diff --git "a/checkpoint-2747520/trainer_state.json" "b/checkpoint-2747520/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2747520/trainer_state.json" @@ -0,0 +1,32509 @@ +{ + "best_metric": 3.8414785861968994, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/4/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2747520, + "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": 11.1231, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.824, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1929, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9737, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8118, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7019, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.598, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5315, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.444, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4024, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3529, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3115, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2496, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2092, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1764, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1286, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1127, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0799, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0415, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0196, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.004, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9743, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815558291179756e-05, + "loss": 4.955, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807172343669236e-05, + "loss": 4.9223, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798786396158716e-05, + "loss": 4.9166, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8945, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8715, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8521, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8266, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8179, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.803, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7952, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7789, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7661, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7568, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7461, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7349, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7039, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7035, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6783, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6836, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6638, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6661, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6447, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.643, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6326, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6258, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6149, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5886, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5976, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5989, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5916, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5715, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5587, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5602, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5471, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5613, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5225, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5405, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5297, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5101, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5199, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5046, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4946, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4899, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4998, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4796, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4763, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4694, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4607, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4691, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4753, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4483, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4599, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.463, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4457, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4344, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4367, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4313, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4215, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4167, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932100031250758e-05, + "loss": 4.4271, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931261436499706e-05, + "loss": 4.4261, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930422841748654e-05, + "loss": 4.4082, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3877, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4003, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4049, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927070100624819e-05, + "loss": 4.3923, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3974, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3791, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3776, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3726, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3707, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3775, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3662, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3823, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3652, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3479, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3519, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3586, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916173282502262e-05, + "loss": 4.3489, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.91533468775121e-05, + "loss": 4.3467, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3452, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3354, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3377, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.316, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3228, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.327, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3217, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.315, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3248, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.9069520160014366e-05, + "loss": 4.2985, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.9061134212503846e-05, + "loss": 4.3105, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3034, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3096, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035992748776015e-05, + "loss": 4.316, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.3044, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.298, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.292, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.2983, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2913, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2913, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2818, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896893792629932e-05, + "loss": 4.2804, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.89605519787888e-05, + "loss": 4.2816, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895216603127827e-05, + "loss": 4.2698, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894378008376775e-05, + "loss": 4.2752, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.2736, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892702456755045e-05, + "loss": 4.2692, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891863862003992e-05, + "loss": 4.2598, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891025267252941e-05, + "loss": 4.2771, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2773, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934971563121e-05, + "loss": 4.2651, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888511120880158e-05, + "loss": 4.2555, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.2629, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2624, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859969745073747e-05, + "loss": 4.2621, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851583797563226e-05, + "loss": 4.257, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843197850052706e-05, + "loss": 4.2564, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834811902542186e-05, + "loss": 4.2518, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826442333835395e-05, + "loss": 4.2488, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818056386324875e-05, + "loss": 4.2436, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880967043881436e-05, + "loss": 4.2466, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880128449130384e-05, + "loss": 4.2379, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879291492259705e-05, + "loss": 4.2334, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878452897508653e-05, + "loss": 4.2444, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877614302757601e-05, + "loss": 4.2327, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876775708006549e-05, + "loss": 4.2407, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2297, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875100156384818e-05, + "loss": 4.2235, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.195745468139648, + "eval_runtime": 307.7836, + "eval_samples_per_second": 1239.803, + "eval_steps_per_second": 38.745, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874261561633766e-05, + "loss": 4.2157, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873422966882714e-05, + "loss": 4.2142, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872584372131662e-05, + "loss": 4.2256, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871747415260983e-05, + "loss": 4.2177, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709088205099316e-05, + "loss": 4.2193, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700702257588796e-05, + "loss": 4.2085, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692316310078276e-05, + "loss": 4.2066, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683946741371485e-05, + "loss": 4.1983, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675560793860965e-05, + "loss": 4.2119, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667174846350445e-05, + "loss": 4.2045, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658788898839925e-05, + "loss": 4.2167, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650419330133134e-05, + "loss": 4.1982, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864204976142634e-05, + "loss": 4.1934, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863366381391582e-05, + "loss": 4.188, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.86252778664053e-05, + "loss": 4.1854, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861689191889478e-05, + "loss": 4.1827, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860850597138426e-05, + "loss": 4.1927, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860012002387375e-05, + "loss": 4.1782, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859173407636323e-05, + "loss": 4.1782, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858334812885271e-05, + "loss": 4.1981, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857497856014592e-05, + "loss": 4.1831, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.85665926126354e-05, + "loss": 4.1831, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855820666512488e-05, + "loss": 4.173, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854982071761436e-05, + "loss": 4.1847, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854145114890757e-05, + "loss": 4.1698, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853306520139705e-05, + "loss": 4.1711, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852467925388653e-05, + "loss": 4.1689, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851629330637601e-05, + "loss": 4.1623, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507923737669216e-05, + "loss": 4.1563, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84995377901587e-05, + "loss": 4.1566, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849115184264818e-05, + "loss": 4.1653, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848276589513766e-05, + "loss": 4.1647, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847439632643087e-05, + "loss": 4.159, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846601037892035e-05, + "loss": 4.1649, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845762443140983e-05, + "loss": 4.1598, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844923848389931e-05, + "loss": 4.158, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844086891519252e-05, + "loss": 4.1461, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432482967682e-05, + "loss": 4.1469, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842409702017148e-05, + "loss": 4.1362, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841571107266096e-05, + "loss": 4.1488, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840734150395417e-05, + "loss": 4.1345, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839895555644366e-05, + "loss": 4.1483, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839056960893314e-05, + "loss": 4.1345, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382200040226346e-05, + "loss": 4.138, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373814092715826e-05, + "loss": 4.1386, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365428145205306e-05, + "loss": 4.1348, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8357042197694786e-05, + "loss": 4.1334, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348672628987995e-05, + "loss": 4.1186, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340286681477475e-05, + "loss": 4.1242, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331900733966955e-05, + "loss": 4.1353, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323514786456435e-05, + "loss": 4.1308, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315145217749644e-05, + "loss": 4.1231, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306759270239124e-05, + "loss": 4.1126, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829837332272861e-05, + "loss": 4.1226, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828998737521809e-05, + "loss": 4.1088, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.82816178065113e-05, + "loss": 4.1323, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827323185900078e-05, + "loss": 4.1026, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826484591149026e-05, + "loss": 4.1241, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825645996397974e-05, + "loss": 4.1165, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824809039527295e-05, + "loss": 4.1038, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823970444776243e-05, + "loss": 4.1143, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823131850025191e-05, + "loss": 4.1111, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822293255274139e-05, + "loss": 4.0983, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.82145629840346e-05, + "loss": 4.0998, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820617703652408e-05, + "loss": 4.114, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197791089013564e-05, + "loss": 4.1013, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189405141503044e-05, + "loss": 4.0995, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818103557279625e-05, + "loss": 4.096, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817264962528573e-05, + "loss": 4.0922, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816426367777521e-05, + "loss": 4.1017, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815587773026469e-05, + "loss": 4.1133, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.81475081615579e-05, + "loss": 4.0929, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813912221404738e-05, + "loss": 4.1094, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813073626653686e-05, + "loss": 4.1092, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812235031902634e-05, + "loss": 4.0954, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811398075031955e-05, + "loss": 4.0906, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810559480280903e-05, + "loss": 4.0995, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809720885529852e-05, + "loss": 4.0949, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088822907788e-05, + "loss": 4.0859, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808045333908121e-05, + "loss": 4.0888, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807206739157069e-05, + "loss": 4.0938, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806368144406017e-05, + "loss": 4.101, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805529549654965e-05, + "loss": 4.0883, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046925927842856e-05, + "loss": 4.0733, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038539980332336e-05, + "loss": 4.0826, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030154032821816e-05, + "loss": 4.0863, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021768085311296e-05, + "loss": 4.0839, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013398516604505e-05, + "loss": 4.0899, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8005012569093985e-05, + "loss": 4.0756, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799662662158347e-05, + "loss": 4.0714, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988240674072945e-05, + "loss": 4.0713, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797987110536616e-05, + "loss": 4.0738, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797148515785564e-05, + "loss": 4.0777, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796309921034512e-05, + "loss": 4.0739, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954713262834594e-05, + "loss": 4.0909, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794634369412781e-05, + "loss": 4.0787, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793795774661729e-05, + "loss": 4.06, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792957179910677e-05, + "loss": 4.0717, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792118585159624e-05, + "loss": 4.0721, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791279990408572e-05, + "loss": 4.0722, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790441395657521e-05, + "loss": 4.0694, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789604438786842e-05, + "loss": 4.0671, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.78876584403579e-05, + "loss": 4.0618, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787927249284738e-05, + "loss": 4.0715, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787088654533686e-05, + "loss": 4.0471, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786250059782634e-05, + "loss": 4.0601, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785413102911955e-05, + "loss": 4.0593, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784574508160903e-05, + "loss": 4.0614, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783735913409851e-05, + "loss": 4.0509, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782897318658799e-05, + "loss": 4.0616, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782058723907747e-05, + "loss": 4.0475, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781220129156695e-05, + "loss": 4.0539, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780383172286016e-05, + "loss": 4.0513, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779544577534964e-05, + "loss": 4.052, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778705982783912e-05, + "loss": 4.0673, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.77786738803286e-05, + "loss": 4.058, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777030431162181e-05, + "loss": 4.051, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776191836411129e-05, + "loss": 4.0467, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775353241660077e-05, + "loss": 4.0513, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774514646909025e-05, + "loss": 4.0494, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773676052157973e-05, + "loss": 4.0472, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772837457406921e-05, + "loss": 4.0433, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771998862655869e-05, + "loss": 4.0426, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771160267904817e-05, + "loss": 4.0466, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770323311034138e-05, + "loss": 4.0342, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769484716283086e-05, + "loss": 4.0414, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768646121532034e-05, + "loss": 4.0402, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767807526780983e-05, + "loss": 4.0405, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.7669705699103036e-05, + "loss": 4.0289, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.7661319751592516e-05, + "loss": 4.0511, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.7652933804081996e-05, + "loss": 4.0546, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.7644547856571476e-05, + "loss": 4.0387, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636194666668415e-05, + "loss": 4.0316, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627808719157894e-05, + "loss": 4.039, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619422771647374e-05, + "loss": 4.0425, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7611036824136854e-05, + "loss": 4.042, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602650876626334e-05, + "loss": 4.0368, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759428130791955e-05, + "loss": 4.0373, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758589536040903e-05, + "loss": 4.0337, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757750941289851e-05, + "loss": 4.0385, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756912346538799e-05, + "loss": 4.0265, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756073751787747e-05, + "loss": 4.0361, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755235157036695e-05, + "loss": 4.0328, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754398200166016e-05, + "loss": 4.0204, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753559605414964e-05, + "loss": 4.034, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752721010663912e-05, + "loss": 4.0251, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.75188241591286e-05, + "loss": 4.0333, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751043821161808e-05, + "loss": 4.0217, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750205226410755e-05, + "loss": 4.019, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.027148246765137, + "eval_runtime": 308.4603, + "eval_samples_per_second": 1237.083, + "eval_steps_per_second": 38.66, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749366631659703e-05, + "loss": 4.0165, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748528036908652e-05, + "loss": 4.0089, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476894421576e-05, + "loss": 4.0276, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746850847406548e-05, + "loss": 4.0195, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746012252655496e-05, + "loss": 4.0273, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745173657904444e-05, + "loss": 4.0088, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744335063153392e-05, + "loss": 4.0148, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.74349646840234e-05, + "loss": 4.0027, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742659511531661e-05, + "loss": 4.0154, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741820916780609e-05, + "loss": 4.0179, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740982322029557e-05, + "loss": 4.0187, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740143727278505e-05, + "loss": 4.0108, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7393067704078257e-05, + "loss": 4.0019, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384681756567737e-05, + "loss": 4.0019, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376295809057216e-05, + "loss": 3.9998, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73679098615467e-05, + "loss": 3.9995, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735952391403618e-05, + "loss": 4.005, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735113796652566e-05, + "loss": 3.9962, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734275201901514e-05, + "loss": 3.9974, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334366071504616e-05, + "loss": 4.0199, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732599650279783e-05, + "loss": 4.0015, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731761055528731e-05, + "loss": 4.007, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730922460777679e-05, + "loss": 3.9941, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300838660266265e-05, + "loss": 4.0089, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292452712755745e-05, + "loss": 3.9855, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.7284066765245225e-05, + "loss": 4.0003, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.7275680817734705e-05, + "loss": 3.9945, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726731124902792e-05, + "loss": 3.9927, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.72589253015174e-05, + "loss": 3.981, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725053935400688e-05, + "loss": 3.9854, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724215340649636e-05, + "loss": 3.9962, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723376745898584e-05, + "loss": 3.9979, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722538151147532e-05, + "loss": 3.9935, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.72169955639648e-05, + "loss": 3.994, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720862599525801e-05, + "loss": 3.9913, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720024004774749e-05, + "loss": 3.9956, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719185410023697e-05, + "loss": 3.9793, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718346815272645e-05, + "loss": 3.9825, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717509858401966e-05, + "loss": 3.9723, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716671263650914e-05, + "loss": 3.9886, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715832668899862e-05, + "loss": 3.9761, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149940741488105e-05, + "loss": 3.9856, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141554793977585e-05, + "loss": 3.9783, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133168846467065e-05, + "loss": 3.9727, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124799277760274e-05, + "loss": 3.9868, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116413330249754e-05, + "loss": 3.9755, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108027382739234e-05, + "loss": 3.9777, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.959, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709127186652192e-05, + "loss": 3.9716, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.70828859190114e-05, + "loss": 3.9785, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707449997150088e-05, + "loss": 3.9762, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706611402399036e-05, + "loss": 3.9731, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705772807647984e-05, + "loss": 3.9563, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9706, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704097256026254e-05, + "loss": 3.958, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703258661275202e-05, + "loss": 3.9822, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.70242006652415e-05, + "loss": 3.9542, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701581471773098e-05, + "loss": 3.9722, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700742877022045e-05, + "loss": 3.9732, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699904282270993e-05, + "loss": 3.9538, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699065687519941e-05, + "loss": 3.963, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9668, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9525, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696551541147158e-05, + "loss": 3.9575, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695712946396106e-05, + "loss": 3.9669, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694874351645054e-05, + "loss": 3.9636, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694035756894003e-05, + "loss": 3.9517, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693198800023324e-05, + "loss": 3.9568, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692360205272272e-05, + "loss": 3.9482, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.69152161052122e-05, + "loss": 3.9602, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906830157701677e-05, + "loss": 3.9728, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9555, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.971, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881688693973846e-05, + "loss": 3.9674, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873302746463326e-05, + "loss": 3.9608, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9488, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9659, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9561, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9555, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9505, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9572, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681463387149715e-05, + "loss": 3.9696, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680624792398663e-05, + "loss": 3.952, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.938, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9452, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.67811064602588e-05, + "loss": 3.9542, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677272051274828e-05, + "loss": 3.9536, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9586, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9412, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674757904902045e-05, + "loss": 3.9439, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.9363, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9435, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9496, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714051637782104e-05, + "loss": 3.9478, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705665690271584e-05, + "loss": 3.9658, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697279742761064e-05, + "loss": 3.9453, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688893795250544e-05, + "loss": 3.9382, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668052422654375e-05, + "loss": 3.9422, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667213827903323e-05, + "loss": 3.9414, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666375233152271e-05, + "loss": 3.9501, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.9449, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9405, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663861086779488e-05, + "loss": 3.9389, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663022492028437e-05, + "loss": 3.9467, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662183897277385e-05, + "loss": 3.9237, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9384, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660506707775281e-05, + "loss": 3.9337, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659669750904602e-05, + "loss": 3.9367, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65883115615355e-05, + "loss": 3.9307, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.9387, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9264, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9304, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554784150297146e-05, + "loss": 3.9361, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546398202786626e-05, + "loss": 3.9306, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9482, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9416, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212567390588e-05, + "loss": 3.9362, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651287079154828e-05, + "loss": 3.9269, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9317, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9317, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648772932782045e-05, + "loss": 3.9304, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647934338030993e-05, + "loss": 3.9303, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470957432799404e-05, + "loss": 3.9207, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462571485288884e-05, + "loss": 3.9319, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.64542019165821e-05, + "loss": 3.9185, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644581596907158e-05, + "loss": 3.9251, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643743002156106e-05, + "loss": 3.9244, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642904407405054e-05, + "loss": 3.9236, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9147, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.9394, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640390261032271e-05, + "loss": 3.9406, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639551666281219e-05, + "loss": 3.9296, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.9141, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9297, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9262, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636198925157384e-05, + "loss": 3.9322, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635360330406332e-05, + "loss": 3.9237, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.9247, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.925, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328461840335494e-05, + "loss": 3.9303, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320075892824974e-05, + "loss": 3.9199, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311689945314454e-05, + "loss": 3.9242, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9233, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629493442909714e-05, + "loss": 3.9131, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628654848158662e-05, + "loss": 3.9252, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.62781625340761e-05, + "loss": 3.9232, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.919, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9146, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625302107034827e-05, + "loss": 3.9115, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.950533390045166, + "eval_runtime": 303.159, + "eval_samples_per_second": 1258.716, + "eval_steps_per_second": 39.336, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624463512283775e-05, + "loss": 3.9135, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623624917532723e-05, + "loss": 3.9061, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.9198, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621949365910993e-05, + "loss": 3.9137, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621110771159941e-05, + "loss": 3.9239, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620272176408889e-05, + "loss": 3.9043, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9118, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.8983, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177580300361056e-05, + "loss": 3.913, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169194352850536e-05, + "loss": 3.9148, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.916, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.908, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144052889122705e-05, + "loss": 3.9022, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135666941612185e-05, + "loss": 3.901, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127280994101665e-05, + "loss": 3.8965, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611889504659115e-05, + "loss": 3.899, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611052547788436e-05, + "loss": 3.9027, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610213953037384e-05, + "loss": 3.8952, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609375358286332e-05, + "loss": 3.8959, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.60853676353528e-05, + "loss": 3.9215, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607699806664601e-05, + "loss": 3.9036, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606861211913549e-05, + "loss": 3.9033, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606022617162497e-05, + "loss": 3.8969, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605184022411445e-05, + "loss": 3.9069, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604347065540766e-05, + "loss": 3.8903, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603508470789714e-05, + "loss": 3.9056, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602669876038662e-05, + "loss": 3.896, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183128128761e-05, + "loss": 3.894, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009943244169315e-05, + "loss": 3.8815, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001557296658795e-05, + "loss": 3.8897, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993171349148274e-05, + "loss": 3.8974, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984785401637754e-05, + "loss": 3.9011, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976415832930964e-05, + "loss": 3.9029, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5968029885420443e-05, + "loss": 3.8994, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959643937909923e-05, + "loss": 3.8914, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951257990399403e-05, + "loss": 3.9018, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594287204288888e-05, + "loss": 3.8845, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593450247418209e-05, + "loss": 3.8921, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592611652667157e-05, + "loss": 3.8775, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591773057916105e-05, + "loss": 3.892, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590934463165054e-05, + "loss": 3.8831, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590097506294375e-05, + "loss": 3.893, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589258911543323e-05, + "loss": 3.8884, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588420316792271e-05, + "loss": 3.8782, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587581722041219e-05, + "loss": 3.8954, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586743127290166e-05, + "loss": 3.8859, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585906170419488e-05, + "loss": 3.8822, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585067575668436e-05, + "loss": 3.8698, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584228980917384e-05, + "loss": 3.8787, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583390386166331e-05, + "loss": 3.8861, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582551791415279e-05, + "loss": 3.8839, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817148345446006e-05, + "loss": 3.8819, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808762397935486e-05, + "loss": 3.8694, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800376450424966e-05, + "loss": 3.8807, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579200688171818e-05, + "loss": 3.8661, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578362093420766e-05, + "loss": 3.8886, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5775234986697135e-05, + "loss": 3.8718, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766849039186615e-05, + "loss": 3.8783, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758463091676095e-05, + "loss": 3.8849, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750077144165575e-05, + "loss": 3.8674, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741707575458784e-05, + "loss": 3.8715, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733321627948264e-05, + "loss": 3.8772, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724935680437744e-05, + "loss": 3.8637, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571654973292723e-05, + "loss": 3.8757, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570818016422044e-05, + "loss": 3.8752, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569979421670992e-05, + "loss": 3.8789, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56914082691994e-05, + "loss": 3.8637, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568302232168888e-05, + "loss": 3.8713, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567465275298209e-05, + "loss": 3.8612, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566626680547157e-05, + "loss": 3.8721, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565788085796105e-05, + "loss": 3.8829, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564949491045053e-05, + "loss": 3.8713, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564110896294001e-05, + "loss": 3.8848, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563273939423322e-05, + "loss": 3.8825, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.56243534467227e-05, + "loss": 3.8795, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615967499212184e-05, + "loss": 3.86, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607581551701664e-05, + "loss": 3.8795, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559921198299487e-05, + "loss": 3.8758, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559082603548435e-05, + "loss": 3.8669, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558244008797383e-05, + "loss": 3.8694, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557405414046331e-05, + "loss": 3.8732, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556568457175652e-05, + "loss": 3.8871, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557298624246e-05, + "loss": 3.869, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554891267673548e-05, + "loss": 3.854, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554052672922496e-05, + "loss": 3.8658, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553215716051817e-05, + "loss": 3.8681, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552377121300765e-05, + "loss": 3.8727, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551538526549714e-05, + "loss": 3.8726, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550699931798662e-05, + "loss": 3.8627, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549862974927983e-05, + "loss": 3.8628, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549024380176931e-05, + "loss": 3.8533, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548185785425879e-05, + "loss": 3.8603, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547347190674827e-05, + "loss": 3.8629, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465102338041476e-05, + "loss": 3.874, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456716390530956e-05, + "loss": 3.8864, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448330443020436e-05, + "loss": 3.8637, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439944495509916e-05, + "loss": 3.8539, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431574926803125e-05, + "loss": 3.8635, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423188979292605e-05, + "loss": 3.8609, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541480303178209e-05, + "loss": 3.8713, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540641708427157e-05, + "loss": 3.8626, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539804751556478e-05, + "loss": 3.8629, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538966156805426e-05, + "loss": 3.8588, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538127562054374e-05, + "loss": 3.871, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537288967303322e-05, + "loss": 3.8448, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.53645037255227e-05, + "loss": 3.8566, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535613415681591e-05, + "loss": 3.8519, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534774820930539e-05, + "loss": 3.8641, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533936226179487e-05, + "loss": 3.85, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533097631428435e-05, + "loss": 3.8595, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532260674557756e-05, + "loss": 3.8483, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314220798067045e-05, + "loss": 3.8534, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305834850556525e-05, + "loss": 3.8562, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297448903046005e-05, + "loss": 3.8567, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289079334339214e-05, + "loss": 3.8675, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280693386828694e-05, + "loss": 3.8678, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.52723238181219e-05, + "loss": 3.8579, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526393787061138e-05, + "loss": 3.8507, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525555192310086e-05, + "loss": 3.8547, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524716597559034e-05, + "loss": 3.8589, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523878002807982e-05, + "loss": 3.8495, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52303940805693e-05, + "loss": 3.8538, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522200813305878e-05, + "loss": 3.8521, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521362218554826e-05, + "loss": 3.8507, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520525261684148e-05, + "loss": 3.8467, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.8468, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518848072182044e-05, + "loss": 3.8474, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518009477430992e-05, + "loss": 3.8523, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517172520560313e-05, + "loss": 3.8374, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8662, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515495331058209e-05, + "loss": 3.8613, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514656736307156e-05, + "loss": 3.86, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513818141556104e-05, + "loss": 3.8367, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512981184685426e-05, + "loss": 3.8546, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512142589934374e-05, + "loss": 3.8581, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511303995183322e-05, + "loss": 3.8529, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104654004322697e-05, + "loss": 3.8496, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509628443561591e-05, + "loss": 3.8507, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508789848810539e-05, + "loss": 3.8511, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079512540594866e-05, + "loss": 3.8572, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5071126593084346e-05, + "loss": 3.8483, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506275702437756e-05, + "loss": 3.8512, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054371076867035e-05, + "loss": 3.8516, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045985129356515e-05, + "loss": 3.8394, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037599181845995e-05, + "loss": 3.8534, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502922961313921e-05, + "loss": 3.8509, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020843665628684e-05, + "loss": 3.8485, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501245771811817e-05, + "loss": 3.8396, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500407177060765e-05, + "loss": 3.8389, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.909938097000122, + "eval_runtime": 303.9015, + "eval_samples_per_second": 1255.64, + "eval_steps_per_second": 39.24, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499568582309713e-05, + "loss": 3.8392, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498729987558661e-05, + "loss": 3.8336, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497891392807609e-05, + "loss": 3.8457, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497052798056557e-05, + "loss": 3.8439, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496214203305505e-05, + "loss": 3.8569, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495375608554453e-05, + "loss": 3.8324, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494537013803401e-05, + "loss": 3.8391, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493698419052349e-05, + "loss": 3.8253, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.49286146218167e-05, + "loss": 3.8457, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492022867430618e-05, + "loss": 3.8437, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491184272679566e-05, + "loss": 3.8405, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490345677928514e-05, + "loss": 3.8405, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895087210578355e-05, + "loss": 3.8303, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886701263067835e-05, + "loss": 3.8371, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878315315557315e-05, + "loss": 3.8243, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869929368046795e-05, + "loss": 3.8333, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861559799340004e-05, + "loss": 3.8285, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853173851829484e-05, + "loss": 3.8276, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844787904318964e-05, + "loss": 3.8327, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836401956808444e-05, + "loss": 3.851, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482803238810165e-05, + "loss": 3.832, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481964644059113e-05, + "loss": 3.8364, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481126049308061e-05, + "loss": 3.8302, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480287454557009e-05, + "loss": 3.838, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479450497686331e-05, + "loss": 3.8261, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478611902935279e-05, + "loss": 3.8362, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477773308184227e-05, + "loss": 3.8282, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476934713433175e-05, + "loss": 3.8256, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476097756562496e-05, + "loss": 3.8169, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475259161811444e-05, + "loss": 3.8225, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474420567060392e-05, + "loss": 3.8305, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47358197230934e-05, + "loss": 3.8338, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727450154386606e-05, + "loss": 3.8365, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4719064206876086e-05, + "loss": 3.8305, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710678259365566e-05, + "loss": 3.8248, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702292311855046e-05, + "loss": 3.8349, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469392274314826e-05, + "loss": 3.8226, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468553679563774e-05, + "loss": 3.8236, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467715084812722e-05, + "loss": 3.8096, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668764900616695e-05, + "loss": 3.8243, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466039533190991e-05, + "loss": 3.82, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465200938439939e-05, + "loss": 3.8321, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464362343688887e-05, + "loss": 3.8232, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635237489378344e-05, + "loss": 3.8134, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462686792067156e-05, + "loss": 3.8311, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461848197316104e-05, + "loss": 3.8227, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461009602565052e-05, + "loss": 3.8177, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460171007814e-05, + "loss": 3.8075, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593340509433216e-05, + "loss": 3.8095, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584954561922696e-05, + "loss": 3.8224, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457656861441217e-05, + "loss": 3.8191, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456818266690165e-05, + "loss": 3.8169, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559813098194865e-05, + "loss": 3.8085, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551427150684345e-05, + "loss": 3.8178, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454304120317382e-05, + "loss": 3.8037, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.45346552556633e-05, + "loss": 3.8232, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526285686956514e-05, + "loss": 3.8051, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517899739445994e-05, + "loss": 3.8188, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450951379193547e-05, + "loss": 3.8185, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501127844424954e-05, + "loss": 3.8112, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492741896914433e-05, + "loss": 3.8067, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448437232820764e-05, + "loss": 3.8166, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447598638069712e-05, + "loss": 3.8022, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.44676004331866e-05, + "loss": 3.81, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445921448567608e-05, + "loss": 3.8178, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445084491696929e-05, + "loss": 3.8151, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444245896945877e-05, + "loss": 3.8028, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443407302194825e-05, + "loss": 3.8061, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442568707443773e-05, + "loss": 3.8032, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441731750573094e-05, + "loss": 3.8055, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440893155822042e-05, + "loss": 3.8186, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.44005456107099e-05, + "loss": 3.8116, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439215966319939e-05, + "loss": 3.8235, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383790094492596e-05, + "loss": 3.8214, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375404146982076e-05, + "loss": 3.821, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4367018199471556e-05, + "loss": 3.8022, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358632251961036e-05, + "loss": 3.8124, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350246304450516e-05, + "loss": 3.82, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341876735743725e-05, + "loss": 3.8063, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333490788233205e-05, + "loss": 3.8075, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325104840722685e-05, + "loss": 3.812, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316718893212165e-05, + "loss": 3.8272, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308349324505374e-05, + "loss": 3.8092, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299963376994854e-05, + "loss": 3.7925, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429157742948434e-05, + "loss": 3.8058, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428319148197382e-05, + "loss": 3.8078, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427482191326703e-05, + "loss": 3.8132, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426643596575651e-05, + "loss": 3.8128, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425805001824599e-05, + "loss": 3.8002, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424966407073547e-05, + "loss": 3.8039, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424127812322495e-05, + "loss": 3.7997, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423290855451816e-05, + "loss": 3.7966, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422452260700764e-05, + "loss": 3.8063, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421613665949712e-05, + "loss": 3.8114, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.42077507119866e-05, + "loss": 3.8269, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419938114327981e-05, + "loss": 3.8118, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190995195769294e-05, + "loss": 3.7915, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182609248258774e-05, + "loss": 3.8031, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174223300748254e-05, + "loss": 3.7985, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165853732041464e-05, + "loss": 3.8131, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157467784530943e-05, + "loss": 3.8083, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149081837020423e-05, + "loss": 3.804, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.41406958895099e-05, + "loss": 3.799, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413232632080311e-05, + "loss": 3.8114, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412394037329259e-05, + "loss": 3.7889, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411555442578207e-05, + "loss": 3.8013, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410716847827155e-05, + "loss": 3.7908, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409879890956476e-05, + "loss": 3.8096, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409041296205425e-05, + "loss": 3.794, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408202701454373e-05, + "loss": 3.7993, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407364106703321e-05, + "loss": 3.7908, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406527149832642e-05, + "loss": 3.7982, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568855508159e-05, + "loss": 3.7998, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404849960330538e-05, + "loss": 3.7981, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404011365579486e-05, + "loss": 3.8099, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403172770828434e-05, + "loss": 3.8096, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023374518381275e-05, + "loss": 3.8017, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014988570870755e-05, + "loss": 3.7939, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006602623360235e-05, + "loss": 3.7964, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998216675849715e-05, + "loss": 3.806, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.39898307283392e-05, + "loss": 3.7878, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398144478082868e-05, + "loss": 3.8006, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397305883331816e-05, + "loss": 3.7904, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396467288580764e-05, + "loss": 3.798, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395630331710085e-05, + "loss": 3.7932, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394791736959033e-05, + "loss": 3.7926, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393953142207981e-05, + "loss": 3.7881, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393114547456929e-05, + "loss": 3.8004, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.39227759058625e-05, + "loss": 3.7836, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391438995835198e-05, + "loss": 3.8087, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390600401084146e-05, + "loss": 3.8013, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389761806333094e-05, + "loss": 3.8114, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889248494624155e-05, + "loss": 3.7779, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880862547113635e-05, + "loss": 3.8021, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872476599603115e-05, + "loss": 3.8, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864090652092595e-05, + "loss": 3.7983, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855704704582075e-05, + "loss": 3.795, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847335135875284e-05, + "loss": 3.7996, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838949188364764e-05, + "loss": 3.7944, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830563240854244e-05, + "loss": 3.8046, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382217729334372e-05, + "loss": 3.7874, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381380772463693e-05, + "loss": 3.7965, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380542177712641e-05, + "loss": 3.7947, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379703582961589e-05, + "loss": 3.7874, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378864988210537e-05, + "loss": 3.7946, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378028031339859e-05, + "loss": 3.8012, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377189436588807e-05, + "loss": 3.7933, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376350841837754e-05, + "loss": 3.7834, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375512247086702e-05, + "loss": 3.7889, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.884645700454712, + "eval_runtime": 304.0233, + "eval_samples_per_second": 1255.138, + "eval_steps_per_second": 39.224, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374675290216024e-05, + "loss": 3.7918, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373836695464972e-05, + "loss": 3.7799, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372998100713919e-05, + "loss": 3.789, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372159505962867e-05, + "loss": 3.7944, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371322549092189e-05, + "loss": 3.8011, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370483954341137e-05, + "loss": 3.7859, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369645359590085e-05, + "loss": 3.7832, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368806764839033e-05, + "loss": 3.7726, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367969807968354e-05, + "loss": 3.7893, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3671312132173016e-05, + "loss": 3.7933, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662926184662496e-05, + "loss": 3.7857, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654540237151976e-05, + "loss": 3.7883, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364617066844519e-05, + "loss": 3.7774, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637784720934665e-05, + "loss": 3.7838, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629398773424145e-05, + "loss": 3.7744, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3621012825913625e-05, + "loss": 3.7808, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361264325720684e-05, + "loss": 3.7731, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604257309696314e-05, + "loss": 3.7809, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.35958713621858e-05, + "loss": 3.7755, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358748541467528e-05, + "loss": 3.7973, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357911584596849e-05, + "loss": 3.784, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357072989845797e-05, + "loss": 3.7895, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356234395094745e-05, + "loss": 3.7754, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355395800343693e-05, + "loss": 3.7861, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354558843473014e-05, + "loss": 3.7728, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353720248721962e-05, + "loss": 3.7846, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.35288165397091e-05, + "loss": 3.7828, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352043059219858e-05, + "loss": 3.7699, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351206102349179e-05, + "loss": 3.7654, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350367507598127e-05, + "loss": 3.7723, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349528912847075e-05, + "loss": 3.7807, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486903180960234e-05, + "loss": 3.7819, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347853361225344e-05, + "loss": 3.7843, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347014766474292e-05, + "loss": 3.7871, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34617617172324e-05, + "loss": 3.7744, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345337576972188e-05, + "loss": 3.7812, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344500620101509e-05, + "loss": 3.7739, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343662025350457e-05, + "loss": 3.7722, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342823430599405e-05, + "loss": 3.7585, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341984835848353e-05, + "loss": 3.7767, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341147878977674e-05, + "loss": 3.769, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340309284226622e-05, + "loss": 3.7815, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.33947068947557e-05, + "loss": 3.7719, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338632094724519e-05, + "loss": 3.7657, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.33779513785384e-05, + "loss": 3.7809, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336956543102788e-05, + "loss": 3.7702, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336117948351736e-05, + "loss": 3.7692, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335279353600684e-05, + "loss": 3.7605, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344423967300046e-05, + "loss": 3.7587, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3336038019789526e-05, + "loss": 3.7738, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327652072279006e-05, + "loss": 3.771, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3319266124768486e-05, + "loss": 3.7677, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310896556061695e-05, + "loss": 3.7629, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302510608551175e-05, + "loss": 3.7706, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294124661040655e-05, + "loss": 3.7507, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328573871353014e-05, + "loss": 3.7756, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327736914482335e-05, + "loss": 3.7594, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326898319731283e-05, + "loss": 3.7678, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326059724980231e-05, + "loss": 3.7673, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325221130229179e-05, + "loss": 3.7644, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243841733585e-05, + "loss": 3.7583, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323545578607448e-05, + "loss": 3.7682, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322706983856396e-05, + "loss": 3.7594, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321868389105344e-05, + "loss": 3.7602, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321031432234665e-05, + "loss": 3.7689, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320192837483613e-05, + "loss": 3.7666, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319354242732561e-05, + "loss": 3.7529, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185156479815095e-05, + "loss": 3.7631, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176786911108304e-05, + "loss": 3.7539, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168400963597784e-05, + "loss": 3.7577, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3160015016087264e-05, + "loss": 3.7717, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151629068576744e-05, + "loss": 3.7667, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314325949986995e-05, + "loss": 3.7722, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313487355235943e-05, + "loss": 3.7698, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312648760484891e-05, + "loss": 3.7778, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311810165733839e-05, + "loss": 3.7571, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.31097320886316e-05, + "loss": 3.7629, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310134614112108e-05, + "loss": 3.7716, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309296019361056e-05, + "loss": 3.7556, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308457424610005e-05, + "loss": 3.7647, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307620467739326e-05, + "loss": 3.7671, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306781872988274e-05, + "loss": 3.7728, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305943278237222e-05, + "loss": 3.763, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.30510468348617e-05, + "loss": 3.7508, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304267726615491e-05, + "loss": 3.7566, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303429131864439e-05, + "loss": 3.7608, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302590537113387e-05, + "loss": 3.7651, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301751942362335e-05, + "loss": 3.7648, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3009149854916556e-05, + "loss": 3.7572, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000763907406036e-05, + "loss": 3.7611, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2992377959895516e-05, + "loss": 3.7529, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983992012385e-05, + "loss": 3.7507, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297562244367821e-05, + "loss": 3.7572, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296723649616769e-05, + "loss": 3.7688, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295885054865717e-05, + "loss": 3.7817, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295046460114665e-05, + "loss": 3.7657, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294209503243986e-05, + "loss": 3.7436, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293370908492934e-05, + "loss": 3.7611, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292532313741882e-05, + "loss": 3.7547, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.29169371899083e-05, + "loss": 3.7682, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290856762120151e-05, + "loss": 3.7592, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290018167369099e-05, + "loss": 3.7587, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289179572618047e-05, + "loss": 3.7557, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883426157473685e-05, + "loss": 3.7605, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2875040209963165e-05, + "loss": 3.7479, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866654262452645e-05, + "loss": 3.7554, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858268314942125e-05, + "loss": 3.7443, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849898746235334e-05, + "loss": 3.7664, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841512798724814e-05, + "loss": 3.7493, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833126851214294e-05, + "loss": 3.7521, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824740903703774e-05, + "loss": 3.7437, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816354956193254e-05, + "loss": 3.7569, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280798538748646e-05, + "loss": 3.753, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279959943997594e-05, + "loss": 3.7523, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279121349246542e-05, + "loss": 3.7667, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.27828275449549e-05, + "loss": 3.7659, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277447435505185e-05, + "loss": 3.758, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276608840754133e-05, + "loss": 3.7519, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275770246003081e-05, + "loss": 3.7493, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274931651252029e-05, + "loss": 3.7608, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274093056500977e-05, + "loss": 3.7451, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273254461749925e-05, + "loss": 3.7553, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272415866998873e-05, + "loss": 3.7436, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271577272247821e-05, + "loss": 3.7566, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270740315377142e-05, + "loss": 3.7428, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26990172062609e-05, + "loss": 3.7502, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269063125875038e-05, + "loss": 3.7499, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268224531123986e-05, + "loss": 3.7512, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267387574253307e-05, + "loss": 3.7462, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266548979502255e-05, + "loss": 3.7609, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265710384751203e-05, + "loss": 3.7608, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264871790000151e-05, + "loss": 3.7639, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264034833129472e-05, + "loss": 3.7361, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.26319623837842e-05, + "loss": 3.7593, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262357643627368e-05, + "loss": 3.7553, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261519048876316e-05, + "loss": 3.7568, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260682092005637e-05, + "loss": 3.7485, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259843497254585e-05, + "loss": 3.7553, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.259004902503533e-05, + "loss": 3.7512, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258166307752481e-05, + "loss": 3.762, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2573293508818026e-05, + "loss": 3.7438, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564907561307506e-05, + "loss": 3.7568, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556521613796986e-05, + "loss": 3.7502, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254813566628646e-05, + "loss": 3.7465, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539766097579675e-05, + "loss": 3.7527, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2531380150069155e-05, + "loss": 3.7512, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522994202558635e-05, + "loss": 3.7557, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251460825504811e-05, + "loss": 3.738, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2506238686341324e-05, + "loss": 3.749, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.868586301803589, + "eval_runtime": 304.0381, + "eval_samples_per_second": 1255.076, + "eval_steps_per_second": 39.222, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497852738830804e-05, + "loss": 3.7463, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489466791320284e-05, + "loss": 3.7369, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2481080843809764e-05, + "loss": 3.7475, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472694896299244e-05, + "loss": 3.7531, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464308948788724e-05, + "loss": 3.7596, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455923001278204e-05, + "loss": 3.741, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447537053767684e-05, + "loss": 3.7367, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439151106257164e-05, + "loss": 3.7378, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243078153755037e-05, + "loss": 3.7433, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242239559003985e-05, + "loss": 3.7531, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241400964252933e-05, + "loss": 3.7434, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240562369501881e-05, + "loss": 3.7452, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239727050511576e-05, + "loss": 3.7385, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238888455760524e-05, + "loss": 3.7391, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238049861009472e-05, + "loss": 3.7358, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.23721126625842e-05, + "loss": 3.7371, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236372671507368e-05, + "loss": 3.7338, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235534076756316e-05, + "loss": 3.7356, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234695482005264e-05, + "loss": 3.7375, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233856887254212e-05, + "loss": 3.7521, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233019930383533e-05, + "loss": 3.7432, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232181335632481e-05, + "loss": 3.7505, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313427408814287e-05, + "loss": 3.7319, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2305041461303767e-05, + "loss": 3.7464, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296671892596976e-05, + "loss": 3.7303, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288285945086456e-05, + "loss": 3.7447, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227989999757594e-05, + "loss": 3.7372, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227151405006542e-05, + "loss": 3.7285, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226314448135863e-05, + "loss": 3.7317, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225475853384811e-05, + "loss": 3.7306, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224637258633759e-05, + "loss": 3.7378, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223798663882707e-05, + "loss": 3.7423, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222961707012028e-05, + "loss": 3.7427, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222123112260976e-05, + "loss": 3.7491, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221284517509924e-05, + "loss": 3.7273, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220447560639245e-05, + "loss": 3.7436, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219608965888193e-05, + "loss": 3.7369, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218770371137141e-05, + "loss": 3.7258, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179317763860896e-05, + "loss": 3.7211, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170948195154105e-05, + "loss": 3.731, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162562247643585e-05, + "loss": 3.734, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154176300133065e-05, + "loss": 3.741, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145790352622545e-05, + "loss": 3.7291, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137420783915754e-05, + "loss": 3.7258, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2129034836405234e-05, + "loss": 3.7435, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120648888894714e-05, + "loss": 3.7318, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112262941384194e-05, + "loss": 3.7297, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21038933726774e-05, + "loss": 3.7208, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209550742516688e-05, + "loss": 3.7176, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208712147765636e-05, + "loss": 3.7341, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207873553014585e-05, + "loss": 3.7329, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207036596143906e-05, + "loss": 3.7287, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206198001392854e-05, + "loss": 3.7215, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205359406641802e-05, + "loss": 3.7314, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.20452081189075e-05, + "loss": 3.7094, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203683855020071e-05, + "loss": 3.7357, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202845260269019e-05, + "loss": 3.721, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.202006665517967e-05, + "loss": 3.7234, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201168070766915e-05, + "loss": 3.7325, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200331113896236e-05, + "loss": 3.7225, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199492519145184e-05, + "loss": 3.7194, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986539243941317e-05, + "loss": 3.7346, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781532964308e-05, + "loss": 3.7167, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196978372772401e-05, + "loss": 3.7211, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196139778021349e-05, + "loss": 3.7293, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195301183270297e-05, + "loss": 3.7277, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194462588519245e-05, + "loss": 3.7143, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193625631648566e-05, + "loss": 3.7231, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192787036897514e-05, + "loss": 3.7132, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191948442146462e-05, + "loss": 3.7183, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.19110984739541e-05, + "loss": 3.7315, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190272890524731e-05, + "loss": 3.7263, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189434295773679e-05, + "loss": 3.736, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188595701022627e-05, + "loss": 3.7287, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187757106271575e-05, + "loss": 3.7409, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869201494008966e-05, + "loss": 3.7172, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860815546498446e-05, + "loss": 3.729, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1852429598987926e-05, + "loss": 3.732, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1844043651477406e-05, + "loss": 3.7143, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835674082770615e-05, + "loss": 3.7263, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827288135260095e-05, + "loss": 3.7299, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818902187749575e-05, + "loss": 3.7357, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1810516240239055e-05, + "loss": 3.7246, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1802146671532264e-05, + "loss": 3.7116, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793760724021744e-05, + "loss": 3.7169, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785374776511224e-05, + "loss": 3.7229, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776988829000704e-05, + "loss": 3.7284, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176861926029392e-05, + "loss": 3.7268, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.17602333127834e-05, + "loss": 3.7243, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175184736527288e-05, + "loss": 3.7149, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174346141776236e-05, + "loss": 3.7161, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173509184905557e-05, + "loss": 3.7128, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172670590154505e-05, + "loss": 3.7205, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171831995403453e-05, + "loss": 3.7307, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170993400652401e-05, + "loss": 3.7398, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170156443781722e-05, + "loss": 3.7305, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.16931784903067e-05, + "loss": 3.7105, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168479254279618e-05, + "loss": 3.7217, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676422974089393e-05, + "loss": 3.716, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1668037026578873e-05, + "loss": 3.728, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659651079068353e-05, + "loss": 3.7218, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165126513155783e-05, + "loss": 3.727, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164289556285104e-05, + "loss": 3.7197, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163450961534052e-05, + "loss": 3.7174, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162612366783e-05, + "loss": 3.715, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161773772031948e-05, + "loss": 3.7148, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160936815161269e-05, + "loss": 3.7082, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160098220410217e-05, + "loss": 3.727, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159259625659165e-05, + "loss": 3.7126, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158421030908113e-05, + "loss": 3.7139, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157584074037435e-05, + "loss": 3.7105, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156745479286383e-05, + "loss": 3.7135, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155906884535331e-05, + "loss": 3.7207, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155068289784278e-05, + "loss": 3.7144, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1542313329135996e-05, + "loss": 3.7294, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.1533927381625476e-05, + "loss": 3.7255, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.1525557812918685e-05, + "loss": 3.7231, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1517171865408165e-05, + "loss": 3.7194, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508785917897645e-05, + "loss": 3.7056, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500399970387125e-05, + "loss": 3.7275, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1492014022876605e-05, + "loss": 3.7149, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483628075366085e-05, + "loss": 3.7156, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475242127855565e-05, + "loss": 3.707, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466856180345045e-05, + "loss": 3.7188, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458486611638254e-05, + "loss": 3.7088, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1450100664127734e-05, + "loss": 3.7125, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441714716617214e-05, + "loss": 3.7111, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433328769106694e-05, + "loss": 3.7183, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14249592003999e-05, + "loss": 3.7071, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141657325288938e-05, + "loss": 3.7274, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140818730537886e-05, + "loss": 3.7192, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139980135786834e-05, + "loss": 3.7293, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139143178916156e-05, + "loss": 3.7031, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138304584165104e-05, + "loss": 3.7233, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137465989414052e-05, + "loss": 3.7193, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136627394663e-05, + "loss": 3.7183, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135790437792321e-05, + "loss": 3.7167, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134951843041269e-05, + "loss": 3.7205, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134113248290217e-05, + "loss": 3.7119, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133274653539165e-05, + "loss": 3.7317, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324376966684857e-05, + "loss": 3.7034, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315991019174337e-05, + "loss": 3.7194, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307605071663816e-05, + "loss": 3.7152, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299219124153296e-05, + "loss": 3.7127, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129084955544651e-05, + "loss": 3.7141, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128246360793599e-05, + "loss": 3.7156, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.12740940392292e-05, + "loss": 3.7197, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126570809171868e-05, + "loss": 3.7, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125732214420816e-05, + "loss": 3.7151, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8581292629241943, + "eval_runtime": 303.1213, + "eval_samples_per_second": 1258.872, + "eval_steps_per_second": 39.341, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124893619669764e-05, + "loss": 3.7141, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124055024918712e-05, + "loss": 3.7007, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.12321643016766e-05, + "loss": 3.7114, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122377835416608e-05, + "loss": 3.7145, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121539240665556e-05, + "loss": 3.7247, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120702283794877e-05, + "loss": 3.7091, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119863689043825e-05, + "loss": 3.7019, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119025094292773e-05, + "loss": 3.7015, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118186499541721e-05, + "loss": 3.7108, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1173495426710426e-05, + "loss": 3.7157, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1165109479199906e-05, + "loss": 3.708, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156723531689386e-05, + "loss": 3.7096, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148353962982595e-05, + "loss": 3.7074, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139968015472075e-05, + "loss": 3.7036, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131582067961555e-05, + "loss": 3.6985, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123196120451035e-05, + "loss": 3.7004, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114810172940515e-05, + "loss": 3.7009, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106424225429995e-05, + "loss": 3.7009, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1098038277919475e-05, + "loss": 3.7033, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089652330408955e-05, + "loss": 3.7133, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081282761702164e-05, + "loss": 3.7123, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107289681419165e-05, + "loss": 3.7138, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106452724548486e-05, + "loss": 3.6982, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105614129797434e-05, + "loss": 3.7091, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104775535046382e-05, + "loss": 3.697, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.10393694029533e-05, + "loss": 3.7135, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103098345544278e-05, + "loss": 3.6996, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102259750793226e-05, + "loss": 3.6967, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101421156042174e-05, + "loss": 3.6974, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100582561291121e-05, + "loss": 3.6992, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099745604420443e-05, + "loss": 3.7015, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098907009669391e-05, + "loss": 3.7086, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098068414918339e-05, + "loss": 3.712, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097229820167287e-05, + "loss": 3.7084, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963928632966084e-05, + "loss": 3.6985, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955542685455564e-05, + "loss": 3.7097, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094715673794504e-05, + "loss": 3.7052, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093878716923825e-05, + "loss": 3.6879, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093040122172773e-05, + "loss": 3.6917, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092201527421721e-05, + "loss": 3.6948, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913629326706686e-05, + "loss": 3.7001, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905243379196166e-05, + "loss": 3.7068, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896857431685646e-05, + "loss": 3.6971, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888471484175126e-05, + "loss": 3.6938, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0880085536664606e-05, + "loss": 3.7079, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087171596795782e-05, + "loss": 3.6993, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.08633300204473e-05, + "loss": 3.6997, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085496045174051e-05, + "loss": 3.6845, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084657450422999e-05, + "loss": 3.6803, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083818855671947e-05, + "loss": 3.7052, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082980260920895e-05, + "loss": 3.6949, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082141666169843e-05, + "loss": 3.6998, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081303071418791e-05, + "loss": 3.6917, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080464476667739e-05, + "loss": 3.6917, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079625881916687e-05, + "loss": 3.6788, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078790562926381e-05, + "loss": 3.6987, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077951968175329e-05, + "loss": 3.6913, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771133734242776e-05, + "loss": 3.6912, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762747786732255e-05, + "loss": 3.7028, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754361839221735e-05, + "loss": 3.6899, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745975891711215e-05, + "loss": 3.6866, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737589944200695e-05, + "loss": 3.7022, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0729203996690175e-05, + "loss": 3.686, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720834427983384e-05, + "loss": 3.6833, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712448480472864e-05, + "loss": 3.6998, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0704062532962344e-05, + "loss": 3.6961, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695676585451824e-05, + "loss": 3.68, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068730701674503e-05, + "loss": 3.695, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067892106923451e-05, + "loss": 3.6811, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067053512172399e-05, + "loss": 3.6848, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066214917421347e-05, + "loss": 3.6982, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065377960550669e-05, + "loss": 3.6951, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064539365799617e-05, + "loss": 3.6989, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063700771048565e-05, + "loss": 3.6965, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062862176297513e-05, + "loss": 3.7085, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.062025219426834e-05, + "loss": 3.6868, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061186624675782e-05, + "loss": 3.6959, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.06034802992473e-05, + "loss": 3.7004, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059511073054051e-05, + "loss": 3.6827, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058672478302999e-05, + "loss": 3.6943, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057833883551947e-05, + "loss": 3.7004, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056995288800895e-05, + "loss": 3.7009, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056156694049843e-05, + "loss": 3.6948, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553180992987914e-05, + "loss": 3.6818, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544795045477394e-05, + "loss": 3.6784, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0536409097966874e-05, + "loss": 3.6902, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052803952926008e-05, + "loss": 3.6977, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051965358174956e-05, + "loss": 3.6957, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051126763423904e-05, + "loss": 3.6919, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502881686728516e-05, + "loss": 3.6799, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049451211802173e-05, + "loss": 3.6866, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048612617051121e-05, + "loss": 3.6825, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047774022300069e-05, + "loss": 3.69, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469354275490165e-05, + "loss": 3.6953, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046098470678338e-05, + "loss": 3.7102, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045259875927287e-05, + "loss": 3.6959, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044421281176235e-05, + "loss": 3.6808, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043582686425182e-05, + "loss": 3.6861, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.04274409167413e-05, + "loss": 3.6855, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041905496923078e-05, + "loss": 3.6977, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041066902172026e-05, + "loss": 3.6896, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040229945301347e-05, + "loss": 3.6978, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039391350550295e-05, + "loss": 3.6892, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038552755799243e-05, + "loss": 3.6802, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037714161048191e-05, + "loss": 3.6897, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036877204177512e-05, + "loss": 3.6823, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0360386094264605e-05, + "loss": 3.6791, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0352000146754085e-05, + "loss": 3.6907, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343614199243565e-05, + "loss": 3.6847, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335244630536774e-05, + "loss": 3.6811, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326858683026254e-05, + "loss": 3.6825, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318472735515734e-05, + "loss": 3.6789, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0310086788005214e-05, + "loss": 3.6903, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301700840494694e-05, + "loss": 3.6802, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293314892984174e-05, + "loss": 3.7016, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284928945473654e-05, + "loss": 3.6948, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027655937676686e-05, + "loss": 3.6936, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026818980806007e-05, + "loss": 3.6861, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025980386054955e-05, + "loss": 3.6753, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025141791303904e-05, + "loss": 3.6911, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024303196552852e-05, + "loss": 3.6889, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234646018018e-05, + "loss": 3.6832, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022626007050748e-05, + "loss": 3.6759, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021787412299696e-05, + "loss": 3.6894, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020950455429017e-05, + "loss": 3.6758, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020111860677965e-05, + "loss": 3.6834, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019273265926913e-05, + "loss": 3.6782, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018434671175861e-05, + "loss": 3.6893, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175977143051817e-05, + "loss": 3.6728, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167591195541297e-05, + "loss": 3.6979, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159205248030776e-05, + "loss": 3.687, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150819300520256e-05, + "loss": 3.6988, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014244973181347e-05, + "loss": 3.6737, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013408016310668e-05, + "loss": 3.6933, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012569421559616e-05, + "loss": 3.688, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011730826808564e-05, + "loss": 3.6911, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010892232057512e-05, + "loss": 3.686, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.01005363730646e-05, + "loss": 3.6856, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009215042555408e-05, + "loss": 3.6842, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008376447804356e-05, + "loss": 3.6977, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007539490933677e-05, + "loss": 3.6746, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006700896182625e-05, + "loss": 3.6886, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005862301431573e-05, + "loss": 3.6866, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005023706680521e-05, + "loss": 3.6842, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041867498098426e-05, + "loss": 3.684, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033481550587906e-05, + "loss": 3.6835, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0025095603077386e-05, + "loss": 3.6916, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016709655566866e-05, + "loss": 3.6685, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008323708056346e-05, + "loss": 3.6879, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.851038694381714, + "eval_runtime": 303.3271, + "eval_samples_per_second": 1258.018, + "eval_steps_per_second": 39.314, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999937760545826e-05, + "loss": 3.678, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.99915518130353e-05, + "loss": 3.6723, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998316586552478e-05, + "loss": 3.6794, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997477991801426e-05, + "loss": 3.6828, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996639397050374e-05, + "loss": 3.6962, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995802440179695e-05, + "loss": 3.6776, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994963845428643e-05, + "loss": 3.6766, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941252506775915e-05, + "loss": 3.6746, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932866559265395e-05, + "loss": 3.6763, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924496990558604e-05, + "loss": 3.6882, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9916111043048084e-05, + "loss": 3.6765, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907725095537564e-05, + "loss": 3.6825, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899339148027044e-05, + "loss": 3.6731, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890953200516523e-05, + "loss": 3.6726, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882567253006003e-05, + "loss": 3.6722, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987418130549548e-05, + "loss": 3.6692, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986579535798496e-05, + "loss": 3.669, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985742578927817e-05, + "loss": 3.6726, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984903984176765e-05, + "loss": 3.6754, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984065389425713e-05, + "loss": 3.6799, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983226794674661e-05, + "loss": 3.6834, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982389837803983e-05, + "loss": 3.6877, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981551243052931e-05, + "loss": 3.6684, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980712648301879e-05, + "loss": 3.6794, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798756914312e-05, + "loss": 3.6703, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979037096680148e-05, + "loss": 3.6811, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978198501929096e-05, + "loss": 3.6731, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977359907178044e-05, + "loss": 3.669, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976521312426992e-05, + "loss": 3.6684, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.97568271767594e-05, + "loss": 3.6673, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748457608052606e-05, + "loss": 3.667, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9740071660542086e-05, + "loss": 3.6818, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731685713031566e-05, + "loss": 3.6797, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723299765521046e-05, + "loss": 3.6789, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971491381801053e-05, + "loss": 3.6703, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970652787050001e-05, + "loss": 3.6809, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698141922989486e-05, + "loss": 3.6747, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96897723542827e-05, + "loss": 3.6609, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968138640677218e-05, + "loss": 3.6654, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967300045926166e-05, + "loss": 3.6659, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664614511751135e-05, + "loss": 3.6687, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9656228564240615e-05, + "loss": 3.6775, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964785899553383e-05, + "loss": 3.6708, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963947304802331e-05, + "loss": 3.6647, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631087100512784e-05, + "loss": 3.6761, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962270115300227e-05, + "loss": 3.668, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961431520549175e-05, + "loss": 3.6726, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960594563678496e-05, + "loss": 3.6581, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959755968927444e-05, + "loss": 3.6474, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958917374176392e-05, + "loss": 3.6793, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.95807877942534e-05, + "loss": 3.6662, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957240184674288e-05, + "loss": 3.6726, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956401589923236e-05, + "loss": 3.6649, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955562995172184e-05, + "loss": 3.6591, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954724400421132e-05, + "loss": 3.6546, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953889081430826e-05, + "loss": 3.6695, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953050486679774e-05, + "loss": 3.6592, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522118919287224e-05, + "loss": 3.6654, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513732971776704e-05, + "loss": 3.6772, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505347024266184e-05, + "loss": 3.658, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496961076755664e-05, + "loss": 3.6575, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488575129245144e-05, + "loss": 3.6742, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480189181734624e-05, + "loss": 3.6565, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947181961302783e-05, + "loss": 3.6543, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946343366551731e-05, + "loss": 3.6726, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945504771800679e-05, + "loss": 3.6631, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944666177049627e-05, + "loss": 3.6547, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943827582298575e-05, + "loss": 3.6663, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942988987547523e-05, + "loss": 3.6564, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942150392796471e-05, + "loss": 3.6552, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941311798045419e-05, + "loss": 3.6736, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940474841174741e-05, + "loss": 3.6673, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939636246423689e-05, + "loss": 3.6669, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.93879928955301e-05, + "loss": 3.6697, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937960694801958e-05, + "loss": 3.6815, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937122100050906e-05, + "loss": 3.6593, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936283505299854e-05, + "loss": 3.6689, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935444910548802e-05, + "loss": 3.668, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9346079536781227e-05, + "loss": 3.6577, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337693589270706e-05, + "loss": 3.6615, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329307641760186e-05, + "loss": 3.6757, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320921694249666e-05, + "loss": 3.6689, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312535746739146e-05, + "loss": 3.6732, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930416617803236e-05, + "loss": 3.6522, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929578023052184e-05, + "loss": 3.6481, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928739428301132e-05, + "loss": 3.6659, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9279008335500795e-05, + "loss": 3.6694, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270622387990275e-05, + "loss": 3.6679, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9262236440479755e-05, + "loss": 3.6651, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925386687177297e-05, + "loss": 3.6505, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245480924262444e-05, + "loss": 3.6608, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237094976751924e-05, + "loss": 3.6561, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9228709029241404e-05, + "loss": 3.6584, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220323081730884e-05, + "loss": 3.6719, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.92119535130241e-05, + "loss": 3.6759, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920356756551358e-05, + "loss": 3.6705, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919518161800306e-05, + "loss": 3.658, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918679567049254e-05, + "loss": 3.6568, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917840972298202e-05, + "loss": 3.6618, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917004015427523e-05, + "loss": 3.6703, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916165420676471e-05, + "loss": 3.6616, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915326825925419e-05, + "loss": 3.6709, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914488231174367e-05, + "loss": 3.6611, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913649636423315e-05, + "loss": 3.6545, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912811041672263e-05, + "loss": 3.6615, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911972446921211e-05, + "loss": 3.6529, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911135490050532e-05, + "loss": 3.6555, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.91029689529948e-05, + "loss": 3.662, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909458300548428e-05, + "loss": 3.659, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086197057973764e-05, + "loss": 3.6537, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077827489266973e-05, + "loss": 3.6525, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069441541756453e-05, + "loss": 3.6515, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9061055594245933e-05, + "loss": 3.6631, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905266964673541e-05, + "loss": 3.6532, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904428369922489e-05, + "loss": 3.6752, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903589775171437e-05, + "loss": 3.6709, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902751180420385e-05, + "loss": 3.6652, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901914223549706e-05, + "loss": 3.6572, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901075628798654e-05, + "loss": 3.653, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900237034047602e-05, + "loss": 3.6633, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.89939843929655e-05, + "loss": 3.659, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898561482425872e-05, + "loss": 3.6555, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.89772288767482e-05, + "loss": 3.6529, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896884292923768e-05, + "loss": 3.6642, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896045698172716e-05, + "loss": 3.6519, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895207103421663e-05, + "loss": 3.6535, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894368508670611e-05, + "loss": 3.6489, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893529913919559e-05, + "loss": 3.6637, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892692957048881e-05, + "loss": 3.6486, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891854362297828e-05, + "loss": 3.6664, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891015767546776e-05, + "loss": 3.6627, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890177172795724e-05, + "loss": 3.6721, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889338578044672e-05, + "loss": 3.6486, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8885016211739936e-05, + "loss": 3.6685, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876630264229416e-05, + "loss": 3.6562, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868244316718896e-05, + "loss": 3.664, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859858369208376e-05, + "loss": 3.6607, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851472421697856e-05, + "loss": 3.6543, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843102852991065e-05, + "loss": 3.6596, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834716905480545e-05, + "loss": 3.6705, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826330957970025e-05, + "loss": 3.6469, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817945010459505e-05, + "loss": 3.661, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809575441752714e-05, + "loss": 3.6635, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801189494242194e-05, + "loss": 3.6601, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792803546731674e-05, + "loss": 3.6503, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784417599221154e-05, + "loss": 3.6572, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877604803051437e-05, + "loss": 3.6643, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876766208300385e-05, + "loss": 3.6469, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875927613549333e-05, + "loss": 3.6587, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.846762180328369, + "eval_runtime": 305.4163, + "eval_samples_per_second": 1249.413, + "eval_steps_per_second": 39.045, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875089018798281e-05, + "loss": 3.6526, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874250424047229e-05, + "loss": 3.6469, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.87341346717655e-05, + "loss": 3.6517, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872574872425498e-05, + "loss": 3.6618, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871736277674446e-05, + "loss": 3.6714, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870897682923394e-05, + "loss": 3.65, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870059088172342e-05, + "loss": 3.6477, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.86922049342129e-05, + "loss": 3.6519, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868381898670238e-05, + "loss": 3.6427, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675449417995594e-05, + "loss": 3.6658, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8667063470485074e-05, + "loss": 3.6456, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8658677522974554e-05, + "loss": 3.6533, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650291575464034e-05, + "loss": 3.6578, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864192200675724e-05, + "loss": 3.6441, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863353605924672e-05, + "loss": 3.6419, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.86251501117362e-05, + "loss": 3.6442, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861676416422568e-05, + "loss": 3.6428, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860839459551889e-05, + "loss": 3.6508, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.860000864800837e-05, + "loss": 3.6451, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859162270049785e-05, + "loss": 3.6519, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858323675298733e-05, + "loss": 3.6597, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857485080547681e-05, + "loss": 3.6603, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856648123677003e-05, + "loss": 3.6487, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855809528925951e-05, + "loss": 3.6469, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854970934174899e-05, + "loss": 3.6461, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854132339423847e-05, + "loss": 3.6573, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853293744672794e-05, + "loss": 3.649, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852455149921742e-05, + "loss": 3.6455, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.85161655517069e-05, + "loss": 3.642, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850777960419638e-05, + "loss": 3.6411, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499426414293326e-05, + "loss": 3.6406, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491040466782805e-05, + "loss": 3.6574, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482654519272285e-05, + "loss": 3.6566, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474268571761765e-05, + "loss": 3.654, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465882624251245e-05, + "loss": 3.646, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457496676740725e-05, + "loss": 3.6481, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844912710803394e-05, + "loss": 3.6545, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440741160523414e-05, + "loss": 3.6369, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432355213012894e-05, + "loss": 3.6417, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423969265502374e-05, + "loss": 3.636, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415583317991854e-05, + "loss": 3.6421, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407197370481334e-05, + "loss": 3.6518, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839882780177454e-05, + "loss": 3.643, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839044185426402e-05, + "loss": 3.6391, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.83820559067535e-05, + "loss": 3.6507, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837366995924298e-05, + "loss": 3.6456, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.83653003905362e-05, + "loss": 3.6432, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835691444302568e-05, + "loss": 3.6382, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834852849551516e-05, + "loss": 3.6165, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834014254800464e-05, + "loss": 3.6578, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833175660049412e-05, + "loss": 3.6401, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.83233706529836e-05, + "loss": 3.6506, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831498470547308e-05, + "loss": 3.6373, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830659875796256e-05, + "loss": 3.6373, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.82982455680595e-05, + "loss": 3.6327, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828985962054898e-05, + "loss": 3.6401, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828147367303846e-05, + "loss": 3.637, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827308772552794e-05, + "loss": 3.6396, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826470177801742e-05, + "loss": 3.6535, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825633220931063e-05, + "loss": 3.6325, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824794626180011e-05, + "loss": 3.6314, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823956031428959e-05, + "loss": 3.6515, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823117436677907e-05, + "loss": 3.6337, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822278841926855e-05, + "loss": 3.6292, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821441885056176e-05, + "loss": 3.6457, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820603290305124e-05, + "loss": 3.6399, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819764695554072e-05, + "loss": 3.6289, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.81892610080302e-05, + "loss": 3.6401, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818087506051968e-05, + "loss": 3.6299, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817248911300916e-05, + "loss": 3.6343, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816410316549864e-05, + "loss": 3.6446, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815573359679186e-05, + "loss": 3.6434, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814734764928134e-05, + "loss": 3.6459, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813896170177082e-05, + "loss": 3.6429, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81305757542603e-05, + "loss": 3.6567, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812218980674977e-05, + "loss": 3.6297, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811380385923925e-05, + "loss": 3.6518, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810541791172873e-05, + "loss": 3.6372, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097048343021946e-05, + "loss": 3.6363, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808866239551142e-05, + "loss": 3.6367, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.80802764480009e-05, + "loss": 3.6509, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807189050049038e-05, + "loss": 3.6454, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063520931783595e-05, + "loss": 3.6494, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055134984273075e-05, + "loss": 3.6254, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046749036762555e-05, + "loss": 3.6267, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038363089252035e-05, + "loss": 3.6403, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029977141741515e-05, + "loss": 3.6425, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021607573034724e-05, + "loss": 3.6387, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013221625524204e-05, + "loss": 3.6439, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004835678013684e-05, + "loss": 3.6298, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996449730503164e-05, + "loss": 3.6371, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798808016179637e-05, + "loss": 3.6333, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797969421428585e-05, + "loss": 3.6328, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797130826677533e-05, + "loss": 3.646, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796292231926481e-05, + "loss": 3.6531, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795455275055803e-05, + "loss": 3.647, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794616680304751e-05, + "loss": 3.6298, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793778085553699e-05, + "loss": 3.6335, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792939490802647e-05, + "loss": 3.6362, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792100896051595e-05, + "loss": 3.6455, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791263939180916e-05, + "loss": 3.6401, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790425344429864e-05, + "loss": 3.645, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789586749678812e-05, + "loss": 3.6386, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78874815492776e-05, + "loss": 3.6332, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879111980570806e-05, + "loss": 3.6357, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870726033060286e-05, + "loss": 3.6277, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862340085549766e-05, + "loss": 3.6329, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853954138039246e-05, + "loss": 3.6402, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845568190528726e-05, + "loss": 3.6374, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783719862182194e-05, + "loss": 3.6293, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782881267431142e-05, + "loss": 3.6316, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.78204267268009e-05, + "loss": 3.621, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781204077929038e-05, + "loss": 3.6419, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780365483177986e-05, + "loss": 3.6299, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779526888426934e-05, + "loss": 3.6489, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778689931556255e-05, + "loss": 3.6447, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777851336805203e-05, + "loss": 3.6478, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777014379934524e-05, + "loss": 3.633, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776175785183472e-05, + "loss": 3.6297, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77533719043242e-05, + "loss": 3.6422, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774498595681368e-05, + "loss": 3.6377, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773660000930317e-05, + "loss": 3.6306, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772821406179265e-05, + "loss": 3.6249, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719828114282127e-05, + "loss": 3.6382, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711442166771607e-05, + "loss": 3.6286, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770305621926108e-05, + "loss": 3.6288, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694686650554296e-05, + "loss": 3.6293, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686300703043776e-05, + "loss": 3.6365, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677914755533255e-05, + "loss": 3.627, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766952880802273e-05, + "loss": 3.6413, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661159239315945e-05, + "loss": 3.6358, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652773291805424e-05, + "loss": 3.6535, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644387344294904e-05, + "loss": 3.6237, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636001396784384e-05, + "loss": 3.6427, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627615449273864e-05, + "loss": 3.6325, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761924588056708e-05, + "loss": 3.6415, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610859933056553e-05, + "loss": 3.6346, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760247398554603e-05, + "loss": 3.6335, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759408803803551e-05, + "loss": 3.6337, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758571846932873e-05, + "loss": 3.6524, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.75773325218182e-05, + "loss": 3.6238, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756894657430768e-05, + "loss": 3.6391, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756056062679716e-05, + "loss": 3.6352, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755219105809038e-05, + "loss": 3.6354, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754380511057986e-05, + "loss": 3.6266, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753541916306934e-05, + "loss": 3.6342, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752703321555882e-05, + "loss": 3.6381, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751866364685203e-05, + "loss": 3.6316, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751027769934151e-05, + "loss": 3.6325, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.844078302383423, + "eval_runtime": 305.452, + "eval_samples_per_second": 1249.267, + "eval_steps_per_second": 39.041, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750189175183099e-05, + "loss": 3.6257, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749350580432047e-05, + "loss": 3.6223, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748511985680995e-05, + "loss": 3.628, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747673390929943e-05, + "loss": 3.6411, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468364340592636e-05, + "loss": 3.6462, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459978393082116e-05, + "loss": 3.6297, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451592445571596e-05, + "loss": 3.6274, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443206498061076e-05, + "loss": 3.6262, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434820550550556e-05, + "loss": 3.6216, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742645098184377e-05, + "loss": 3.6395, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741806503433325e-05, + "loss": 3.6228, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740967908682273e-05, + "loss": 3.6305, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740129313931221e-05, + "loss": 3.6349, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739292357060542e-05, + "loss": 3.6191, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.73845376230949e-05, + "loss": 3.6207, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737615167558438e-05, + "loss": 3.6189, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736776572807386e-05, + "loss": 3.624, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735939615936707e-05, + "loss": 3.6249, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735101021185655e-05, + "loss": 3.6222, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734262426434603e-05, + "loss": 3.6308, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733423831683551e-05, + "loss": 3.6344, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325868748128725e-05, + "loss": 3.6358, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317482800618205e-05, + "loss": 3.6266, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309096853107685e-05, + "loss": 3.6235, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300710905597165e-05, + "loss": 3.6251, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292341336890374e-05, + "loss": 3.6329, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283955389379854e-05, + "loss": 3.6232, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275569441869334e-05, + "loss": 3.6273, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267183494358814e-05, + "loss": 3.6194, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258797546848294e-05, + "loss": 3.6168, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.72504279781415e-05, + "loss": 3.6178, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724204203063098e-05, + "loss": 3.6321, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723365608312046e-05, + "loss": 3.6364, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722527013560994e-05, + "loss": 3.6272, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721688418809943e-05, + "loss": 3.6283, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720851461939264e-05, + "loss": 3.6215, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720012867188212e-05, + "loss": 3.6347, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.71917427243716e-05, + "loss": 3.618, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718335677686108e-05, + "loss": 3.6166, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717497082935056e-05, + "loss": 3.613, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716660126064377e-05, + "loss": 3.6213, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715821531313325e-05, + "loss": 3.6235, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714982936562273e-05, + "loss": 3.6248, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714144341811221e-05, + "loss": 3.6194, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713307384940542e-05, + "loss": 3.6258, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246879018949e-05, + "loss": 3.6236, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116301954384384e-05, + "loss": 3.62, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107916006873863e-05, + "loss": 3.6163, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709954643816707e-05, + "loss": 3.5972, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709116049065655e-05, + "loss": 3.6311, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708277454314603e-05, + "loss": 3.6166, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707438859563551e-05, + "loss": 3.6281, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7066002648124986e-05, + "loss": 3.6196, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057616700614466e-05, + "loss": 3.6126, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704924713190768e-05, + "loss": 3.6073, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040861184397155e-05, + "loss": 3.6189, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032475236886635e-05, + "loss": 3.6175, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702408928937612e-05, + "loss": 3.6112, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701571972066934e-05, + "loss": 3.632, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700733377315881e-05, + "loss": 3.6157, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699894782564829e-05, + "loss": 3.6067, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699056187813777e-05, + "loss": 3.6243, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982192309430986e-05, + "loss": 3.6153, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697380636192046e-05, + "loss": 3.6095, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696542041440994e-05, + "loss": 3.6241, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695703446689942e-05, + "loss": 3.6165, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.69486485193889e-05, + "loss": 3.6083, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694027895068211e-05, + "loss": 3.6204, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693189300317159e-05, + "loss": 3.6074, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923507055661075e-05, + "loss": 3.6106, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915121108150555e-05, + "loss": 3.6228, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906751539443764e-05, + "loss": 3.6211, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898365591933244e-05, + "loss": 3.6242, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889979644422724e-05, + "loss": 3.6177, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881593696912204e-05, + "loss": 3.6379, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687322412820541e-05, + "loss": 3.6121, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686483818069489e-05, + "loss": 3.6266, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685645223318437e-05, + "loss": 3.6152, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684806628567385e-05, + "loss": 3.6128, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683969671696706e-05, + "loss": 3.6138, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683131076945654e-05, + "loss": 3.6312, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682292482194603e-05, + "loss": 3.6202, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681453887443551e-05, + "loss": 3.6322, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680615292692499e-05, + "loss": 3.602, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.67977833582182e-05, + "loss": 3.6043, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678939741070768e-05, + "loss": 3.6185, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678101146319716e-05, + "loss": 3.6248, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677262551568664e-05, + "loss": 3.6158, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676423956817612e-05, + "loss": 3.6184, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755869999469327e-05, + "loss": 3.6128, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747484051958807e-05, + "loss": 3.611, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739098104448286e-05, + "loss": 3.6121, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730712156937766e-05, + "loss": 3.6113, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672234258823098e-05, + "loss": 3.6239, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671395664072046e-05, + "loss": 3.6331, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670557069320994e-05, + "loss": 3.627, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669718474569942e-05, + "loss": 3.6076, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.66887987981889e-05, + "loss": 3.6091, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668041285067838e-05, + "loss": 3.6148, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667202690316786e-05, + "loss": 3.6196, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666365733446107e-05, + "loss": 3.6215, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665527138695055e-05, + "loss": 3.6192, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664688543944003e-05, + "loss": 3.6193, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663849949192951e-05, + "loss": 3.6097, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663012992322272e-05, + "loss": 3.6145, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.66217439757122e-05, + "loss": 3.6089, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661335802820168e-05, + "loss": 3.6089, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660497208069116e-05, + "loss": 3.6201, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659658613318065e-05, + "loss": 3.6146, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588216564473856e-05, + "loss": 3.6049, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579830616963336e-05, + "loss": 3.6114, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571444669452816e-05, + "loss": 3.5995, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656305872194229e-05, + "loss": 3.6204, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655467277443177e-05, + "loss": 3.613, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6546303205724985e-05, + "loss": 3.6239, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537917258214465e-05, + "loss": 3.6229, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652953131070394e-05, + "loss": 3.6262, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521161741997154e-05, + "loss": 3.6111, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512775794486634e-05, + "loss": 3.6116, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504389846976114e-05, + "loss": 3.6154, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6496003899465594e-05, + "loss": 3.6189, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487617951955074e-05, + "loss": 3.6084, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479232004444554e-05, + "loss": 3.604, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470846056934033e-05, + "loss": 3.617, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462460109423513e-05, + "loss": 3.6094, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645409054071672e-05, + "loss": 3.6063, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.64457045932062e-05, + "loss": 3.6072, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643731864569568e-05, + "loss": 3.6178, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642893269818516e-05, + "loss": 3.602, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642056312947837e-05, + "loss": 3.6221, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641217718196785e-05, + "loss": 3.6155, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640379123445734e-05, + "loss": 3.6301, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639540528694682e-05, + "loss": 3.6023, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638703571824003e-05, + "loss": 3.6194, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637864977072951e-05, + "loss": 3.6194, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637026382321899e-05, + "loss": 3.6156, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636187787570847e-05, + "loss": 3.6151, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6353508307001676e-05, + "loss": 3.6112, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6345122359491156e-05, + "loss": 3.6116, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336736411980636e-05, + "loss": 3.6296, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328350464470116e-05, + "loss": 3.6067, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319980895763325e-05, + "loss": 3.617, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311594948252805e-05, + "loss": 3.6149, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630320900074229e-05, + "loss": 3.6109, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629482305323177e-05, + "loss": 3.6086, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628645348452498e-05, + "loss": 3.6128, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627806753701446e-05, + "loss": 3.6146, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626968158950394e-05, + "loss": 3.6145, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626129564199342e-05, + "loss": 3.6082, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8416991233825684, + "eval_runtime": 305.6522, + "eval_samples_per_second": 1248.448, + "eval_steps_per_second": 39.015, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625292607328663e-05, + "loss": 3.6078, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624454012577611e-05, + "loss": 3.6025, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623615417826559e-05, + "loss": 3.6076, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622776823075507e-05, + "loss": 3.6176, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621939866204828e-05, + "loss": 3.6219, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621101271453776e-05, + "loss": 3.6098, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202626767027245e-05, + "loss": 3.6078, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194240819516725e-05, + "loss": 3.6075, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185854872006205e-05, + "loss": 3.5997, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177485303299415e-05, + "loss": 3.6168, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169099355788894e-05, + "loss": 3.6072, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160713408278374e-05, + "loss": 3.6119, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152327460767854e-05, + "loss": 3.6119, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143957892061063e-05, + "loss": 3.5967, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135571944550543e-05, + "loss": 3.6015, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612718599704002e-05, + "loss": 3.5933, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.61188000495295e-05, + "loss": 3.6058, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611043048082271e-05, + "loss": 3.606, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61020445333122e-05, + "loss": 3.5994, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609365858580168e-05, + "loss": 3.6085, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608527263829116e-05, + "loss": 3.614, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607690306958437e-05, + "loss": 3.6161, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606851712207385e-05, + "loss": 3.6064, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606013117456333e-05, + "loss": 3.606, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605174522705281e-05, + "loss": 3.606, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604337565834602e-05, + "loss": 3.6102, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.60349897108355e-05, + "loss": 3.6015, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602660376332498e-05, + "loss": 3.6069, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601821781581446e-05, + "loss": 3.6021, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009848247107666e-05, + "loss": 3.5961, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600146229959715e-05, + "loss": 3.6009, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599307635208663e-05, + "loss": 3.6094, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598469040457611e-05, + "loss": 3.6083, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597632083586932e-05, + "loss": 3.6161, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.59679348883588e-05, + "loss": 3.5997, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595954894084828e-05, + "loss": 3.6035, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595116299333776e-05, + "loss": 3.6146, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594277704582724e-05, + "loss": 3.5936, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593440747712045e-05, + "loss": 3.5987, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592602152960993e-05, + "loss": 3.5941, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591763558209941e-05, + "loss": 3.6025, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590924963458889e-05, + "loss": 3.6008, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900880065882106e-05, + "loss": 3.6029, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892494118371586e-05, + "loss": 3.6016, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884108170861066e-05, + "loss": 3.6012, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875722223350546e-05, + "loss": 3.6077, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867352654643755e-05, + "loss": 3.5951, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858966707133235e-05, + "loss": 3.5981, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850580759622715e-05, + "loss": 3.5751, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842194812112195e-05, + "loss": 3.6115, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833825243405404e-05, + "loss": 3.5971, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825439295894884e-05, + "loss": 3.6044, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5817053348384364e-05, + "loss": 3.5996, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808667400873844e-05, + "loss": 3.5921, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580029783216706e-05, + "loss": 3.587, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579191188465654e-05, + "loss": 3.5964, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578352593714602e-05, + "loss": 3.6013, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577513998963549e-05, + "loss": 3.5874, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576677042092871e-05, + "loss": 3.6118, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575838447341819e-05, + "loss": 3.5994, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574999852590767e-05, + "loss": 3.5799, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574161257839714e-05, + "loss": 3.6057, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573324300969036e-05, + "loss": 3.5982, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572485706217984e-05, + "loss": 3.5896, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571647111466931e-05, + "loss": 3.5987, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.57080851671588e-05, + "loss": 3.5995, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569971559845201e-05, + "loss": 3.5853, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691329650941494e-05, + "loss": 3.6018, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568294370343097e-05, + "loss": 3.5862, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567455775592045e-05, + "loss": 3.5883, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566618818721366e-05, + "loss": 3.6072, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565780223970314e-05, + "loss": 3.5978, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649416292192616e-05, + "loss": 3.6055, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5641030344682096e-05, + "loss": 3.6014, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632644397171576e-05, + "loss": 3.6106, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624274828464785e-05, + "loss": 3.595, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615888880954265e-05, + "loss": 3.61, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607502933443745e-05, + "loss": 3.5915, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559911698593323e-05, + "loss": 3.5954, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559074741722644e-05, + "loss": 3.5944, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558236146971592e-05, + "loss": 3.6096, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.55739755222054e-05, + "loss": 3.6021, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556558957469488e-05, + "loss": 3.6123, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555722000598809e-05, + "loss": 3.5825, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554883405847757e-05, + "loss": 3.5843, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554044811096705e-05, + "loss": 3.5986, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553206216345653e-05, + "loss": 3.6039, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552369259474974e-05, + "loss": 3.5939, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551530664723922e-05, + "loss": 3.6031, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55069206997287e-05, + "loss": 3.5938, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498534752218185e-05, + "loss": 3.5861, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490165183511394e-05, + "loss": 3.5927, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481779236000874e-05, + "loss": 3.5912, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473393288490354e-05, + "loss": 3.6053, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5465007340979834e-05, + "loss": 3.6115, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545663777227304e-05, + "loss": 3.6126, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544825182476252e-05, + "loss": 3.5854, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439865877252e-05, + "loss": 3.5938, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543147992974148e-05, + "loss": 3.5939, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542309398223096e-05, + "loss": 3.602, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541472441352417e-05, + "loss": 3.5996, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540633846601365e-05, + "loss": 3.602, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539795251850314e-05, + "loss": 3.597, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538956657099262e-05, + "loss": 3.5933, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538119700228583e-05, + "loss": 3.5974, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537281105477531e-05, + "loss": 3.5851, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536442510726479e-05, + "loss": 3.5913, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535603915975427e-05, + "loss": 3.596, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534766959104748e-05, + "loss": 3.5988, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533928364353696e-05, + "loss": 3.5845, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533089769602644e-05, + "loss": 3.5929, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532251174851592e-05, + "loss": 3.5771, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314142179809126e-05, + "loss": 3.6043, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305756232298606e-05, + "loss": 3.5911, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529737028478809e-05, + "loss": 3.6048, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528898433727757e-05, + "loss": 3.5997, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528061476857078e-05, + "loss": 3.6058, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527224519986399e-05, + "loss": 3.5934, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526385925235347e-05, + "loss": 3.5881, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525547330484295e-05, + "loss": 3.6014, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524708735733243e-05, + "loss": 3.5953, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523870140982191e-05, + "loss": 3.5928, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523031546231139e-05, + "loss": 3.584, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522192951480087e-05, + "loss": 3.5941, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521354356729035e-05, + "loss": 3.5879, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520517399858356e-05, + "loss": 3.5913, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196788051073046e-05, + "loss": 3.587, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188402103562526e-05, + "loss": 3.5985, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5180016156052006e-05, + "loss": 3.5829, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171646587345215e-05, + "loss": 3.6049, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163260639834695e-05, + "loss": 3.5945, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154874692324175e-05, + "loss": 3.6115, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146488744813655e-05, + "loss": 3.5832, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138119176106864e-05, + "loss": 3.6005, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129733228596344e-05, + "loss": 3.5967, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121347281085824e-05, + "loss": 3.5964, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5112961333575304e-05, + "loss": 3.5963, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510459176486851e-05, + "loss": 3.5905, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096205817358e-05, + "loss": 3.5964, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508781986984748e-05, + "loss": 3.6087, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507943392233696e-05, + "loss": 3.59, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507104797482644e-05, + "loss": 3.5952, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506267840611965e-05, + "loss": 3.595, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505429245860913e-05, + "loss": 3.5933, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504590651109861e-05, + "loss": 3.5924, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503752056358809e-05, + "loss": 3.593, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.50291509948813e-05, + "loss": 3.5914, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502076504737078e-05, + "loss": 3.5948, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501237909986026e-05, + "loss": 3.5868, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.841529130935669, + "eval_runtime": 305.169, + "eval_samples_per_second": 1250.425, + "eval_steps_per_second": 39.077, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500399315234974e-05, + "loss": 3.6031, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499560720483922e-05, + "loss": 3.5791, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.49872212573287e-05, + "loss": 3.588, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497883530981818e-05, + "loss": 3.6022, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970465741111393e-05, + "loss": 3.5969, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496207979360087e-05, + "loss": 3.5924, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953693846090347e-05, + "loss": 3.5925, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945307898579827e-05, + "loss": 3.586, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936921951069306e-05, + "loss": 3.5799, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928552382362516e-05, + "loss": 3.5927, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920166434851996e-05, + "loss": 3.5908, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911780487341476e-05, + "loss": 3.5915, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903394539830955e-05, + "loss": 3.5931, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489502497112417e-05, + "loss": 3.5768, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488663902361365e-05, + "loss": 3.5813, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487825307610313e-05, + "loss": 3.5773, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486986712859261e-05, + "loss": 3.5867, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486149755988582e-05, + "loss": 3.5855, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.48531116123753e-05, + "loss": 3.5796, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484472566486478e-05, + "loss": 3.5889, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483633971735426e-05, + "loss": 3.5953, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482797014864747e-05, + "loss": 3.5977, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481958420113695e-05, + "loss": 3.5885, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481119825362643e-05, + "loss": 3.5849, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480281230611591e-05, + "loss": 3.5903, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794442737409125e-05, + "loss": 3.5912, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786056789898605e-05, + "loss": 3.5835, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777670842388085e-05, + "loss": 3.5862, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769284894877565e-05, + "loss": 3.5815, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760915326170774e-05, + "loss": 3.5779, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752529378660254e-05, + "loss": 3.5846, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744143431149734e-05, + "loss": 3.5865, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735757483639214e-05, + "loss": 3.5875, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472738791493242e-05, + "loss": 3.5971, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47190019674219e-05, + "loss": 3.5851, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471061601991138e-05, + "loss": 3.5864, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470223007240086e-05, + "loss": 3.5947, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469386050369408e-05, + "loss": 3.5757, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468547455618356e-05, + "loss": 3.5773, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467708860867304e-05, + "loss": 3.5799, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466870266116252e-05, + "loss": 3.5802, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660316713652e-05, + "loss": 3.5798, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465194714494521e-05, + "loss": 3.5852, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464356119743469e-05, + "loss": 3.5838, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463517524992417e-05, + "loss": 3.58, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462678930241365e-05, + "loss": 3.5897, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618419733706857e-05, + "loss": 3.58, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610033786196337e-05, + "loss": 3.5796, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601647838685816e-05, + "loss": 3.5594, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593261891175296e-05, + "loss": 3.5921, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458489232246851e-05, + "loss": 3.577, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457650637495799e-05, + "loss": 3.5843, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456812042744747e-05, + "loss": 3.5805, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455973447993695e-05, + "loss": 3.5742, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455136491123016e-05, + "loss": 3.5684, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454297896371964e-05, + "loss": 3.5783, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453459301620912e-05, + "loss": 3.5868, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.45262070686986e-05, + "loss": 3.5674, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451783749999181e-05, + "loss": 3.5937, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450945155248129e-05, + "loss": 3.5811, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450106560497077e-05, + "loss": 3.5619, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449267965746025e-05, + "loss": 3.5883, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448429370994973e-05, + "loss": 3.574, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475924141242946e-05, + "loss": 3.575, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467538193732426e-05, + "loss": 3.5797, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459152246221906e-05, + "loss": 3.5818, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450766298711386e-05, + "loss": 3.5721, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442396730004595e-05, + "loss": 3.583, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4434010782494075e-05, + "loss": 3.5673, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425624834983555e-05, + "loss": 3.5725, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417238887473035e-05, + "loss": 3.5835, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408869318766244e-05, + "loss": 3.5811, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400483371255724e-05, + "loss": 3.5873, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392097423745204e-05, + "loss": 3.5784, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383711476234684e-05, + "loss": 3.5964, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43753419075279e-05, + "loss": 3.5762, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436695596001738e-05, + "loss": 3.5913, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435857001250686e-05, + "loss": 3.5722, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435018406499634e-05, + "loss": 3.5781, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434179811748582e-05, + "loss": 3.571, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433342854877903e-05, + "loss": 3.5876, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432504260126851e-05, + "loss": 3.5836, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431665665375799e-05, + "loss": 3.5945, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430827070624747e-05, + "loss": 3.5693, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429990113754068e-05, + "loss": 3.567, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429151519003016e-05, + "loss": 3.5764, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428312924251964e-05, + "loss": 3.586, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274743295009124e-05, + "loss": 3.5758, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426637372630233e-05, + "loss": 3.5839, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425798777879181e-05, + "loss": 3.5764, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424960183128129e-05, + "loss": 3.569, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.42412322625745e-05, + "loss": 3.5767, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423284631506398e-05, + "loss": 3.5706, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422446036755346e-05, + "loss": 3.5853, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421607442004294e-05, + "loss": 3.5941, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420770485133615e-05, + "loss": 3.5917, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419931890382563e-05, + "loss": 3.5692, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419093295631511e-05, + "loss": 3.5743, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418254700880459e-05, + "loss": 3.578, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417417744009781e-05, + "loss": 3.5815, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416579149258729e-05, + "loss": 3.5835, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415740554507677e-05, + "loss": 3.583, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414901959756624e-05, + "loss": 3.5766, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140650028859456e-05, + "loss": 3.5738, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132264081348936e-05, + "loss": 3.5841, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123878133838416e-05, + "loss": 3.5654, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411549218632789e-05, + "loss": 3.5736, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107122617621105e-05, + "loss": 3.5774, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098736670110585e-05, + "loss": 3.5792, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090350722600065e-05, + "loss": 3.5694, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081964775089545e-05, + "loss": 3.5775, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407359520638276e-05, + "loss": 3.5564, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406520925887224e-05, + "loss": 3.582, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056823311361714e-05, + "loss": 3.5789, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048437363851194e-05, + "loss": 3.5804, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040051416340674e-05, + "loss": 3.5858, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403168184763389e-05, + "loss": 3.59, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.40233122789271e-05, + "loss": 3.5741, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401492633141658e-05, + "loss": 3.5722, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400654038390606e-05, + "loss": 3.5809, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399815443639554e-05, + "loss": 3.5753, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398976848888502e-05, + "loss": 3.5719, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39813825413745e-05, + "loss": 3.5713, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397299659386398e-05, + "loss": 3.5736, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396461064635346e-05, + "loss": 3.5728, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395624107764667e-05, + "loss": 3.5699, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394785513013615e-05, + "loss": 3.5716, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393946918262563e-05, + "loss": 3.576, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393108323511511e-05, + "loss": 3.5665, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922713666408316e-05, + "loss": 3.5839, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914327718897796e-05, + "loss": 3.5764, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905941771387276e-05, + "loss": 3.5956, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897555823876756e-05, + "loss": 3.5611, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388918625516997e-05, + "loss": 3.5854, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388080030765945e-05, + "loss": 3.5819, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387241436014893e-05, + "loss": 3.5753, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386402841263841e-05, + "loss": 3.5756, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385565884393162e-05, + "loss": 3.5734, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38472728964211e-05, + "loss": 3.5827, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383888694891058e-05, + "loss": 3.5873, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383050100140006e-05, + "loss": 3.5709, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382213143269327e-05, + "loss": 3.5784, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381374548518275e-05, + "loss": 3.579, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380535953767223e-05, + "loss": 3.5735, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379697359016171e-05, + "loss": 3.5727, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788604021454926e-05, + "loss": 3.5779, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780218073944406e-05, + "loss": 3.5721, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771832126433886e-05, + "loss": 3.5789, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763446178923366e-05, + "loss": 3.5695, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8414785861968994, + "eval_runtime": 309.0687, + "eval_samples_per_second": 1234.648, + "eval_steps_per_second": 38.584, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3755076610216575e-05, + "loss": 3.5775, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746690662706055e-05, + "loss": 3.5614, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738304715195535e-05, + "loss": 3.5694, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729918767685015e-05, + "loss": 3.5872, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721549198978224e-05, + "loss": 3.5788, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713163251467704e-05, + "loss": 3.5774, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704777303957184e-05, + "loss": 3.5714, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696391356446664e-05, + "loss": 3.5674, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368802178773988e-05, + "loss": 3.5595, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367963584022936e-05, + "loss": 3.5805, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367124989271884e-05, + "loss": 3.5731, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366286394520832e-05, + "loss": 3.5728, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365449437650153e-05, + "loss": 3.5772, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364610842899101e-05, + "loss": 3.5605, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363772248148049e-05, + "loss": 3.5611, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362933653396997e-05, + "loss": 3.5614, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362096696526318e-05, + "loss": 3.571, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361258101775266e-05, + "loss": 3.5663, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360419507024214e-05, + "loss": 3.5643, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359580912273162e-05, + "loss": 3.5669, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358743955402483e-05, + "loss": 3.5819, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357905360651431e-05, + "loss": 3.5766, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357066765900379e-05, + "loss": 3.5731, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356228171149327e-05, + "loss": 3.5669, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355391214278648e-05, + "loss": 3.5725, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354552619527596e-05, + "loss": 3.5705, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353714024776544e-05, + "loss": 3.5692, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352875430025492e-05, + "loss": 3.5733, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352038473154813e-05, + "loss": 3.5608, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351199878403761e-05, + "loss": 3.5593, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350361283652709e-05, + "loss": 3.5657, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349522688901657e-05, + "loss": 3.5681, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348685732030979e-05, + "loss": 3.5754, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347847137279927e-05, + "loss": 3.5779, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347008542528875e-05, + "loss": 3.566, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346169947777823e-05, + "loss": 3.5707, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453329909071436e-05, + "loss": 3.5775, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444943961560916e-05, + "loss": 3.5538, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436558014050396e-05, + "loss": 3.5621, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428172066539876e-05, + "loss": 3.5617, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419802497833085e-05, + "loss": 3.5631, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411416550322565e-05, + "loss": 3.5643, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403030602812045e-05, + "loss": 3.5701, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394644655301525e-05, + "loss": 3.5689, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338627508659474e-05, + "loss": 3.5618, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337788913908422e-05, + "loss": 3.5707, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33695031915737e-05, + "loss": 3.565, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336111724406318e-05, + "loss": 3.5589, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335274767535639e-05, + "loss": 3.5443, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334436172784587e-05, + "loss": 3.5711, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333597578033535e-05, + "loss": 3.5606, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332758983282483e-05, + "loss": 3.5695, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331922026411804e-05, + "loss": 3.5621, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331083431660752e-05, + "loss": 3.552, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302448369097e-05, + "loss": 3.5532, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329406242158648e-05, + "loss": 3.5614, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285692852879694e-05, + "loss": 3.5696, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277306905369174e-05, + "loss": 3.548, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268920957858654e-05, + "loss": 3.5776, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260535010348134e-05, + "loss": 3.5655, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325216544164134e-05, + "loss": 3.5468, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324377949413082e-05, + "loss": 3.569, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.32353935466203e-05, + "loss": 3.5564, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322700759910978e-05, + "loss": 3.5638, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321863803040299e-05, + "loss": 3.5559, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321025208289247e-05, + "loss": 3.5703, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320186613538195e-05, + "loss": 3.5505, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319348018787143e-05, + "loss": 3.5658, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318509424036091e-05, + "loss": 3.5474, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317672467165413e-05, + "loss": 3.5599, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316833872414361e-05, + "loss": 3.564, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315995277663309e-05, + "loss": 3.5702, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315156682912257e-05, + "loss": 3.5641, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314319726041578e-05, + "loss": 3.5632, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313481131290526e-05, + "loss": 3.5777, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126425365394737e-05, + "loss": 3.5603, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311803941788421e-05, + "loss": 3.5727, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109669849177426e-05, + "loss": 3.5602, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101283901666906e-05, + "loss": 3.5612, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092897954156386e-05, + "loss": 3.5592, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084512006645866e-05, + "loss": 3.5661, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307614243793908e-05, + "loss": 3.569, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306775649042856e-05, + "loss": 3.5733, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305937054291804e-05, + "loss": 3.5585, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050984595407514e-05, + "loss": 3.5469, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304261502670073e-05, + "loss": 3.5584, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303422907919021e-05, + "loss": 3.5654, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025843131679683e-05, + "loss": 3.5604, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017457184169163e-05, + "loss": 3.5666, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300908761546238e-05, + "loss": 3.559, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300070166795186e-05, + "loss": 3.5526, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299231572044133e-05, + "loss": 3.5587, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298392977293082e-05, + "loss": 3.5543, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975560204224035e-05, + "loss": 3.5711, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296717425671351e-05, + "loss": 3.5708, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295878830920299e-05, + "loss": 3.577, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295040236169247e-05, + "loss": 3.5526, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2942032792985684e-05, + "loss": 3.5614, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293364684547516e-05, + "loss": 3.5602, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292526089796464e-05, + "loss": 3.5635, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291687495045412e-05, + "loss": 3.5728, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290850538174733e-05, + "loss": 3.563, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2900119434236806e-05, + "loss": 3.5612, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891733486726286e-05, + "loss": 3.5562, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288334753921577e-05, + "loss": 3.5685, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287497797050898e-05, + "loss": 3.5459, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286659202299846e-05, + "loss": 3.5549, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285820607548794e-05, + "loss": 3.563, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284983650678116e-05, + "loss": 3.563, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284145055927063e-05, + "loss": 3.5522, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283306461176011e-05, + "loss": 3.56, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282467866424959e-05, + "loss": 3.5441, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281629271673907e-05, + "loss": 3.5679, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280792314803228e-05, + "loss": 3.5572, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279953720052176e-05, + "loss": 3.563, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279115125301124e-05, + "loss": 3.5718, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782781684304456e-05, + "loss": 3.5722, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277441211559767e-05, + "loss": 3.5554, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276602616808715e-05, + "loss": 3.5582, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275764022057663e-05, + "loss": 3.5642, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749254273066105e-05, + "loss": 3.5547, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740868325555585e-05, + "loss": 3.5592, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732482378045065e-05, + "loss": 3.5517, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724096430534544e-05, + "loss": 3.5583, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715710483024024e-05, + "loss": 3.5532, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707340914317234e-05, + "loss": 3.5503, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698954966806713e-05, + "loss": 3.5593, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690569019296193e-05, + "loss": 3.5584, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268218307178568e-05, + "loss": 3.5507, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267381350307889e-05, + "loss": 3.5686, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266542755556837e-05, + "loss": 3.5608, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265704160805785e-05, + "loss": 3.5757, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264865566054733e-05, + "loss": 3.5528, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264028609184054e-05, + "loss": 3.5643, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263190014433002e-05, + "loss": 3.5667, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.26235141968195e-05, + "loss": 3.5596, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261512824930898e-05, + "loss": 3.5565, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260675868060219e-05, + "loss": 3.5576, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259837273309167e-05, + "loss": 3.5659, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258998678558115e-05, + "loss": 3.5698, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581600838070634e-05, + "loss": 3.5576, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257323126936384e-05, + "loss": 3.5604, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256484532185332e-05, + "loss": 3.5629, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.25564593743428e-05, + "loss": 3.5566, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254807342683228e-05, + "loss": 3.5529, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253970385812549e-05, + "loss": 3.5659, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253131791061497e-05, + "loss": 3.5554, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252293196310445e-05, + "loss": 3.5634, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251454601559393e-05, + "loss": 3.5516, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.843310594558716, + "eval_runtime": 309.0842, + "eval_samples_per_second": 1234.586, + "eval_steps_per_second": 38.582, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250617644688714e-05, + "loss": 3.5697, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249779049937662e-05, + "loss": 3.5496, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.24894045518661e-05, + "loss": 3.5523, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248101860435559e-05, + "loss": 3.567, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472649035648797e-05, + "loss": 3.566, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2464263088138277e-05, + "loss": 3.5618, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455877140627757e-05, + "loss": 3.5504, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447491193117236e-05, + "loss": 3.5524, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2439105245606716e-05, + "loss": 3.5461, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2430735676899926e-05, + "loss": 3.5661, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2422349729389405e-05, + "loss": 3.5537, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2413963781878885e-05, + "loss": 3.561, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405577834368365e-05, + "loss": 3.5561, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397208265661574e-05, + "loss": 3.5469, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388822318151054e-05, + "loss": 3.5482, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238043637064054e-05, + "loss": 3.5451, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237205042313002e-05, + "loss": 3.5552, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236368085442323e-05, + "loss": 3.5466, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235529490691271e-05, + "loss": 3.5524, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234690895940219e-05, + "loss": 3.5488, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233852301189167e-05, + "loss": 3.5615, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233015344318488e-05, + "loss": 3.563, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232176749567436e-05, + "loss": 3.5563, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231338154816384e-05, + "loss": 3.5507, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230499560065332e-05, + "loss": 3.5616, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229662603194653e-05, + "loss": 3.5513, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228824008443601e-05, + "loss": 3.5517, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227985413692549e-05, + "loss": 3.5585, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271468189414975e-05, + "loss": 3.5432, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263098620708184e-05, + "loss": 3.5432, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254712673197664e-05, + "loss": 3.5483, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246326725687144e-05, + "loss": 3.5505, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237940778176624e-05, + "loss": 3.5621, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222957120946983e-05, + "loss": 3.563, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222118526195931e-05, + "loss": 3.5464, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221279931444879e-05, + "loss": 3.5586, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220441336693827e-05, + "loss": 3.5584, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219604379823148e-05, + "loss": 3.5394, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218765785072096e-05, + "loss": 3.5472, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217927190321044e-05, + "loss": 3.546, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217088595569993e-05, + "loss": 3.5443, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216251638699314e-05, + "loss": 3.55, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215413043948262e-05, + "loss": 3.5592, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.21457444919721e-05, + "loss": 3.5469, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213735854446158e-05, + "loss": 3.5457, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128988975754787e-05, + "loss": 3.5539, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120603028244266e-05, + "loss": 3.5463, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2112217080733746e-05, + "loss": 3.5453, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103831133223226e-05, + "loss": 3.5289, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095461564516435e-05, + "loss": 3.5546, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2087075617005915e-05, + "loss": 3.5494, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078689669495395e-05, + "loss": 3.5565, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207030372198488e-05, + "loss": 3.5457, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206193415327809e-05, + "loss": 3.5347, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205354820576757e-05, + "loss": 3.5397, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204516225825705e-05, + "loss": 3.5473, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203677631074653e-05, + "loss": 3.5504, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202840674203974e-05, + "loss": 3.5307, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.202002079452922e-05, + "loss": 3.5625, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.20116348470187e-05, + "loss": 3.5475, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200324889950818e-05, + "loss": 3.5351, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199487933080139e-05, + "loss": 3.5536, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198649338329087e-05, + "loss": 3.542, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197810743578035e-05, + "loss": 3.5456, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969721488269836e-05, + "loss": 3.5386, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961351919563045e-05, + "loss": 3.5526, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952965972052525e-05, + "loss": 3.54, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944580024542005e-05, + "loss": 3.5433, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193619407703148e-05, + "loss": 3.5406, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927824508324694e-05, + "loss": 3.5405, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919438560814174e-05, + "loss": 3.5471, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1911052613303654e-05, + "loss": 3.5594, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190266666579313e-05, + "loss": 3.5481, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189429709708634e-05, + "loss": 3.5469, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188591114957582e-05, + "loss": 3.5597, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18775252020653e-05, + "loss": 3.5429, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186913925455478e-05, + "loss": 3.5549, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186075330704426e-05, + "loss": 3.5486, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185238373833748e-05, + "loss": 3.5496, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184399779082695e-05, + "loss": 3.5423, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183561184331643e-05, + "loss": 3.548, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182722589580591e-05, + "loss": 3.5515, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181885632709913e-05, + "loss": 3.5587, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.18104703795886e-05, + "loss": 3.5455, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180208443207808e-05, + "loss": 3.5308, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179369848456756e-05, + "loss": 3.5426, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785328915860776e-05, + "loss": 3.5501, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776942968350256e-05, + "loss": 3.5472, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768557020839736e-05, + "loss": 3.5486, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1760171073329216e-05, + "loss": 3.544, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751801504622425e-05, + "loss": 3.5354, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743415557111905e-05, + "loss": 3.5402, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1735029609601385e-05, + "loss": 3.5389, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1726643662090865e-05, + "loss": 3.553, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1718274093384074e-05, + "loss": 3.5531, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1709888145873554e-05, + "loss": 3.5676, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701502198363034e-05, + "loss": 3.5339, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1693116250852514e-05, + "loss": 3.546, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168474668214573e-05, + "loss": 3.5487, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167636073463521e-05, + "loss": 3.5482, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166797478712469e-05, + "loss": 3.5511, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165958883961417e-05, + "loss": 3.5483, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165121927090738e-05, + "loss": 3.5476, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164283332339686e-05, + "loss": 3.5371, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163444737588634e-05, + "loss": 3.5538, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162606142837582e-05, + "loss": 3.53, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161769185966903e-05, + "loss": 3.5386, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160930591215851e-05, + "loss": 3.5449, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160091996464799e-05, + "loss": 3.55, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159253401713747e-05, + "loss": 3.5378, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1584164448430684e-05, + "loss": 3.5404, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575778500920164e-05, + "loss": 3.5358, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567392553409644e-05, + "loss": 3.5439, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1559006605899124e-05, + "loss": 3.5428, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155063703719233e-05, + "loss": 3.551, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154225108968181e-05, + "loss": 3.5568, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153386514217129e-05, + "loss": 3.5563, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.15254955734645e-05, + "loss": 3.5388, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151710962595398e-05, + "loss": 3.5432, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150872367844346e-05, + "loss": 3.5501, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150033773093294e-05, + "loss": 3.5407, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149195178342242e-05, + "loss": 3.5425, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.14835658359119e-05, + "loss": 3.5404, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147517988840139e-05, + "loss": 3.5417, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146679394089087e-05, + "loss": 3.5416, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145842437218408e-05, + "loss": 3.5326, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145003842467356e-05, + "loss": 3.5453, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144165247716304e-05, + "loss": 3.543, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143326652965252e-05, + "loss": 3.5365, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424896960945726e-05, + "loss": 3.547, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416511013435206e-05, + "loss": 3.5485, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1408125065924686e-05, + "loss": 3.5567, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399739118414166e-05, + "loss": 3.5417, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391369549707375e-05, + "loss": 3.5433, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1382983602196855e-05, + "loss": 3.554, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374597654686335e-05, + "loss": 3.5404, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136621170717582e-05, + "loss": 3.5429, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135784213846903e-05, + "loss": 3.541, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134945619095851e-05, + "loss": 3.5515, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134107024344799e-05, + "loss": 3.5511, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133268429593747e-05, + "loss": 3.5457, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132431472723068e-05, + "loss": 3.543, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131592877972016e-05, + "loss": 3.5478, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130754283220964e-05, + "loss": 3.538, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129915688469912e-05, + "loss": 3.5385, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129078731599233e-05, + "loss": 3.5487, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128240136848181e-05, + "loss": 3.5378, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127401542097129e-05, + "loss": 3.5545, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265645852264505e-05, + "loss": 3.5316, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8432068824768066, + "eval_runtime": 309.8653, + "eval_samples_per_second": 1231.474, + "eval_steps_per_second": 38.484, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257259904753985e-05, + "loss": 3.5397, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248873957243465e-05, + "loss": 3.5393, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240488009732945e-05, + "loss": 3.5358, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1232118441026154e-05, + "loss": 3.5501, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223732493515634e-05, + "loss": 3.5499, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1215346546005114e-05, + "loss": 3.5494, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1206960598494594e-05, + "loss": 3.5328, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1198574650984073e-05, + "loss": 3.5357, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119020508227728e-05, + "loss": 3.5361, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118181913476676e-05, + "loss": 3.5466, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117343318725624e-05, + "loss": 3.5403, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116504723974573e-05, + "loss": 3.5447, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115667767103894e-05, + "loss": 3.5395, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114829172352842e-05, + "loss": 3.53, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.11399057760179e-05, + "loss": 3.5322, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113151982850738e-05, + "loss": 3.5284, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112315025980059e-05, + "loss": 3.5411, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111476431229007e-05, + "loss": 3.5315, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110637836477955e-05, + "loss": 3.5362, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109799241726903e-05, + "loss": 3.5357, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089622848562236e-05, + "loss": 3.5488, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1081236901051716e-05, + "loss": 3.5456, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.1072850953541196e-05, + "loss": 3.5396, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106446500603068e-05, + "loss": 3.5375, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105609543732389e-05, + "loss": 3.5452, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104770948981337e-05, + "loss": 3.5403, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103932354230285e-05, + "loss": 3.5344, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1030937594792325e-05, + "loss": 3.5444, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102256802608554e-05, + "loss": 3.5259, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101418207857502e-05, + "loss": 3.5277, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.10057961310645e-05, + "loss": 3.5343, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997410183553974e-05, + "loss": 3.5382, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098904061484719e-05, + "loss": 3.5454, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098065466733667e-05, + "loss": 3.5432, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097226871982615e-05, + "loss": 3.5361, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096388277231563e-05, + "loss": 3.5399, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955513203608846e-05, + "loss": 3.5438, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0947127256098326e-05, + "loss": 3.5267, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.09387413085878e-05, + "loss": 3.5369, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093035536107728e-05, + "loss": 3.5243, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921985792370495e-05, + "loss": 3.5319, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913599844859975e-05, + "loss": 3.5344, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090521389734945e-05, + "loss": 3.5421, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089682794983893e-05, + "loss": 3.533, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888458381132144e-05, + "loss": 3.5281, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0880072433621624e-05, + "loss": 3.5426, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871686486111103e-05, + "loss": 3.5335, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863300538600583e-05, + "loss": 3.5289, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.08549309698938e-05, + "loss": 3.5137, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084654502238327e-05, + "loss": 3.5409, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083815907487275e-05, + "loss": 3.5353, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082977312736223e-05, + "loss": 3.5384, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082140355865545e-05, + "loss": 3.5308, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081301761114492e-05, + "loss": 3.5213, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.08046316636344e-05, + "loss": 3.5226, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079624571612388e-05, + "loss": 3.525, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.07878761474171e-05, + "loss": 3.5391, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077949019990658e-05, + "loss": 3.5233, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077110425239606e-05, + "loss": 3.5384, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076271830488554e-05, + "loss": 3.5316, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754348736178746e-05, + "loss": 3.5247, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0745962788668226e-05, + "loss": 3.5374, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0737576841157706e-05, + "loss": 3.5283, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0729190893647186e-05, + "loss": 3.5305, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720821324940395e-05, + "loss": 3.5224, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0712435377429875e-05, + "loss": 3.5401, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0704049429919355e-05, + "loss": 3.5243, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695663482408835e-05, + "loss": 3.5284, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068729391370205e-05, + "loss": 3.5184, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067890796619153e-05, + "loss": 3.5285, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067052201868101e-05, + "loss": 3.5299, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066213607117049e-05, + "loss": 3.5424, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065375012365997e-05, + "loss": 3.5321, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064538055495318e-05, + "loss": 3.5368, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063699460744266e-05, + "loss": 3.5407, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062860865993214e-05, + "loss": 3.5351, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062022271242162e-05, + "loss": 3.5321, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061185314371483e-05, + "loss": 3.535, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060346719620431e-05, + "loss": 3.5343, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059508124869379e-05, + "loss": 3.5281, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058669530118327e-05, + "loss": 3.5339, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578325732476485e-05, + "loss": 3.5431, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569939784965964e-05, + "loss": 3.5423, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561553837455444e-05, + "loss": 3.5293, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553167889944924e-05, + "loss": 3.5148, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544798321238133e-05, + "loss": 3.5251, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536412373727613e-05, + "loss": 3.5367, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0528026426217093e-05, + "loss": 3.531, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051964047870657e-05, + "loss": 3.536, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511270909999782e-05, + "loss": 3.5319, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502884962489266e-05, + "loss": 3.5227, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494499014978746e-05, + "loss": 3.5223, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486113067468226e-05, + "loss": 3.5225, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477743498761435e-05, + "loss": 3.5383, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469357551250915e-05, + "loss": 3.5353, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460971603740395e-05, + "loss": 3.5486, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452585656229875e-05, + "loss": 3.5266, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444216087523087e-05, + "loss": 3.5301, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435830140012567e-05, + "loss": 3.5323, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427444192502047e-05, + "loss": 3.5356, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419058244991527e-05, + "loss": 3.5369, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410688676284736e-05, + "loss": 3.5338, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040230272877422e-05, + "loss": 3.5322, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.03939167812637e-05, + "loss": 3.5223, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038553083375318e-05, + "loss": 3.5407, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037716126504639e-05, + "loss": 3.5172, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036877531753587e-05, + "loss": 3.5248, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036038937002535e-05, + "loss": 3.531, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035200342251483e-05, + "loss": 3.5312, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034363385380804e-05, + "loss": 3.5191, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033524790629752e-05, + "loss": 3.5301, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326861958787e-05, + "loss": 3.5156, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031847601127648e-05, + "loss": 3.5334, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.031010644256969e-05, + "loss": 3.5289, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301720495059173e-05, + "loss": 3.5345, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293334547548653e-05, + "loss": 3.5386, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284948600038133e-05, + "loss": 3.54, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276579031331342e-05, + "loss": 3.5278, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268193083820822e-05, + "loss": 3.53, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259807136310302e-05, + "loss": 3.5344, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251421188799782e-05, + "loss": 3.5243, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243051620092994e-05, + "loss": 3.5293, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234665672582474e-05, + "loss": 3.5257, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226279725071954e-05, + "loss": 3.5291, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217893777561434e-05, + "loss": 3.5239, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209524208854643e-05, + "loss": 3.5221, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201138261344127e-05, + "loss": 3.5285, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192752313833607e-05, + "loss": 3.5276, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184366366323087e-05, + "loss": 3.5241, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175996797616296e-05, + "loss": 3.527, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167610850105776e-05, + "loss": 3.535, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159224902595256e-05, + "loss": 3.5445, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150838955084736e-05, + "loss": 3.524, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142469386377948e-05, + "loss": 3.5276, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134083438867428e-05, + "loss": 3.5381, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125697491356908e-05, + "loss": 3.5288, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117311543846388e-05, + "loss": 3.529, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108941975139597e-05, + "loss": 3.5279, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010055602762908e-05, + "loss": 3.5386, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009217008011856e-05, + "loss": 3.5289, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008378413260804e-05, + "loss": 3.5339, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007541456390125e-05, + "loss": 3.5285, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006702861639073e-05, + "loss": 3.5272, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005864266888021e-05, + "loss": 3.5281, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.005025672136969e-05, + "loss": 3.5225, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041887152662902e-05, + "loss": 3.5347, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033501205152382e-05, + "loss": 3.5244, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025115257641862e-05, + "loss": 3.5397, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001672931013134e-05, + "loss": 3.5162, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000835974142455e-05, + "loss": 3.5291, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.844294786453247, + "eval_runtime": 310.1414, + "eval_samples_per_second": 1230.377, + "eval_steps_per_second": 38.45, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999997379391403e-05, + "loss": 3.5222, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991587846403514e-05, + "loss": 3.5207, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983201898892994e-05, + "loss": 3.5351, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974815951382474e-05, + "loss": 3.5356, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966446382675683e-05, + "loss": 3.5364, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958060435165163e-05, + "loss": 3.5197, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949674487654643e-05, + "loss": 3.5219, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941288540144123e-05, + "loss": 3.516, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932918971437335e-05, + "loss": 3.5363, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924533023926815e-05, + "loss": 3.5229, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916147076416295e-05, + "loss": 3.5342, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990776112890577e-05, + "loss": 3.5246, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899391560198984e-05, + "loss": 3.5193, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9891005612688468e-05, + "loss": 3.5171, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882619665177948e-05, + "loss": 3.5168, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987423371766742e-05, + "loss": 3.5227, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865864148960637e-05, + "loss": 3.5206, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857478201450117e-05, + "loss": 3.5197, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849092253939597e-05, + "loss": 3.5185, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840706306429073e-05, + "loss": 3.5366, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983233673772229e-05, + "loss": 3.5294, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982395079021177e-05, + "loss": 3.5304, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815564842701242e-05, + "loss": 3.5207, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807178895190722e-05, + "loss": 3.5321, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798809326483938e-05, + "loss": 3.5239, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979042337897342e-05, + "loss": 3.5245, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782037431462895e-05, + "loss": 3.5263, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773651483952375e-05, + "loss": 3.5126, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976528191524559e-05, + "loss": 3.5168, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756895967735067e-05, + "loss": 3.5154, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748510020224547e-05, + "loss": 3.528, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740140451517763e-05, + "loss": 3.526, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731754504007243e-05, + "loss": 3.5287, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723368556496716e-05, + "loss": 3.5265, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714982608986196e-05, + "loss": 3.5237, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706596661475676e-05, + "loss": 3.5292, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698227092768892e-05, + "loss": 3.5128, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968984114525837e-05, + "loss": 3.5226, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681455197747848e-05, + "loss": 3.5066, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673085629041064e-05, + "loss": 3.5239, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664699681530537e-05, + "loss": 3.5152, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965631373402002e-05, + "loss": 3.5299, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.96479277865095e-05, + "loss": 3.5169, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639558217802716e-05, + "loss": 3.5164, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963117227029219e-05, + "loss": 3.5263, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962278632278167e-05, + "loss": 3.5204, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961440037527115e-05, + "loss": 3.516, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606030806564365e-05, + "loss": 3.5016, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597644859053842e-05, + "loss": 3.5211, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589258911543322e-05, + "loss": 3.5244, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580872964032802e-05, + "loss": 3.5246, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957250339532601e-05, + "loss": 3.5137, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956411744781549e-05, + "loss": 3.5081, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555731500304974e-05, + "loss": 3.5087, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547345552794454e-05, + "loss": 3.5086, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538975984087663e-05, + "loss": 3.5308, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530590036577143e-05, + "loss": 3.5062, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522204089066623e-05, + "loss": 3.5245, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513818141556103e-05, + "loss": 3.5228, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505448572849316e-05, + "loss": 3.5065, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497062625338796e-05, + "loss": 3.5236, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488676677828276e-05, + "loss": 3.513, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480290730317756e-05, + "loss": 3.5156, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471921161610965e-05, + "loss": 3.5129, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463535214100445e-05, + "loss": 3.5244, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455149266589928e-05, + "loss": 3.512, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446763319079408e-05, + "loss": 3.5124, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438393750372617e-05, + "loss": 3.5117, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9430007802862097e-05, + "loss": 3.5124, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421621855351577e-05, + "loss": 3.5164, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413235907841057e-05, + "loss": 3.5276, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940486633913427e-05, + "loss": 3.5155, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939648039162375e-05, + "loss": 3.525, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938809444411323e-05, + "loss": 3.5257, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937970849660271e-05, + "loss": 3.5209, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937133892789592e-05, + "loss": 3.5179, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.93629529803854e-05, + "loss": 3.5199, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935456703287488e-05, + "loss": 3.522, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934618108536436e-05, + "loss": 3.5149, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933781151665757e-05, + "loss": 3.5178, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932942556914705e-05, + "loss": 3.527, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932103962163653e-05, + "loss": 3.529, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931265367412601e-05, + "loss": 3.5127, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304284105419223e-05, + "loss": 3.5004, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295898157908703e-05, + "loss": 3.5119, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287512210398183e-05, + "loss": 3.5239, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279126262887663e-05, + "loss": 3.5166, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270756694180872e-05, + "loss": 3.5238, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262370746670352e-05, + "loss": 3.5112, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253984799159835e-05, + "loss": 3.5154, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245598851649315e-05, + "loss": 3.5104, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237212904138795e-05, + "loss": 3.5108, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228843335432004e-05, + "loss": 3.5234, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220457387921484e-05, + "loss": 3.5205, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9212071440410964e-05, + "loss": 3.534, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203685492900444e-05, + "loss": 3.518, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195315924193657e-05, + "loss": 3.5113, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186929976683137e-05, + "loss": 3.5178, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178544029172617e-05, + "loss": 3.5216, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170158081662097e-05, + "loss": 3.5212, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161788512955306e-05, + "loss": 3.5232, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915340256544479e-05, + "loss": 3.5158, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914501661793427e-05, + "loss": 3.5113, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136647049227478e-05, + "loss": 3.5237, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128261101716958e-05, + "loss": 3.5075, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119875154206438e-05, + "loss": 3.5111, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111489206695918e-05, + "loss": 3.5177, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103103259185398e-05, + "loss": 3.5154, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909473369047861e-05, + "loss": 3.5065, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908634774296809e-05, + "loss": 3.5206, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907796179545757e-05, + "loss": 3.5042, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906959222675078e-05, + "loss": 3.5165, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906120627924026e-05, + "loss": 3.5148, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905282033172974e-05, + "loss": 3.5199, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044434384219223e-05, + "loss": 3.5285, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9036064815512432e-05, + "loss": 3.5235, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902767886800191e-05, + "loss": 3.5127, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901929292049139e-05, + "loss": 3.5145, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901090697298087e-05, + "loss": 3.523, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002537404274084e-05, + "loss": 3.5103, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994151456763564e-05, + "loss": 3.5143, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985765509253044e-05, + "loss": 3.5101, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977379561742524e-05, + "loss": 3.5113, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968993614232004e-05, + "loss": 3.5161, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960624045525213e-05, + "loss": 3.5074, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952238098014693e-05, + "loss": 3.514, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943852150504176e-05, + "loss": 3.5146, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935466202993656e-05, + "loss": 3.5106, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8927096634286865e-05, + "loss": 3.5092, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918710686776345e-05, + "loss": 3.524, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910324739265825e-05, + "loss": 3.5313, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901938791755305e-05, + "loss": 3.5194, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893569223048518e-05, + "loss": 3.5075, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885183275537998e-05, + "loss": 3.5185, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876797328027478e-05, + "loss": 3.519, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868427759320687e-05, + "loss": 3.5181, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8860041811810167e-05, + "loss": 3.515, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851655864299647e-05, + "loss": 3.5248, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884326991678913e-05, + "loss": 3.5144, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883488396927861e-05, + "loss": 3.5216, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882651440057182e-05, + "loss": 3.5146, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.88181284530613e-05, + "loss": 3.5166, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880974250555078e-05, + "loss": 3.5109, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880137293684399e-05, + "loss": 3.5079, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879298698933347e-05, + "loss": 3.525, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878460104182295e-05, + "loss": 3.5107, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877621509431243e-05, + "loss": 3.5224, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876784552560564e-05, + "loss": 3.509, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875945957809512e-05, + "loss": 3.5091, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.845889091491699, + "eval_runtime": 320.4276, + "eval_samples_per_second": 1190.881, + "eval_steps_per_second": 37.216, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.87510736305846e-05, + "loss": 3.5101, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742687683074084e-05, + "loss": 3.5111, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734318114367293e-05, + "loss": 3.521, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725932166856773e-05, + "loss": 3.5177, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717546219346253e-05, + "loss": 3.5227, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709160271835733e-05, + "loss": 3.5078, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700790703128945e-05, + "loss": 3.5047, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692404755618425e-05, + "loss": 3.5045, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8684018808107905e-05, + "loss": 3.5184, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675632860597385e-05, + "loss": 3.5121, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667263291890594e-05, + "loss": 3.5216, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658877344380074e-05, + "loss": 3.5082, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650491396869554e-05, + "loss": 3.509, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8642105449359037e-05, + "loss": 3.5018, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633735880652246e-05, + "loss": 3.5042, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625349933141726e-05, + "loss": 3.5037, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616963985631206e-05, + "loss": 3.5104, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608578038120686e-05, + "loss": 3.5081, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.86002084694139e-05, + "loss": 3.5007, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859182252190338e-05, + "loss": 3.5292, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858343657439286e-05, + "loss": 3.5178, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857505062688234e-05, + "loss": 3.5155, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566681058175548e-05, + "loss": 3.5063, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558295110665028e-05, + "loss": 3.5183, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549909163154508e-05, + "loss": 3.505, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541523215643984e-05, + "loss": 3.5144, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533137268133464e-05, + "loss": 3.5086, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852476769942668e-05, + "loss": 3.5053, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851638175191616e-05, + "loss": 3.4994, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507995804405637e-05, + "loss": 3.5015, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499609856895116e-05, + "loss": 3.5147, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8491240288188332e-05, + "loss": 3.5145, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482854340677812e-05, + "loss": 3.5122, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474468393167285e-05, + "loss": 3.5167, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466082445656765e-05, + "loss": 3.5102, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845771287694998e-05, + "loss": 3.5092, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449326929439458e-05, + "loss": 3.5038, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440940981928938e-05, + "loss": 3.5076, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432555034418418e-05, + "loss": 3.4965, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424185465711634e-05, + "loss": 3.5114, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415799518201107e-05, + "loss": 3.4991, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840741357069059e-05, + "loss": 3.5176, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839902762318007e-05, + "loss": 3.5011, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839065805447328e-05, + "loss": 3.5061, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838227210696276e-05, + "loss": 3.5124, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837388615945224e-05, + "loss": 3.5052, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365516590745455e-05, + "loss": 3.5035, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835713064323493e-05, + "loss": 3.4916, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834874469572441e-05, + "loss": 3.503, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834035874821389e-05, + "loss": 3.5122, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833197280070337e-05, + "loss": 3.5088, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832360323199658e-05, + "loss": 3.5019, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831521728448606e-05, + "loss": 3.4919, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306831336975544e-05, + "loss": 3.4994, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298445389465024e-05, + "loss": 3.4933, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8290075820758233e-05, + "loss": 3.5183, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281689873247713e-05, + "loss": 3.4938, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273303925737193e-05, + "loss": 3.5121, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264917978226673e-05, + "loss": 3.5051, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256548409519885e-05, + "loss": 3.4957, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8248162462009365e-05, + "loss": 3.5081, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239776514498845e-05, + "loss": 3.5037, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231390566988325e-05, + "loss": 3.498, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8223020998281534e-05, + "loss": 3.4986, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214635050771014e-05, + "loss": 3.5115, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206249103260498e-05, + "loss": 3.5018, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197863155749977e-05, + "loss": 3.4987, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189493587043187e-05, + "loss": 3.4984, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8181107639532667e-05, + "loss": 3.4999, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172721692022146e-05, + "loss": 3.5024, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164335744511626e-05, + "loss": 3.5169, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815596617580484e-05, + "loss": 3.4994, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814758022829432e-05, + "loss": 3.5144, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81391942807838e-05, + "loss": 3.5121, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813080833327328e-05, + "loss": 3.5077, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122438764566488e-05, + "loss": 3.4988, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8114052817055968e-05, + "loss": 3.5105, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105666869545448e-05, + "loss": 3.5098, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809728092203493e-05, + "loss": 3.4998, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808891135332814e-05, + "loss": 3.5052, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.808052540581762e-05, + "loss": 3.5099, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.80721394583071e-05, + "loss": 3.5166, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806375351079658e-05, + "loss": 3.5002, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055383942089793e-05, + "loss": 3.4948, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046997994579273e-05, + "loss": 3.4956, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038612047068753e-05, + "loss": 3.5083, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8030226099558232e-05, + "loss": 3.506, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802185653085144e-05, + "loss": 3.5113, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801347058334092e-05, + "loss": 3.5016, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.80050846358304e-05, + "loss": 3.4975, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996698688319885e-05, + "loss": 3.4965, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988329119613094e-05, + "loss": 3.4976, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979943172102574e-05, + "loss": 3.5057, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971557224592054e-05, + "loss": 3.5059, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963171277081534e-05, + "loss": 3.5221, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954801708374746e-05, + "loss": 3.5103, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946415760864226e-05, + "loss": 3.4958, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7938029813353706e-05, + "loss": 3.5069, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929643865843186e-05, + "loss": 3.5037, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921274297136395e-05, + "loss": 3.5095, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912888349625875e-05, + "loss": 3.5076, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904502402115355e-05, + "loss": 3.5014, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789611645460484e-05, + "loss": 3.4995, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887746885898048e-05, + "loss": 3.5133, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879360938387528e-05, + "loss": 3.4918, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870974990877007e-05, + "loss": 3.5013, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862589043366487e-05, + "loss": 3.5005, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.78542194746597e-05, + "loss": 3.5062, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784583352714918e-05, + "loss": 3.4921, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783744757963866e-05, + "loss": 3.5063, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782906163212814e-05, + "loss": 3.4956, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782069206342135e-05, + "loss": 3.4991, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781230611591083e-05, + "loss": 3.5031, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780392016840031e-05, + "loss": 3.503, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795534220889792e-05, + "loss": 3.517, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787164652183e-05, + "loss": 3.5114, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777877870467248e-05, + "loss": 3.5033, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777039275716196e-05, + "loss": 3.5016, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776200680965144e-05, + "loss": 3.5055, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753637240944654e-05, + "loss": 3.4989, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745251293434134e-05, + "loss": 3.4989, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736865345923614e-05, + "loss": 3.4999, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728479398413093e-05, + "loss": 3.4996, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7720109829706303e-05, + "loss": 3.5028, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711723882195783e-05, + "loss": 3.493, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703337934685262e-05, + "loss": 3.5011, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694951987174746e-05, + "loss": 3.499, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686582418467955e-05, + "loss": 3.5004, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678196470957435e-05, + "loss": 3.4921, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669810523446915e-05, + "loss": 3.5124, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661424575936395e-05, + "loss": 3.5172, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7653055007229607e-05, + "loss": 3.5047, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644669059719087e-05, + "loss": 3.4952, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636283112208567e-05, + "loss": 3.5053, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627897164698047e-05, + "loss": 3.5066, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619527595991256e-05, + "loss": 3.5062, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611141648480736e-05, + "loss": 3.5011, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602755700970216e-05, + "loss": 3.5089, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.75943697534597e-05, + "loss": 3.4993, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758600018475291e-05, + "loss": 3.5112, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757761423724239e-05, + "loss": 3.4992, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756922828973187e-05, + "loss": 3.5069, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.756084234222135e-05, + "loss": 3.5018, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755247277351456e-05, + "loss": 3.4919, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754408682600404e-05, + "loss": 3.5113, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753570087849352e-05, + "loss": 3.5002, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527314930983e-05, + "loss": 3.5086, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751894536227621e-05, + "loss": 3.494, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.751055941476569e-05, + "loss": 3.4953, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.845820665359497, + "eval_runtime": 321.0736, + "eval_samples_per_second": 1188.485, + "eval_steps_per_second": 37.141, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750217346725517e-05, + "loss": 3.4992, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493787519744653e-05, + "loss": 3.4925, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485401572234133e-05, + "loss": 3.5104, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7477015624723606e-05, + "loss": 3.5027, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468646056016822e-05, + "loss": 3.513, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460260108506302e-05, + "loss": 3.4953, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.745187416099578e-05, + "loss": 3.4945, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744348821348526e-05, + "loss": 3.4893, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435118644778475e-05, + "loss": 3.5023, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426732697267954e-05, + "loss": 3.5046, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418346749757428e-05, + "loss": 3.5039, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409960802246908e-05, + "loss": 3.4987, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401591233540123e-05, + "loss": 3.4947, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393205286029603e-05, + "loss": 3.4925, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738481933851908e-05, + "loss": 3.492, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737643339100856e-05, + "loss": 3.4943, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7368063822301776e-05, + "loss": 3.494, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359677874791252e-05, + "loss": 3.4939, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351291927280732e-05, + "loss": 3.4912, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342905979770212e-05, + "loss": 3.516, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334536411063428e-05, + "loss": 3.5027, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.73261504635529e-05, + "loss": 3.5049, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731776451604238e-05, + "loss": 3.4931, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730937856853186e-05, + "loss": 3.5081, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7301008999825077e-05, + "loss": 3.4867, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292623052314554e-05, + "loss": 3.503, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7284237104804034e-05, + "loss": 3.4961, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275851157293514e-05, + "loss": 3.4953, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267481588586723e-05, + "loss": 3.4841, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7259095641076206e-05, + "loss": 3.4874, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250709693565686e-05, + "loss": 3.502, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242323746055166e-05, + "loss": 3.5027, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233954177348375e-05, + "loss": 3.5009, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225568229837855e-05, + "loss": 3.5009, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217182282327335e-05, + "loss": 3.4961, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208796334816815e-05, + "loss": 3.5003, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200426766110027e-05, + "loss": 3.4892, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7192040818599507e-05, + "loss": 3.4932, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183654871088987e-05, + "loss": 3.4834, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175268923578467e-05, + "loss": 3.5, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166899354871676e-05, + "loss": 3.4889, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158513407361156e-05, + "loss": 3.502, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.715012745985064e-05, + "loss": 3.4924, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714174151234012e-05, + "loss": 3.4883, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713337194363333e-05, + "loss": 3.5046, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712498599612281e-05, + "loss": 3.4923, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711660004861229e-05, + "loss": 3.4919, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.71082304799055e-05, + "loss": 3.4746, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709984453239498e-05, + "loss": 3.4924, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709145858488446e-05, + "loss": 3.4977, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708307263737394e-05, + "loss": 3.4948, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707470306866715e-05, + "loss": 3.4913, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706631712115663e-05, + "loss": 3.4777, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705793117364611e-05, + "loss": 3.4886, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049545226135593e-05, + "loss": 3.4815, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7041175657428802e-05, + "loss": 3.5035, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032789709918282e-05, + "loss": 3.4823, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024403762407762e-05, + "loss": 3.4982, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7016017814897242e-05, + "loss": 3.4953, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007648246190455e-05, + "loss": 3.4819, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999262298679935e-05, + "loss": 3.49, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990876351169415e-05, + "loss": 3.4949, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982490403658895e-05, + "loss": 3.4846, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6974120834952104e-05, + "loss": 3.4879, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965734887441584e-05, + "loss": 3.4975, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957348939931064e-05, + "loss": 3.4927, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948962992420547e-05, + "loss": 3.482, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940593423713756e-05, + "loss": 3.4886, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932207476203236e-05, + "loss": 3.482, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923821528692716e-05, + "loss": 3.49, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915435581182196e-05, + "loss": 3.5051, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6907049633671676e-05, + "loss": 3.4867, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689868006496489e-05, + "loss": 3.5023, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689029411745437e-05, + "loss": 3.4977, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688190816994385e-05, + "loss": 3.4976, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873522222433328e-05, + "loss": 3.4874, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6865152653726537e-05, + "loss": 3.4996, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856766706216017e-05, + "loss": 3.4942, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.68483807587055e-05, + "loss": 3.491, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683999481119498e-05, + "loss": 3.4918, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683162524248819e-05, + "loss": 3.4974, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682323929497767e-05, + "loss": 3.5063, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681485334746715e-05, + "loss": 3.4897, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680646739995663e-05, + "loss": 3.4795, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6798097831249842e-05, + "loss": 3.4807, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789711883739322e-05, + "loss": 3.4953, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781325936228802e-05, + "loss": 3.496, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772939988718282e-05, + "loss": 3.4996, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.676457042001149e-05, + "loss": 3.4864, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675618447250097e-05, + "loss": 3.4898, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747798524990454e-05, + "loss": 3.4805, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739412577479934e-05, + "loss": 3.4852, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6731043008773143e-05, + "loss": 3.4933, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722657061262623e-05, + "loss": 3.4977, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714271113752103e-05, + "loss": 3.512, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705885166241583e-05, + "loss": 3.4935, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697515597534796e-05, + "loss": 3.4851, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6689129650024276e-05, + "loss": 3.4944, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680743702513756e-05, + "loss": 3.4896, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672357755003236e-05, + "loss": 3.4988, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663988186296445e-05, + "loss": 3.4957, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655602238785925e-05, + "loss": 3.4893, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6647216291275408e-05, + "loss": 3.4906, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638830343764888e-05, + "loss": 3.499, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630460775058097e-05, + "loss": 3.4758, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622074827547577e-05, + "loss": 3.4917, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613688880037057e-05, + "loss": 3.4838, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605302932526537e-05, + "loss": 3.4905, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659693336381975e-05, + "loss": 3.481, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658854741630923e-05, + "loss": 3.4939, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.658016146879871e-05, + "loss": 3.4816, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657177552128819e-05, + "loss": 3.4871, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.65634059525814e-05, + "loss": 3.4926, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655502000507088e-05, + "loss": 3.4857, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654663405756036e-05, + "loss": 3.5064, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653826448885357e-05, + "loss": 3.4996, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652987854134305e-05, + "loss": 3.4921, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.652149259383253e-05, + "loss": 3.485, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651310664632201e-05, + "loss": 3.4917, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504737077615223e-05, + "loss": 3.4873, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496351130104703e-05, + "loss": 3.4888, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487965182594183e-05, + "loss": 3.4886, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479579235083663e-05, + "loss": 3.483, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6471209666376872e-05, + "loss": 3.4924, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462823718866352e-05, + "loss": 3.4804, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454437771355832e-05, + "loss": 3.4881, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6446051823845312e-05, + "loss": 3.4857, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437682255138524e-05, + "loss": 3.4874, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429296307628004e-05, + "loss": 3.4799, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420910360117484e-05, + "loss": 3.502, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412524412606964e-05, + "loss": 3.5054, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404154843900177e-05, + "loss": 3.4957, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395768896389657e-05, + "loss": 3.4779, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387382948879137e-05, + "loss": 3.4945, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378997001368617e-05, + "loss": 3.4896, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370627432661826e-05, + "loss": 3.4953, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362241485151306e-05, + "loss": 3.4883, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353855537640786e-05, + "loss": 3.4936, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345469590130266e-05, + "loss": 3.4896, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633708364261975e-05, + "loss": 3.4981, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328714073912958e-05, + "loss": 3.492, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320328126402438e-05, + "loss": 3.4912, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311942178891918e-05, + "loss": 3.4896, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303556231381398e-05, + "loss": 3.4821, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629518666267461e-05, + "loss": 3.4945, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628680071516409e-05, + "loss": 3.4916, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627841476765357e-05, + "loss": 3.492, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6270028820143044e-05, + "loss": 3.4826, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626165925143626e-05, + "loss": 3.4831, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8475005626678467, + "eval_runtime": 303.7919, + "eval_samples_per_second": 1256.093, + "eval_steps_per_second": 39.254, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625327330392574e-05, + "loss": 3.4883, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624488735641522e-05, + "loss": 3.484, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236517787708432e-05, + "loss": 3.4948, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6228131840197912e-05, + "loss": 3.4903, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219745892687392e-05, + "loss": 3.5015, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621135994517687e-05, + "loss": 3.4836, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202973997666348e-05, + "loss": 3.4834, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194604428959564e-05, + "loss": 3.4739, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186218481449044e-05, + "loss": 3.4908, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177832533938517e-05, + "loss": 3.49, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169462965231733e-05, + "loss": 3.4908, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6161077017721213e-05, + "loss": 3.4853, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152691070210693e-05, + "loss": 3.4826, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614430512270017e-05, + "loss": 3.481, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135935553993385e-05, + "loss": 3.4768, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127549606482865e-05, + "loss": 3.4819, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6119163658972345e-05, + "loss": 3.4802, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611077771146182e-05, + "loss": 3.4809, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102408142755034e-05, + "loss": 3.4784, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6094022195244518e-05, + "loss": 3.5058, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608563624773399e-05, + "loss": 3.4923, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607725030022347e-05, + "loss": 3.486, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068880731516687e-05, + "loss": 3.4837, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060494784006167e-05, + "loss": 3.4909, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6052108836495643e-05, + "loss": 3.4766, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043722888985123e-05, + "loss": 3.4939, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035336941474603e-05, + "loss": 3.4823, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602696737276782e-05, + "loss": 3.4813, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018581425257292e-05, + "loss": 3.4709, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010195477746772e-05, + "loss": 3.477, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001809530236256e-05, + "loss": 3.4878, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993439961529465e-05, + "loss": 3.4904, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5985054014018945e-05, + "loss": 3.4927, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976668066508425e-05, + "loss": 3.4896, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968282118997905e-05, + "loss": 3.479, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959912550291117e-05, + "loss": 3.4907, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951526602780597e-05, + "loss": 3.4751, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5943140655270077e-05, + "loss": 3.4853, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934754707759557e-05, + "loss": 3.4701, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926385139052766e-05, + "loss": 3.4851, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917999191542246e-05, + "loss": 3.4776, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909613244031726e-05, + "loss": 3.4895, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590122729652121e-05, + "loss": 3.4835, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589285772781442e-05, + "loss": 3.4722, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884471780303898e-05, + "loss": 3.4903, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5876085832793378e-05, + "loss": 3.4809, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867699885282858e-05, + "loss": 3.4782, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585933031657607e-05, + "loss": 3.4679, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585094436906555e-05, + "loss": 3.4764, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584255842155503e-05, + "loss": 3.4834, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583417247404451e-05, + "loss": 3.4838, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582580290533772e-05, + "loss": 3.479, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.58174169578272e-05, + "loss": 3.4677, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.580903101031668e-05, + "loss": 3.4773, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800645062806163e-05, + "loss": 3.4687, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792275494099372e-05, + "loss": 3.4879, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783889546588852e-05, + "loss": 3.4757, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775503599078332e-05, + "loss": 3.481, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5767117651567812e-05, + "loss": 3.484, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758748082861024e-05, + "loss": 3.4714, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750362135350504e-05, + "loss": 3.4744, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741976187839984e-05, + "loss": 3.481, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733590240329464e-05, + "loss": 3.4706, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5725220671622673e-05, + "loss": 3.4779, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716834724112153e-05, + "loss": 3.4815, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708448776601633e-05, + "loss": 3.4827, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5700062829091117e-05, + "loss": 3.471, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691693260384326e-05, + "loss": 3.4767, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683307312873806e-05, + "loss": 3.471, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674921365363286e-05, + "loss": 3.4758, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666535417852766e-05, + "loss": 3.4888, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658165849145978e-05, + "loss": 3.4767, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649779901635458e-05, + "loss": 3.4906, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641393954124938e-05, + "loss": 3.4864, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5633008006614418e-05, + "loss": 3.4872, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624638437907627e-05, + "loss": 3.4709, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616252490397107e-05, + "loss": 3.4863, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607866542886587e-05, + "loss": 3.4862, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559948059537607e-05, + "loss": 3.4768, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559111102666928e-05, + "loss": 3.4815, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558272507915876e-05, + "loss": 3.4835, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557433913164824e-05, + "loss": 3.4942, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556595318413772e-05, + "loss": 3.4781, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555758361543093e-05, + "loss": 3.4654, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554919766792041e-05, + "loss": 3.4714, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554081172040989e-05, + "loss": 3.4793, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553242577289937e-05, + "loss": 3.4834, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552405620419258e-05, + "loss": 3.4837, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551567025668206e-05, + "loss": 3.4782, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550728430917154e-05, + "loss": 3.4775, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549889836166102e-05, + "loss": 3.4696, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490528792954233e-05, + "loss": 3.474, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5482142845443713e-05, + "loss": 3.4777, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473756897933193e-05, + "loss": 3.4888, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465370950422673e-05, + "loss": 3.5025, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5457001381715885e-05, + "loss": 3.4774, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448615434205365e-05, + "loss": 3.4712, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440229486694845e-05, + "loss": 3.4846, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431843539184325e-05, + "loss": 3.4769, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423473970477534e-05, + "loss": 3.4878, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5415088022967014e-05, + "loss": 3.4797, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406702075456494e-05, + "loss": 3.4788, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398316127945974e-05, + "loss": 3.4757, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389946559239187e-05, + "loss": 3.4879, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381560611728667e-05, + "loss": 3.4665, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5373174664218147e-05, + "loss": 3.4764, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364788716707627e-05, + "loss": 3.4703, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356419148000836e-05, + "loss": 3.4827, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534803320049032e-05, + "loss": 3.4693, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.53396472529798e-05, + "loss": 3.4777, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533126130546928e-05, + "loss": 3.4709, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322891736762488e-05, + "loss": 3.4742, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314505789251968e-05, + "loss": 3.4775, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5306119841741448e-05, + "loss": 3.4784, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297733894230928e-05, + "loss": 3.4893, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528936432552414e-05, + "loss": 3.4905, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528097837801362e-05, + "loss": 3.4807, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.52725924305031e-05, + "loss": 3.4737, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526420648299258e-05, + "loss": 3.4789, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525583691428579e-05, + "loss": 3.478, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247450966775273e-05, + "loss": 3.4726, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5239065019264753e-05, + "loss": 3.4769, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230679071754233e-05, + "loss": 3.4792, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522230950304744e-05, + "loss": 3.4771, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521392355553692e-05, + "loss": 3.4715, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.52055376080264e-05, + "loss": 3.4745, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519715166051588e-05, + "loss": 3.4715, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188782091809094e-05, + "loss": 3.4771, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180396144298574e-05, + "loss": 3.4663, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5172010196788054e-05, + "loss": 3.4898, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163624249277534e-05, + "loss": 3.4894, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155254680570743e-05, + "loss": 3.4902, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146868733060226e-05, + "loss": 3.4637, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138482785549706e-05, + "loss": 3.4815, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5130096838039186e-05, + "loss": 3.4843, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121727269332395e-05, + "loss": 3.4802, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113341321821875e-05, + "loss": 3.4771, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104955374311355e-05, + "loss": 3.4808, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096569426800835e-05, + "loss": 3.4781, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088199858094048e-05, + "loss": 3.4875, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079813910583528e-05, + "loss": 3.4788, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071427963073008e-05, + "loss": 3.4779, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5063042015562488e-05, + "loss": 3.4792, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054672446855697e-05, + "loss": 3.4674, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504628649934518e-05, + "loss": 3.4846, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503790055183466e-05, + "loss": 3.4831, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502951460432414e-05, + "loss": 3.4794, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502114503561735e-05, + "loss": 3.469, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501275908810683e-05, + "loss": 3.4707, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.84787654876709, + "eval_runtime": 303.9538, + "eval_samples_per_second": 1255.424, + "eval_steps_per_second": 39.233, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500437314059631e-05, + "loss": 3.4765, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499598719308579e-05, + "loss": 3.4727, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498760124557527e-05, + "loss": 3.4774, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497921529806475e-05, + "loss": 3.4815, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970845729357958e-05, + "loss": 3.4936, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962459781847438e-05, + "loss": 3.473, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4954073834336918e-05, + "loss": 3.4701, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945687886826398e-05, + "loss": 3.461, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493731831811961e-05, + "loss": 3.4819, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492893237060909e-05, + "loss": 3.4805, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492054642309857e-05, + "loss": 3.4758, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491216047558805e-05, + "loss": 3.4767, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490379090688126e-05, + "loss": 3.468, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895404959370743e-05, + "loss": 3.4741, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4887019011860222e-05, + "loss": 3.4612, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878633064349702e-05, + "loss": 3.4739, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487026349564291e-05, + "loss": 3.4648, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486187754813239e-05, + "loss": 3.4692, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485349160062187e-05, + "loss": 3.473, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484510565311135e-05, + "loss": 3.4896, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836736084404564e-05, + "loss": 3.4758, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828350136894044e-05, + "loss": 3.4769, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819964189383524e-05, + "loss": 3.4716, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811578241873e-05, + "loss": 3.4778, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803208673166213e-05, + "loss": 3.4681, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794822725655696e-05, + "loss": 3.4816, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786436778145176e-05, + "loss": 3.472, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778067209438385e-05, + "loss": 3.4664, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769681261927865e-05, + "loss": 3.4601, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761295314417345e-05, + "loss": 3.4654, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752909366906825e-05, + "loss": 3.4741, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744539798200038e-05, + "loss": 3.4789, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736153850689518e-05, + "loss": 3.4812, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727767903178997e-05, + "loss": 3.4769, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719381955668474e-05, + "loss": 3.4683, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710996008157954e-05, + "loss": 3.4784, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702626439451166e-05, + "loss": 3.4664, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469424049194065e-05, + "loss": 3.4709, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685854544430126e-05, + "loss": 3.4561, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677468596919606e-05, + "loss": 3.4716, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.466909902821282e-05, + "loss": 3.4671, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660713080702295e-05, + "loss": 3.4807, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465232713319178e-05, + "loss": 3.4701, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464394118568126e-05, + "loss": 3.461, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463557161697447e-05, + "loss": 3.4797, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4627185669463948e-05, + "loss": 3.4719, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618799721953428e-05, + "loss": 3.4659, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610413774442908e-05, + "loss": 3.4581, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460204420573612e-05, + "loss": 3.4605, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.45936582582256e-05, + "loss": 3.4737, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458527231071508e-05, + "loss": 3.4703, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457688636320456e-05, + "loss": 3.4663, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456851679449777e-05, + "loss": 3.4599, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456013084698725e-05, + "loss": 3.4668, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455174489947673e-05, + "loss": 3.4583, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543358951966212e-05, + "loss": 3.4756, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453498938325942e-05, + "loss": 3.4612, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.45266034357489e-05, + "loss": 3.4721, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451821748823838e-05, + "loss": 3.4691, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450983154072786e-05, + "loss": 3.4661, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501461972021074e-05, + "loss": 3.4603, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4493076024510554e-05, + "loss": 3.4723, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484690077000034e-05, + "loss": 3.4595, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476320508293243e-05, + "loss": 3.4685, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467934560782723e-05, + "loss": 3.4724, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459548613272203e-05, + "loss": 3.471, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4451162665761683e-05, + "loss": 3.4596, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442793097054895e-05, + "loss": 3.464, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434407149544375e-05, + "loss": 3.4605, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426021202033855e-05, + "loss": 3.458, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417635254523335e-05, + "loss": 3.4755, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409265685816544e-05, + "loss": 3.4671, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400879738306028e-05, + "loss": 3.4792, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392493790795507e-05, + "loss": 3.4756, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384107843284987e-05, + "loss": 3.4784, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375738274578197e-05, + "loss": 3.46, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367352327067676e-05, + "loss": 3.4682, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358966379557156e-05, + "loss": 3.478, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350580432046636e-05, + "loss": 3.4636, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434221086333985e-05, + "loss": 3.4683, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433382491582933e-05, + "loss": 3.4704, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432543896831881e-05, + "loss": 3.482, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431705302080829e-05, + "loss": 3.4663, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308683452101498e-05, + "loss": 3.4525, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.430029750459098e-05, + "loss": 3.4611, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429191155708046e-05, + "loss": 3.4658, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428352560956994e-05, + "loss": 3.4715, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427515604086315e-05, + "loss": 3.4747, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.426677009335263e-05, + "loss": 3.4636, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.425838414584211e-05, + "loss": 3.4663, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424999819833159e-05, + "loss": 3.4618, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241628629624803e-05, + "loss": 3.4582, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233242682114282e-05, + "loss": 3.4682, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224856734603762e-05, + "loss": 3.4755, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216470787093242e-05, + "loss": 3.4907, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420810121838645e-05, + "loss": 3.4716, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199715270875935e-05, + "loss": 3.4575, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191329323365415e-05, + "loss": 3.4705, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182943375854895e-05, + "loss": 3.4612, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174573807148104e-05, + "loss": 3.4776, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166187859637584e-05, + "loss": 3.4711, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157801912127064e-05, + "loss": 3.4668, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149415964616544e-05, + "loss": 3.4615, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4141046395909756e-05, + "loss": 3.4742, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132660448399236e-05, + "loss": 3.4568, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124274500888716e-05, + "loss": 3.4666, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115888553378193e-05, + "loss": 3.4556, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107518984671405e-05, + "loss": 3.4721, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409913303716089e-05, + "loss": 3.4593, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409074708965037e-05, + "loss": 3.4638, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082361142139845e-05, + "loss": 3.458, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073991573433058e-05, + "loss": 3.4664, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065605625922537e-05, + "loss": 3.4672, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057219678412017e-05, + "loss": 3.4653, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048833730901497e-05, + "loss": 3.4789, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404046416219471e-05, + "loss": 3.4793, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403207821468419e-05, + "loss": 3.4682, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023692267173666e-05, + "loss": 3.463, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015306319663146e-05, + "loss": 3.4661, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400693675095636e-05, + "loss": 3.4712, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998550803445842e-05, + "loss": 3.4552, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.399016485593532e-05, + "loss": 3.4662, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.39817789084248e-05, + "loss": 3.4604, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397340933971801e-05, + "loss": 3.4675, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396502339220749e-05, + "loss": 3.4628, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956637444696968e-05, + "loss": 3.463, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394825149718645e-05, + "loss": 3.4599, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939881928479664e-05, + "loss": 3.4701, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393149598096914e-05, + "loss": 3.4568, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392311003345862e-05, + "loss": 3.4759, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.39147240859481e-05, + "loss": 3.4729, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906354517241312e-05, + "loss": 3.4827, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897968569730792e-05, + "loss": 3.4517, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889582622220272e-05, + "loss": 3.472, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881196674709752e-05, + "loss": 3.4736, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872827106002965e-05, + "loss": 3.4673, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386444115849244e-05, + "loss": 3.4671, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385605521098192e-05, + "loss": 3.4711, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847685642275137e-05, + "loss": 3.4635, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839299694764614e-05, + "loss": 3.4781, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830913747254094e-05, + "loss": 3.4629, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822527799743574e-05, + "loss": 3.4661, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814158231036786e-05, + "loss": 3.4654, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805772283526266e-05, + "loss": 3.4593, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797386336015746e-05, + "loss": 3.4656, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3789000388505226e-05, + "loss": 3.4768, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780630819798435e-05, + "loss": 3.4657, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772244872287915e-05, + "loss": 3.4557, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763858924777395e-05, + "loss": 3.4629, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8499889373779297, + "eval_runtime": 305.848, + "eval_samples_per_second": 1247.649, + "eval_steps_per_second": 38.99, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755472977266875e-05, + "loss": 3.4666, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374708702975636e-05, + "loss": 3.4597, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373870108224584e-05, + "loss": 3.4655, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730315134735318e-05, + "loss": 3.471, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721945566028527e-05, + "loss": 3.4768, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713559618518007e-05, + "loss": 3.464, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705173671007487e-05, + "loss": 3.456, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696787723496967e-05, + "loss": 3.4496, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368841815479018e-05, + "loss": 3.4673, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.368003220727966e-05, + "loss": 3.4701, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367164625976914e-05, + "loss": 3.4618, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663260312258616e-05, + "loss": 3.4668, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365489074355183e-05, + "loss": 3.4558, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646504796041312e-05, + "loss": 3.461, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638118848530792e-05, + "loss": 3.452, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362973290102027e-05, + "loss": 3.4628, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.362136333231348e-05, + "loss": 3.4504, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.361297738480296e-05, + "loss": 3.4611, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.360459143729244e-05, + "loss": 3.4577, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.359620548978192e-05, + "loss": 3.4772, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587835921075133e-05, + "loss": 3.4659, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579449973564613e-05, + "loss": 3.4721, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357106402605409e-05, + "loss": 3.4581, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356267807854357e-05, + "loss": 3.4678, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554308509836782e-05, + "loss": 3.4552, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545922562326266e-05, + "loss": 3.4694, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537536614815742e-05, + "loss": 3.4624, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529150667305222e-05, + "loss": 3.4528, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520781098598435e-05, + "loss": 3.449, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3512395151087915e-05, + "loss": 3.4547, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350400920357739e-05, + "loss": 3.4647, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495623256066875e-05, + "loss": 3.4651, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487253687360087e-05, + "loss": 3.4686, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478867739849564e-05, + "loss": 3.4688, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470481792339044e-05, + "loss": 3.4572, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462095844828524e-05, + "loss": 3.4632, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453726276121736e-05, + "loss": 3.4575, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445340328611216e-05, + "loss": 3.4601, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436954381100696e-05, + "loss": 3.4438, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.342858481239391e-05, + "loss": 3.4619, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.342019886488339e-05, + "loss": 3.4555, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411812917372865e-05, + "loss": 3.4691, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403426969862345e-05, + "loss": 3.4563, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339505740115556e-05, + "loss": 3.4526, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386671453645037e-05, + "loss": 3.4689, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378285506134517e-05, + "loss": 3.458, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369899558623997e-05, + "loss": 3.4551, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.336152998991721e-05, + "loss": 3.4479, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335314404240669e-05, + "loss": 3.4494, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334475809489617e-05, + "loss": 3.4603, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333637214738565e-05, + "loss": 3.4612, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3328002578678862e-05, + "loss": 3.4538, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331961663116834e-05, + "loss": 3.4488, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.331123068365782e-05, + "loss": 3.4561, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.33028447361473e-05, + "loss": 3.4426, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329447516744051e-05, + "loss": 3.4647, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328608921992999e-05, + "loss": 3.4527, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327770327241947e-05, + "loss": 3.4577, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326931732490895e-05, + "loss": 3.4557, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.326094775620216e-05, + "loss": 3.4563, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252561808691643e-05, + "loss": 3.4495, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244175861181123e-05, + "loss": 3.4584, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235789913670603e-05, + "loss": 3.4516, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227420344963812e-05, + "loss": 3.4528, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3219034397453292e-05, + "loss": 3.4618, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210648449942772e-05, + "loss": 3.4592, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202262502432252e-05, + "loss": 3.4459, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193892933725465e-05, + "loss": 3.4566, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185506986214945e-05, + "loss": 3.4485, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177121038704425e-05, + "loss": 3.4463, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168735091193905e-05, + "loss": 3.4656, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160365522487114e-05, + "loss": 3.4582, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151979574976597e-05, + "loss": 3.4662, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143593627466077e-05, + "loss": 3.4625, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135207679955557e-05, + "loss": 3.4717, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126838111248766e-05, + "loss": 3.4522, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118452163738246e-05, + "loss": 3.4572, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3110066216227726e-05, + "loss": 3.4643, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101680268717206e-05, + "loss": 3.4508, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309331070001042e-05, + "loss": 3.4601, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.30849247524999e-05, + "loss": 3.4634, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307653880498938e-05, + "loss": 3.4643, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068152857478858e-05, + "loss": 3.4568, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059783288772067e-05, + "loss": 3.4434, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.305139734126155e-05, + "loss": 3.4492, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304301139375103e-05, + "loss": 3.4549, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303462544624051e-05, + "loss": 3.4595, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302625587753372e-05, + "loss": 3.4624, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.30178699300232e-05, + "loss": 3.4552, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300948398251268e-05, + "loss": 3.4581, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.300109803500216e-05, + "loss": 3.4478, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992728466295372e-05, + "loss": 3.4482, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984342518784852e-05, + "loss": 3.4528, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975956571274332e-05, + "loss": 3.4653, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967570623763812e-05, + "loss": 3.4779, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295920105505702e-05, + "loss": 3.4631, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950815107546504e-05, + "loss": 3.4447, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942429160035984e-05, + "loss": 3.4621, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293404321252546e-05, + "loss": 3.4526, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925673643818673e-05, + "loss": 3.4643, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2917287696308153e-05, + "loss": 3.4566, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908901748797633e-05, + "loss": 3.4561, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900515801287113e-05, + "loss": 3.453, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2892146232580326e-05, + "loss": 3.4602, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883760285069806e-05, + "loss": 3.4493, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875374337559286e-05, + "loss": 3.4563, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866988390048762e-05, + "loss": 3.444, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858618821341975e-05, + "loss": 3.4629, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850232873831458e-05, + "loss": 3.4492, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841846926320935e-05, + "loss": 3.4513, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833460978810415e-05, + "loss": 3.4437, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2825091410103627e-05, + "loss": 3.4573, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816705462593107e-05, + "loss": 3.4571, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808319515082584e-05, + "loss": 3.4541, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799933567572067e-05, + "loss": 3.4655, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279156399886528e-05, + "loss": 3.4669, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.278317805135476e-05, + "loss": 3.4604, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774792103844236e-05, + "loss": 3.4526, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766406156333716e-05, + "loss": 3.4507, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275803658762693e-05, + "loss": 3.4616, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274965064011641e-05, + "loss": 3.4447, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741264692605888e-05, + "loss": 3.456, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732878745095368e-05, + "loss": 3.4463, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.272450917638858e-05, + "loss": 3.4595, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2716123228878057e-05, + "loss": 3.4442, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707737281367537e-05, + "loss": 3.4528, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269935133385702e-05, + "loss": 3.4532, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690981765150233e-05, + "loss": 3.4537, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.268259581763971e-05, + "loss": 3.4475, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267420987012919e-05, + "loss": 3.4599, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266582392261867e-05, + "loss": 3.4623, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657454353911882e-05, + "loss": 3.4678, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2649068406401362e-05, + "loss": 3.4406, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640682458890842e-05, + "loss": 3.4608, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632296511380322e-05, + "loss": 3.4584, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262392694267353e-05, + "loss": 3.46, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261554099516301e-05, + "loss": 3.4521, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260715504765249e-05, + "loss": 3.4622, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598769100141974e-05, + "loss": 3.4541, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590399531435183e-05, + "loss": 3.4667, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2582013583924663e-05, + "loss": 3.4484, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573627636414143e-05, + "loss": 3.4576, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565258067707352e-05, + "loss": 3.451, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556872120196836e-05, + "loss": 3.4513, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548486172686316e-05, + "loss": 3.4555, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2540100225175796e-05, + "loss": 3.4589, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531730656469005e-05, + "loss": 3.4606, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523344708958485e-05, + "loss": 3.441, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514958761447965e-05, + "loss": 3.4549, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8510310649871826, + "eval_runtime": 303.0287, + "eval_samples_per_second": 1259.257, + "eval_steps_per_second": 39.353, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506572813937445e-05, + "loss": 3.4555, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498203245230657e-05, + "loss": 3.4492, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489817297720137e-05, + "loss": 3.4539, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481431350209617e-05, + "loss": 3.4629, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2473045402699097e-05, + "loss": 3.4686, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464675833992306e-05, + "loss": 3.4511, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245628988648179e-05, + "loss": 3.4431, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244790393897127e-05, + "loss": 3.4459, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243951799146075e-05, + "loss": 3.4518, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.243114842275396e-05, + "loss": 3.4612, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.242276247524344e-05, + "loss": 3.4502, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414376527732918e-05, + "loss": 3.4566, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405990580222398e-05, + "loss": 3.4498, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239762101151561e-05, + "loss": 3.4455, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238923506400509e-05, + "loss": 3.4466, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238084911649457e-05, + "loss": 3.4504, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237246316898405e-05, + "loss": 3.4423, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.236409360027726e-05, + "loss": 3.4476, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355707652766743e-05, + "loss": 3.448, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347321705256223e-05, + "loss": 3.4631, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338935757745703e-05, + "loss": 3.4556, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330566189038912e-05, + "loss": 3.4622, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2322180241528392e-05, + "loss": 3.4434, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313794294017872e-05, + "loss": 3.4597, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305408346507352e-05, + "loss": 3.4447, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2297038777800564e-05, + "loss": 3.4597, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288652830290044e-05, + "loss": 3.4492, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280266882779524e-05, + "loss": 3.4401, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271880935269004e-05, + "loss": 3.4424, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263511366562213e-05, + "loss": 3.4429, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2255125419051697e-05, + "loss": 3.4525, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246739471541177e-05, + "loss": 3.4543, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238353524030657e-05, + "loss": 3.4562, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229983955323866e-05, + "loss": 3.4623, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221598007813346e-05, + "loss": 3.4407, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2213212060302826e-05, + "loss": 3.4557, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2204826112792306e-05, + "loss": 3.4506, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196456544085518e-05, + "loss": 3.443, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2188070596574998e-05, + "loss": 3.4375, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179684649064478e-05, + "loss": 3.4453, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171298701553955e-05, + "loss": 3.4491, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162929132847167e-05, + "loss": 3.4554, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2154543185336647e-05, + "loss": 3.4455, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214615723782613e-05, + "loss": 3.4421, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137771290315607e-05, + "loss": 3.4607, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212940172160882e-05, + "loss": 3.4456, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.21210157740983e-05, + "loss": 3.4456, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112629826587776e-05, + "loss": 3.4389, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210424387907726e-05, + "loss": 3.4331, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2095874310370472e-05, + "loss": 3.4499, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208748836285995e-05, + "loss": 3.4497, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2079102415349428e-05, + "loss": 3.4453, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070716467838908e-05, + "loss": 3.4368, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.206234689913212e-05, + "loss": 3.4468, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.20539609516216e-05, + "loss": 3.4315, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204557500411108e-05, + "loss": 3.4527, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203718905660056e-05, + "loss": 3.4399, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028819487893773e-05, + "loss": 3.442, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202043354038325e-05, + "loss": 3.4494, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.201204759287273e-05, + "loss": 3.4433, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003661645362213e-05, + "loss": 3.4394, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995292076655425e-05, + "loss": 3.4533, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986906129144902e-05, + "loss": 3.4373, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978520181634382e-05, + "loss": 3.4418, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1970134234123862e-05, + "loss": 3.4503, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961764665417074e-05, + "loss": 3.4469, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953378717906554e-05, + "loss": 3.4364, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944992770396034e-05, + "loss": 3.4451, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936623201689247e-05, + "loss": 3.4359, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928237254178723e-05, + "loss": 3.4381, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919851306668203e-05, + "loss": 3.4517, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911465359157683e-05, + "loss": 3.4453, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.19030957904509e-05, + "loss": 3.456, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894709842940376e-05, + "loss": 3.4476, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886323895429856e-05, + "loss": 3.4613, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877937947919336e-05, + "loss": 3.4402, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869552000408816e-05, + "loss": 3.4498, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1861182431702028e-05, + "loss": 3.4532, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852796484191508e-05, + "loss": 3.4378, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844410536680988e-05, + "loss": 3.4471, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1836040967974197e-05, + "loss": 3.4521, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827655020463677e-05, + "loss": 3.4555, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819269072953157e-05, + "loss": 3.4447, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810883125442637e-05, + "loss": 3.4358, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180251355673585e-05, + "loss": 3.4362, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179412760922533e-05, + "loss": 3.4426, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.178574166171481e-05, + "loss": 3.4497, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177735571420429e-05, + "loss": 3.4517, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.17689861454975e-05, + "loss": 3.4483, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.176060019798698e-05, + "loss": 3.4376, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175221425047646e-05, + "loss": 3.4406, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174382830296594e-05, + "loss": 3.4377, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173545873425915e-05, + "loss": 3.4427, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172707278674863e-05, + "loss": 3.4553, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171868683923811e-05, + "loss": 3.4625, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.171030089172759e-05, + "loss": 3.4538, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701931323020803e-05, + "loss": 3.4357, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1693545375510283e-05, + "loss": 3.4472, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1685159427999763e-05, + "loss": 3.4432, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676773480489243e-05, + "loss": 3.4522, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1668403911782452e-05, + "loss": 3.4464, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1660017964271932e-05, + "loss": 3.4505, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651632016761415e-05, + "loss": 3.4433, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643246069250895e-05, + "loss": 3.4448, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634876500544104e-05, + "loss": 3.4427, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626490553033584e-05, + "loss": 3.4405, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1618104605523064e-05, + "loss": 3.4328, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609718658012544e-05, + "loss": 3.4518, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1601349089305757e-05, + "loss": 3.4394, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592963141795237e-05, + "loss": 3.4395, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584577194284717e-05, + "loss": 3.4366, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1576191246774197e-05, + "loss": 3.4412, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567821678067406e-05, + "loss": 3.4478, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559435730556886e-05, + "loss": 3.4434, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.155104978304637e-05, + "loss": 3.4555, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.154266383553585e-05, + "loss": 3.4532, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534294266829058e-05, + "loss": 3.4505, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525908319318538e-05, + "loss": 3.4459, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517522371808018e-05, + "loss": 3.4346, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1509136424297498e-05, + "loss": 3.4548, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150076685559071e-05, + "loss": 3.439, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.149238090808019e-05, + "loss": 3.4413, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.148399496056967e-05, + "loss": 3.4359, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475609013059147e-05, + "loss": 3.4452, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.146723944435236e-05, + "loss": 3.4352, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145885349684184e-05, + "loss": 3.4406, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450467549331323e-05, + "loss": 3.4404, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.14420816018208e-05, + "loss": 3.4468, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433712033114012e-05, + "loss": 3.4369, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.142532608560349e-05, + "loss": 3.4525, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.141694013809297e-05, + "loss": 3.447, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140855419058245e-05, + "loss": 3.4574, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1400184621875664e-05, + "loss": 3.433, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391798674365144e-05, + "loss": 3.4496, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138341272685462e-05, + "loss": 3.4495, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.13750267793441e-05, + "loss": 3.4452, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366657210637313e-05, + "loss": 3.4443, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1358271263126793e-05, + "loss": 3.4498, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349885315616273e-05, + "loss": 3.4385, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341499368105753e-05, + "loss": 3.46, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1333129799398965e-05, + "loss": 3.4347, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324743851888445e-05, + "loss": 3.4474, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1316357904377922e-05, + "loss": 3.4417, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307971956867405e-05, + "loss": 3.4422, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299602388160618e-05, + "loss": 3.4416, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1291216440650094e-05, + "loss": 3.4464, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282830493139574e-05, + "loss": 3.45, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274444545629054e-05, + "loss": 3.4279, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1266074976922267e-05, + "loss": 3.4461, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8524069786071777, + "eval_runtime": 302.7283, + "eval_samples_per_second": 1260.507, + "eval_steps_per_second": 39.392, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257689029411747e-05, + "loss": 3.4453, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249303081901227e-05, + "loss": 3.4368, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240917134390707e-05, + "loss": 3.4424, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232531186880187e-05, + "loss": 3.4472, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1224161618173396e-05, + "loss": 3.4565, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215775670662876e-05, + "loss": 3.4417, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207389723152356e-05, + "loss": 3.4318, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119900377564184e-05, + "loss": 3.4349, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190634206935048e-05, + "loss": 3.4421, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182248259424528e-05, + "loss": 3.4484, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173862311914008e-05, + "loss": 3.4407, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165476364403488e-05, + "loss": 3.4415, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.11571067956967e-05, + "loss": 3.4391, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114872084818618e-05, + "loss": 3.4395, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114033490067566e-05, + "loss": 3.4301, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113194895316514e-05, + "loss": 3.4354, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112357938445835e-05, + "loss": 3.4341, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111519343694783e-05, + "loss": 3.4366, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110680748943731e-05, + "loss": 3.4381, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098421541926793e-05, + "loss": 3.4481, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.109005197322e-05, + "loss": 3.4486, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108166602570948e-05, + "loss": 3.4493, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107328007819896e-05, + "loss": 3.4349, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106489413068844e-05, + "loss": 3.4447, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056524561981654e-05, + "loss": 3.4337, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1048138614471134e-05, + "loss": 3.4531, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039752666960614e-05, + "loss": 3.4346, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031366719450094e-05, + "loss": 3.4324, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022997150743303e-05, + "loss": 3.433, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014611203232783e-05, + "loss": 3.4361, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1006225255722263e-05, + "loss": 3.4383, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997839308211746e-05, + "loss": 3.4446, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989469739504955e-05, + "loss": 3.4475, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0981083791994435e-05, + "loss": 3.4455, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972697844483915e-05, + "loss": 3.434, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964311896973395e-05, + "loss": 3.4444, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955942328266608e-05, + "loss": 3.4395, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947556380756088e-05, + "loss": 3.4289, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0939170433245568e-05, + "loss": 3.4308, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930784485735044e-05, + "loss": 3.4314, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922414917028257e-05, + "loss": 3.4384, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0914028969517737e-05, + "loss": 3.4434, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905643022007217e-05, + "loss": 3.4351, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089727345330043e-05, + "loss": 3.4307, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088888750578991e-05, + "loss": 3.4469, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.088050155827939e-05, + "loss": 3.4383, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087211561076887e-05, + "loss": 3.438, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863746042062078e-05, + "loss": 3.4241, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085536009455156e-05, + "loss": 3.4203, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084697414704104e-05, + "loss": 3.445, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838588199530518e-05, + "loss": 3.4345, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.083021863082373e-05, + "loss": 3.436, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082183268331321e-05, + "loss": 3.4312, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081344673580269e-05, + "loss": 3.43, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080506078829217e-05, + "loss": 3.4211, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796691219585383e-05, + "loss": 3.4384, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0788305272074863e-05, + "loss": 3.4325, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779919324564343e-05, + "loss": 3.4311, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077153337705382e-05, + "loss": 3.4416, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.076316380834703e-05, + "loss": 3.4315, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754777860836515e-05, + "loss": 3.4264, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074639191332599e-05, + "loss": 3.4449, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073800596581547e-05, + "loss": 3.4286, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729636397108684e-05, + "loss": 3.4265, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0721250449598164e-05, + "loss": 3.4419, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071286450208764e-05, + "loss": 3.4353, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704478554577124e-05, + "loss": 3.4213, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0696108985870336e-05, + "loss": 3.4387, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687723038359816e-05, + "loss": 3.4249, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679337090849293e-05, + "loss": 3.4238, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670951143338773e-05, + "loss": 3.4412, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662581574631985e-05, + "loss": 3.4363, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0654195627121465e-05, + "loss": 3.4399, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645809679610945e-05, + "loss": 3.4376, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637423732100425e-05, + "loss": 3.4524, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0629054163393638e-05, + "loss": 3.4318, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620668215883114e-05, + "loss": 3.4385, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0612282268372594e-05, + "loss": 3.4431, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603896320862078e-05, + "loss": 3.4259, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059552675215529e-05, + "loss": 3.4342, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0587140804644767e-05, + "loss": 3.4443, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578754857134247e-05, + "loss": 3.4418, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570368909623726e-05, + "loss": 3.437, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056199934091694e-05, + "loss": 3.4256, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055361339340642e-05, + "loss": 3.4211, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.05452274458959e-05, + "loss": 3.4334, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053684149838538e-05, + "loss": 3.4411, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528471929678588e-05, + "loss": 3.4387, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0520085982168068e-05, + "loss": 3.4365, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511700034657548e-05, + "loss": 3.423, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050331408714703e-05, + "loss": 3.4321, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049494451844024e-05, + "loss": 3.4275, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048655857092972e-05, + "loss": 3.4356, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.04781726234192e-05, + "loss": 3.4401, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046978667590868e-05, + "loss": 3.4535, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461417107201893e-05, + "loss": 3.4428, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0453031159691373e-05, + "loss": 3.4277, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444645212180853e-05, + "loss": 3.4366, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436259264670332e-05, + "loss": 3.433, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042788969596354e-05, + "loss": 3.4428, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041950374845302e-05, + "loss": 3.4337, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.04111178009425e-05, + "loss": 3.4431, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402731853431985e-05, + "loss": 3.4338, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394362284725194e-05, + "loss": 3.4262, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385976337214674e-05, + "loss": 3.436, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377590389704154e-05, + "loss": 3.4278, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0369204442193634e-05, + "loss": 3.425, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360834873486846e-05, + "loss": 3.4376, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352448925976326e-05, + "loss": 3.4324, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0344062978465806e-05, + "loss": 3.4264, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335677030955286e-05, + "loss": 3.4305, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327307462248495e-05, + "loss": 3.428, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318921514737975e-05, + "loss": 3.4372, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310535567227455e-05, + "loss": 3.4289, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030214961971694e-05, + "loss": 3.4483, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293780051010148e-05, + "loss": 3.4425, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285394103499628e-05, + "loss": 3.4422, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0277008155989108e-05, + "loss": 3.4332, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268622208478587e-05, + "loss": 3.4214, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.02602526397718e-05, + "loss": 3.4393, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025186669226128e-05, + "loss": 3.4335, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024348074475076e-05, + "loss": 3.4297, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023509479724024e-05, + "loss": 3.4258, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022672522853345e-05, + "loss": 3.4349, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021833928102293e-05, + "loss": 3.4259, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020995333351241e-05, + "loss": 3.4315, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020158376480562e-05, + "loss": 3.426, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.01931978172951e-05, + "loss": 3.4374, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.018481186978458e-05, + "loss": 3.422, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.017642592227406e-05, + "loss": 3.4437, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016805635356727e-05, + "loss": 3.436, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159670406056754e-05, + "loss": 3.4484, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151284458546234e-05, + "loss": 3.4226, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142898511035714e-05, + "loss": 3.4416, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134528942328923e-05, + "loss": 3.4367, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0126142994818403e-05, + "loss": 3.4388, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117757047307883e-05, + "loss": 3.4314, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109371099797363e-05, + "loss": 3.4332, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0101001531090575e-05, + "loss": 3.4349, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092615583580055e-05, + "loss": 3.4474, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0084229636069535e-05, + "loss": 3.4251, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007584368855901e-05, + "loss": 3.4357, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067474119852224e-05, + "loss": 3.4327, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0059088172341707e-05, + "loss": 3.4319, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050702224831187e-05, + "loss": 3.4323, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042316277320664e-05, + "loss": 3.4313, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033946708613876e-05, + "loss": 3.4422, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025560761103356e-05, + "loss": 3.415, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0017174813592833e-05, + "loss": 3.4385, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.854395866394043, + "eval_runtime": 304.8421, + "eval_samples_per_second": 1251.766, + "eval_steps_per_second": 39.119, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008788866082316e-05, + "loss": 3.4321, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.000041929737553e-05, + "loss": 3.427, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.999203334986501e-05, + "loss": 3.4299, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983647402354485e-05, + "loss": 3.4361, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975261454843965e-05, + "loss": 3.4481, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966891886137178e-05, + "loss": 3.4287, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995850593862666e-05, + "loss": 3.4277, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9950119991116138e-05, + "loss": 3.4252, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941734043605617e-05, + "loss": 3.4274, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993336447489883e-05, + "loss": 3.4405, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924978527388307e-05, + "loss": 3.4265, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916592579877786e-05, + "loss": 3.436, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990820663236727e-05, + "loss": 3.4262, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899837063660482e-05, + "loss": 3.426, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989145111614996e-05, + "loss": 3.4253, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988306516863944e-05, + "loss": 3.4252, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.987467922112892e-05, + "loss": 3.4211, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986630965242213e-05, + "loss": 3.4276, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985792370491161e-05, + "loss": 3.4274, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984953775740109e-05, + "loss": 3.4343, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984115180989057e-05, + "loss": 3.4386, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.983278224118378e-05, + "loss": 3.4431, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.982439629367326e-05, + "loss": 3.4216, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981601034616274e-05, + "loss": 3.4345, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807624398652224e-05, + "loss": 3.4259, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799254829945433e-05, + "loss": 3.4406, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790868882434913e-05, + "loss": 3.4258, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782482934924393e-05, + "loss": 3.4257, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9774096987413872e-05, + "loss": 3.4236, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765727418707085e-05, + "loss": 3.4209, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757341471196565e-05, + "loss": 3.4224, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748955523686045e-05, + "loss": 3.437, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740569576175525e-05, + "loss": 3.4356, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9732200007468734e-05, + "loss": 3.4337, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723814059958214e-05, + "loss": 3.4253, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9715428112447694e-05, + "loss": 3.4347, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9707042164937177e-05, + "loss": 3.4284, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698672596230386e-05, + "loss": 3.4187, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690286648719866e-05, + "loss": 3.4213, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681900701209346e-05, + "loss": 3.4215, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673514753698826e-05, + "loss": 3.425, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.966514518499204e-05, + "loss": 3.4317, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.965675923748152e-05, + "loss": 3.4263, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648373289971e-05, + "loss": 3.4202, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.963998734246048e-05, + "loss": 3.4336, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631617773753688e-05, + "loss": 3.4238, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9623231826243168e-05, + "loss": 3.4289, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614845878732647e-05, + "loss": 3.4163, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960647631002586e-05, + "loss": 3.4043, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959809036251534e-05, + "loss": 3.4354, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.958970441500482e-05, + "loss": 3.425, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.95813184674943e-05, + "loss": 3.4271, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957294889878751e-05, + "loss": 3.4212, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564562951276992e-05, + "loss": 3.415, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9556177003766472e-05, + "loss": 3.4149, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547791056255952e-05, + "loss": 3.4267, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953942148754916e-05, + "loss": 3.419, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953103554003864e-05, + "loss": 3.4222, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952264959252812e-05, + "loss": 3.4349, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.95142636450176e-05, + "loss": 3.4167, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505894076310814e-05, + "loss": 3.4175, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497508128800294e-05, + "loss": 3.4341, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9489122181289774e-05, + "loss": 3.4185, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480736233779254e-05, + "loss": 3.4157, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472366665072463e-05, + "loss": 3.4323, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463980717561946e-05, + "loss": 3.4223, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455594770051426e-05, + "loss": 3.4135, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447208822540906e-05, + "loss": 3.4255, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438839253834115e-05, + "loss": 3.417, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430453306323595e-05, + "loss": 3.4139, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9422067358813075e-05, + "loss": 3.4336, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413681411302555e-05, + "loss": 3.4256, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9405311842595767e-05, + "loss": 3.4285, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396925895085247e-05, + "loss": 3.4274, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388539947574727e-05, + "loss": 3.4404, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9380154000064204e-05, + "loss": 3.4194, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371784431357416e-05, + "loss": 3.4304, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363398483846896e-05, + "loss": 3.429, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935501253633638e-05, + "loss": 3.4174, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346626588825856e-05, + "loss": 3.4214, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933825702011907e-05, + "loss": 3.438, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932987107260855e-05, + "loss": 3.4311, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932148512509803e-05, + "loss": 3.4313, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931309917758751e-05, + "loss": 3.4117, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930472960888072e-05, + "loss": 3.4081, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.92963436613702e-05, + "loss": 3.4237, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287957713859678e-05, + "loss": 3.4311, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279571766349157e-05, + "loss": 3.4298, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927120219764237e-05, + "loss": 3.4267, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.926281625013185e-05, + "loss": 3.4129, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925443030262133e-05, + "loss": 3.4218, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924604435511081e-05, + "loss": 3.4187, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237674786404022e-05, + "loss": 3.42, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.92292888388935e-05, + "loss": 3.4349, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922090289138298e-05, + "loss": 3.4371, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212516943872462e-05, + "loss": 3.4339, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9204147375165675e-05, + "loss": 3.4183, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.919576142765515e-05, + "loss": 3.4204, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918737548014463e-05, + "loss": 3.4228, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917898953263411e-05, + "loss": 3.4321, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170619963927324e-05, + "loss": 3.4227, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9162234016416804e-05, + "loss": 3.4335, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153848068906284e-05, + "loss": 3.4235, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145462121395763e-05, + "loss": 3.4186, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9137092552688973e-05, + "loss": 3.4245, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128706605178453e-05, + "loss": 3.4161, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9120320657667932e-05, + "loss": 3.4159, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111934710157416e-05, + "loss": 3.4251, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103565141450625e-05, + "loss": 3.4243, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9095179193940105e-05, + "loss": 3.4179, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086793246429585e-05, + "loss": 3.4152, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078407298919065e-05, + "loss": 3.4162, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9070037730212277e-05, + "loss": 3.4257, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061651782701757e-05, + "loss": 3.4173, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9053265835191237e-05, + "loss": 3.4379, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044896266484446e-05, + "loss": 3.4355, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036510318973926e-05, + "loss": 3.4311, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9028124371463406e-05, + "loss": 3.4203, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019738423952886e-05, + "loss": 3.4171, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901135247644237e-05, + "loss": 3.4283, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.900298290773558e-05, + "loss": 3.4194, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.899459696022506e-05, + "loss": 3.4186, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898621101271454e-05, + "loss": 3.416, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977841444007748e-05, + "loss": 3.4274, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896945549649723e-05, + "loss": 3.4176, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896106954898671e-05, + "loss": 3.4174, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895268360147619e-05, + "loss": 3.4139, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.89443140327694e-05, + "loss": 3.4291, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893592808525888e-05, + "loss": 3.4128, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892754213774836e-05, + "loss": 3.4293, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891915619023784e-05, + "loss": 3.4275, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910786621531052e-05, + "loss": 3.4376, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902400674020532e-05, + "loss": 3.4141, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8894014726510012e-05, + "loss": 3.4334, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8885628778999492e-05, + "loss": 3.4214, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.88772592102927e-05, + "loss": 3.4281, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868873262782185e-05, + "loss": 3.426, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860487315271665e-05, + "loss": 3.4204, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8852101367761145e-05, + "loss": 3.4248, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843731799054354e-05, + "loss": 3.437, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8835345851543834e-05, + "loss": 3.4151, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826959904033314e-05, + "loss": 3.4239, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818573956522793e-05, + "loss": 3.4269, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8810204387816006e-05, + "loss": 3.4248, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801818440305486e-05, + "loss": 3.4156, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793432492794966e-05, + "loss": 3.4223, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8785046545284446e-05, + "loss": 3.431, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776676976577655e-05, + "loss": 3.4085, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768291029067135e-05, + "loss": 3.426, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.8561275005340576, + "eval_runtime": 304.1549, + "eval_samples_per_second": 1254.594, + "eval_steps_per_second": 39.207, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759905081556618e-05, + "loss": 3.418, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751519134046098e-05, + "loss": 3.4177, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743133186535575e-05, + "loss": 3.4171, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734747239025055e-05, + "loss": 3.4285, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726377670318267e-05, + "loss": 3.4374, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717991722807747e-05, + "loss": 3.417, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709605775297227e-05, + "loss": 3.4165, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701219827786707e-05, + "loss": 3.4186, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869285025907992e-05, + "loss": 3.4117, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.86844643115694e-05, + "loss": 3.4328, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8676078364058876e-05, + "loss": 3.4153, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667692416548356e-05, + "loss": 3.4215, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8659322847841572e-05, + "loss": 3.4261, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865093690033105e-05, + "loss": 3.4106, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864255095282053e-05, + "loss": 3.4115, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863416500531001e-05, + "loss": 3.4134, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862579543660322e-05, + "loss": 3.4133, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.86174094890927e-05, + "loss": 3.4203, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860902354158218e-05, + "loss": 3.4141, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860063759407166e-05, + "loss": 3.4214, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8592268025364873e-05, + "loss": 3.4297, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858388207785435e-05, + "loss": 3.4315, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857549613034383e-05, + "loss": 3.4175, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856711018283331e-05, + "loss": 3.4164, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558740614126522e-05, + "loss": 3.4173, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550354666616002e-05, + "loss": 3.4321, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541968719105482e-05, + "loss": 3.417, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533582771594962e-05, + "loss": 3.4146, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852521320288817e-05, + "loss": 3.4117, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516827255377654e-05, + "loss": 3.4113, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508441307867134e-05, + "loss": 3.4106, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8500055360356614e-05, + "loss": 3.4275, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491685791649823e-05, + "loss": 3.4263, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483299844139303e-05, + "loss": 3.4254, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474913896628783e-05, + "loss": 3.4144, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466527949118263e-05, + "loss": 3.4182, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458158380411476e-05, + "loss": 3.424, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449772432900956e-05, + "loss": 3.4089, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441386485390436e-05, + "loss": 3.4131, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8433000537879916e-05, + "loss": 3.406, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424630969173125e-05, + "loss": 3.4135, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416245021662605e-05, + "loss": 3.4226, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407859074152088e-05, + "loss": 3.4154, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399473126641568e-05, + "loss": 3.4131, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8391103557934777e-05, + "loss": 3.4216, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382717610424257e-05, + "loss": 3.4166, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374331662913737e-05, + "loss": 3.4153, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365945715403217e-05, + "loss": 3.409, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835757614669643e-05, + "loss": 3.3904, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834919019918591e-05, + "loss": 3.4285, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.834080425167539e-05, + "loss": 3.414, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.833241830416487e-05, + "loss": 3.4205, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832404873545808e-05, + "loss": 3.4096, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831566278794756e-05, + "loss": 3.4076, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8307276840437042e-05, + "loss": 3.4053, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298890892926522e-05, + "loss": 3.4118, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829052132421973e-05, + "loss": 3.4115, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.828213537670921e-05, + "loss": 3.4111, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827374942919869e-05, + "loss": 3.4247, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826536348168817e-05, + "loss": 3.4053, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256993912981383e-05, + "loss": 3.4071, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248607965470863e-05, + "loss": 3.4233, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8240222017960343e-05, + "loss": 3.4079, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231836070449823e-05, + "loss": 3.4052, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223466501743032e-05, + "loss": 3.4203, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8215080554232512e-05, + "loss": 3.414, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206694606721995e-05, + "loss": 3.405, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198308659211472e-05, + "loss": 3.4153, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189939090504684e-05, + "loss": 3.4069, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181553142994164e-05, + "loss": 3.4084, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173167195483644e-05, + "loss": 3.4185, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164797626776857e-05, + "loss": 3.4158, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156411679266337e-05, + "loss": 3.4206, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8148025731755817e-05, + "loss": 3.4156, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139639784245297e-05, + "loss": 3.4305, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131270215538506e-05, + "loss": 3.4065, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122884268027986e-05, + "loss": 3.4253, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114498320517466e-05, + "loss": 3.4116, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8106112373006946e-05, + "loss": 3.4093, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097742804300158e-05, + "loss": 3.412, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089356856789638e-05, + "loss": 3.4259, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080970909279118e-05, + "loss": 3.419, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072584961768595e-05, + "loss": 3.422, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.806421539306181e-05, + "loss": 3.4028, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805582944555129e-05, + "loss": 3.4003, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.804744349804077e-05, + "loss": 3.4123, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8039057550530247e-05, + "loss": 3.4189, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.803068798182346e-05, + "loss": 3.4141, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802230203431294e-05, + "loss": 3.4189, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801391608680242e-05, + "loss": 3.4056, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.80055301392919e-05, + "loss": 3.4122, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7997160570585112e-05, + "loss": 3.4092, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988774623074592e-05, + "loss": 3.4062, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.798038867556407e-05, + "loss": 3.4214, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.797200272805355e-05, + "loss": 3.4301, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963633159346764e-05, + "loss": 3.4252, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7955247211836244e-05, + "loss": 3.4065, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794686126432572e-05, + "loss": 3.4122, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.79384753168152e-05, + "loss": 3.4148, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7930105748108413e-05, + "loss": 3.4194, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921719800597893e-05, + "loss": 3.4146, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913333853087373e-05, + "loss": 3.4199, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904947905576853e-05, + "loss": 3.4137, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896578336870066e-05, + "loss": 3.4112, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7888192389359542e-05, + "loss": 3.4136, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879806441849022e-05, + "loss": 3.4043, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7871420494338502e-05, + "loss": 3.4093, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7863050925631715e-05, + "loss": 3.4133, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854664978121194e-05, + "loss": 3.415, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846279030610674e-05, + "loss": 3.4055, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837893083100154e-05, + "loss": 3.4076, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829523514393363e-05, + "loss": 3.4006, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7821137566882843e-05, + "loss": 3.4196, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812751619372327e-05, + "loss": 3.4081, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804365671861807e-05, + "loss": 3.4254, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795996103155016e-05, + "loss": 3.4196, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787610155644496e-05, + "loss": 3.4259, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779224208133976e-05, + "loss": 3.4089, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770838260623456e-05, + "loss": 3.4064, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762468691916668e-05, + "loss": 3.4176, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7754082744406148e-05, + "loss": 3.4141, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745696796895628e-05, + "loss": 3.4079, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737310849385108e-05, + "loss": 3.4049, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728941280678317e-05, + "loss": 3.4167, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720555333167797e-05, + "loss": 3.4082, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771216938565728e-05, + "loss": 3.4073, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770378343814676e-05, + "loss": 3.4081, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769541386943997e-05, + "loss": 3.4141, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768702792192945e-05, + "loss": 3.405, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767864197441893e-05, + "loss": 3.4177, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.767025602690841e-05, + "loss": 3.4139, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661886458201622e-05, + "loss": 3.4321, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653500510691102e-05, + "loss": 3.4025, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7645114563180582e-05, + "loss": 3.4212, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636728615670062e-05, + "loss": 3.41, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762835904696327e-05, + "loss": 3.4191, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761997309945275e-05, + "loss": 3.4108, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611587151942234e-05, + "loss": 3.4108, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7603201204431714e-05, + "loss": 3.4136, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7594831635724923e-05, + "loss": 3.4309, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7586445688214403e-05, + "loss": 3.4026, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7578059740703883e-05, + "loss": 3.4173, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569690171997096e-05, + "loss": 3.4134, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7561304224486576e-05, + "loss": 3.4126, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552918276976055e-05, + "loss": 3.4037, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544532329465535e-05, + "loss": 3.4117, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536162760758745e-05, + "loss": 3.4152, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527776813248224e-05, + "loss": 3.4096, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519390865737704e-05, + "loss": 3.4132, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.856904983520508, + "eval_runtime": 319.4105, + "eval_samples_per_second": 1194.673, + "eval_steps_per_second": 37.334, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7511004918227188e-05, + "loss": 3.4083, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502635349520397e-05, + "loss": 3.4059, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494249402009877e-05, + "loss": 3.4072, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485863454499357e-05, + "loss": 3.4213, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477477506988837e-05, + "loss": 3.4267, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746910793828205e-05, + "loss": 3.4092, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.746072199077153e-05, + "loss": 3.4069, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745233604326101e-05, + "loss": 3.4056, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.744395009575049e-05, + "loss": 3.4056, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435580527043698e-05, + "loss": 3.4211, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7427194579533178e-05, + "loss": 3.4041, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418808632022658e-05, + "loss": 3.4117, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.741042268451214e-05, + "loss": 3.4157, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740205311580535e-05, + "loss": 3.4011, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739366716829483e-05, + "loss": 3.4031, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.738528122078431e-05, + "loss": 3.3994, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376895273273787e-05, + "loss": 3.4041, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368525704567003e-05, + "loss": 3.4073, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7360139757056483e-05, + "loss": 3.4066, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351753809545963e-05, + "loss": 3.4128, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734336786203544e-05, + "loss": 3.4158, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334998293328652e-05, + "loss": 3.4211, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326612345818132e-05, + "loss": 3.4087, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7318226398307612e-05, + "loss": 3.404, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309840450797092e-05, + "loss": 3.4103, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301470882090304e-05, + "loss": 3.4163, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7293084934579784e-05, + "loss": 3.4053, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728469898706926e-05, + "loss": 3.4096, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727631303955874e-05, + "loss": 3.4044, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267943470851957e-05, + "loss": 3.3989, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259557523341437e-05, + "loss": 3.402, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7251171575830913e-05, + "loss": 3.4126, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242785628320393e-05, + "loss": 3.4196, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7234416059613606e-05, + "loss": 3.412, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7226030112103082e-05, + "loss": 3.4084, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217644164592565e-05, + "loss": 3.4037, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7209258217082045e-05, + "loss": 3.4145, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200888648375258e-05, + "loss": 3.4034, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192502700864734e-05, + "loss": 3.4023, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184116753354214e-05, + "loss": 3.3965, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175730805843694e-05, + "loss": 3.4058, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716736123713691e-05, + "loss": 3.4065, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158975289626387e-05, + "loss": 3.4088, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150589342115867e-05, + "loss": 3.4034, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142203394605347e-05, + "loss": 3.4102, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133833825898556e-05, + "loss": 3.405, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125447878388036e-05, + "loss": 3.4029, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711706193087752e-05, + "loss": 3.4009, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108675983367e-05, + "loss": 3.3819, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7100306414660208e-05, + "loss": 3.4177, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091920467149688e-05, + "loss": 3.4019, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083534519639168e-05, + "loss": 3.4104, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7075148572128648e-05, + "loss": 3.4023, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706677900342186e-05, + "loss": 3.3969, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705839305591134e-05, + "loss": 3.3932, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.705000710840082e-05, + "loss": 3.405, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.704163753969403e-05, + "loss": 3.4031, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703325159218351e-05, + "loss": 3.3973, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702486564467299e-05, + "loss": 3.4165, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016479697162473e-05, + "loss": 3.4011, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7008110128455682e-05, + "loss": 3.3908, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999724180945162e-05, + "loss": 3.4126, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991338233434642e-05, + "loss": 3.4, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982952285924122e-05, + "loss": 3.3969, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974582717217334e-05, + "loss": 3.4104, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6966196769706814e-05, + "loss": 3.4029, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957810822196294e-05, + "loss": 3.3948, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6949424874685774e-05, + "loss": 3.4059, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6941055305978983e-05, + "loss": 3.3943, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932669358468463e-05, + "loss": 3.3952, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6924283410957943e-05, + "loss": 3.4089, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915897463447426e-05, + "loss": 3.4069, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907527894740636e-05, + "loss": 3.4102, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6899141947230115e-05, + "loss": 3.4019, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890755999719595e-05, + "loss": 3.425, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6882370052209075e-05, + "loss": 3.4003, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6874000483502288e-05, + "loss": 3.4123, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865614535991768e-05, + "loss": 3.4021, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6857228588481248e-05, + "loss": 3.3994, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848842640970728e-05, + "loss": 3.3995, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840473072263937e-05, + "loss": 3.419, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832087124753417e-05, + "loss": 3.4064, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823701177242897e-05, + "loss": 3.4146, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681531522973238e-05, + "loss": 3.3885, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.680694566102559e-05, + "loss": 3.3895, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.679855971351507e-05, + "loss": 3.4053, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.679017376600455e-05, + "loss": 3.4108, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.678178781849403e-05, + "loss": 3.4031, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677341824978724e-05, + "loss": 3.4071, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676503230227672e-05, + "loss": 3.4017, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.67566463547662e-05, + "loss": 3.3959, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674826040725568e-05, + "loss": 3.4007, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673989083854889e-05, + "loss": 3.397, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.673150489103837e-05, + "loss": 3.4116, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.672311894352785e-05, + "loss": 3.4213, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714732996017334e-05, + "loss": 3.4182, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6706363427310543e-05, + "loss": 3.3957, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697977479800023e-05, + "loss": 3.3999, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689591532289503e-05, + "loss": 3.4052, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6681205584778983e-05, + "loss": 3.406, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672836016072195e-05, + "loss": 3.4071, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664450068561675e-05, + "loss": 3.4079, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6656064121051155e-05, + "loss": 3.4069, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664767817354063e-05, + "loss": 3.4, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6639308604833844e-05, + "loss": 3.4037, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630922657323324e-05, + "loss": 3.3959, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622536709812804e-05, + "loss": 3.397, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6614150762302284e-05, + "loss": 3.4072, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605781193595497e-05, + "loss": 3.403, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6597395246084976e-05, + "loss": 3.3932, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6589009298574453e-05, + "loss": 3.3987, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580623351063933e-05, + "loss": 3.3887, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657225378235715e-05, + "loss": 3.4096, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656386783484663e-05, + "loss": 3.4013, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6555481887336105e-05, + "loss": 3.411, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6547095939825585e-05, + "loss": 3.4128, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538726371118798e-05, + "loss": 3.4155, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530340423608278e-05, + "loss": 3.3987, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521954476097758e-05, + "loss": 3.4007, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513568528587238e-05, + "loss": 3.4041, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650519895988045e-05, + "loss": 3.4057, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496813012369927e-05, + "loss": 3.3971, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488427064859407e-05, + "loss": 3.3934, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6480041117348887e-05, + "loss": 3.4047, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.64716715486421e-05, + "loss": 3.3996, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646328560113158e-05, + "loss": 3.3963, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.645489965362106e-05, + "loss": 3.3974, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.644653008491427e-05, + "loss": 3.4074, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643814413740375e-05, + "loss": 3.3904, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429758189893228e-05, + "loss": 3.4099, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642137224238271e-05, + "loss": 3.406, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6413002673675924e-05, + "loss": 3.4194, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.64046167261654e-05, + "loss": 3.3911, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639623077865488e-05, + "loss": 3.4099, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638784483114436e-05, + "loss": 3.4084, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379475262437573e-05, + "loss": 3.4042, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6371089314927053e-05, + "loss": 3.4027, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362703367416533e-05, + "loss": 3.4016, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6354317419906013e-05, + "loss": 3.4019, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345947851199225e-05, + "loss": 3.4198, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6337561903688702e-05, + "loss": 3.3972, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6329175956178182e-05, + "loss": 3.4061, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320790008667665e-05, + "loss": 3.4046, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312420439960874e-05, + "loss": 3.3994, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6304034492450354e-05, + "loss": 3.3984, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295648544939834e-05, + "loss": 3.4028, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6287262597429314e-05, + "loss": 3.4039, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278893028722527e-05, + "loss": 3.4042, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6270507081212006e-05, + "loss": 3.399, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.857703924179077, + "eval_runtime": 310.0886, + "eval_samples_per_second": 1230.587, + "eval_steps_per_second": 38.457, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6262121133701486e-05, + "loss": 3.3998, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253735186190966e-05, + "loss": 3.3973, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245349238680446e-05, + "loss": 3.398, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236963291169926e-05, + "loss": 3.4091, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228593722463135e-05, + "loss": 3.4148, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.622020777495262e-05, + "loss": 3.4014, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.62118218274421e-05, + "loss": 3.3986, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620343587993158e-05, + "loss": 3.3967, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6195066311224788e-05, + "loss": 3.3912, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186680363714268e-05, + "loss": 3.4101, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178294416203748e-05, + "loss": 3.3981, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169908468693228e-05, + "loss": 3.4037, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616153889998644e-05, + "loss": 3.4032, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.615315295247592e-05, + "loss": 3.3894, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.61447670049654e-05, + "loss": 3.3926, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613638105745488e-05, + "loss": 3.3867, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612801148874809e-05, + "loss": 3.399, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119625541237572e-05, + "loss": 3.3972, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6111239593727052e-05, + "loss": 3.3944, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.610285364621653e-05, + "loss": 3.4006, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609448407750974e-05, + "loss": 3.4074, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608609812999922e-05, + "loss": 3.4097, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.60777121824887e-05, + "loss": 3.4016, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.606932623497818e-05, + "loss": 3.3985, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060956666271394e-05, + "loss": 3.4004, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052570718760874e-05, + "loss": 3.4066, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6044184771250354e-05, + "loss": 3.3942, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603579882373983e-05, + "loss": 3.3988, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6027429255033043e-05, + "loss": 3.3947, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6019043307522523e-05, + "loss": 3.3874, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010657360012003e-05, + "loss": 3.3961, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6002271412501483e-05, + "loss": 3.403, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993901843794695e-05, + "loss": 3.4019, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5985515896284175e-05, + "loss": 3.4103, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597712994877365e-05, + "loss": 3.3923, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968744001263135e-05, + "loss": 3.3961, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5960374432556347e-05, + "loss": 3.4041, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951988485045824e-05, + "loss": 3.3908, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943602537535304e-05, + "loss": 3.3945, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5935216590024784e-05, + "loss": 3.3893, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926847021317996e-05, + "loss": 3.3959, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5918461073807476e-05, + "loss": 3.3955, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5910075126296956e-05, + "loss": 3.3985, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590170555759017e-05, + "loss": 3.3958, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.589331961007965e-05, + "loss": 3.3961, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884933662569125e-05, + "loss": 3.4032, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876547715058605e-05, + "loss": 3.3896, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586817814635182e-05, + "loss": 3.3918, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859792198841298e-05, + "loss": 3.3701, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851406251330778e-05, + "loss": 3.4044, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5843020303820258e-05, + "loss": 3.3925, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.583465073511347e-05, + "loss": 3.3966, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582626478760295e-05, + "loss": 3.3929, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581787884009243e-05, + "loss": 3.3854, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580949289258191e-05, + "loss": 3.3822, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5801123323875122e-05, + "loss": 3.3908, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.57927373763646e-05, + "loss": 3.3967, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.578435142885408e-05, + "loss": 3.3836, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.577596548134356e-05, + "loss": 3.4062, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576759591263677e-05, + "loss": 3.3959, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575920996512625e-05, + "loss": 3.3766, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575082401761573e-05, + "loss": 3.4015, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574243807010521e-05, + "loss": 3.3936, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.573406850139842e-05, + "loss": 3.387, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725682553887904e-05, + "loss": 3.3968, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5717296606377384e-05, + "loss": 3.3967, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708910658866864e-05, + "loss": 3.3842, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700541090160073e-05, + "loss": 3.3984, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5692155142649553e-05, + "loss": 3.3848, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683769195139033e-05, + "loss": 3.3826, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5675383247628513e-05, + "loss": 3.4026, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5667013678921725e-05, + "loss": 3.3936, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658627731411205e-05, + "loss": 3.4003, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650241783900685e-05, + "loss": 3.3957, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641855836390165e-05, + "loss": 3.4078, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633486267683374e-05, + "loss": 3.3929, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5625100320172857e-05, + "loss": 3.4045, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616714372662337e-05, + "loss": 3.3894, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5608328425151817e-05, + "loss": 3.3917, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599958856445026e-05, + "loss": 3.3911, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591572908934506e-05, + "loss": 3.4052, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583186961423986e-05, + "loss": 3.3975, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574801013913466e-05, + "loss": 3.4063, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556643144520668e-05, + "loss": 3.3793, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555804549769616e-05, + "loss": 3.378, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554965955018564e-05, + "loss": 3.3929, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.554127360267512e-05, + "loss": 3.3991, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532904033968328e-05, + "loss": 3.3915, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524518086457808e-05, + "loss": 3.399, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551613213894729e-05, + "loss": 3.3917, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550774619143677e-05, + "loss": 3.385, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549937662272998e-05, + "loss": 3.3918, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.549099067521946e-05, + "loss": 3.3892, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548260472770894e-05, + "loss": 3.403, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547421878019842e-05, + "loss": 3.4048, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465849211491632e-05, + "loss": 3.4093, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457463263981112e-05, + "loss": 3.3813, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5449077316470592e-05, + "loss": 3.3948, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440691368960072e-05, + "loss": 3.3938, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.543232180025328e-05, + "loss": 3.399, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542393585274276e-05, + "loss": 3.3963, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415549905232245e-05, + "loss": 3.4003, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5407163957721725e-05, + "loss": 3.3943, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398794389014934e-05, + "loss": 3.3911, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5390408441504414e-05, + "loss": 3.3948, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5382022493993894e-05, + "loss": 3.3837, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373636546483374e-05, + "loss": 3.3894, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5365266977776586e-05, + "loss": 3.3922, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356881030266066e-05, + "loss": 3.3956, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348495082755546e-05, + "loss": 3.3828, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5340109135245023e-05, + "loss": 3.3913, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331739566538235e-05, + "loss": 3.3775, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5323353619027715e-05, + "loss": 3.4031, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.53149676715172e-05, + "loss": 3.3887, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306581724006675e-05, + "loss": 3.4001, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298212155299887e-05, + "loss": 3.3981, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289826207789367e-05, + "loss": 3.4053, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5281440260278844e-05, + "loss": 3.3909, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527307069157206e-05, + "loss": 3.3875, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526468474406154e-05, + "loss": 3.3983, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.525629879655102e-05, + "loss": 3.394, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247912849040496e-05, + "loss": 3.3897, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239543280333709e-05, + "loss": 3.385, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523115733282319e-05, + "loss": 3.3914, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222771385312667e-05, + "loss": 3.3884, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214385437802147e-05, + "loss": 3.3887, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5206015869095361e-05, + "loss": 3.3858, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197629921584841e-05, + "loss": 3.3953, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.518924397407432e-05, + "loss": 3.3837, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.51808580265638e-05, + "loss": 3.4016, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172488457857012e-05, + "loss": 3.3909, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164102510346492e-05, + "loss": 3.409, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.515571656283597e-05, + "loss": 3.3828, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.514733061532545e-05, + "loss": 3.4001, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138961046618662e-05, + "loss": 3.3953, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.513057509910814e-05, + "loss": 3.3935, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.512218915159762e-05, + "loss": 3.3955, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.51138032040871e-05, + "loss": 3.3873, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105433635380315e-05, + "loss": 3.3968, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5097047687869791e-05, + "loss": 3.4069, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088661740359273e-05, + "loss": 3.3868, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5080275792848753e-05, + "loss": 3.3948, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071906224141965e-05, + "loss": 3.3933, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063520276631444e-05, + "loss": 3.3905, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5055134329120924e-05, + "loss": 3.3907, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046748381610404e-05, + "loss": 3.3917, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5038378812903614e-05, + "loss": 3.3934, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029992865393094e-05, + "loss": 3.3944, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021606917882574e-05, + "loss": 3.3863, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8583037853240967, + "eval_runtime": 304.8214, + "eval_samples_per_second": 1251.851, + "eval_steps_per_second": 39.121, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5013220970372054e-05, + "loss": 3.3939, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004851401665265e-05, + "loss": 3.3814, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996465454154745e-05, + "loss": 3.3893, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4988079506644227e-05, + "loss": 3.4031, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979693559133707e-05, + "loss": 3.3984, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4971323990426916e-05, + "loss": 3.3925, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962938042916397e-05, + "loss": 3.3935, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954552095405877e-05, + "loss": 3.3864, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4946166147895357e-05, + "loss": 3.3823, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937796579188568e-05, + "loss": 3.3955, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4929410631678048e-05, + "loss": 3.3929, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4921024684167528e-05, + "loss": 3.3934, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912638736657008e-05, + "loss": 3.3928, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4904269167950219e-05, + "loss": 3.3789, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895883220439699e-05, + "loss": 3.385, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.488749727292918e-05, + "loss": 3.379, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.487911132541866e-05, + "loss": 3.3897, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.487074175671187e-05, + "loss": 3.3869, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862355809201351e-05, + "loss": 3.3863, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853969861690831e-05, + "loss": 3.3907, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845583914180311e-05, + "loss": 3.3978, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4837214345473522e-05, + "loss": 3.3991, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828828397963002e-05, + "loss": 3.3925, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820442450452482e-05, + "loss": 3.3832, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4812056502941962e-05, + "loss": 3.3933, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803686934235172e-05, + "loss": 3.3952, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795300986724652e-05, + "loss": 3.3866, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786915039214132e-05, + "loss": 3.3869, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778529091703614e-05, + "loss": 3.3842, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4770159522996823e-05, + "loss": 3.3801, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761773575486305e-05, + "loss": 3.3876, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4753387627975785e-05, + "loss": 3.39, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4745001680465265e-05, + "loss": 3.3918, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736632111758475e-05, + "loss": 3.3992, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4728246164247955e-05, + "loss": 3.3874, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719860216737435e-05, + "loss": 3.387, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711490648030646e-05, + "loss": 3.3933, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4703104700520126e-05, + "loss": 3.3797, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694718753009606e-05, + "loss": 3.383, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4686332805499086e-05, + "loss": 3.3837, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677963236792297e-05, + "loss": 3.3837, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669577289281777e-05, + "loss": 3.384, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661191341771258e-05, + "loss": 3.3902, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652805394260738e-05, + "loss": 3.3874, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644435825553947e-05, + "loss": 3.3828, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4636049878043429e-05, + "loss": 3.3917, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627663930532909e-05, + "loss": 3.3825, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4619277983022389e-05, + "loss": 3.3822, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.46109084143156e-05, + "loss": 3.3631, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.460252246680508e-05, + "loss": 3.3956, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.459413651929456e-05, + "loss": 3.3794, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585750571784038e-05, + "loss": 3.3877, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457738100307725e-05, + "loss": 3.3808, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.456899505556673e-05, + "loss": 3.3762, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560609108056212e-05, + "loss": 3.3737, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4552223160545689e-05, + "loss": 3.382, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543853591838901e-05, + "loss": 3.3898, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535467644328383e-05, + "loss": 3.3728, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4527081696817863e-05, + "loss": 3.3967, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.451869574930734e-05, + "loss": 3.3837, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510326180600553e-05, + "loss": 3.369, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501940233090033e-05, + "loss": 3.393, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493554285579512e-05, + "loss": 3.3794, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4485168338068992e-05, + "loss": 3.3794, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476798769362204e-05, + "loss": 3.3812, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468412821851684e-05, + "loss": 3.3872, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4460026874341162e-05, + "loss": 3.3763, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451640926830642e-05, + "loss": 3.3894, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443271358123855e-05, + "loss": 3.3743, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434885410613336e-05, + "loss": 3.3764, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426499463102813e-05, + "loss": 3.3884, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4418113515592293e-05, + "loss": 3.3848, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409743946885507e-05, + "loss": 3.3911, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4401357999374984e-05, + "loss": 3.383, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392972051864465e-05, + "loss": 3.4027, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384586104353945e-05, + "loss": 3.3833, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4376216535647158e-05, + "loss": 3.3948, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367830588136636e-05, + "loss": 3.3773, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359444640626116e-05, + "loss": 3.3829, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4351058693115596e-05, + "loss": 3.3768, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342689124408808e-05, + "loss": 3.3944, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4334303176898287e-05, + "loss": 3.3898, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325917229387767e-05, + "loss": 3.3963, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317531281877247e-05, + "loss": 3.3741, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4309161713170457e-05, + "loss": 3.3698, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300775765659937e-05, + "loss": 3.3787, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4292389818149417e-05, + "loss": 3.3897, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4284003870638899e-05, + "loss": 3.3825, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275634301932108e-05, + "loss": 3.3891, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.426724835442159e-05, + "loss": 3.3823, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425886240691107e-05, + "loss": 3.3737, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.425047645940055e-05, + "loss": 3.3809, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.424210689069376e-05, + "loss": 3.3751, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.423372094318324e-05, + "loss": 3.3914, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.422533499567272e-05, + "loss": 3.3999, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.42169490481622e-05, + "loss": 3.3997, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208579479455411e-05, + "loss": 3.3743, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200193531944891e-05, + "loss": 3.3827, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191807584434371e-05, + "loss": 3.3837, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183421636923853e-05, + "loss": 3.3848, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4175052068217062e-05, + "loss": 3.3876, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166666120706543e-05, + "loss": 3.3899, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158280173196023e-05, + "loss": 3.3814, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149910604489232e-05, + "loss": 3.3781, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141524656978714e-05, + "loss": 3.3899, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133138709468194e-05, + "loss": 3.3711, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124752761957674e-05, + "loss": 3.3801, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4116383193250885e-05, + "loss": 3.3818, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107997245740365e-05, + "loss": 3.3848, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099611298229845e-05, + "loss": 3.3747, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4091225350719325e-05, + "loss": 3.384, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082855782012535e-05, + "loss": 3.364, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074469834502015e-05, + "loss": 3.3882, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4066083886991497e-05, + "loss": 3.3854, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057697939480977e-05, + "loss": 3.3852, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4049328370774186e-05, + "loss": 3.3918, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040942423263668e-05, + "loss": 3.3961, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032556475753148e-05, + "loss": 3.3809, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4024170528242628e-05, + "loss": 3.38, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015800959535838e-05, + "loss": 3.3873, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4007415012025318e-05, + "loss": 3.3825, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3999029064514798e-05, + "loss": 3.379, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990643117004278e-05, + "loss": 3.3794, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982273548297489e-05, + "loss": 3.3818, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973887600786969e-05, + "loss": 3.3816, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.396550165327645e-05, + "loss": 3.3766, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.395711570576593e-05, + "loss": 3.3802, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.394874613705914e-05, + "loss": 3.3824, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940360189548621e-05, + "loss": 3.3727, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931974242038101e-05, + "loss": 3.3903, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923588294527581e-05, + "loss": 3.3824, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3915218725820792e-05, + "loss": 3.4018, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906832778310272e-05, + "loss": 3.3707, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898446830799752e-05, + "loss": 3.3916, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3890060883289232e-05, + "loss": 3.387, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881691314582443e-05, + "loss": 3.3817, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873305367071923e-05, + "loss": 3.3831, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864919419561403e-05, + "loss": 3.3795, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856533472050881e-05, + "loss": 3.3909, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3848163903344093e-05, + "loss": 3.3957, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839777955833575e-05, + "loss": 3.3785, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831392008323055e-05, + "loss": 3.3837, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3823006060812532e-05, + "loss": 3.3845, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814636492105746e-05, + "loss": 3.379, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3806250544595226e-05, + "loss": 3.3793, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797864597084706e-05, + "loss": 3.3874, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789478649574184e-05, + "loss": 3.3782, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3781109080867396e-05, + "loss": 3.3836, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772723133356876e-05, + "loss": 3.376, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.859776496887207, + "eval_runtime": 304.7192, + "eval_samples_per_second": 1252.271, + "eval_steps_per_second": 39.134, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3764337185846355e-05, + "loss": 3.3981, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755951238335835e-05, + "loss": 3.3732, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747565290825315e-05, + "loss": 3.3753, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3739179343314795e-05, + "loss": 3.3953, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730809774608005e-05, + "loss": 3.3876, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722423827097485e-05, + "loss": 3.3864, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3714037879586967e-05, + "loss": 3.3802, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705651932076447e-05, + "loss": 3.3753, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3697282363369656e-05, + "loss": 3.3726, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688896415859138e-05, + "loss": 3.3899, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680510468348618e-05, + "loss": 3.3803, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3672124520838098e-05, + "loss": 3.3813, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663754952131308e-05, + "loss": 3.3866, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3655369004620788e-05, + "loss": 3.3689, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646983057110268e-05, + "loss": 3.3711, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638597109599748e-05, + "loss": 3.3703, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630227540892959e-05, + "loss": 3.3799, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621841593382439e-05, + "loss": 3.3768, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.361345564587192e-05, + "loss": 3.3776, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.36050696983614e-05, + "loss": 3.3751, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359670012965461e-05, + "loss": 3.3898, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3588314182144091e-05, + "loss": 3.3875, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579928234633571e-05, + "loss": 3.385, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571542287123051e-05, + "loss": 3.3765, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3563172718416262e-05, + "loss": 3.3837, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554786770905742e-05, + "loss": 3.3821, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546400823395222e-05, + "loss": 3.3794, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3538014875884702e-05, + "loss": 3.3799, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529645307177913e-05, + "loss": 3.3724, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521259359667393e-05, + "loss": 3.3673, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512873412156874e-05, + "loss": 3.3772, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504487464646354e-05, + "loss": 3.3776, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3496117895939563e-05, + "loss": 3.3847, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487731948429045e-05, + "loss": 3.3868, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3479346000918525e-05, + "loss": 3.3765, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470960053408005e-05, + "loss": 3.3804, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462590484701216e-05, + "loss": 3.3842, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3454204537190696e-05, + "loss": 3.3658, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445818589680176e-05, + "loss": 3.3753, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437432642169656e-05, + "loss": 3.3723, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3429063073462866e-05, + "loss": 3.3733, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420677125952346e-05, + "loss": 3.3729, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3412291178441826e-05, + "loss": 3.3819, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403905230931308e-05, + "loss": 3.3808, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395535662224517e-05, + "loss": 3.3719, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3387149714713999e-05, + "loss": 3.3804, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378763767203479e-05, + "loss": 3.3751, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3370377819692955e-05, + "loss": 3.3708, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.336200825098617e-05, + "loss": 3.3564, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.335362230347565e-05, + "loss": 3.3824, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.334523635596513e-05, + "loss": 3.3733, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.333686678725834e-05, + "loss": 3.3786, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.332848083974782e-05, + "loss": 3.372, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.33200948922373e-05, + "loss": 3.3643, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311708944726778e-05, + "loss": 3.3635, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330333937601999e-05, + "loss": 3.3732, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.329495342850947e-05, + "loss": 3.3822, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286567480998952e-05, + "loss": 3.3615, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3278181533488429e-05, + "loss": 3.3902, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269811964781641e-05, + "loss": 3.3735, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261426017271123e-05, + "loss": 3.3598, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3253040069760603e-05, + "loss": 3.38, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.324465412225008e-05, + "loss": 3.3687, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3236284553543294e-05, + "loss": 3.3754, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227898606032774e-05, + "loss": 3.3669, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219512658522252e-05, + "loss": 3.3815, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3211126711011732e-05, + "loss": 3.3643, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202757142304944e-05, + "loss": 3.3799, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194371194794424e-05, + "loss": 3.3589, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185985247283903e-05, + "loss": 3.3699, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177599299773383e-05, + "loss": 3.3743, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3169229731066595e-05, + "loss": 3.3815, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160843783556077e-05, + "loss": 3.3756, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152457836045553e-05, + "loss": 3.3763, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3144071888535033e-05, + "loss": 3.3913, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135702319828247e-05, + "loss": 3.3729, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3127316372317724e-05, + "loss": 3.3813, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118930424807206e-05, + "loss": 3.3735, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110544477296686e-05, + "loss": 3.3723, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3102174908589898e-05, + "loss": 3.373, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093788961079376e-05, + "loss": 3.3805, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085403013568856e-05, + "loss": 3.3791, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3077017066058336e-05, + "loss": 3.3831, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068647497351549e-05, + "loss": 3.3701, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3060261549841027e-05, + "loss": 3.3607, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051875602330507e-05, + "loss": 3.3688, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043489654819987e-05, + "loss": 3.3765, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3035120086113198e-05, + "loss": 3.374, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026734138602678e-05, + "loss": 3.3795, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.301834819109216e-05, + "loss": 3.3728, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.300996224358164e-05, + "loss": 3.3624, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001592674874848e-05, + "loss": 3.3724, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.299320672736433e-05, + "loss": 3.3669, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.298482077985381e-05, + "loss": 3.3844, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.297643483234329e-05, + "loss": 3.3823, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.29680652636365e-05, + "loss": 3.3882, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.295967931612598e-05, + "loss": 3.3656, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.295129336861546e-05, + "loss": 3.374, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.294290742110494e-05, + "loss": 3.3736, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934537852398151e-05, + "loss": 3.3742, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2926151904887631e-05, + "loss": 3.3832, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917765957377111e-05, + "loss": 3.3743, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909380009866593e-05, + "loss": 3.3747, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2901010441159802e-05, + "loss": 3.3696, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892624493649284e-05, + "loss": 3.3826, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2884238546138764e-05, + "loss": 3.3579, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875868977431973e-05, + "loss": 3.3684, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867483029921454e-05, + "loss": 3.3721, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2859097082410934e-05, + "loss": 3.377, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850711134900414e-05, + "loss": 3.3666, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842341566193625e-05, + "loss": 3.3748, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833955618683105e-05, + "loss": 3.3554, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825569671172585e-05, + "loss": 3.3797, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2817183723662065e-05, + "loss": 3.3713, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808814154955276e-05, + "loss": 3.3745, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800428207444756e-05, + "loss": 3.3853, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2792042259934237e-05, + "loss": 3.3858, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783656312423717e-05, + "loss": 3.3677, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2775286743716926e-05, + "loss": 3.3726, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766900796206408e-05, + "loss": 3.3789, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758514848695888e-05, + "loss": 3.3692, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2750128901185368e-05, + "loss": 3.3738, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741759332478579e-05, + "loss": 3.3664, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733373384968059e-05, + "loss": 3.3725, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724987437457539e-05, + "loss": 3.3689, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716601489947019e-05, + "loss": 3.3648, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.270823192124023e-05, + "loss": 3.3738, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.269984597372971e-05, + "loss": 3.3728, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691460026219191e-05, + "loss": 3.365, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2683074078708671e-05, + "loss": 3.3818, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.267470451000188e-05, + "loss": 3.3737, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2666318562491362e-05, + "loss": 3.39, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657932614980842e-05, + "loss": 3.367, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649546667470322e-05, + "loss": 3.3785, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2641177098763532e-05, + "loss": 3.3783, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632791151253012e-05, + "loss": 3.374, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624405203742492e-05, + "loss": 3.3708, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2616019256231972e-05, + "loss": 3.3694, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607649687525183e-05, + "loss": 3.3806, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599263740014663e-05, + "loss": 3.3853, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590877792504145e-05, + "loss": 3.3705, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582491844993621e-05, + "loss": 3.3712, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2574122276286834e-05, + "loss": 3.3769, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565736328776315e-05, + "loss": 3.3704, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2557350381265795e-05, + "loss": 3.3661, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548964433755272e-05, + "loss": 3.3794, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540594865048486e-05, + "loss": 3.3703, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532208917537966e-05, + "loss": 3.3762, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523822970027446e-05, + "loss": 3.3638, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8609323501586914, + "eval_runtime": 312.8501, + "eval_samples_per_second": 1219.725, + "eval_steps_per_second": 38.117, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515437022516924e-05, + "loss": 3.3729, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2507067453810137e-05, + "loss": 3.3657, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498681506299615e-05, + "loss": 3.3669, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2490295558789097e-05, + "loss": 3.3828, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481909611278577e-05, + "loss": 3.3818, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2473540042571787e-05, + "loss": 3.3748, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2465154095061267e-05, + "loss": 3.3675, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456768147550747e-05, + "loss": 3.368, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2448382200040227e-05, + "loss": 3.3608, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2440012631333438e-05, + "loss": 3.3831, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431626683822918e-05, + "loss": 3.371, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2423240736312398e-05, + "loss": 3.3762, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414854788801878e-05, + "loss": 3.3728, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406501598898821e-05, + "loss": 3.3594, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2398115651388301e-05, + "loss": 3.3636, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389729703877781e-05, + "loss": 3.3589, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.238134375636726e-05, + "loss": 3.3722, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372957808856741e-05, + "loss": 3.3631, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364571861346221e-05, + "loss": 3.3715, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2356185913835701e-05, + "loss": 3.3655, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.234779996632518e-05, + "loss": 3.3797, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2339430397618392e-05, + "loss": 3.3785, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2331044450107872e-05, + "loss": 3.3729, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.232265850259735e-05, + "loss": 3.3671, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2314272555086832e-05, + "loss": 3.3767, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305902986380042e-05, + "loss": 3.3697, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297517038869522e-05, + "loss": 3.3662, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2289131091359002e-05, + "loss": 3.3752, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280745143848482e-05, + "loss": 3.3598, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2272375575141695e-05, + "loss": 3.358, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263989627631175e-05, + "loss": 3.3665, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255603680120653e-05, + "loss": 3.3667, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2247217732610133e-05, + "loss": 3.3776, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238848163903345e-05, + "loss": 3.3783, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230462216392824e-05, + "loss": 3.3622, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2222076268882304e-05, + "loss": 3.3742, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213690321371785e-05, + "loss": 3.3724, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2205320752664996e-05, + "loss": 3.3575, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196934805154476e-05, + "loss": 3.366, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188548857643956e-05, + "loss": 3.3622, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2180162910133436e-05, + "loss": 3.3616, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171793341426647e-05, + "loss": 3.3676, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163407393916127e-05, + "loss": 3.3773, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2155021446405607e-05, + "loss": 3.3642, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146635498895087e-05, + "loss": 3.3615, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2138265930188297e-05, + "loss": 3.3723, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129879982677777e-05, + "loss": 3.365, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121494035167257e-05, + "loss": 3.3605, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2113108087656739e-05, + "loss": 3.345, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104738518949948e-05, + "loss": 3.3714, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209635257143943e-05, + "loss": 3.3656, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208796662392891e-05, + "loss": 3.3696, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079580676418388e-05, + "loss": 3.3621, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.20712111077116e-05, + "loss": 3.3534, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.206282516020108e-05, + "loss": 3.3573, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.205443921269056e-05, + "loss": 3.3639, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2046053265180038e-05, + "loss": 3.3713, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037683696473251e-05, + "loss": 3.351, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2029297748962731e-05, + "loss": 3.3783, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020911801452211e-05, + "loss": 3.3629, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.201252585394169e-05, + "loss": 3.3554, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2004156285234902e-05, + "loss": 3.3704, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995770337724382e-05, + "loss": 3.3589, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1987384390213862e-05, + "loss": 3.3642, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1979014821507072e-05, + "loss": 3.3546, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970628873996554e-05, + "loss": 3.372, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1962242926486034e-05, + "loss": 3.3618, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953856978975512e-05, + "loss": 3.3617, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1945487410268725e-05, + "loss": 3.3589, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1937101462758205e-05, + "loss": 3.3578, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928715515247683e-05, + "loss": 3.3631, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1920329567737165e-05, + "loss": 3.375, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911959999030375e-05, + "loss": 3.3642, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903574051519855e-05, + "loss": 3.3655, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1895188104009335e-05, + "loss": 3.3784, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886802156498815e-05, + "loss": 3.3642, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1878432587792026e-05, + "loss": 3.3697, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1870046640281508e-05, + "loss": 3.3676, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861660692770986e-05, + "loss": 3.3682, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1853274745260466e-05, + "loss": 3.3612, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844905176553678e-05, + "loss": 3.367, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836519229043157e-05, + "loss": 3.369, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1828133281532637e-05, + "loss": 3.3752, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819747334022118e-05, + "loss": 3.3619, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1811377765315329e-05, + "loss": 3.3485, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802991817804807e-05, + "loss": 3.3597, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794605870294289e-05, + "loss": 3.3671, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1786219922783769e-05, + "loss": 3.3665, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.177785035407698e-05, + "loss": 3.3671, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.176946440656646e-05, + "loss": 3.364, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.176107845905594e-05, + "loss": 3.3554, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.175269251154542e-05, + "loss": 3.3603, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.174432294283863e-05, + "loss": 3.3577, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.173593699532811e-05, + "loss": 3.3711, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.172755104781759e-05, + "loss": 3.3711, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.171916510030707e-05, + "loss": 3.3858, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710795531600281e-05, + "loss": 3.3544, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1702409584089761e-05, + "loss": 3.3656, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1694023636579243e-05, + "loss": 3.3672, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168563768906872e-05, + "loss": 3.3686, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1677268120361932e-05, + "loss": 3.3701, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668882172851413e-05, + "loss": 3.3675, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660496225340893e-05, + "loss": 3.3679, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1652110277830372e-05, + "loss": 3.3575, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643740709123584e-05, + "loss": 3.3745, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1635354761613064e-05, + "loss": 3.3487, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626968814102544e-05, + "loss": 3.3596, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618582866592024e-05, + "loss": 3.3623, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1610213297885235e-05, + "loss": 3.3675, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601827350374715e-05, + "loss": 3.3586, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593441402864195e-05, + "loss": 3.3584, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1585055455353675e-05, + "loss": 3.3547, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576685886646885e-05, + "loss": 3.3649, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1568299939136367e-05, + "loss": 3.3618, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559913991625845e-05, + "loss": 3.37, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551528044115325e-05, + "loss": 3.3729, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1543158475408538e-05, + "loss": 3.3734, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534772527898018e-05, + "loss": 3.356, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1526386580387496e-05, + "loss": 3.3635, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1518000632876978e-05, + "loss": 3.3712, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509631064170188e-05, + "loss": 3.3611, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1501245116659667e-05, + "loss": 3.3602, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492859169149148e-05, + "loss": 3.361, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1484473221638628e-05, + "loss": 3.3614, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1476103652931839e-05, + "loss": 3.3617, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467717705421319e-05, + "loss": 3.3544, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1459331757910799e-05, + "loss": 3.3648, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450945810400279e-05, + "loss": 3.3626, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442576241693491e-05, + "loss": 3.3559, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.143419029418297e-05, + "loss": 3.3674, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.142580434667245e-05, + "loss": 3.3668, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417434777965662e-05, + "loss": 3.3773, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.140904883045514e-05, + "loss": 3.3627, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.140066288294462e-05, + "loss": 3.3635, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1392276935434102e-05, + "loss": 3.3721, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383907366727313e-05, + "loss": 3.3602, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375521419216793e-05, + "loss": 3.3628, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1367135471706273e-05, + "loss": 3.3612, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358749524195753e-05, + "loss": 3.3723, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1350379955488965e-05, + "loss": 3.3704, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341994007978443e-05, + "loss": 3.3649, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333608060467923e-05, + "loss": 3.3643, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1325222112957403e-05, + "loss": 3.3661, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316852544250614e-05, + "loss": 3.3572, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308466596740094e-05, + "loss": 3.3568, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1300080649229574e-05, + "loss": 3.3703, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291694701719054e-05, + "loss": 3.3588, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1283325133012265e-05, + "loss": 3.371, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274939185501746e-05, + "loss": 3.3519, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.861021041870117, + "eval_runtime": 335.2729, + "eval_samples_per_second": 1138.15, + "eval_steps_per_second": 35.568, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266553237991226e-05, + "loss": 3.3416, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1258167290480705e-05, + "loss": 3.3615, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249781342970184e-05, + "loss": 3.3569, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1241395395459666e-05, + "loss": 3.3698, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1233025826752877e-05, + "loss": 3.3715, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224639879242355e-05, + "loss": 3.3668, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1216253931731837e-05, + "loss": 3.3564, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207867984221317e-05, + "loss": 3.3536, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1199498415514528e-05, + "loss": 3.3572, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1191112468004008e-05, + "loss": 3.3678, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182726520493487e-05, + "loss": 3.3621, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1174340572982967e-05, + "loss": 3.3659, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165971004276178e-05, + "loss": 3.3614, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157601435569389e-05, + "loss": 3.351, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.114921548805887e-05, + "loss": 3.3533, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.114082954054835e-05, + "loss": 3.3508, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1132443593037829e-05, + "loss": 3.3623, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1124057645527309e-05, + "loss": 3.355, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.111567169801679e-05, + "loss": 3.3604, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1107285750506269e-05, + "loss": 3.3578, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098899802995749e-05, + "loss": 3.3697, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090530234288961e-05, + "loss": 3.3686, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1082144286778441e-05, + "loss": 3.361, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.107375833926792e-05, + "loss": 3.3585, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1065372391757401e-05, + "loss": 3.3671, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1057002823050612e-05, + "loss": 3.3625, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.104861687554009e-05, + "loss": 3.3547, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1040230928029572e-05, + "loss": 3.3631, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031844980519052e-05, + "loss": 3.349, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1023475411812263e-05, + "loss": 3.3491, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1015089464301742e-05, + "loss": 3.3554, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006703516791222e-05, + "loss": 3.3596, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0998317569280702e-05, + "loss": 3.3655, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989948000573915e-05, + "loss": 3.3659, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981562053063393e-05, + "loss": 3.3579, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0973176105552873e-05, + "loss": 3.3628, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964790158042355e-05, + "loss": 3.3651, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0956420589335564e-05, + "loss": 3.348, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0948034641825044e-05, + "loss": 3.3596, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939648694314525e-05, + "loss": 3.3481, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0931262746804005e-05, + "loss": 3.3555, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922893178097216e-05, + "loss": 3.3578, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914507230586696e-05, + "loss": 3.367, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0906121283076176e-05, + "loss": 3.3556, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897735335565654e-05, + "loss": 3.3502, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0889365766858867e-05, + "loss": 3.3647, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880979819348347e-05, + "loss": 3.3567, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872593871837827e-05, + "loss": 3.3502, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0864207924327307e-05, + "loss": 3.336, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855838355620517e-05, + "loss": 3.3634, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847452408109997e-05, + "loss": 3.3552, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0839066460599479e-05, + "loss": 3.359, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830680513088957e-05, + "loss": 3.3515, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082231094438217e-05, + "loss": 3.3475, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.081392499687165e-05, + "loss": 3.347, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805539049361128e-05, + "loss": 3.3505, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0797153101850608e-05, + "loss": 3.3628, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.078878353314382e-05, + "loss": 3.3477, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.07803975856333e-05, + "loss": 3.3636, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0772011638122779e-05, + "loss": 3.3544, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.076362569061226e-05, + "loss": 3.3478, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0755256121905471e-05, + "loss": 3.3597, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746870174394951e-05, + "loss": 3.3517, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0738484226884431e-05, + "loss": 3.3514, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0730098279373911e-05, + "loss": 3.3469, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721728710667124e-05, + "loss": 3.3631, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0713342763156602e-05, + "loss": 3.3515, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704956815646082e-05, + "loss": 3.3532, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696570868135562e-05, + "loss": 3.3459, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0688201299428774e-05, + "loss": 3.3503, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679815351918252e-05, + "loss": 3.3515, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0671429404407732e-05, + "loss": 3.3645, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0663043456897214e-05, + "loss": 3.3533, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654673888190423e-05, + "loss": 3.3582, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0646287940679905e-05, + "loss": 3.3657, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637901993169385e-05, + "loss": 3.3589, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629516045658865e-05, + "loss": 3.3557, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0621146476952075e-05, + "loss": 3.3588, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612760529441555e-05, + "loss": 3.358, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0604374581931035e-05, + "loss": 3.3522, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595988634420514e-05, + "loss": 3.356, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587619065713726e-05, + "loss": 3.3651, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0579233118203206e-05, + "loss": 3.3645, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570847170692686e-05, + "loss": 3.3525, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0562477601985897e-05, + "loss": 3.3374, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0554091654475377e-05, + "loss": 3.3485, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545705706964858e-05, + "loss": 3.3602, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0537319759454338e-05, + "loss": 3.3565, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528950190747548e-05, + "loss": 3.3594, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.052056424323703e-05, + "loss": 3.358, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0512178295726509e-05, + "loss": 3.3475, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503792348215987e-05, + "loss": 3.3464, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.04954227795092e-05, + "loss": 3.3485, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.048703683199868e-05, + "loss": 3.3623, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.047865088448816e-05, + "loss": 3.3584, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.047026493697764e-05, + "loss": 3.374, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.046189536827085e-05, + "loss": 3.3508, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.045350942076033e-05, + "loss": 3.3543, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0445123473249812e-05, + "loss": 3.3587, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.043673752573929e-05, + "loss": 3.3603, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0428367957032501e-05, + "loss": 3.36, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419982009521983e-05, + "loss": 3.3572, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411596062011461e-05, + "loss": 3.3556, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0403210114500941e-05, + "loss": 3.3485, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394840545794154e-05, + "loss": 3.367, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0386454598283633e-05, + "loss": 3.3401, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0378068650773112e-05, + "loss": 3.3493, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369682703262593e-05, + "loss": 3.3561, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0361313134555804e-05, + "loss": 3.356, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352927187045284e-05, + "loss": 3.347, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344541239534764e-05, + "loss": 3.3553, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0336155292024244e-05, + "loss": 3.3385, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327785723317455e-05, + "loss": 3.3569, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0319399775806935e-05, + "loss": 3.3543, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0311013828296415e-05, + "loss": 3.3567, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302627880785895e-05, + "loss": 3.3644, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0294258312079107e-05, + "loss": 3.3663, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285872364568585e-05, + "loss": 3.3499, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277486417058065e-05, + "loss": 3.3552, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0269100469547547e-05, + "loss": 3.3579, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260730900840758e-05, + "loss": 3.3495, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0252344953330236e-05, + "loss": 3.3557, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243959005819718e-05, + "loss": 3.3499, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235573058309198e-05, + "loss": 3.3525, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0227203489602409e-05, + "loss": 3.3494, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218817542091888e-05, + "loss": 3.3506, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0210431594581368e-05, + "loss": 3.3546, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0202045647070848e-05, + "loss": 3.3519, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.019367607836406e-05, + "loss": 3.3492, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0185290130853539e-05, + "loss": 3.3543, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176904183343019e-05, + "loss": 3.357, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0168518235832499e-05, + "loss": 3.3687, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.016014866712571e-05, + "loss": 3.3489, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.015176271961519e-05, + "loss": 3.3543, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0143376772104671e-05, + "loss": 3.3623, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.013499082459415e-05, + "loss": 3.3569, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.012662125588736e-05, + "loss": 3.3547, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0118235308376842e-05, + "loss": 3.3525, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109849360866322e-05, + "loss": 3.3645, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.01014634133558e-05, + "loss": 3.3555, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0093093844649013e-05, + "loss": 3.3584, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084707897138493e-05, + "loss": 3.354, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0076321949627971e-05, + "loss": 3.3514, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067936002117453e-05, + "loss": 3.3506, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059566433410663e-05, + "loss": 3.3489, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0051180485900143e-05, + "loss": 3.3613, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042794538389623e-05, + "loss": 3.3486, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0034424969682834e-05, + "loss": 3.365, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0026039022172314e-05, + "loss": 3.3429, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017653074661794e-05, + "loss": 3.3527, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.861816644668579, + "eval_runtime": 315.3347, + "eval_samples_per_second": 1210.114, + "eval_steps_per_second": 37.817, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0009267127151274e-05, + "loss": 3.3487, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000897558444487e-05, + "loss": 3.348, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992511610933966e-06, + "loss": 3.359, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.984125663423445e-06, + "loss": 3.3614, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975739715912925e-06, + "loss": 3.3603, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.967370147206137e-06, + "loss": 3.3481, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958984199695617e-06, + "loss": 3.3474, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950598252185097e-06, + "loss": 3.3423, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.942212304674577e-06, + "loss": 3.3625, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933842735967788e-06, + "loss": 3.3488, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.925456788457268e-06, + "loss": 3.3605, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.917070840946748e-06, + "loss": 3.352, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908684893436228e-06, + "loss": 3.3459, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.90031532472944e-06, + "loss": 3.3424, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891929377218918e-06, + "loss": 3.3435, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.883543429708398e-06, + "loss": 3.35, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.875157482197878e-06, + "loss": 3.3479, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866787913491091e-06, + "loss": 3.3493, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.858401965980569e-06, + "loss": 3.3462, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.850016018470049e-06, + "loss": 3.3623, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.84163007095953e-06, + "loss": 3.3563, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.83326050225274e-06, + "loss": 3.3549, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.824874554742221e-06, + "loss": 3.3488, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.816488607231701e-06, + "loss": 3.3595, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.808102659721181e-06, + "loss": 3.3528, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799733091014392e-06, + "loss": 3.3506, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.791347143503872e-06, + "loss": 3.3525, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782961195993352e-06, + "loss": 3.3399, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774575248482832e-06, + "loss": 3.3431, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.766205679776043e-06, + "loss": 3.3445, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757819732265523e-06, + "loss": 3.3549, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.749433784755003e-06, + "loss": 3.3541, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.741047837244483e-06, + "loss": 3.3564, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732678268537693e-06, + "loss": 3.3535, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.724292321027175e-06, + "loss": 3.3514, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715906373516655e-06, + "loss": 3.3546, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707520426006133e-06, + "loss": 3.34, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.699150857299346e-06, + "loss": 3.3507, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690764909788826e-06, + "loss": 3.3343, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.682378962278304e-06, + "loss": 3.3491, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673993014767784e-06, + "loss": 3.3425, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665623446060997e-06, + "loss": 3.3567, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.657237498550476e-06, + "loss": 3.3445, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648851551039956e-06, + "loss": 3.3457, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.640465603529436e-06, + "loss": 3.3524, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.632096034822647e-06, + "loss": 3.3469, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623710087312129e-06, + "loss": 3.3414, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.615324139801607e-06, + "loss": 3.3284, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606938192291087e-06, + "loss": 3.3499, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.5985686235843e-06, + "loss": 3.3508, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.590182676073778e-06, + "loss": 3.3509, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581796728563258e-06, + "loss": 3.3404, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.573410781052738e-06, + "loss": 3.3366, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.56504121234595e-06, + "loss": 3.3378, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.556655264835428e-06, + "loss": 3.3368, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.54826931732491e-06, + "loss": 3.3603, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.53988336981439e-06, + "loss": 3.3357, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.5315138011076e-06, + "loss": 3.3546, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.52312785359708e-06, + "loss": 3.3483, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.51474190608656e-06, + "loss": 3.3329, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.506372337379772e-06, + "loss": 3.3506, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497986389869251e-06, + "loss": 3.3417, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.489600442358731e-06, + "loss": 3.3421, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.481214494848211e-06, + "loss": 3.339, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472844926141424e-06, + "loss": 3.3551, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.464458978630902e-06, + "loss": 3.3418, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.456073031120382e-06, + "loss": 3.3415, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447687083609864e-06, + "loss": 3.3403, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.439317514903075e-06, + "loss": 3.3399, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430931567392553e-06, + "loss": 3.3447, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422545619882034e-06, + "loss": 3.3545, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.414159672371514e-06, + "loss": 3.3425, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405790103664725e-06, + "loss": 3.3519, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.397404156154205e-06, + "loss": 3.3557, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.389018208643685e-06, + "loss": 3.3503, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380632261133165e-06, + "loss": 3.3457, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.372262692426376e-06, + "loss": 3.3513, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363876744915856e-06, + "loss": 3.3503, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.355490797405336e-06, + "loss": 3.3454, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.347104849894816e-06, + "loss": 3.3454, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338735281188027e-06, + "loss": 3.3563, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.330349333677506e-06, + "loss": 3.3562, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321963386166988e-06, + "loss": 3.341, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.313577438656466e-06, + "loss": 3.3276, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.305207869949679e-06, + "loss": 3.3396, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296821922439159e-06, + "loss": 3.3501, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.288435974928637e-06, + "loss": 3.3453, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.280050027418117e-06, + "loss": 3.3501, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.27168045871133e-06, + "loss": 3.3419, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.26329451120081e-06, + "loss": 3.3443, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254908563690288e-06, + "loss": 3.3382, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.24652261617977e-06, + "loss": 3.3394, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.23815304747298e-06, + "loss": 3.3526, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.22976709996246e-06, + "loss": 3.3487, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.22138115245194e-06, + "loss": 3.3638, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.21299520494142e-06, + "loss": 3.3484, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204625636234633e-06, + "loss": 3.3413, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.19623968872411e-06, + "loss": 3.3507, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.18785374121359e-06, + "loss": 3.3508, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.17946779370307e-06, + "loss": 3.3491, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.171098224996283e-06, + "loss": 3.3492, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162712277485761e-06, + "loss": 3.3438, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.154326329975241e-06, + "loss": 3.3416, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145940382464723e-06, + "loss": 3.3514, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137570813757934e-06, + "loss": 3.3362, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.129184866247414e-06, + "loss": 3.3423, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120798918736894e-06, + "loss": 3.3433, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.112412971226374e-06, + "loss": 3.3437, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.104043402519585e-06, + "loss": 3.3365, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095657455009064e-06, + "loss": 3.3509, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.087271507498544e-06, + "loss": 3.3317, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078885559988024e-06, + "loss": 3.3458, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070515991281235e-06, + "loss": 3.3431, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.062130043770715e-06, + "loss": 3.3474, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053744096260195e-06, + "loss": 3.3567, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.045358148749675e-06, + "loss": 3.3537, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036988580042886e-06, + "loss": 3.34, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028602632532367e-06, + "loss": 3.3444, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.020216685021847e-06, + "loss": 3.3527, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011830737511326e-06, + "loss": 3.3398, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.003461168804538e-06, + "loss": 3.3438, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.995075221294018e-06, + "loss": 3.3404, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986689273783498e-06, + "loss": 3.3416, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.978303326272976e-06, + "loss": 3.3477, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969933757566189e-06, + "loss": 3.3373, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.961547810055669e-06, + "loss": 3.3426, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.953161862545149e-06, + "loss": 3.3448, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.944775915034629e-06, + "loss": 3.3408, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.93640634632784e-06, + "loss": 3.3397, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.92802039881732e-06, + "loss": 3.3513, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.9196344513068e-06, + "loss": 3.361, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.91126488260001e-06, + "loss": 3.3477, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902878935089492e-06, + "loss": 3.3372, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.894492987578972e-06, + "loss": 3.3491, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.88610704006845e-06, + "loss": 3.3486, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877737471361663e-06, + "loss": 3.3483, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.869351523851142e-06, + "loss": 3.3441, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.86096557634062e-06, + "loss": 3.3553, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852579628830102e-06, + "loss": 3.344, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.844210060123313e-06, + "loss": 3.3509, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835824112612793e-06, + "loss": 3.3422, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.827438165102273e-06, + "loss": 3.3455, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.819052217591753e-06, + "loss": 3.3414, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810682648884964e-06, + "loss": 3.3368, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.802296701374446e-06, + "loss": 3.3546, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793910753863924e-06, + "loss": 3.3387, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785524806353404e-06, + "loss": 3.3536, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.777155237646616e-06, + "loss": 3.3386, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768769290136094e-06, + "loss": 3.338, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.862476110458374, + "eval_runtime": 305.0655, + "eval_samples_per_second": 1250.849, + "eval_steps_per_second": 39.09, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.760383342625574e-06, + "loss": 3.3409, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.751997395115056e-06, + "loss": 3.3435, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743611447604536e-06, + "loss": 3.3519, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.735241878897745e-06, + "loss": 3.3475, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726855931387227e-06, + "loss": 3.3516, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.718469983876707e-06, + "loss": 3.3404, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.710084036366185e-06, + "loss": 3.3343, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701714467659397e-06, + "loss": 3.3362, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.693328520148877e-06, + "loss": 3.3497, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684942572638357e-06, + "loss": 3.343, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676556625127837e-06, + "loss": 3.3522, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.668187056421048e-06, + "loss": 3.3408, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659801108910528e-06, + "loss": 3.3366, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.65143154020374e-06, + "loss": 3.3319, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.643045592693219e-06, + "loss": 3.3356, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634659645182699e-06, + "loss": 3.3353, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.62627369767218e-06, + "loss": 3.341, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.617887750161659e-06, + "loss": 3.3402, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.609501802651139e-06, + "loss": 3.3329, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.601115855140619e-06, + "loss": 3.3576, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.592746286433831e-06, + "loss": 3.3479, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.58436033892331e-06, + "loss": 3.3468, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.575974391412791e-06, + "loss": 3.3369, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.567588443902271e-06, + "loss": 3.3493, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.55921887519548e-06, + "loss": 3.3366, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.550832927684962e-06, + "loss": 3.3436, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.542446980174442e-06, + "loss": 3.3408, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.534061032663922e-06, + "loss": 3.337, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.525691463957132e-06, + "loss": 3.3306, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.517305516446612e-06, + "loss": 3.3348, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.508919568936092e-06, + "loss": 3.3455, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.500533621425572e-06, + "loss": 3.3443, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.492164052718783e-06, + "loss": 3.3432, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.483778105208263e-06, + "loss": 3.347, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.475392157697743e-06, + "loss": 3.3408, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.467006210187223e-06, + "loss": 3.3411, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.458636641480434e-06, + "loss": 3.3342, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.450250693969915e-06, + "loss": 3.3411, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441864746459395e-06, + "loss": 3.3282, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.433478798948874e-06, + "loss": 3.3429, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.425109230242086e-06, + "loss": 3.3326, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416723282731566e-06, + "loss": 3.3488, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.408337335221044e-06, + "loss": 3.3355, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399951387710526e-06, + "loss": 3.3392, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391581819003737e-06, + "loss": 3.3432, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.383195871493217e-06, + "loss": 3.3384, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374809923982697e-06, + "loss": 3.3337, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.366423976472177e-06, + "loss": 3.3218, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.358054407765387e-06, + "loss": 3.3352, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349668460254869e-06, + "loss": 3.3428, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.341282512744347e-06, + "loss": 3.3405, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332896565233827e-06, + "loss": 3.332, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.32452699652704e-06, + "loss": 3.3257, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.316141049016518e-06, + "loss": 3.3326, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307755101505998e-06, + "loss": 3.3269, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.299369153995478e-06, + "loss": 3.3531, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.29099958528869e-06, + "loss": 3.3273, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282613637778169e-06, + "loss": 3.3467, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.27422769026765e-06, + "loss": 3.3351, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.26584174275713e-06, + "loss": 3.3286, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.257472174050341e-06, + "loss": 3.3394, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.249086226539821e-06, + "loss": 3.3344, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240700279029301e-06, + "loss": 3.3305, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.232314331518781e-06, + "loss": 3.3307, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.223944762811992e-06, + "loss": 3.3449, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.215558815301472e-06, + "loss": 3.336, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.207172867790952e-06, + "loss": 3.3318, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198786920280432e-06, + "loss": 3.3306, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.190417351573642e-06, + "loss": 3.3303, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.182031404063122e-06, + "loss": 3.3326, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.173645456552604e-06, + "loss": 3.3475, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.165259509042082e-06, + "loss": 3.3331, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.156889940335293e-06, + "loss": 3.3448, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.148503992824775e-06, + "loss": 3.3464, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.140118045314255e-06, + "loss": 3.3405, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131732097803733e-06, + "loss": 3.3329, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.123362529096945e-06, + "loss": 3.3435, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114976581586425e-06, + "loss": 3.3432, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106590634075905e-06, + "loss": 3.3333, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.098204686565385e-06, + "loss": 3.3375, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089835117858596e-06, + "loss": 3.3416, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081449170348076e-06, + "loss": 3.346, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.073063222837556e-06, + "loss": 3.3325, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064693654130767e-06, + "loss": 3.3278, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.056307706620247e-06, + "loss": 3.3283, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.047921759109728e-06, + "loss": 3.3403, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.039535811599207e-06, + "loss": 3.3388, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.031166242892419e-06, + "loss": 3.3415, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022780295381899e-06, + "loss": 3.3351, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.014394347871377e-06, + "loss": 3.3307, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.006008400360857e-06, + "loss": 3.3281, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.99763883165407e-06, + "loss": 3.3341, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.98925288414355e-06, + "loss": 3.3371, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980866936633028e-06, + "loss": 3.3387, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.97248098912251e-06, + "loss": 3.3569, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.96411142041572e-06, + "loss": 3.3424, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.9557254729052e-06, + "loss": 3.3282, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.94733952539468e-06, + "loss": 3.3433, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.93895357788416e-06, + "loss": 3.339, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.930584009177373e-06, + "loss": 3.3425, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.922198061666851e-06, + "loss": 3.3393, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913812114156331e-06, + "loss": 3.335, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905426166645811e-06, + "loss": 3.3317, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.897056597939023e-06, + "loss": 3.3461, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888670650428502e-06, + "loss": 3.3252, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.880284702917982e-06, + "loss": 3.3357, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.871898755407463e-06, + "loss": 3.3321, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863529186700674e-06, + "loss": 3.3366, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.855143239190154e-06, + "loss": 3.3251, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.846757291679634e-06, + "loss": 3.3378, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.838371344169114e-06, + "loss": 3.3292, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.830001775462325e-06, + "loss": 3.3338, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.821615827951805e-06, + "loss": 3.3369, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.813229880441285e-06, + "loss": 3.3334, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804843932930765e-06, + "loss": 3.3498, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.796474364223975e-06, + "loss": 3.3471, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.788088416713455e-06, + "loss": 3.3357, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779702469202935e-06, + "loss": 3.3327, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.771316521692415e-06, + "loss": 3.3397, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.762946952985626e-06, + "loss": 3.3328, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.754561005475108e-06, + "loss": 3.3326, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.746175057964588e-06, + "loss": 3.3325, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737789110454066e-06, + "loss": 3.333, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.729419541747278e-06, + "loss": 3.337, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.721033594236758e-06, + "loss": 3.3278, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712647646726238e-06, + "loss": 3.3341, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.704261699215717e-06, + "loss": 3.3323, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695892130508929e-06, + "loss": 3.3337, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.687506182998409e-06, + "loss": 3.3277, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.679120235487889e-06, + "loss": 3.3442, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.670734287977369e-06, + "loss": 3.3514, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.66236471927058e-06, + "loss": 3.3409, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.653978771760061e-06, + "loss": 3.3287, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.64559282424954e-06, + "loss": 3.3393, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.63720687673902e-06, + "loss": 3.339, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628837308032231e-06, + "loss": 3.3402, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.620451360521712e-06, + "loss": 3.3354, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.61206541301119e-06, + "loss": 3.3434, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603695844304402e-06, + "loss": 3.3316, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.595309896793883e-06, + "loss": 3.3445, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.586923949283362e-06, + "loss": 3.3306, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.578538001772842e-06, + "loss": 3.3387, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.5701684330660534e-06, + "loss": 3.3348, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561782485555534e-06, + "loss": 3.3251, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.5533965380450125e-06, + "loss": 3.3453, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.545010590534493e-06, + "loss": 3.3334, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536641021827705e-06, + "loss": 3.3442, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.528255074317185e-06, + "loss": 3.328, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519869126806664e-06, + "loss": 3.3299, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.862786293029785, + "eval_runtime": 304.9735, + "eval_samples_per_second": 1251.227, + "eval_steps_per_second": 39.102, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.511483179296144e-06, + "loss": 3.3341, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.503097231785625e-06, + "loss": 3.3304, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.494711284275104e-06, + "loss": 3.3435, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.486325336764584e-06, + "loss": 3.337, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.4779557680577955e-06, + "loss": 3.3462, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.4695698205472754e-06, + "loss": 3.3298, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.4611838730367545e-06, + "loss": 3.3284, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.452814304329966e-06, + "loss": 3.3235, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.444428356819447e-06, + "loss": 3.3389, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.436042409308925e-06, + "loss": 3.3382, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.427656461798406e-06, + "loss": 3.3401, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.419286893091618e-06, + "loss": 3.3332, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.410900945581098e-06, + "loss": 3.328, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.402531376874308e-06, + "loss": 3.3251, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.394145429363788e-06, + "loss": 3.3246, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.385759481853269e-06, + "loss": 3.3279, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.3773735343427474e-06, + "loss": 3.3275, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.368987586832228e-06, + "loss": 3.3302, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.360601639321708e-06, + "loss": 3.326, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.352215691811189e-06, + "loss": 3.3514, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.343846123104399e-06, + "loss": 3.3394, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.335460175593879e-06, + "loss": 3.3391, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.32707422808336e-06, + "loss": 3.3275, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.318688280572839e-06, + "loss": 3.3423, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.3103187118660505e-06, + "loss": 3.3231, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.30193276435553e-06, + "loss": 3.3379, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.293546816845011e-06, + "loss": 3.3301, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.2851608693344895e-06, + "loss": 3.3307, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.276791300627701e-06, + "loss": 3.3208, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.268405353117182e-06, + "loss": 3.3225, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.260019405606662e-06, + "loss": 3.3363, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.251633458096141e-06, + "loss": 3.337, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.243263889389353e-06, + "loss": 3.3369, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.2348779418788326e-06, + "loss": 3.3373, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.226491994368312e-06, + "loss": 3.3302, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.2181060468577925e-06, + "loss": 3.3326, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.209736478151004e-06, + "loss": 3.3265, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.201350530640484e-06, + "loss": 3.3297, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.192964583129963e-06, + "loss": 3.3196, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.184578635619443e-06, + "loss": 3.336, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.176209066912655e-06, + "loss": 3.3255, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.167823119402136e-06, + "loss": 3.3393, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.159437171891614e-06, + "loss": 3.3276, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.151051224381095e-06, + "loss": 3.3238, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.142681655674306e-06, + "loss": 3.3374, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.134295708163785e-06, + "loss": 3.3285, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.125909760653265e-06, + "loss": 3.3259, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.117523813142746e-06, + "loss": 3.3108, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.109154244435958e-06, + "loss": 3.3291, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.100768296925436e-06, + "loss": 3.3324, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.092382349414917e-06, + "loss": 3.3306, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.083996401904397e-06, + "loss": 3.3267, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.0756268331976084e-06, + "loss": 3.3153, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.0672408856870876e-06, + "loss": 3.3254, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.0588549381765675e-06, + "loss": 3.3179, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.050468990666048e-06, + "loss": 3.3404, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.042099421959258e-06, + "loss": 3.3191, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.033713474448739e-06, + "loss": 3.3355, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.025327526938219e-06, + "loss": 3.3308, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.016941579427699e-06, + "loss": 3.3163, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.00857201072091e-06, + "loss": 3.3245, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 7.00018606321039e-06, + "loss": 3.3308, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.9918001156998705e-06, + "loss": 3.3198, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.983414168189349e-06, + "loss": 3.3234, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.97504459948256e-06, + "loss": 3.3338, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.966658651972041e-06, + "loss": 3.3321, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.958272704461521e-06, + "loss": 3.3187, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.949886756951e-06, + "loss": 3.3269, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.941517188244212e-06, + "loss": 3.3175, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.933131240733693e-06, + "loss": 3.3247, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.924745293223173e-06, + "loss": 3.3395, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.916359345712652e-06, + "loss": 3.3238, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.9079897770058634e-06, + "loss": 3.3361, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.899603829495343e-06, + "loss": 3.3342, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.8912178819848225e-06, + "loss": 3.3353, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.8828319344743024e-06, + "loss": 3.3216, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.874462365767514e-06, + "loss": 3.3379, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.866076418256995e-06, + "loss": 3.3325, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.857690470746474e-06, + "loss": 3.3296, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.849304523235954e-06, + "loss": 3.3278, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.840934954529166e-06, + "loss": 3.3323, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.832549007018646e-06, + "loss": 3.3396, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.824163059508125e-06, + "loss": 3.3241, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.815793490801336e-06, + "loss": 3.3161, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.807407543290817e-06, + "loss": 3.3141, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.799021595780296e-06, + "loss": 3.3307, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.790635648269776e-06, + "loss": 3.3312, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.782266079562988e-06, + "loss": 3.3344, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.773880132052468e-06, + "loss": 3.3237, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.765494184541947e-06, + "loss": 3.3252, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.757108237031428e-06, + "loss": 3.3178, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.748738668324639e-06, + "loss": 3.3224, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.740352720814119e-06, + "loss": 3.3282, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.731966773303598e-06, + "loss": 3.3323, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.723580825793078e-06, + "loss": 3.3472, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.71521125708629e-06, + "loss": 3.3298, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.706825309575769e-06, + "loss": 3.3223, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.698439362065249e-06, + "loss": 3.3327, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.69005341455473e-06, + "loss": 3.3262, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.6816838458479415e-06, + "loss": 3.3356, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.6732978983374206e-06, + "loss": 3.3291, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.6649119508269005e-06, + "loss": 3.3261, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.656526003316381e-06, + "loss": 3.3264, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.648156434609591e-06, + "loss": 3.336, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.639770487099071e-06, + "loss": 3.3158, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.631384539588552e-06, + "loss": 3.3289, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.622998592078032e-06, + "loss": 3.3197, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.614629023371243e-06, + "loss": 3.3264, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.606243075860723e-06, + "loss": 3.3183, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.597857128350203e-06, + "loss": 3.328, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.589471180839682e-06, + "loss": 3.3177, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.5811016121328934e-06, + "loss": 3.3247, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.572715664622374e-06, + "loss": 3.3309, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.564329717111854e-06, + "loss": 3.3221, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.555943769601333e-06, + "loss": 3.3424, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.547574200894545e-06, + "loss": 3.338, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.539188253384025e-06, + "loss": 3.3289, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.530802305873506e-06, + "loss": 3.3245, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.522416358362984e-06, + "loss": 3.3278, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.5140467896561964e-06, + "loss": 3.3262, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.505660842145676e-06, + "loss": 3.3258, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.4972748946351555e-06, + "loss": 3.3248, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.4888889471246355e-06, + "loss": 3.3221, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.480519378417847e-06, + "loss": 3.3302, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.472133430907328e-06, + "loss": 3.3199, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.463747483396806e-06, + "loss": 3.327, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.455361535886287e-06, + "loss": 3.3244, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.446991967179499e-06, + "loss": 3.3232, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.4386060196689786e-06, + "loss": 3.3181, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.430220072158458e-06, + "loss": 3.3386, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.421834124647938e-06, + "loss": 3.3426, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.413464555941149e-06, + "loss": 3.3323, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.405078608430628e-06, + "loss": 3.3167, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.396692660920109e-06, + "loss": 3.3315, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.388306713409589e-06, + "loss": 3.3287, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.379937144702801e-06, + "loss": 3.3331, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.37155119719228e-06, + "loss": 3.3261, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.36316524968176e-06, + "loss": 3.3316, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.354779302171241e-06, + "loss": 3.3244, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.346409733464452e-06, + "loss": 3.3341, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.338023785953931e-06, + "loss": 3.3277, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.329637838443411e-06, + "loss": 3.328, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.321268269736623e-06, + "loss": 3.324, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.312882322226102e-06, + "loss": 3.3207, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.304496374715582e-06, + "loss": 3.3329, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.296110427205063e-06, + "loss": 3.3287, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.2877408584982745e-06, + "loss": 3.3308, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.279354910987753e-06, + "loss": 3.3185, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.2709689634772335e-06, + "loss": 3.3204, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.863189697265625, + "eval_runtime": 319.6061, + "eval_samples_per_second": 1193.941, + "eval_steps_per_second": 37.312, + "step": 2671200 + }, + { + "epoch": 1.0, + "learning_rate": 6.2625830159667135e-06, + "loss": 3.3274, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.254213447259925e-06, + "loss": 3.3255, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.245827499749404e-06, + "loss": 3.3315, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.237441552238884e-06, + "loss": 3.3289, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.229055604728364e-06, + "loss": 3.338, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.220686036021576e-06, + "loss": 3.3225, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.212300088511056e-06, + "loss": 3.3213, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.203914141000536e-06, + "loss": 3.3123, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.195528193490016e-06, + "loss": 3.3312, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.187158624783227e-06, + "loss": 3.3291, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.178772677272706e-06, + "loss": 3.3289, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.170386729762186e-06, + "loss": 3.3223, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.162000782251666e-06, + "loss": 3.3196, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.153631213544878e-06, + "loss": 3.319, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.145245266034358e-06, + "loss": 3.3165, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.136859318523838e-06, + "loss": 3.3204, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.128473371013318e-06, + "loss": 3.3207, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.120103802306529e-06, + "loss": 3.3205, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.111717854796009e-06, + "loss": 3.317, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.1033319072854885e-06, + "loss": 3.3431, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.0949459597749685e-06, + "loss": 3.3291, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.08657639106818e-06, + "loss": 3.3251, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.078190443557659e-06, + "loss": 3.3225, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.06980449604714e-06, + "loss": 3.3306, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.061418548536619e-06, + "loss": 3.3166, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.053048979829832e-06, + "loss": 3.3332, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.044663032319311e-06, + "loss": 3.3198, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.0362770848087915e-06, + "loss": 3.3207, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.027891137298271e-06, + "loss": 3.3098, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.019521568591482e-06, + "loss": 3.3166, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.011135621080962e-06, + "loss": 3.3267, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 6.002749673570441e-06, + "loss": 3.3272, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.994363726059922e-06, + "loss": 3.3336, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.985994157353133e-06, + "loss": 3.3306, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.977608209842613e-06, + "loss": 3.3175, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.969222262332093e-06, + "loss": 3.3266, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.960836314821573e-06, + "loss": 3.3146, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.9524667461147844e-06, + "loss": 3.3233, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.944080798604264e-06, + "loss": 3.3089, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.935694851093744e-06, + "loss": 3.3238, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.9273089035832235e-06, + "loss": 3.317, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.918939334876435e-06, + "loss": 3.3294, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.910553387365915e-06, + "loss": 3.3225, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.902167439855395e-06, + "loss": 3.3128, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.893781492344875e-06, + "loss": 3.3307, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.885411923638087e-06, + "loss": 3.3197, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.8770259761275666e-06, + "loss": 3.3162, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.8686400286170465e-06, + "loss": 3.307, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.860270459910257e-06, + "loss": 3.3147, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.851884512399738e-06, + "loss": 3.3239, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.843498564889217e-06, + "loss": 3.3205, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.835112617378697e-06, + "loss": 3.3182, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.826743048671909e-06, + "loss": 3.3077, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.818357101161388e-06, + "loss": 3.3161, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.809971153650869e-06, + "loss": 3.3066, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.801585206140348e-06, + "loss": 3.3288, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.7932156374335595e-06, + "loss": 3.3166, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.7848296899230394e-06, + "loss": 3.3235, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.776443742412519e-06, + "loss": 3.3214, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.768057794901999e-06, + "loss": 3.3111, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.759688226195211e-06, + "loss": 3.3143, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.751302278684691e-06, + "loss": 3.3215, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.74291633117417e-06, + "loss": 3.3122, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.734530383663651e-06, + "loss": 3.3176, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.726160814956862e-06, + "loss": 3.322, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.717774867446342e-06, + "loss": 3.3238, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.7093889199358215e-06, + "loss": 3.3099, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.7010029724253015e-06, + "loss": 3.3182, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.692633403718513e-06, + "loss": 3.3094, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.684247456207992e-06, + "loss": 3.3152, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.675861508697473e-06, + "loss": 3.3268, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.667475561186952e-06, + "loss": 3.3158, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.659105992480164e-06, + "loss": 3.3303, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.650720044969644e-06, + "loss": 3.3265, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.642334097459124e-06, + "loss": 3.3272, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.633948149948604e-06, + "loss": 3.3098, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.625578581241815e-06, + "loss": 3.3259, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.617192633731294e-06, + "loss": 3.3247, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.608806686220774e-06, + "loss": 3.3177, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.600420738710255e-06, + "loss": 3.323, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.592051170003466e-06, + "loss": 3.3229, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.583665222492946e-06, + "loss": 3.3315, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.575279274982426e-06, + "loss": 3.3144, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.566893327471906e-06, + "loss": 3.3075, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.558523758765117e-06, + "loss": 3.3101, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.550137811254597e-06, + "loss": 3.3187, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.5417518637440765e-06, + "loss": 3.3218, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.5333659162335565e-06, + "loss": 3.3226, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.524996347526768e-06, + "loss": 3.3189, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.516610400016248e-06, + "loss": 3.3177, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.508224452505728e-06, + "loss": 3.3082, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.499838504995208e-06, + "loss": 3.3138, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.49146893628842e-06, + "loss": 3.3165, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.483082988777899e-06, + "loss": 3.3297, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.4746970412673795e-06, + "loss": 3.3409, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.466311093756859e-06, + "loss": 3.32, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.45794152505007e-06, + "loss": 3.3118, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.44955557753955e-06, + "loss": 3.3262, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.441169630029029e-06, + "loss": 3.3165, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.43278368251851e-06, + "loss": 3.3285, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.424414113811721e-06, + "loss": 3.3194, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.416028166301202e-06, + "loss": 3.3188, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.407642218790681e-06, + "loss": 3.3188, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.399256271280162e-06, + "loss": 3.3294, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.3908867025733724e-06, + "loss": 3.3072, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.382500755062852e-06, + "loss": 3.3177, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.374114807552332e-06, + "loss": 3.309, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.3657288600418115e-06, + "loss": 3.3232, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.357359291335023e-06, + "loss": 3.3107, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.348973343824503e-06, + "loss": 3.3191, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.340587396313983e-06, + "loss": 3.3096, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.332201448803463e-06, + "loss": 3.3167, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.323831880096675e-06, + "loss": 3.3196, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.3154459325861546e-06, + "loss": 3.3178, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.3070599850756345e-06, + "loss": 3.3306, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.298690416368845e-06, + "loss": 3.3307, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.290304468858326e-06, + "loss": 3.3215, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.281918521347805e-06, + "loss": 3.3141, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.273532573837285e-06, + "loss": 3.3191, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.265146626326765e-06, + "loss": 3.3202, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.256777057619977e-06, + "loss": 3.3114, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.248391110109457e-06, + "loss": 3.3149, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.240005162598937e-06, + "loss": 3.3186, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.231619215088417e-06, + "loss": 3.3175, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.2232496463816274e-06, + "loss": 3.3128, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.214863698871108e-06, + "loss": 3.3161, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.206477751360587e-06, + "loss": 3.3147, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.198108182653799e-06, + "loss": 3.3191, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.189722235143279e-06, + "loss": 3.3076, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.181336287632758e-06, + "loss": 3.3301, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.172950340122239e-06, + "loss": 3.328, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.16458077141545e-06, + "loss": 3.3278, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.15619482390493e-06, + "loss": 3.3064, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.1478088763944095e-06, + "loss": 3.3214, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.13942292888389e-06, + "loss": 3.3246, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.131053360177101e-06, + "loss": 3.3191, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.122667412666581e-06, + "loss": 3.3189, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.114281465156061e-06, + "loss": 3.3222, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.10589551764554e-06, + "loss": 3.3192, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.097525948938752e-06, + "loss": 3.3285, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.089140001428232e-06, + "loss": 3.3199, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.080754053917712e-06, + "loss": 3.3184, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.072368106407192e-06, + "loss": 3.3181, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.063998537700403e-06, + "loss": 3.3088, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.055612590189883e-06, + "loss": 3.3253, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.047226642679362e-06, + "loss": 3.3226, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.038840695168843e-06, + "loss": 3.3189, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.030471126462054e-06, + "loss": 3.3079, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.022085178951534e-06, + "loss": 3.3114, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 3.8629090785980225, + "eval_runtime": 303.0182, + "eval_samples_per_second": 1259.301, + "eval_steps_per_second": 39.354, + "step": 2747520 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.9159299661036954e+18, + "trial_name": null, + "trial_params": null +}