-06, + "loss": 3.3207, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.4227434758311105e-06, + "loss": 3.3182, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.4143575283205896e-06, + "loss": 3.312, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.4059715808100695e-06, + "loss": 3.3208, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.3975856332995495e-06, + "loss": 3.3225, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.389216064592761e-06, + "loss": 3.3107, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.380830117082241e-06, + "loss": 3.3183, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.372444169571721e-06, + "loss": 3.3158, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.364058222061201e-06, + "loss": 3.3228, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.355672274550681e-06, + "loss": 3.3046, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.3473027058438926e-06, + "loss": 3.3292, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.338916758333372e-06, + "loss": 3.303, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.330530810822852e-06, + "loss": 3.331, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.322144863312332e-06, + "loss": 3.3176, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.3137589158018115e-06, + "loss": 3.311, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.3053729682912915e-06, + "loss": 3.3291, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.2969870207807715e-06, + "loss": 3.3331, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.288617452073983e-06, + "loss": 3.3181, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.280231504563462e-06, + "loss": 3.3172, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.271861935856674e-06, + "loss": 3.3208, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.263475988346154e-06, + "loss": 3.3176, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.255090040835634e-06, + "loss": 3.3129, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.246704093325114e-06, + "loss": 3.3164, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.238318145814594e-06, + "loss": 3.3166, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.229932198304074e-06, + "loss": 3.3218, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.221562629597284e-06, + "loss": 3.3157, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.213176682086764e-06, + "loss": 3.319, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.204790734576244e-06, + "loss": 3.3077, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.196404787065724e-06, + "loss": 3.3165, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.188018839555204e-06, + "loss": 3.3134, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.179632892044684e-06, + "loss": 3.3235, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.171263323337896e-06, + "loss": 3.3274, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.162877375827376e-06, + "loss": 3.3219, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.154491428316855e-06, + "loss": 3.308, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.146105480806336e-06, + "loss": 3.3224, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.137719533295815e-06, + "loss": 3.32, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.129333585785296e-06, + "loss": 3.3237, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.120947638274775e-06, + "loss": 3.3102, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.112561690764255e-06, + "loss": 3.3276, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.104208500861197e-06, + "loss": 3.3263, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.095822553350678e-06, + "loss": 3.3318, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.087436605840158e-06, + "loss": 3.3186, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.079050658329637e-06, + "loss": 3.324, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.070664710819118e-06, + "loss": 3.3219, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.062295142112329e-06, + "loss": 3.3131, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.0539091946018086e-06, + "loss": 3.3239, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.0455232470912885e-06, + "loss": 3.3336, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.0371372995807685e-06, + "loss": 3.3228, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.028767730873979e-06, + "loss": 3.3133, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.02038178336346e-06, + "loss": 3.3137, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.864339590072632, + "eval_runtime": 307.9312, + "eval_samples_per_second": 1239.208, + "eval_steps_per_second": 38.726, + "step": 2747520 + }, + { + "epoch": 1.0, + "learning_rate": 5.011995835852939e-06, + "loss": 3.3091, + "step": 2747904 + }, + { + "epoch": 1.0, + "learning_rate": 5.003609888342419e-06, + "loss": 3.3117, + "step": 2748416 + }, + { + "epoch": 1.0, + "learning_rate": 4.995240319635631e-06, + "loss": 3.3221, + "step": 2748928 + }, + { + "epoch": 1.0, + "learning_rate": 4.986854372125111e-06, + "loss": 3.3216, + "step": 2749440 + }, + { + "epoch": 1.0, + "learning_rate": 4.978468424614591e-06, + "loss": 3.3313, + "step": 2749952 + }, + { + "epoch": 1.0, + "learning_rate": 4.970082477104071e-06, + "loss": 3.3158, + "step": 2750464 + }, + { + "epoch": 1.0, + "learning_rate": 4.961696529593551e-06, + "loss": 3.3154, + "step": 2750976 + }, + { + "epoch": 1.0, + "learning_rate": 4.953326960886761e-06, + "loss": 3.3025, + "step": 2751488 + }, + { + "epoch": 1.0, + "learning_rate": 4.944941013376242e-06, + "loss": 3.3194, + "step": 2752000 + }, + { + "epoch": 1.0, + "learning_rate": 4.936555065865721e-06, + "loss": 3.3173, + "step": 2752512 + }, + { + "epoch": 1.0, + "learning_rate": 4.928169118355201e-06, + "loss": 3.319, + "step": 2753024 + }, + { + "epoch": 1.0, + "learning_rate": 4.919783170844681e-06, + "loss": 3.3249, + "step": 2753536 + }, + { + "epoch": 1.0, + "learning_rate": 4.911413602137893e-06, + "loss": 3.3131, + "step": 2754048 + }, + { + "epoch": 1.0, + "learning_rate": 4.903027654627373e-06, + "loss": 3.3099, + "step": 2754560 + }, + { + "epoch": 1.0, + "learning_rate": 4.894641707116853e-06, + "loss": 3.3106, + "step": 2755072 + }, + { + "epoch": 1.0, + "learning_rate": 4.886255759606333e-06, + "loss": 3.3062, + "step": 2755584 + }, + { + "epoch": 1.0, + "learning_rate": 4.8778861908995435e-06, + "loss": 3.3112, + "step": 2756096 + }, + { + "epoch": 1.0, + "learning_rate": 4.869500243389024e-06, + "loss": 3.3122, + "step": 2756608 + }, + { + "epoch": 1.0, + "learning_rate": 4.861114295878503e-06, + "loss": 3.309, + "step": 2757120 + }, + { + "epoch": 1.0, + "learning_rate": 4.852728348367983e-06, + "loss": 3.3331, + "step": 2757632 + }, + { + "epoch": 1.0, + "learning_rate": 4.844342400857463e-06, + "loss": 3.3201, + "step": 2758144 + }, + { + "epoch": 1.0, + "learning_rate": 4.835972832150674e-06, + "loss": 3.3189, + "step": 2758656 + }, + { + "epoch": 1.0, + "learning_rate": 4.827586884640155e-06, + "loss": 3.3236, + "step": 2759168 + }, + { + "epoch": 1.0, + "learning_rate": 4.819200937129634e-06, + "loss": 3.3238, + "step": 2759680 + }, + { + "epoch": 1.0, + "learning_rate": 4.810814989619115e-06, + "loss": 3.31, + "step": 2760192 + }, + { + "epoch": 1.0, + "learning_rate": 4.802429042108594e-06, + "loss": 3.319, + "step": 2760704 + }, + { + "epoch": 1.0, + "learning_rate": 4.794059473401806e-06, + "loss": 3.3192, + "step": 2761216 + }, + { + "epoch": 1.0, + "learning_rate": 4.7856735258912855e-06, + "loss": 3.3117, + "step": 2761728 + }, + { + "epoch": 1.0, + "learning_rate": 4.7772875783807655e-06, + "loss": 3.3013, + "step": 2762240 + }, + { + "epoch": 1.0, + "learning_rate": 4.7689016308702454e-06, + "loss": 3.3046, + "step": 2762752 + }, + { + "epoch": 1.01, + "learning_rate": 4.760532062163456e-06, + "loss": 3.3204, + "step": 2763264 + }, + { + "epoch": 1.01, + "learning_rate": 4.752146114652937e-06, + "loss": 3.3191, + "step": 2763776 + }, + { + "epoch": 1.01, + "learning_rate": 4.743760167142416e-06, + "loss": 3.3184, + "step": 2764288 + }, + { + "epoch": 1.01, + "learning_rate": 4.735374219631897e-06, + "loss": 3.3207, + "step": 2764800 + }, + { + "epoch": 1.01, + "learning_rate": 4.726988272121376e-06, + "loss": 3.3084, + "step": 2765312 + }, + { + "epoch": 1.01, + "learning_rate": 4.718618703414588e-06, + "loss": 3.3167, + "step": 2765824 + }, + { + "epoch": 1.01, + "learning_rate": 4.710232755904068e-06, + "loss": 3.3105, + "step": 2766336 + }, + { + "epoch": 1.01, + "learning_rate": 4.701846808393548e-06, + "loss": 3.3185, + "step": 2766848 + }, + { + "epoch": 1.01, + "learning_rate": 4.6934608608830276e-06, + "loss": 3.3, + "step": 2767360 + }, + { + "epoch": 1.01, + "learning_rate": 4.6850749133725075e-06, + "loss": 3.3087, + "step": 2767872 + }, + { + "epoch": 1.01, + "learning_rate": 4.676705344665719e-06, + "loss": 3.3075, + "step": 2768384 + }, + { + "epoch": 1.01, + "learning_rate": 4.668319397155198e-06, + "loss": 3.3291, + "step": 2768896 + }, + { + "epoch": 1.01, + "learning_rate": 4.659933449644679e-06, + "loss": 3.3185, + "step": 2769408 + }, + { + "epoch": 1.01, + "learning_rate": 4.651547502134158e-06, + "loss": 3.3147, + "step": 2769920 + }, + { + "epoch": 1.01, + "learning_rate": 4.643161554623638e-06, + "loss": 3.3182, + "step": 2770432 + }, + { + "epoch": 1.01, + "learning_rate": 4.63479198591685e-06, + "loss": 3.3175, + "step": 2770944 + }, + { + "epoch": 1.01, + "learning_rate": 4.62640603840633e-06, + "loss": 3.3226, + "step": 2771456 + }, + { + "epoch": 1.01, + "learning_rate": 4.61802009089581e-06, + "loss": 3.2988, + "step": 2771968 + }, + { + "epoch": 1.01, + "learning_rate": 4.60963414338529e-06, + "loss": 3.3074, + "step": 2772480 + }, + { + "epoch": 1.01, + "learning_rate": 4.601264574678501e-06, + "loss": 3.3212, + "step": 2772992 + }, + { + "epoch": 1.01, + "learning_rate": 4.59287862716798e-06, + "loss": 3.3214, + "step": 2773504 + }, + { + "epoch": 1.01, + "learning_rate": 4.58449267965746e-06, + "loss": 3.3053, + "step": 2774016 + }, + { + "epoch": 1.01, + "learning_rate": 4.57610673214694e-06, + "loss": 3.3036, + "step": 2774528 + }, + { + "epoch": 1.01, + "learning_rate": 4.56772078463642e-06, + "loss": 3.3115, + "step": 2775040 + }, + { + "epoch": 1.01, + "learning_rate": 4.559351215929632e-06, + "loss": 3.2997, + "step": 2775552 + }, + { + "epoch": 1.01, + "learning_rate": 4.550965268419111e-06, + "loss": 3.3153, + "step": 2776064 + }, + { + "epoch": 1.01, + "learning_rate": 4.542579320908592e-06, + "loss": 3.3057, + "step": 2776576 + }, + { + "epoch": 1.01, + "learning_rate": 4.534193373398071e-06, + "loss": 3.3155, + "step": 2777088 + }, + { + "epoch": 1.01, + "learning_rate": 4.525807425887551e-06, + "loss": 3.3152, + "step": 2777600 + }, + { + "epoch": 1.01, + "learning_rate": 4.517421478377031e-06, + "loss": 3.3104, + "step": 2778112 + }, + { + "epoch": 1.01, + "learning_rate": 4.509035530866511e-06, + "loss": 3.3032, + "step": 2778624 + }, + { + "epoch": 1.01, + "learning_rate": 4.500649583355991e-06, + "loss": 3.3072, + "step": 2779136 + }, + { + "epoch": 1.01, + "learning_rate": 4.492296393452933e-06, + "loss": 3.3061, + "step": 2779648 + }, + { + "epoch": 1.01, + "learning_rate": 4.483910445942414e-06, + "loss": 3.3096, + "step": 2780160 + }, + { + "epoch": 1.01, + "learning_rate": 4.475524498431893e-06, + "loss": 3.3138, + "step": 2780672 + }, + { + "epoch": 1.01, + "learning_rate": 4.467138550921374e-06, + "loss": 3.3052, + "step": 2781184 + }, + { + "epoch": 1.01, + "learning_rate": 4.458752603410853e-06, + "loss": 3.3064, + "step": 2781696 + }, + { + "epoch": 1.01, + "learning_rate": 4.450383034704065e-06, + "loss": 3.2998, + "step": 2782208 + }, + { + "epoch": 1.01, + "learning_rate": 4.441997087193545e-06, + "loss": 3.3035, + "step": 2782720 + }, + { + "epoch": 1.01, + "learning_rate": 4.4336111396830246e-06, + "loss": 3.3127, + "step": 2783232 + }, + { + "epoch": 1.01, + "learning_rate": 4.4252251921725045e-06, + "loss": 3.3199, + "step": 2783744 + }, + { + "epoch": 1.01, + "learning_rate": 4.416855623465715e-06, + "loss": 3.3112, + "step": 2784256 + }, + { + "epoch": 1.01, + "learning_rate": 4.408469675955196e-06, + "loss": 3.3185, + "step": 2784768 + }, + { + "epoch": 1.01, + "learning_rate": 4.400083728444675e-06, + "loss": 3.3204, + "step": 2785280 + }, + { + "epoch": 1.01, + "learning_rate": 4.391697780934156e-06, + "loss": 3.3196, + "step": 2785792 + }, + { + "epoch": 1.01, + "learning_rate": 4.383311833423635e-06, + "loss": 3.2997, + "step": 2786304 + }, + { + "epoch": 1.01, + "learning_rate": 4.374942264716847e-06, + "loss": 3.314, + "step": 2786816 + }, + { + "epoch": 1.01, + "learning_rate": 4.366556317206327e-06, + "loss": 3.3139, + "step": 2787328 + }, + { + "epoch": 1.01, + "learning_rate": 4.358170369695806e-06, + "loss": 3.3026, + "step": 2787840 + }, + { + "epoch": 1.01, + "learning_rate": 4.349784422185287e-06, + "loss": 3.3142, + "step": 2788352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3414148534784974e-06, + "loss": 3.3168, + "step": 2788864 + }, + { + "epoch": 1.01, + "learning_rate": 4.333028905967978e-06, + "loss": 3.3258, + "step": 2789376 + }, + { + "epoch": 1.01, + "learning_rate": 4.324642958457457e-06, + "loss": 3.3089, + "step": 2789888 + }, + { + "epoch": 1.01, + "learning_rate": 4.316257010946938e-06, + "loss": 3.2942, + "step": 2790400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307871063436417e-06, + "loss": 3.3057, + "step": 2790912 + }, + { + "epoch": 1.01, + "learning_rate": 4.299501494729629e-06, + "loss": 3.3126, + "step": 2791424 + }, + { + "epoch": 1.01, + "learning_rate": 4.291115547219109e-06, + "loss": 3.3114, + "step": 2791936 + }, + { + "epoch": 1.01, + "learning_rate": 4.282729599708588e-06, + "loss": 3.3146, + "step": 2792448 + }, + { + "epoch": 1.01, + "learning_rate": 4.274343652198069e-06, + "loss": 3.3157, + "step": 2792960 + }, + { + "epoch": 1.02, + "learning_rate": 4.265957704687548e-06, + "loss": 3.3144, + "step": 2793472 + }, + { + "epoch": 1.02, + "learning_rate": 4.257571757177029e-06, + "loss": 3.3037, + "step": 2793984 + }, + { + "epoch": 1.02, + "learning_rate": 4.249185809666508e-06, + "loss": 3.3054, + "step": 2794496 + }, + { + "epoch": 1.02, + "learning_rate": 4.240799862155988e-06, + "loss": 3.3047, + "step": 2795008 + }, + { + "epoch": 1.02, + "learning_rate": 4.232446672252931e-06, + "loss": 3.318, + "step": 2795520 + }, + { + "epoch": 1.02, + "learning_rate": 4.224060724742411e-06, + "loss": 3.314, + "step": 2796032 + }, + { + "epoch": 1.02, + "learning_rate": 4.215674777231891e-06, + "loss": 3.3221, + "step": 2796544 + }, + { + "epoch": 1.02, + "learning_rate": 4.20728882972137e-06, + "loss": 3.2984, + "step": 2797056 + }, + { + "epoch": 1.02, + "learning_rate": 4.198902882210851e-06, + "loss": 3.3159, + "step": 2797568 + }, + { + "epoch": 1.02, + "learning_rate": 4.190533313504062e-06, + "loss": 3.3165, + "step": 2798080 + }, + { + "epoch": 1.02, + "learning_rate": 4.182147365993542e-06, + "loss": 3.3161, + "step": 2798592 + }, + { + "epoch": 1.02, + "learning_rate": 4.1737614184830216e-06, + "loss": 3.3082, + "step": 2799104 + }, + { + "epoch": 1.02, + "learning_rate": 4.1653754709725015e-06, + "loss": 3.3064, + "step": 2799616 + }, + { + "epoch": 1.02, + "learning_rate": 4.157005902265713e-06, + "loss": 3.3128, + "step": 2800128 + }, + { + "epoch": 1.02, + "learning_rate": 4.148619954755193e-06, + "loss": 3.315, + "step": 2800640 + }, + { + "epoch": 1.02, + "learning_rate": 4.140234007244673e-06, + "loss": 3.2989, + "step": 2801152 + }, + { + "epoch": 1.02, + "learning_rate": 4.131848059734152e-06, + "loss": 3.3155, + "step": 2801664 + }, + { + "epoch": 1.02, + "learning_rate": 4.123462112223633e-06, + "loss": 3.3054, + "step": 2802176 + }, + { + "epoch": 1.02, + "learning_rate": 4.115076164713112e-06, + "loss": 3.3132, + "step": 2802688 + }, + { + "epoch": 1.02, + "learning_rate": 4.106690217202593e-06, + "loss": 3.2947, + "step": 2803200 + }, + { + "epoch": 1.02, + "learning_rate": 4.098320648495804e-06, + "loss": 3.318, + "step": 2803712 + }, + { + "epoch": 1.02, + "learning_rate": 4.089934700985284e-06, + "loss": 3.3059, + "step": 2804224 + }, + { + "epoch": 1.02, + "learning_rate": 4.081548753474764e-06, + "loss": 3.3187, + "step": 2804736 + }, + { + "epoch": 1.02, + "learning_rate": 4.073162805964243e-06, + "loss": 3.3095, + "step": 2805248 + }, + { + "epoch": 1.02, + "learning_rate": 4.064793237257454e-06, + "loss": 3.3013, + "step": 2805760 + }, + { + "epoch": 1.02, + "learning_rate": 4.056407289746934e-06, + "loss": 3.3193, + "step": 2806272 + }, + { + "epoch": 1.02, + "learning_rate": 4.048021342236414e-06, + "loss": 3.3245, + "step": 2806784 + }, + { + "epoch": 1.02, + "learning_rate": 4.039635394725894e-06, + "loss": 3.3125, + "step": 2807296 + }, + { + "epoch": 1.02, + "learning_rate": 4.031249447215374e-06, + "loss": 3.3054, + "step": 2807808 + }, + { + "epoch": 1.02, + "learning_rate": 4.022879878508586e-06, + "loss": 3.3138, + "step": 2808320 + }, + { + "epoch": 1.02, + "learning_rate": 4.014493930998066e-06, + "loss": 3.3104, + "step": 2808832 + }, + { + "epoch": 1.02, + "learning_rate": 4.006107983487546e-06, + "loss": 3.3034, + "step": 2809344 + }, + { + "epoch": 1.02, + "learning_rate": 3.997722035977025e-06, + "loss": 3.3107, + "step": 2809856 + }, + { + "epoch": 1.02, + "learning_rate": 3.9893524672702365e-06, + "loss": 3.3052, + "step": 2810368 + }, + { + "epoch": 1.02, + "learning_rate": 3.980966519759716e-06, + "loss": 3.3128, + "step": 2810880 + }, + { + "epoch": 1.02, + "learning_rate": 3.972580572249196e-06, + "loss": 3.3083, + "step": 2811392 + }, + { + "epoch": 1.02, + "learning_rate": 3.964194624738676e-06, + "loss": 3.3123, + "step": 2811904 + }, + { + "epoch": 1.02, + "learning_rate": 3.955808677228156e-06, + "loss": 3.3, + "step": 2812416 + }, + { + "epoch": 1.02, + "learning_rate": 3.947422729717636e-06, + "loss": 3.3056, + "step": 2812928 + }, + { + "epoch": 1.02, + "learning_rate": 3.939036782207116e-06, + "loss": 3.3077, + "step": 2813440 + }, + { + "epoch": 1.02, + "learning_rate": 3.930667213500328e-06, + "loss": 3.3156, + "step": 2813952 + }, + { + "epoch": 1.02, + "learning_rate": 3.922281265989807e-06, + "loss": 3.3123, + "step": 2814464 + }, + { + "epoch": 1.02, + "learning_rate": 3.913895318479288e-06, + "loss": 3.3173, + "step": 2814976 + }, + { + "epoch": 1.02, + "learning_rate": 3.905509370968767e-06, + "loss": 3.2996, + "step": 2815488 + }, + { + "epoch": 1.02, + "learning_rate": 3.8971398022619785e-06, + "loss": 3.3128, + "step": 2816000 + }, + { + "epoch": 1.02, + "learning_rate": 3.8887538547514584e-06, + "loss": 3.314, + "step": 2816512 + }, + { + "epoch": 1.02, + "learning_rate": 3.8803679072409376e-06, + "loss": 3.3172, + "step": 2817024 + }, + { + "epoch": 1.02, + "learning_rate": 3.871981959730418e-06, + "loss": 3.3013, + "step": 2817536 + }, + { + "epoch": 1.02, + "learning_rate": 3.863596012219898e-06, + "loss": 3.3165, + "step": 2818048 + }, + { + "epoch": 1.02, + "learning_rate": 3.85522644351311e-06, + "loss": 3.3152, + "step": 2818560 + }, + { + "epoch": 1.02, + "learning_rate": 3.846840496002589e-06, + "loss": 3.3278, + "step": 2819072 + }, + { + "epoch": 1.02, + "learning_rate": 3.83845454849207e-06, + "loss": 3.3054, + "step": 2819584 + }, + { + "epoch": 1.02, + "learning_rate": 3.830068600981549e-06, + "loss": 3.3169, + "step": 2820096 + }, + { + "epoch": 1.02, + "learning_rate": 3.821682653471029e-06, + "loss": 3.314, + "step": 2820608 + }, + { + "epoch": 1.02, + "learning_rate": 3.8133130847642406e-06, + "loss": 3.3049, + "step": 2821120 + }, + { + "epoch": 1.02, + "learning_rate": 3.80492713725372e-06, + "loss": 3.3153, + "step": 2821632 + }, + { + "epoch": 1.02, + "learning_rate": 3.7965411897432005e-06, + "loss": 3.3229, + "step": 2822144 + }, + { + "epoch": 1.02, + "learning_rate": 3.78815524223268e-06, + "loss": 3.3169, + "step": 2822656 + }, + { + "epoch": 1.02, + "learning_rate": 3.7797856735258916e-06, + "loss": 3.3022, + "step": 2823168 + }, + { + "epoch": 1.02, + "learning_rate": 3.771399726015371e-06, + "loss": 3.3086, + "step": 2823680 + }, + { + "epoch": 1.03, + "eval_loss": 3.864070415496826, + "eval_runtime": 303.2186, + "eval_samples_per_second": 1258.468, + "eval_steps_per_second": 39.328, + "step": 2823840 + }, + { + "epoch": 0.0, + "learning_rate": 3.763030157308583e-06, + "loss": 3.298, + "step": 2824192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7546442097980624e-06, + "loss": 3.3013, + "step": 2824704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7462582622875427e-06, + "loss": 3.3137, + "step": 2825216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7378723147770223e-06, + "loss": 3.3146, + "step": 2825728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7294863672665022e-06, + "loss": 3.3184, + "step": 2826240 + }, + { + "epoch": 0.0, + "learning_rate": 3.721100419755982e-06, + "loss": 3.3116, + "step": 2826752 + }, + { + "epoch": 0.0, + "learning_rate": 3.712714472245462e-06, + "loss": 3.3066, + "step": 2827264 + }, + { + "epoch": 0.0, + "learning_rate": 3.7043449035386738e-06, + "loss": 3.2999, + "step": 2827776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6959589560281533e-06, + "loss": 3.3088, + "step": 2828288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6875730085176337e-06, + "loss": 3.3104, + "step": 2828800 + }, + { + "epoch": 0.0, + "learning_rate": 3.679187061007113e-06, + "loss": 3.3105, + "step": 2829312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6708011134965927e-06, + "loss": 3.3173, + "step": 2829824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6624315447898044e-06, + "loss": 3.3049, + "step": 2830336 + }, + { + "epoch": 0.0, + "learning_rate": 3.654045597279284e-06, + "loss": 3.3028, + "step": 2830848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6456596497687643e-06, + "loss": 3.3015, + "step": 2831360 + }, + { + "epoch": 0.0, + "learning_rate": 3.637273702258244e-06, + "loss": 3.2968, + "step": 2831872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6289041335514555e-06, + "loss": 3.3045, + "step": 2832384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6205181860409354e-06, + "loss": 3.3048, + "step": 2832896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6121322385304154e-06, + "loss": 3.3005, + "step": 2833408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6037462910198953e-06, + "loss": 3.3231, + "step": 2833920 + }, + { + "epoch": 0.0, + "learning_rate": 3.595360343509375e-06, + "loss": 3.3142, + "step": 2834432 + }, + { + "epoch": 0.0, + "learning_rate": 3.5869907748025865e-06, + "loss": 3.3127, + "step": 2834944 + }, + { + "epoch": 0.0, + "learning_rate": 3.578604827292066e-06, + "loss": 3.3129, + "step": 2835456 + }, + { + "epoch": 0.0, + "learning_rate": 3.5702188797815464e-06, + "loss": 3.3174, + "step": 2835968 + }, + { + "epoch": 0.0, + "learning_rate": 3.561832932271026e-06, + "loss": 3.3004, + "step": 2836480 + }, + { + "epoch": 0.0, + "learning_rate": 3.5534469847605063e-06, + "loss": 3.3105, + "step": 2836992 + }, + { + "epoch": 0.0, + "learning_rate": 3.545061037249986e-06, + "loss": 3.3157, + "step": 2837504 + }, + { + "epoch": 0.0, + "learning_rate": 3.5366914685431975e-06, + "loss": 3.2999, + "step": 2838016 + }, + { + "epoch": 0.0, + "learning_rate": 3.528305521032677e-06, + "loss": 3.293, + "step": 2838528 + }, + { + "epoch": 0.0, + "learning_rate": 3.519919573522157e-06, + "loss": 3.2998, + "step": 2839040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5115336260116374e-06, + "loss": 3.3105, + "step": 2839552 + }, + { + "epoch": 0.01, + "learning_rate": 3.503147678501117e-06, + "loss": 3.309, + "step": 2840064 + }, + { + "epoch": 0.01, + "learning_rate": 3.4947781097943285e-06, + "loss": 3.3104, + "step": 2840576 + }, + { + "epoch": 0.01, + "learning_rate": 3.486392162283808e-06, + "loss": 3.3145, + "step": 2841088 + }, + { + "epoch": 0.01, + "learning_rate": 3.4780062147732884e-06, + "loss": 3.3021, + "step": 2841600 + }, + { + "epoch": 0.01, + "learning_rate": 3.469620267262768e-06, + "loss": 3.3056, + "step": 2842112 + }, + { + "epoch": 0.01, + "learning_rate": 3.4612343197522475e-06, + "loss": 3.302, + "step": 2842624 + }, + { + "epoch": 0.01, + "learning_rate": 3.452864751045459e-06, + "loss": 3.3094, + "step": 2843136 + }, + { + "epoch": 0.01, + "learning_rate": 3.4444788035349387e-06, + "loss": 3.2934, + "step": 2843648 + }, + { + "epoch": 0.01, + "learning_rate": 3.436092856024419e-06, + "loss": 3.2993, + "step": 2844160 + }, + { + "epoch": 0.01, + "learning_rate": 3.427706908513899e-06, + "loss": 3.3031, + "step": 2844672 + }, + { + "epoch": 0.01, + "learning_rate": 3.419320961003379e-06, + "loss": 3.3204, + "step": 2845184 + }, + { + "epoch": 0.01, + "learning_rate": 3.410935013492859e-06, + "loss": 3.309, + "step": 2845696 + }, + { + "epoch": 0.01, + "learning_rate": 3.4025490659823384e-06, + "loss": 3.3071, + "step": 2846208 + }, + { + "epoch": 0.01, + "learning_rate": 3.39417949727555e-06, + "loss": 3.3135, + "step": 2846720 + }, + { + "epoch": 0.01, + "learning_rate": 3.3857935497650296e-06, + "loss": 3.305, + "step": 2847232 + }, + { + "epoch": 0.01, + "learning_rate": 3.37740760225451e-06, + "loss": 3.3135, + "step": 2847744 + }, + { + "epoch": 0.01, + "learning_rate": 3.3690216547439895e-06, + "loss": 3.295, + "step": 2848256 + }, + { + "epoch": 0.01, + "learning_rate": 3.360635707233469e-06, + "loss": 3.2945, + "step": 2848768 + }, + { + "epoch": 0.01, + "learning_rate": 3.3522661385266807e-06, + "loss": 3.3122, + "step": 2849280 + }, + { + "epoch": 0.01, + "learning_rate": 3.3438801910161607e-06, + "loss": 3.3126, + "step": 2849792 + }, + { + "epoch": 0.01, + "learning_rate": 3.3354942435056406e-06, + "loss": 3.298, + "step": 2850304 + }, + { + "epoch": 0.01, + "learning_rate": 3.3271082959951206e-06, + "loss": 3.297, + "step": 2850816 + }, + { + "epoch": 0.01, + "learning_rate": 3.3187223484846005e-06, + "loss": 3.3061, + "step": 2851328 + }, + { + "epoch": 0.01, + "learning_rate": 3.3103527797778117e-06, + "loss": 3.2886, + "step": 2851840 + }, + { + "epoch": 0.01, + "learning_rate": 3.301966832267292e-06, + "loss": 3.3066, + "step": 2852352 + }, + { + "epoch": 0.01, + "learning_rate": 3.2935808847567716e-06, + "loss": 3.2993, + "step": 2852864 + }, + { + "epoch": 0.01, + "learning_rate": 3.285194937246251e-06, + "loss": 3.3045, + "step": 2853376 + }, + { + "epoch": 0.01, + "learning_rate": 3.2768089897357316e-06, + "loss": 3.3124, + "step": 2853888 + }, + { + "epoch": 0.01, + "learning_rate": 3.268423042225211e-06, + "loss": 3.3006, + "step": 2854400 + }, + { + "epoch": 0.01, + "learning_rate": 3.2600370947146915e-06, + "loss": 3.2988, + "step": 2854912 + }, + { + "epoch": 0.01, + "learning_rate": 3.251651147204171e-06, + "loss": 3.2979, + "step": 2855424 + }, + { + "epoch": 0.01, + "learning_rate": 3.243297957301114e-06, + "loss": 3.2996, + "step": 2855936 + }, + { + "epoch": 0.01, + "learning_rate": 3.234912009790594e-06, + "loss": 3.2979, + "step": 2856448 + }, + { + "epoch": 0.01, + "learning_rate": 3.226526062280074e-06, + "loss": 3.3066, + "step": 2856960 + }, + { + "epoch": 0.01, + "learning_rate": 3.2181401147695538e-06, + "loss": 3.3028, + "step": 2857472 + }, + { + "epoch": 0.01, + "learning_rate": 3.2097541672590333e-06, + "loss": 3.2949, + "step": 2857984 + }, + { + "epoch": 0.01, + "learning_rate": 3.201384598552245e-06, + "loss": 3.2954, + "step": 2858496 + }, + { + "epoch": 0.01, + "learning_rate": 3.1929986510417245e-06, + "loss": 3.2932, + "step": 2859008 + }, + { + "epoch": 0.01, + "learning_rate": 3.184612703531205e-06, + "loss": 3.302, + "step": 2859520 + }, + { + "epoch": 0.01, + "learning_rate": 3.1762267560206844e-06, + "loss": 3.3071, + "step": 2860032 + }, + { + "epoch": 0.01, + "learning_rate": 3.167857187313896e-06, + "loss": 3.3051, + "step": 2860544 + }, + { + "epoch": 0.01, + "learning_rate": 3.1594712398033755e-06, + "loss": 3.3093, + "step": 2861056 + }, + { + "epoch": 0.01, + "learning_rate": 3.151085292292856e-06, + "loss": 3.3105, + "step": 2861568 + }, + { + "epoch": 0.01, + "learning_rate": 3.1426993447823355e-06, + "loss": 3.3155, + "step": 2862080 + }, + { + "epoch": 0.01, + "learning_rate": 3.1343297760755475e-06, + "loss": 3.2899, + "step": 2862592 + }, + { + "epoch": 0.01, + "learning_rate": 3.125943828565027e-06, + "loss": 3.3052, + "step": 2863104 + }, + { + "epoch": 0.01, + "learning_rate": 3.117557881054507e-06, + "loss": 3.3081, + "step": 2863616 + }, + { + "epoch": 0.01, + "learning_rate": 3.109171933543987e-06, + "loss": 3.2904, + "step": 2864128 + }, + { + "epoch": 0.01, + "learning_rate": 3.100802364837198e-06, + "loss": 3.3124, + "step": 2864640 + }, + { + "epoch": 0.01, + "learning_rate": 3.092416417326678e-06, + "loss": 3.3032, + "step": 2865152 + }, + { + "epoch": 0.01, + "learning_rate": 3.0840304698161577e-06, + "loss": 3.3175, + "step": 2865664 + }, + { + "epoch": 0.01, + "learning_rate": 3.0756445223056376e-06, + "loss": 3.3031, + "step": 2866176 + }, + { + "epoch": 0.01, + "learning_rate": 3.0672585747951176e-06, + "loss": 3.2858, + "step": 2866688 + }, + { + "epoch": 0.01, + "learning_rate": 3.0588726272845975e-06, + "loss": 3.2969, + "step": 2867200 + }, + { + "epoch": 0.01, + "learning_rate": 3.0504866797740775e-06, + "loss": 3.3021, + "step": 2867712 + }, + { + "epoch": 0.01, + "learning_rate": 3.042117111067289e-06, + "loss": 3.3087, + "step": 2868224 + }, + { + "epoch": 0.01, + "learning_rate": 3.033731163556769e-06, + "loss": 3.3055, + "step": 2868736 + }, + { + "epoch": 0.01, + "learning_rate": 3.0253452160462486e-06, + "loss": 3.3079, + "step": 2869248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0169592685357286e-06, + "loss": 3.3057, + "step": 2869760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0085733210252085e-06, + "loss": 3.2969, + "step": 2870272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0001873735146885e-06, + "loss": 3.2942, + "step": 2870784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9918014260041684e-06, + "loss": 3.2974, + "step": 2871296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9834318572973796e-06, + "loss": 3.3113, + "step": 2871808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9750459097868596e-06, + "loss": 3.305, + "step": 2872320 + }, + { + "epoch": 0.02, + "learning_rate": 2.966659962276339e-06, + "loss": 3.3118, + "step": 2872832 + }, + { + "epoch": 0.02, + "learning_rate": 2.958274014765819e-06, + "loss": 3.2923, + "step": 2873344 + }, + { + "epoch": 0.02, + "learning_rate": 2.949888067255299e-06, + "loss": 3.3081, + "step": 2873856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9415184985485107e-06, + "loss": 3.3069, + "step": 2874368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9331325510379906e-06, + "loss": 3.3107, + "step": 2874880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9247466035274706e-06, + "loss": 3.2976, + "step": 2875392 + }, + { + "epoch": 0.02, + "learning_rate": 2.91636065601695e-06, + "loss": 3.3001, + "step": 2875904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9079910873101618e-06, + "loss": 3.3017, + "step": 2876416 + }, + { + "epoch": 0.02, + "learning_rate": 2.8996051397996413e-06, + "loss": 3.3089, + "step": 2876928 + }, + { + "epoch": 0.02, + "learning_rate": 2.8912191922891213e-06, + "loss": 3.289, + "step": 2877440 + }, + { + "epoch": 0.02, + "learning_rate": 2.882833244778601e-06, + "loss": 3.3067, + "step": 2877952 + }, + { + "epoch": 0.02, + "learning_rate": 2.874447297268081e-06, + "loss": 3.2941, + "step": 2878464 + }, + { + "epoch": 0.02, + "learning_rate": 2.8660777285612924e-06, + "loss": 3.3054, + "step": 2878976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8576917810507723e-06, + "loss": 3.2868, + "step": 2879488 + }, + { + "epoch": 0.02, + "learning_rate": 2.8493058335402523e-06, + "loss": 3.3129, + "step": 2880000 + }, + { + "epoch": 0.02, + "learning_rate": 2.8409198860297322e-06, + "loss": 3.2967, + "step": 2880512 + }, + { + "epoch": 0.02, + "learning_rate": 2.832533938519212e-06, + "loss": 3.3104, + "step": 2881024 + }, + { + "epoch": 0.02, + "learning_rate": 2.8241643698124234e-06, + "loss": 3.3041, + "step": 2881536 + }, + { + "epoch": 0.02, + "learning_rate": 2.8157784223019034e-06, + "loss": 3.2961, + "step": 2882048 + }, + { + "epoch": 0.02, + "learning_rate": 2.8073924747913833e-06, + "loss": 3.307, + "step": 2882560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7990065272808633e-06, + "loss": 3.3187, + "step": 2883072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7906205797703432e-06, + "loss": 3.3042, + "step": 2883584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7822346322598228e-06, + "loss": 3.2954, + "step": 2884096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7738650635530344e-06, + "loss": 3.307, + "step": 2884608 + }, + { + "epoch": 0.02, + "learning_rate": 2.765479116042514e-06, + "loss": 3.3044, + "step": 2885120 + }, + { + "epoch": 0.02, + "learning_rate": 2.757093168531994e-06, + "loss": 3.2952, + "step": 2885632 + }, + { + "epoch": 0.02, + "learning_rate": 2.748707221021474e-06, + "loss": 3.3034, + "step": 2886144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7403212735109542e-06, + "loss": 3.2956, + "step": 2886656 + }, + { + "epoch": 0.02, + "learning_rate": 2.731935326000434e-06, + "loss": 3.3029, + "step": 2887168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7235493784899137e-06, + "loss": 3.3034, + "step": 2887680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7151634309793937e-06, + "loss": 3.3036, + "step": 2888192 + }, + { + "epoch": 0.02, + "learning_rate": 2.706793862272605e-06, + "loss": 3.2896, + "step": 2888704 + }, + { + "epoch": 0.02, + "learning_rate": 2.698407914762085e-06, + "loss": 3.3008, + "step": 2889216 + }, + { + "epoch": 0.02, + "learning_rate": 2.690021967251565e-06, + "loss": 3.2963, + "step": 2889728 + }, + { + "epoch": 0.02, + "learning_rate": 2.6816360197410448e-06, + "loss": 3.3091, + "step": 2890240 + }, + { + "epoch": 0.02, + "learning_rate": 2.673266451034256e-06, + "loss": 3.3065, + "step": 2890752 + }, + { + "epoch": 0.02, + "learning_rate": 2.664880503523736e-06, + "loss": 3.3109, + "step": 2891264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6565109348169476e-06, + "loss": 3.2921, + "step": 2891776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6481249873064275e-06, + "loss": 3.3064, + "step": 2892288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6397390397959075e-06, + "loss": 3.3048, + "step": 2892800 + }, + { + "epoch": 0.02, + "learning_rate": 2.631353092285387e-06, + "loss": 3.307, + "step": 2893312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6229835235785986e-06, + "loss": 3.2968, + "step": 2893824 + }, + { + "epoch": 0.02, + "learning_rate": 2.614597576068078e-06, + "loss": 3.3074, + "step": 2894336 + }, + { + "epoch": 0.02, + "learning_rate": 2.606211628557558e-06, + "loss": 3.3068, + "step": 2894848 + }, + { + "epoch": 0.02, + "learning_rate": 2.597825681047038e-06, + "loss": 3.317, + "step": 2895360 + }, + { + "epoch": 0.02, + "learning_rate": 2.589439733536518e-06, + "loss": 3.2991, + "step": 2895872 + }, + { + "epoch": 0.02, + "learning_rate": 2.5810537860259976e-06, + "loss": 3.3084, + "step": 2896384 + }, + { + "epoch": 0.02, + "learning_rate": 2.5726678385154775e-06, + "loss": 3.3054, + "step": 2896896 + }, + { + "epoch": 0.02, + "learning_rate": 2.564298269808689e-06, + "loss": 3.2979, + "step": 2897408 + }, + { + "epoch": 0.02, + "learning_rate": 2.555912322298169e-06, + "loss": 3.3089, + "step": 2897920 + }, + { + "epoch": 0.02, + "learning_rate": 2.547526374787649e-06, + "loss": 3.3122, + "step": 2898432 + }, + { + "epoch": 0.02, + "learning_rate": 2.539140427277129e-06, + "loss": 3.3135, + "step": 2898944 + }, + { + "epoch": 0.02, + "learning_rate": 2.5307708585703402e-06, + "loss": 3.2941, + "step": 2899456 + }, + { + "epoch": 0.02, + "learning_rate": 2.52238491105982e-06, + "loss": 3.2996, + "step": 2899968 + }, + { + "epoch": 0.03, + "eval_loss": 3.8635849952697754, + "eval_runtime": 321.1649, + "eval_samples_per_second": 1188.147, + "eval_steps_per_second": 37.13, + "step": 2900160 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.0132823108856873e+18, + "trial_name": null, + "trial_params": null +}