diff --git "a/checkpoint-2594880/trainer_state.json" "b/checkpoint-2594880/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2594880/trainer_state.json" @@ -0,0 +1,30705 @@ +{ + "best_metric": 3.8441388607025146, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/transformer/4/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2594880, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9667, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8294, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1889, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9725, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8153, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7074, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5984, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5284, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4533, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3991, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3498, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3057, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2633, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1983, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1707, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.128, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1052, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0766, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0507, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0144, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0063, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9744, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9488, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9306, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9223, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8902, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8672, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8548, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8315, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.825, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8071, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8035, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7744, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7703, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7584, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7472, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7316, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7002, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7035, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6787, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6829, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6692, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6648, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6477, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6469, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6425, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6283, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6291, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5985, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5934, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6002, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5903, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5812, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5552, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5714, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5469, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5708, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5247, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5437, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5263, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5107, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5204, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5062, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4867, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4891, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5047, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4815, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4747, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4709, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4578, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4704, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.4681, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4563, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4667, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4548, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4482, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4315, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4346, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4291, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4187, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4186, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4234, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4236, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4119, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3884, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4052, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4065, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4048, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3881, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.4001, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3872, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3771, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3775, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3761, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3671, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3782, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3571, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3542, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.3506, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3618, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3557, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3393, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914496093000158e-05, + "loss": 4.3401, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3319, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3413, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3155, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.328, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3271, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3225, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3267, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3199, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3052, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3156, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3151, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3112, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3126, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3086, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.3032, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2919, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.2962, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2936, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2819, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2857, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2833, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2915, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2724, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2769, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2688, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2748, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2621, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2809, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2651, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2618, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2619, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2628, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.267, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.266, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2582, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2602, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2557, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2486, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.24, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2458, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2396, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2299, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2382, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2334, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2366, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2373, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2294, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.197614669799805, + "eval_runtime": 304.5092, + "eval_samples_per_second": 1253.134, + "eval_steps_per_second": 39.161, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2126, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2136, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2276, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2182, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.22, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2074, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2021, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2039, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.211, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2079, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2033, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2109, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1821, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1914, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1876, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.177, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1918, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.1822, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1802, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.2057, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857494580253846e-05, + "loss": 4.1827, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1794, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1807, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1897, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854141839130011e-05, + "loss": 4.171, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853303244378958e-05, + "loss": 4.1696, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852464649627906e-05, + "loss": 4.1715, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1663, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850789098006175e-05, + "loss": 4.1671, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849950503255123e-05, + "loss": 4.1611, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849113546384445e-05, + "loss": 4.1791, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482749516333934e-05, + "loss": 4.1645, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847436356882341e-05, + "loss": 4.1629, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846597762131289e-05, + "loss": 4.1619, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845759167380237e-05, + "loss": 4.1625, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.1588, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.1418, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1476, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1357, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1505, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.8407292367542976e-05, + "loss": 4.1402, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1496, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.1405, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1407, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.1464, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1371, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.141, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.83486234925768e-05, + "loss": 4.1275, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1268, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1336, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1321, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.137, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1074, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1322, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1085, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281568670100105e-05, + "loss": 4.1389, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273182722589585e-05, + "loss": 4.1077, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1256, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1177, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248041258861754e-05, + "loss": 4.103, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239655311351234e-05, + "loss": 4.1126, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1104, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.0945, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.82145138476234e-05, + "loss": 4.0984, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820612790011288e-05, + "loss": 4.1151, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1025, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.1033, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818098643638506e-05, + "loss": 4.0992, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.0876, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1041, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1034, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814745902514671e-05, + "loss": 4.102, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.1105, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1023, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.1041, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.0844, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.0985, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809715971888732e-05, + "loss": 4.0903, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.0838, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808040420267001e-05, + "loss": 4.0877, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807201825515949e-05, + "loss": 4.0948, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.0993, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.0914, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804687679143166e-05, + "loss": 4.0729, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803849084392114e-05, + "loss": 4.0799, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0939, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0906, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801334938019331e-05, + "loss": 4.0839, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800496343268279e-05, + "loss": 4.0897, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0868, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0718, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979821968954966e-05, + "loss": 4.0763, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971436021444446e-05, + "loss": 4.0805, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963050073933926e-05, + "loss": 4.0698, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954664126423406e-05, + "loss": 4.0893, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946294557716615e-05, + "loss": 4.0666, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937908610206095e-05, + "loss": 4.0654, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929522662695575e-05, + "loss": 4.0683, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921136715185055e-05, + "loss": 4.0763, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912767146478264e-05, + "loss": 4.077, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904381198967744e-05, + "loss": 4.0634, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895995251457224e-05, + "loss": 4.0608, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887609303946704e-05, + "loss": 4.0562, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787923973523992e-05, + "loss": 4.0729, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.78708537877294e-05, + "loss": 4.0462, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786248421902261e-05, + "loss": 4.0552, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785409827151209e-05, + "loss": 4.0678, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784571232400157e-05, + "loss": 4.0587, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783732637649105e-05, + "loss": 4.0576, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782894042898053e-05, + "loss": 4.0578, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782055448147001e-05, + "loss": 4.0497, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781216853395948e-05, + "loss": 4.0608, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780378258644896e-05, + "loss": 4.0551, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779541301774218e-05, + "loss": 4.058, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778702707023166e-05, + "loss": 4.0594, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777864112272114e-05, + "loss": 4.0621, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770271554014354e-05, + "loss": 4.0521, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761885606503834e-05, + "loss": 4.045, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775349965899331e-05, + "loss": 4.0529, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774511371148279e-05, + "loss": 4.0485, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773672776397227e-05, + "loss": 4.0373, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728341816461747e-05, + "loss": 4.0456, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719955868951227e-05, + "loss": 4.0415, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711569921440707e-05, + "loss": 4.0519, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703200352733916e-05, + "loss": 4.0363, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694814405223396e-05, + "loss": 4.0462, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686428457712876e-05, + "loss": 4.0277, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7678042510202355e-05, + "loss": 4.0457, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766967294149557e-05, + "loss": 4.0329, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766128699398505e-05, + "loss": 4.0499, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765290104647453e-05, + "loss": 4.0413, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764451509896401e-05, + "loss": 4.038, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763614553025722e-05, + "loss": 4.029, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.76277595827467e-05, + "loss": 4.0365, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761937363523618e-05, + "loss": 4.0467, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761098768772566e-05, + "loss": 4.0479, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760261811901887e-05, + "loss": 4.0402, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759423217150835e-05, + "loss": 4.0417, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0339, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757746027648731e-05, + "loss": 4.0344, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569090707780525e-05, + "loss": 4.0274, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560704760270005e-05, + "loss": 4.0323, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552318812759485e-05, + "loss": 4.0288, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543949244052694e-05, + "loss": 4.0173, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535563296542174e-05, + "loss": 4.0302, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527177349031654e-05, + "loss": 4.0245, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518791401521134e-05, + "loss": 4.029, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510405454010614e-05, + "loss": 4.0274, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502019506500094e-05, + "loss": 4.0258, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.0277814865112305, + "eval_runtime": 305.4292, + "eval_samples_per_second": 1249.36, + "eval_steps_per_second": 39.043, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493633558989574e-05, + "loss": 4.0078, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485247611479054e-05, + "loss": 4.0127, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476861663968534e-05, + "loss": 4.0236, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468475716458014e-05, + "loss": 4.0191, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460089768947494e-05, + "loss": 4.0259, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451703821436974e-05, + "loss": 4.0052, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443317873926453e-05, + "loss": 4.0134, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434931926415933e-05, + "loss": 4.0068, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742656235770914e-05, + "loss": 4.0194, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741817641019862e-05, + "loss": 4.0167, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.74097904626881e-05, + "loss": 4.0138, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740140451517758e-05, + "loss": 4.0156, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739303494647079e-05, + "loss": 3.9959, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738464899896027e-05, + "loss": 4.0019, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737626305144975e-05, + "loss": 4.0036, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736787710393923e-05, + "loss": 3.9942, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735949115642871e-05, + "loss": 4.0034, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.73511052089182e-05, + "loss": 3.9988, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734271926140768e-05, + "loss": 3.9978, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0277, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 3.9993, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731757779767985e-05, + "loss": 4.0039, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730919185016933e-05, + "loss": 4.0011, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0122, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9927, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9942, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 3.9983, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267278491420456e-05, + "loss": 3.9966, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9887, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.992, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 4.0068, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9965, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9927, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9961, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9923, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 3.9927, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9749, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9884, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.9722, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9859, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9789, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9893, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9826, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9776, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9861, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9835, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9837, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.9691, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9689, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.9814, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9774, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9774, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9581, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9816, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.9558, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9865, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.9533, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701579833892724e-05, + "loss": 3.9763, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700741239141672e-05, + "loss": 3.9679, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9606, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.963, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698227092768889e-05, + "loss": 3.9649, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697388498017837e-05, + "loss": 3.9473, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9552, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9656, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694874351645054e-05, + "loss": 3.9641, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694035756894003e-05, + "loss": 3.9539, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.956, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692360205272272e-05, + "loss": 3.9498, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.69152161052122e-05, + "loss": 3.9558, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906830157701677e-05, + "loss": 3.9616, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9606, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.9709, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9657, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.965, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9453, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9585, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848161282735495e-05, + "loss": 3.9572, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683977533522498e-05, + "loss": 3.9435, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9556, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.957, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9627, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680624792398663e-05, + "loss": 3.9536, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9368, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9486, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.9573, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677272051274828e-05, + "loss": 3.9575, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9518, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675594861772724e-05, + "loss": 3.9573, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9577, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9386, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9511, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9474, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9404, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.962, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9424, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688877416446815e-05, + "loss": 3.933, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9427, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9505, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9484, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665535000520846e-05, + "loss": 3.9407, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9318, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.9327, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9492, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9232, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9365, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9452, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.936, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.9327, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.9392, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.9319, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9389, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9355, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9349, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653799587647237e-05, + "loss": 3.9401, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652960992896185e-05, + "loss": 3.9434, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521240360255066e-05, + "loss": 3.9397, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512854412744546e-05, + "loss": 3.9239, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504468465234026e-05, + "loss": 3.9308, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.928, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9206, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9338, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9193, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.937, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9212, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9299, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437397263953595e-05, + "loss": 3.9152, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.9284, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9166, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9368, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9314, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9234, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638709795769421e-05, + "loss": 3.9146, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637871201018369e-05, + "loss": 3.924, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637032606267317e-05, + "loss": 3.9323, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.937, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9254, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634518459894534e-05, + "loss": 3.9313, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633679865143482e-05, + "loss": 3.9241, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632841270392429e-05, + "loss": 3.9265, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.9179, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.919, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9223, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9109, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9193, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.9217, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9152, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9196, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625297193393708e-05, + "loss": 3.9153, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.953303813934326, + "eval_runtime": 304.7681, + "eval_samples_per_second": 1252.07, + "eval_steps_per_second": 39.128, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.9101, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9062, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9203, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9098, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621105857518821e-05, + "loss": 3.9214, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.8992, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9111, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9011, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.9169, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9125, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9108, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9112, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.8937, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.9011, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.9026, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.8969, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.8999, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.902, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.8927, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.93, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607691617262736e-05, + "loss": 3.8987, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9028, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9047, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9085, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.8923, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603500281387848e-05, + "loss": 3.9039, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.8977, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.8975, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.8879, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600147540264013e-05, + "loss": 3.8978, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993089455129615e-05, + "loss": 3.9082, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9001, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9019, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.8985, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.8939, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.9017, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.8802, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.8949, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8756, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591764868514239e-05, + "loss": 3.8915, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59092791164356e-05, + "loss": 3.8861, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590089316892508e-05, + "loss": 3.8979, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.8918, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588412127390405e-05, + "loss": 3.8849, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587573532639353e-05, + "loss": 3.8949, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586734937888301e-05, + "loss": 3.8915, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.8889, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.8836, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584220791515518e-05, + "loss": 3.8727, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.8905, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582545239893787e-05, + "loss": 3.8857, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581706645142735e-05, + "loss": 3.8877, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580868050391683e-05, + "loss": 3.8724, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580029455640631e-05, + "loss": 3.8932, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579190860889579e-05, + "loss": 3.8624, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783539040189e-05, + "loss": 3.8981, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577515309267848e-05, + "loss": 3.8653, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576676714516796e-05, + "loss": 3.8838, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575838119765744e-05, + "loss": 3.8792, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8744, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8723, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573323973392961e-05, + "loss": 3.8826, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572485378641909e-05, + "loss": 3.8581, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8653, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570809827020178e-05, + "loss": 3.8806, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569971232269126e-05, + "loss": 3.8754, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569132637518074e-05, + "loss": 3.8681, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568294042767022e-05, + "loss": 3.8691, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674570858963436e-05, + "loss": 3.8591, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666184911452916e-05, + "loss": 3.8702, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657798963942396e-05, + "loss": 3.8757, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.8747, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641043447725085e-05, + "loss": 3.8869, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632657500214565e-05, + "loss": 3.8778, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624271552704045e-05, + "loss": 3.8812, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615885605193525e-05, + "loss": 3.8599, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607516036486734e-05, + "loss": 3.8733, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599130088976214e-05, + "loss": 3.8739, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590744141465694e-05, + "loss": 3.8587, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582358193955174e-05, + "loss": 3.8746, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8704, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.8764, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555721673022735e-05, + "loss": 3.8708, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554883078271683e-05, + "loss": 3.8556, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8679, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8716, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523689318989e-05, + "loss": 3.8774, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551530337147848e-05, + "loss": 3.8705, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550691742396796e-05, + "loss": 3.8705, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8779, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.8572, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548177596024013e-05, + "loss": 3.871, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547339001272961e-05, + "loss": 3.8629, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.863, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8787, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.8647, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543986260149126e-05, + "loss": 3.8511, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8612, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542310708527395e-05, + "loss": 3.8696, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541472113776343e-05, + "loss": 3.8704, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540633519025291e-05, + "loss": 3.8607, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.853, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.53895796740356e-05, + "loss": 3.8539, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538119372652508e-05, + "loss": 3.8704, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537280777901456e-05, + "loss": 3.8442, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536442183150404e-05, + "loss": 3.8557, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535605226279726e-05, + "loss": 3.8653, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534766631528674e-05, + "loss": 3.8617, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533928036777621e-05, + "loss": 3.8509, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533089442026569e-05, + "loss": 3.8643, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322524851558906e-05, + "loss": 3.8571, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314138904048386e-05, + "loss": 3.8574, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530575295653786e-05, + "loss": 3.8603, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529736700902734e-05, + "loss": 3.8554, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8679, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8603, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8636, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8475, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8548, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.855, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238698134061164e-05, + "loss": 3.8428, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230312186550644e-05, + "loss": 3.8559, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221926239040124e-05, + "loss": 3.8466, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213540291529604e-05, + "loss": 3.8573, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205154344019084e-05, + "loss": 3.8463, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.8569, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.836, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518001288029125e-05, + "loss": 3.8556, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517162693278074e-05, + "loss": 3.8459, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516325736407395e-05, + "loss": 3.8592, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8546, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514648546905291e-05, + "loss": 3.8545, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513809952154239e-05, + "loss": 3.8385, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.51297299528356e-05, + "loss": 3.8537, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.8553, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511295805781456e-05, + "loss": 3.8617, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510457211030404e-05, + "loss": 3.8549, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096202541597246e-05, + "loss": 3.8542, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.8521, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079430646576206e-05, + "loss": 3.8586, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8411, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.50626751303589e-05, + "loss": 3.8465, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505428918284838e-05, + "loss": 3.8483, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504590323533786e-05, + "loss": 3.8384, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8466, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8517, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502076177161003e-05, + "loss": 3.8424, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501237582409951e-05, + "loss": 3.844, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500398987658899e-05, + "loss": 3.8506, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9121642112731934, + "eval_runtime": 303.5408, + "eval_samples_per_second": 1257.132, + "eval_steps_per_second": 39.286, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499560392907847e-05, + "loss": 3.829, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498721798156795e-05, + "loss": 3.8359, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497883203405743e-05, + "loss": 3.8479, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497044608654691e-05, + "loss": 3.8415, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496206013903639e-05, + "loss": 3.853, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495367419152587e-05, + "loss": 3.8284, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494528824401535e-05, + "loss": 3.8381, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493690229650483e-05, + "loss": 3.8302, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.8466, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8448, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8334, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903391264070216e-05, + "loss": 3.8488, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489500531655969e-05, + "loss": 3.8214, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488661936904917e-05, + "loss": 3.8313, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487823342153865e-05, + "loss": 3.8345, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486984747402813e-05, + "loss": 3.827, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486146152651761e-05, + "loss": 3.8298, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853091957810824e-05, + "loss": 3.8321, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844706010300304e-05, + "loss": 3.8265, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836320062789784e-05, + "loss": 3.8587, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827950494082993e-05, + "loss": 3.8333, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481956454657247e-05, + "loss": 3.8334, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481117859906195e-05, + "loss": 3.8376, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480279265155143e-05, + "loss": 3.8407, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8235, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478603713533412e-05, + "loss": 3.8378, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47776511878236e-05, + "loss": 3.8296, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476926524031308e-05, + "loss": 3.8306, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476087929280256e-05, + "loss": 3.822, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475250972409578e-05, + "loss": 3.8305, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474412377658526e-05, + "loss": 3.8432, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473573782907474e-05, + "loss": 3.834, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.8341, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471898231285743e-05, + "loss": 3.8329, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471059636534691e-05, + "loss": 3.827, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470221041783639e-05, + "loss": 3.8346, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469382447032587e-05, + "loss": 3.8142, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685454901619076e-05, + "loss": 3.8262, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677068954108556e-05, + "loss": 3.8148, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668683006598036e-05, + "loss": 3.8223, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8239, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465192749038073e-05, + "loss": 3.8326, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464354154287021e-05, + "loss": 3.8264, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463515559535969e-05, + "loss": 3.8214, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.8284, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461840007914238e-05, + "loss": 3.8259, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461001413163186e-05, + "loss": 3.8257, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460162818412134e-05, + "loss": 3.8194, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.8083, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.8288, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457648672039351e-05, + "loss": 3.8179, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456810077288299e-05, + "loss": 3.8245, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455971482537247e-05, + "loss": 3.812, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551345256665685e-05, + "loss": 3.825, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542959309155165e-05, + "loss": 3.8016, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534573361644645e-05, + "loss": 3.8331, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8034, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8155, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.8208, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.8112, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44926763816995e-05, + "loss": 3.814, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.8157, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.8034, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.8, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445914897046116e-05, + "loss": 3.8171, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445076302295064e-05, + "loss": 3.8155, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444237707544012e-05, + "loss": 3.8032, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.8115, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442562155922281e-05, + "loss": 3.7979, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441723561171229e-05, + "loss": 3.8084, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440884966420177e-05, + "loss": 3.8142, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440046371669125e-05, + "loss": 3.8103, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439209414798446e-05, + "loss": 3.8224, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438370820047394e-05, + "loss": 3.8146, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.8258, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8005, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8123, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.8122, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.7949, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8168, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432502294670403e-05, + "loss": 3.8106, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.8148, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.8101, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.7957, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429149553546568e-05, + "loss": 3.8096, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8104, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8165, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.8101, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257984503031066e-05, + "loss": 3.8154, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.8155, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.7996, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.81, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224457091792715e-05, + "loss": 3.8006, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.811, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207685196771675e-05, + "loss": 3.8196, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.802, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190929680554364e-05, + "loss": 3.7966, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.7998, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.8079, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.8158, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415740226931602e-05, + "loss": 3.8001, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.7976, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.7964, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.811, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412387485807767e-05, + "loss": 3.7896, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.7992, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.8072, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.8022, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.7953, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.8097, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.7992, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.7977, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.8046, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.7999, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.8086, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031662193069414e-05, + "loss": 3.8058, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402330900316635e-05, + "loss": 3.804, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401492305565583e-05, + "loss": 3.7896, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400653710814531e-05, + "loss": 3.8, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399815116063479e-05, + "loss": 3.7972, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398976521312427e-05, + "loss": 3.7851, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398137926561375e-05, + "loss": 3.8018, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397299331810323e-05, + "loss": 3.7886, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396460737059271e-05, + "loss": 3.8013, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395623780188593e-05, + "loss": 3.7943, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394785185437541e-05, + "loss": 3.8009, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393946590686489e-05, + "loss": 3.7797, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393107995935437e-05, + "loss": 3.7953, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922710390647576e-05, + "loss": 3.7942, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914324443137056e-05, + "loss": 3.7995, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905938495626536e-05, + "loss": 3.7992, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897552548116016e-05, + "loss": 3.8019, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889182979409225e-05, + "loss": 3.7804, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880797031898705e-05, + "loss": 3.7997, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872411084388185e-05, + "loss": 3.8029, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864025136877665e-05, + "loss": 3.8037, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385565556817088e-05, + "loss": 3.8013, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384726962066036e-05, + "loss": 3.8027, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383888367314984e-05, + "loss": 3.7957, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830497725639314e-05, + "loss": 3.8043, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382212815693253e-05, + "loss": 3.7846, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381374220942201e-05, + "loss": 3.7962, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380535626191148e-05, + "loss": 3.7914, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379697031440096e-05, + "loss": 3.788, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378860074569418e-05, + "loss": 3.7943, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378021479818366e-05, + "loss": 3.7916, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377182885067313e-05, + "loss": 3.7933, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376344290316262e-05, + "loss": 3.7851, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755073334455835e-05, + "loss": 3.7999, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8866825103759766, + "eval_runtime": 304.6467, + "eval_samples_per_second": 1252.569, + "eval_steps_per_second": 39.144, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746687386945315e-05, + "loss": 3.7831, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373830143943479e-05, + "loss": 3.7785, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372991549192427e-05, + "loss": 3.793, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.792, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371315997570696e-05, + "loss": 3.7935, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370477402819644e-05, + "loss": 3.7796, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369638808068592e-05, + "loss": 3.7816, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368801851197913e-05, + "loss": 3.7814, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679632564468606e-05, + "loss": 3.7893, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367126299576182e-05, + "loss": 3.7955, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.36628770482513e-05, + "loss": 3.7802, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7939, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364610515323026e-05, + "loss": 3.7734, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363771920571974e-05, + "loss": 3.7789, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362933325820922e-05, + "loss": 3.7817, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.36209473106987e-05, + "loss": 3.7719, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361257774199191e-05, + "loss": 3.7774, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360419179448139e-05, + "loss": 3.7827, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359580584697087e-05, + "loss": 3.7727, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358741989946035e-05, + "loss": 3.8047, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357905033075356e-05, + "loss": 3.786, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357066438324304e-05, + "loss": 3.783, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562278435732526e-05, + "loss": 3.7848, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553892488222006e-05, + "loss": 3.7914, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545522919515215e-05, + "loss": 3.771, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537136972004695e-05, + "loss": 3.7842, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528751024494175e-05, + "loss": 3.7822, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520365076983655e-05, + "loss": 3.7761, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511995508276864e-05, + "loss": 3.7688, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503609560766344e-05, + "loss": 3.781, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495223613255824e-05, + "loss": 3.7926, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486837665745304e-05, + "loss": 3.783, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347846809703851e-05, + "loss": 3.7864, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347008214952799e-05, + "loss": 3.7812, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346169620201748e-05, + "loss": 3.7748, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345331025450696e-05, + "loss": 3.7836, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344494068580017e-05, + "loss": 3.7709, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343655473828965e-05, + "loss": 3.7709, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342816879077913e-05, + "loss": 3.7661, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341978284326861e-05, + "loss": 3.7717, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341141327456182e-05, + "loss": 3.7737, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.34030273270513e-05, + "loss": 3.7817, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339464137954078e-05, + "loss": 3.7753, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338625543203026e-05, + "loss": 3.7733, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337788586332347e-05, + "loss": 3.7797, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336949991581295e-05, + "loss": 3.7766, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361113968302434e-05, + "loss": 3.7762, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335274439959564e-05, + "loss": 3.7712, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334435845208512e-05, + "loss": 3.7568, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.7801, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.7694, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331920060955356e-05, + "loss": 3.7765, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331081466204304e-05, + "loss": 3.7623, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330242871453252e-05, + "loss": 3.7741, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294042767022e-05, + "loss": 3.7532, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328568957711894e-05, + "loss": 3.7813, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327730362960842e-05, + "loss": 3.7573, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.32689176820979e-05, + "loss": 3.7679, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326053173458739e-05, + "loss": 3.7724, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325214578707687e-05, + "loss": 3.7608, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324375983956635e-05, + "loss": 3.7627, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323537389205583e-05, + "loss": 3.7738, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322698794454531e-05, + "loss": 3.7521, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7514, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210232428327996e-05, + "loss": 3.769, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201846480817476e-05, + "loss": 3.7697, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.7542, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185090964600165e-05, + "loss": 3.7674, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176705017089645e-05, + "loss": 3.7475, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168319069579125e-05, + "loss": 3.7581, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159933122068605e-05, + "loss": 3.7679, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315156355336182e-05, + "loss": 3.7648, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.31431776058513e-05, + "loss": 3.7725, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313479165834078e-05, + "loss": 3.7681, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312640571083026e-05, + "loss": 3.7804, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311803614212347e-05, + "loss": 3.7509, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310965019461295e-05, + "loss": 3.7683, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310128062590616e-05, + "loss": 3.7688, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309289467839564e-05, + "loss": 3.746, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308450873088512e-05, + "loss": 3.7698, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.30761227833746e-05, + "loss": 3.7643, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306773683586408e-05, + "loss": 3.767, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305935088835356e-05, + "loss": 3.765, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7533, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042595372136254e-05, + "loss": 3.7565, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034209424625734e-05, + "loss": 3.7622, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025823477115214e-05, + "loss": 3.7732, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301743752960469e-05, + "loss": 3.7598, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7709, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000682013387383e-05, + "loss": 3.771, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299229606587686e-05, + "loss": 3.7552, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983910118366337e-05, + "loss": 3.7634, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7523, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296715460214903e-05, + "loss": 3.7637, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295876865463851e-05, + "loss": 3.7771, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295038270712799e-05, + "loss": 3.7532, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7547, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293362719091069e-05, + "loss": 3.7496, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292524124340016e-05, + "loss": 3.7645, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.772, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290848572718286e-05, + "loss": 3.7557, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290009977967234e-05, + "loss": 3.7533, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289171383216181e-05, + "loss": 3.7446, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.7666, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874958315944506e-05, + "loss": 3.7418, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286657236843398e-05, + "loss": 3.7575, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858186420923466e-05, + "loss": 3.7572, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849800473412946e-05, + "loss": 3.7592, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284143090470616e-05, + "loss": 3.7524, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833044957195635e-05, + "loss": 3.7607, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824659009685115e-05, + "loss": 3.7558, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816273062174595e-05, + "loss": 3.7513, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280790349346781e-05, + "loss": 3.76, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799517545957284e-05, + "loss": 3.756, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791131598446764e-05, + "loss": 3.7608, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782745650936244e-05, + "loss": 3.7638, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277439246103319e-05, + "loss": 3.7571, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276600651352267e-05, + "loss": 3.7478, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275762056601215e-05, + "loss": 3.7545, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749234618501636e-05, + "loss": 3.7557, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274084867099111e-05, + "loss": 3.7427, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273246272348059e-05, + "loss": 3.7552, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272407677597007e-05, + "loss": 3.7433, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271569082845955e-05, + "loss": 3.7561, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270732125975276e-05, + "loss": 3.7506, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269893531224224e-05, + "loss": 3.7541, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269054936473172e-05, + "loss": 3.7416, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.26821634172212e-05, + "loss": 3.7479, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267379384851441e-05, + "loss": 3.7523, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665407901003887e-05, + "loss": 3.7583, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265702195349337e-05, + "loss": 3.7482, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264863600598285e-05, + "loss": 3.7582, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264026643727606e-05, + "loss": 3.7422, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263188048976554e-05, + "loss": 3.7564, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262349454225502e-05, + "loss": 3.7601, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.26151085947445e-05, + "loss": 3.7591, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260673902603771e-05, + "loss": 3.7567, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259835307852719e-05, + "loss": 3.7635, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258996713101667e-05, + "loss": 3.7488, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258158118350615e-05, + "loss": 3.7628, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257321161479936e-05, + "loss": 3.7415, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256482566728884e-05, + "loss": 3.7522, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255643971977833e-05, + "loss": 3.7475, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254805377226781e-05, + "loss": 3.7456, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253970058236475e-05, + "loss": 3.7502, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253131463485423e-05, + "loss": 3.7446, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522928687343705e-05, + "loss": 3.7557, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2514542739833185e-05, + "loss": 3.734, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2506156792322665e-05, + "loss": 3.7591, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.871105670928955, + "eval_runtime": 305.9761, + "eval_samples_per_second": 1247.127, + "eval_steps_per_second": 38.974, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497770844812145e-05, + "loss": 3.738, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489384897301625e-05, + "loss": 3.736, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480998949791105e-05, + "loss": 3.7523, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472613002280585e-05, + "loss": 3.7497, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464227054770065e-05, + "loss": 3.7531, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455841107259545e-05, + "loss": 3.7378, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447455159749025e-05, + "loss": 3.735, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243908559104224e-05, + "loss": 3.7429, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243069964353172e-05, + "loss": 3.7466, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.24223136960212e-05, + "loss": 3.7531, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241392774851068e-05, + "loss": 3.7418, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240554180100016e-05, + "loss": 3.7474, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239717223229337e-05, + "loss": 3.7358, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238878628478285e-05, + "loss": 3.7362, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238040033727233e-05, + "loss": 3.7417, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237201438976181e-05, + "loss": 3.7323, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236364482105502e-05, + "loss": 3.7357, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.23552588735445e-05, + "loss": 3.7439, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234687292603398e-05, + "loss": 3.7318, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233848697852346e-05, + "loss": 3.7597, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330101031012945e-05, + "loss": 3.7469, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321731462306154e-05, + "loss": 3.7391, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313345514795634e-05, + "loss": 3.7424, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304959567285114e-05, + "loss": 3.7507, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229657361977459e-05, + "loss": 3.7295, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228818767226407e-05, + "loss": 3.7463, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227980172475355e-05, + "loss": 3.7379, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227141577724303e-05, + "loss": 3.7361, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226302982973251e-05, + "loss": 3.73, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254660261025716e-05, + "loss": 3.7391, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246274313515196e-05, + "loss": 3.75, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223788836600468e-05, + "loss": 3.7403, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222951879729789e-05, + "loss": 3.7485, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222113284978737e-05, + "loss": 3.7427, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221274690227685e-05, + "loss": 3.7318, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220437733357006e-05, + "loss": 3.7413, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219599138605954e-05, + "loss": 3.7319, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218760543854902e-05, + "loss": 3.7304, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.7262, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217083354352798e-05, + "loss": 3.7287, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216244759601746e-05, + "loss": 3.7349, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215406164850694e-05, + "loss": 3.7419, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214567570099642e-05, + "loss": 3.7347, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137306132289637e-05, + "loss": 3.733, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128920184779116e-05, + "loss": 3.7393, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120534237268596e-05, + "loss": 3.7341, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112148289758076e-05, + "loss": 3.739, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103795099855015e-05, + "loss": 3.7304, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095409152344495e-05, + "loss": 3.7123, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087023204833975e-05, + "loss": 3.7424, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078637257323454e-05, + "loss": 3.7274, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070251309812934e-05, + "loss": 3.7398, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061865362302414e-05, + "loss": 3.7257, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053495793595623e-05, + "loss": 3.7279, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045109846085103e-05, + "loss": 3.719, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203672389857459e-05, + "loss": 3.738, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202833795106407e-05, + "loss": 3.7209, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201995200355355e-05, + "loss": 3.7273, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201156605604303e-05, + "loss": 3.7374, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200318010853251e-05, + "loss": 3.7168, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199479416102199e-05, + "loss": 3.7207, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19864245923152e-05, + "loss": 3.7405, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197803864480468e-05, + "loss": 3.709, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196966907609789e-05, + "loss": 3.7144, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196128312858737e-05, + "loss": 3.7281, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7295, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7178, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.73, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192773933854529e-05, + "loss": 3.71, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919353391034775e-05, + "loss": 3.7169, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191096744352425e-05, + "loss": 3.7314, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902597874817464e-05, + "loss": 3.7243, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894211927306944e-05, + "loss": 3.7324, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885825979796424e-05, + "loss": 3.7305, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18774400322859e-05, + "loss": 3.7382, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186908684238284e-05, + "loss": 3.7167, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186070089487232e-05, + "loss": 3.7263, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7288, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7078, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7309, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182715710483024e-05, + "loss": 3.7266, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181877115731972e-05, + "loss": 3.7303, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.18103852098092e-05, + "loss": 3.7257, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.7159, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17936296935919e-05, + "loss": 3.7167, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178524374608137e-05, + "loss": 3.726, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177685779857085e-05, + "loss": 3.7282, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.7246, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760102282353546e-05, + "loss": 3.7314, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175171633484302e-05, + "loss": 3.7324, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7196, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734960818625715e-05, + "loss": 3.7239, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726574871115195e-05, + "loss": 3.7144, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718188923604675e-05, + "loss": 3.7313, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170981935489789e-05, + "loss": 3.7338, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170143340738737e-05, + "loss": 3.72, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693047459876844e-05, + "loss": 3.716, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684661512366324e-05, + "loss": 3.7102, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676275564855804e-05, + "loss": 3.7268, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667889617345284e-05, + "loss": 3.7332, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659503669834764e-05, + "loss": 3.7166, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651117722324244e-05, + "loss": 3.7172, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164274815361745e-05, + "loss": 3.7117, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163436220610693e-05, + "loss": 3.7261, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162597625859642e-05, + "loss": 3.7077, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161760668988963e-05, + "loss": 3.7203, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160922074237911e-05, + "loss": 3.7131, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160083479486859e-05, + "loss": 3.7264, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.15924652261618e-05, + "loss": 3.7148, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7222, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157569333114076e-05, + "loss": 3.7216, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156730738363024e-05, + "loss": 3.7124, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155892143611972e-05, + "loss": 3.725, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15505354886092e-05, + "loss": 3.7189, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154216591990241e-05, + "loss": 3.7238, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153377997239189e-05, + "loss": 3.7272, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254104036851e-05, + "loss": 3.714, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7197, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7128, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150025256115354e-05, + "loss": 3.7194, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149186661364302e-05, + "loss": 3.7145, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14834806661325e-05, + "loss": 3.715, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147509471862198e-05, + "loss": 3.7047, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146670877111146e-05, + "loss": 3.7188, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7113, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144995325489415e-05, + "loss": 3.7189, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144156730738363e-05, + "loss": 3.7034, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143318135987311e-05, + "loss": 3.7143, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.7114, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7264, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7143, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7217, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.706, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.722, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.722, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.724, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7201, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7245, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7128, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.726, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.7062, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7158, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7113, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7115, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290669388605465e-05, + "loss": 3.7121, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282283441094945e-05, + "loss": 3.7088, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273897493584425e-05, + "loss": 3.7196, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265511546073905e-05, + "loss": 3.6997, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257125598563384e-05, + "loss": 3.7275, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.86035418510437, + "eval_runtime": 302.9175, + "eval_samples_per_second": 1259.719, + "eval_steps_per_second": 39.367, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248739651052864e-05, + "loss": 3.7049, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.6978, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.7146, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1223598187325033e-05, + "loss": 3.7138, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215212239814513e-05, + "loss": 3.7119, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120684267110773e-05, + "loss": 3.7071, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119845672359721e-05, + "loss": 3.7027, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119007077608669e-05, + "loss": 3.7051, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118168482857617e-05, + "loss": 3.7125, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117331525986938e-05, + "loss": 3.7174, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7072, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115654336484834e-05, + "loss": 3.7098, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114815741733782e-05, + "loss": 3.7058, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.11397714698273e-05, + "loss": 3.6992, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113138552231678e-05, + "loss": 3.7042, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112299957480626e-05, + "loss": 3.6967, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111463000609947e-05, + "loss": 3.7037, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.708, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.6974, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7225, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081086216057394e-05, + "loss": 3.7156, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10727166473506e-05, + "loss": 3.7041, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106433069984008e-05, + "loss": 3.7096, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105594475232956e-05, + "loss": 3.7146, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104755880481904e-05, + "loss": 3.6951, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103918923611225e-05, + "loss": 3.7091, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.7046, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102241734109121e-05, + "loss": 3.7022, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014031393580685e-05, + "loss": 3.6929, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005645446070165e-05, + "loss": 3.7082, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997259498559645e-05, + "loss": 3.712, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7091, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098050398234234e-05, + "loss": 3.7154, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097211803483182e-05, + "loss": 3.7036, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.09637320873213e-05, + "loss": 3.6994, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095534613981078e-05, + "loss": 3.7098, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094697657110399e-05, + "loss": 3.7009, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093859062359347e-05, + "loss": 3.6904, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093020467608295e-05, + "loss": 3.6931, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092181872857243e-05, + "loss": 3.6962, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091343278106191e-05, + "loss": 3.7013, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090506321235512e-05, + "loss": 3.7059, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.08966772648446e-05, + "loss": 3.7034, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888291317334085e-05, + "loss": 3.6973, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879905369823565e-05, + "loss": 3.7061, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871519422313045e-05, + "loss": 3.704, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.0863133474802525e-05, + "loss": 3.7043, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.0854763906095734e-05, + "loss": 3.6967, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846377958585214e-05, + "loss": 3.6739, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0837992011074694e-05, + "loss": 3.7123, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829606063564174e-05, + "loss": 3.6946, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.0821220116053654e-05, + "loss": 3.7081, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812834168543134e-05, + "loss": 3.6904, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0804448221032614e-05, + "loss": 3.697, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796062273522094e-05, + "loss": 3.6848, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.07876927048153e-05, + "loss": 3.7004, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077930675730478e-05, + "loss": 3.6892, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077092080979427e-05, + "loss": 3.6932, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076253486228375e-05, + "loss": 3.7071, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075414891477323e-05, + "loss": 3.6875, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.07457629672627e-05, + "loss": 3.6851, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073739339855592e-05, + "loss": 3.7038, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.07290074510454e-05, + "loss": 3.6794, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072062150353488e-05, + "loss": 3.6803, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071223555602435e-05, + "loss": 3.6951, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070386598731757e-05, + "loss": 3.6958, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069548003980705e-05, + "loss": 3.6897, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068709409229652e-05, + "loss": 3.696, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067870814478601e-05, + "loss": 3.6742, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067032219727549e-05, + "loss": 3.6877, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.06619526285687e-05, + "loss": 3.6987, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653566681058176e-05, + "loss": 3.6926, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645180733547656e-05, + "loss": 3.7042, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636794786037136e-05, + "loss": 3.6964, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628408838526616e-05, + "loss": 3.7042, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620039269819825e-05, + "loss": 3.682, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611653322309305e-05, + "loss": 3.6981, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603267374798785e-05, + "loss": 3.6945, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594881427288265e-05, + "loss": 3.6805, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586495479777745e-05, + "loss": 3.6962, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578109532267225e-05, + "loss": 3.6959, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056973996356044e-05, + "loss": 3.6969, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056135401604992e-05, + "loss": 3.6995, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.05529680685394e-05, + "loss": 3.6822, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054458212102888e-05, + "loss": 3.6824, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053619617351836e-05, + "loss": 3.6941, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052781022600784e-05, + "loss": 3.6957, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051944065730105e-05, + "loss": 3.6947, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051105470979053e-05, + "loss": 3.6941, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050266876228001e-05, + "loss": 3.7002, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049428281476949e-05, + "loss": 3.6912, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048589686725897e-05, + "loss": 3.6892, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047752729855218e-05, + "loss": 3.6834, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046914135104166e-05, + "loss": 3.698, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046075540353114e-05, + "loss": 3.7006, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452369456020625e-05, + "loss": 3.69, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443999887313835e-05, + "loss": 3.6835, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435613939803314e-05, + "loss": 3.6806, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427227992292794e-05, + "loss": 3.6916, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418842044782274e-05, + "loss": 3.7039, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410456097271754e-05, + "loss": 3.683, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402070149761234e-05, + "loss": 3.6889, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039370058105444e-05, + "loss": 3.6829, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038531463354392e-05, + "loss": 3.6876, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.03769286860334e-05, + "loss": 3.6798, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036854273852288e-05, + "loss": 3.6916, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036015679101236e-05, + "loss": 3.6782, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035178722230558e-05, + "loss": 3.6946, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034340127479506e-05, + "loss": 3.6868, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033501532728454e-05, + "loss": 3.6892, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032662937977401e-05, + "loss": 3.6882, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031824343226349e-05, + "loss": 3.6888, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030985748475297e-05, + "loss": 3.6897, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030147153724245e-05, + "loss": 3.6869, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029308558973193e-05, + "loss": 3.6893, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028471602102514e-05, + "loss": 3.699, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027634645231836e-05, + "loss": 3.6843, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026796050480783e-05, + "loss": 3.6891, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025957455729732e-05, + "loss": 3.6821, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.02511886097868e-05, + "loss": 3.6853, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024280266227628e-05, + "loss": 3.6841, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234433093569486e-05, + "loss": 3.6849, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226047146058966e-05, + "loss": 3.6737, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217661198548446e-05, + "loss": 3.6861, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209275251037926e-05, + "loss": 3.6833, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200905682331135e-05, + "loss": 3.6858, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192519734820615e-05, + "loss": 3.6703, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184133787310095e-05, + "loss": 3.6874, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175747839799575e-05, + "loss": 3.6802, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167361892289055e-05, + "loss": 3.6927, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158975944778535e-05, + "loss": 3.6822, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150589997268015e-05, + "loss": 3.6895, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014222042856123e-05, + "loss": 3.6755, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013383448105071e-05, + "loss": 3.6941, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012544853354019e-05, + "loss": 3.6908, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011706258602967e-05, + "loss": 3.692, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010869301732288e-05, + "loss": 3.6913, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010030706981236e-05, + "loss": 3.6919, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009192112230184e-05, + "loss": 3.6839, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008353517479132e-05, + "loss": 3.6961, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007516560608453e-05, + "loss": 3.6771, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006677965857401e-05, + "loss": 3.687, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005839371106349e-05, + "loss": 3.6787, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005000776355297e-05, + "loss": 3.6852, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0041638194846184e-05, + "loss": 3.6766, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033252247335664e-05, + "loss": 3.6778, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024866299825144e-05, + "loss": 3.6845, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016480352314624e-05, + "loss": 3.6723, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008094404804104e-05, + "loss": 3.6964, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8531672954559326, + "eval_runtime": 303.0494, + "eval_samples_per_second": 1259.171, + "eval_steps_per_second": 39.35, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999972483609731e-05, + "loss": 3.6728, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999133888858679e-05, + "loss": 3.6735, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998295294107627e-05, + "loss": 3.6795, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997456699356575e-05, + "loss": 3.6853, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996619742485896e-05, + "loss": 3.6843, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995781147734844e-05, + "loss": 3.6737, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994942552983792e-05, + "loss": 3.6792, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994103958232741e-05, + "loss": 3.6764, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993265363481689e-05, + "loss": 3.6777, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.99242840661101e-05, + "loss": 3.6902, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991589811859958e-05, + "loss": 3.6731, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990751217108906e-05, + "loss": 3.6771, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989912622357854e-05, + "loss": 3.6745, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989075665487175e-05, + "loss": 3.6676, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882370707361227e-05, + "loss": 3.6778, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873984759850707e-05, + "loss": 3.667, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865598812340187e-05, + "loss": 3.673, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857212864829666e-05, + "loss": 3.6799, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848843296122876e-05, + "loss": 3.6649, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840457348612356e-05, + "loss": 3.6917, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983207140110184e-05, + "loss": 3.6885, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823685453591315e-05, + "loss": 3.6767, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815299506080795e-05, + "loss": 3.6756, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806913558570275e-05, + "loss": 3.6852, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979854398986349e-05, + "loss": 3.6729, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790158042352964e-05, + "loss": 3.6762, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781772094842444e-05, + "loss": 3.6757, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773386147331924e-05, + "loss": 3.6729, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765000199821404e-05, + "loss": 3.6697, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756614252310884e-05, + "loss": 3.674, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748228304800364e-05, + "loss": 3.6808, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739842357289844e-05, + "loss": 3.6848, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973148916738679e-05, + "loss": 3.6823, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972310321987627e-05, + "loss": 3.6764, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971471727236575e-05, + "loss": 3.6685, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970633132485523e-05, + "loss": 3.6807, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969796175614844e-05, + "loss": 3.6734, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968957580863792e-05, + "loss": 3.6637, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.96811898611274e-05, + "loss": 3.666, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967280391361688e-05, + "loss": 3.6641, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966441796610636e-05, + "loss": 3.6692, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965603201859584e-05, + "loss": 3.6768, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964766244988905e-05, + "loss": 3.6788, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639276502378534e-05, + "loss": 3.6716, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630890554868014e-05, + "loss": 3.6705, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622504607357494e-05, + "loss": 3.6755, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614118659846974e-05, + "loss": 3.6727, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960574909114018e-05, + "loss": 3.6727, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959736314362966e-05, + "loss": 3.6461, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958897719611914e-05, + "loss": 3.6824, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958059124860862e-05, + "loss": 3.6655, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957222167990183e-05, + "loss": 3.6798, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956383573239131e-05, + "loss": 3.6631, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955544978488079e-05, + "loss": 3.6662, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954706383737027e-05, + "loss": 3.6576, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953869426866349e-05, + "loss": 3.6729, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953030832115297e-05, + "loss": 3.6629, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952192237364245e-05, + "loss": 3.6634, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951353642613193e-05, + "loss": 3.676, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950515047862141e-05, + "loss": 3.6618, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949676453111089e-05, + "loss": 3.6537, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488394962404096e-05, + "loss": 3.6781, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480009014893576e-05, + "loss": 3.6514, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471623067383056e-05, + "loss": 3.6491, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463237119872536e-05, + "loss": 3.6688, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454867551165745e-05, + "loss": 3.6661, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446481603655225e-05, + "loss": 3.6598, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438095656144705e-05, + "loss": 3.666, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429709708634185e-05, + "loss": 3.6481, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.94213401399274e-05, + "loss": 3.6578, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941295419241688e-05, + "loss": 3.67, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940456824490636e-05, + "loss": 3.6618, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939618229739584e-05, + "loss": 3.676, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938779634988532e-05, + "loss": 3.6648, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937942678117853e-05, + "loss": 3.677, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937104083366801e-05, + "loss": 3.6543, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936265488615749e-05, + "loss": 3.6714, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935426893864697e-05, + "loss": 3.6596, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934588299113644e-05, + "loss": 3.655, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933751342242966e-05, + "loss": 3.6672, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932912747491914e-05, + "loss": 3.6725, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320741527408625e-05, + "loss": 3.6663, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.93123555798981e-05, + "loss": 3.6728, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930396963238758e-05, + "loss": 3.6508, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295600063680794e-05, + "loss": 3.6553, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287214116170274e-05, + "loss": 3.6666, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927882816865975e-05, + "loss": 3.6668, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927044222114923e-05, + "loss": 3.6662, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926205627363871e-05, + "loss": 3.6693, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925368670493192e-05, + "loss": 3.6667, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245300757421397e-05, + "loss": 3.6676, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9236914809910877e-05, + "loss": 3.662, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922852886240036e-05, + "loss": 3.6573, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922014291488984e-05, + "loss": 3.6723, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921177334618305e-05, + "loss": 3.6689, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920338739867253e-05, + "loss": 3.6647, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919500145116201e-05, + "loss": 3.6579, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918661550365149e-05, + "loss": 3.6503, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.91782459349447e-05, + "loss": 3.6622, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916985998743418e-05, + "loss": 3.6745, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916147403992366e-05, + "loss": 3.6607, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915308809241314e-05, + "loss": 3.6619, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914471852370635e-05, + "loss": 3.6535, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913633257619583e-05, + "loss": 3.6571, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912794662868532e-05, + "loss": 3.6573, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.91195606811748e-05, + "loss": 3.6583, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911117473366428e-05, + "loss": 3.6514, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102805164957486e-05, + "loss": 3.669, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094419217446966e-05, + "loss": 3.6628, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086033269936446e-05, + "loss": 3.6594, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077647322425926e-05, + "loss": 3.6547, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069261374915406e-05, + "loss": 3.6633, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060891806208615e-05, + "loss": 3.6634, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052505858698095e-05, + "loss": 3.6607, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044119911187575e-05, + "loss": 3.6636, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035733963677055e-05, + "loss": 3.6702, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027364394970264e-05, + "loss": 3.6539, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901899482626348e-05, + "loss": 3.6645, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901060887875296e-05, + "loss": 3.6518, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900222293124244e-05, + "loss": 3.6599, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899383698373192e-05, + "loss": 3.6571, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.89854510362214e-05, + "loss": 3.6532, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897706508871088e-05, + "loss": 3.6504, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896867914120036e-05, + "loss": 3.6594, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896029319368984e-05, + "loss": 3.6584, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895192362498305e-05, + "loss": 3.6598, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894353767747253e-05, + "loss": 3.6453, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893515172996201e-05, + "loss": 3.6574, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892676578245149e-05, + "loss": 3.6529, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918396213744704e-05, + "loss": 3.6662, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910010266234184e-05, + "loss": 3.6578, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901624318723664e-05, + "loss": 3.659, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893238371213144e-05, + "loss": 3.6492, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884852423702624e-05, + "loss": 3.6681, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887648285499583e-05, + "loss": 3.6643, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886809690748531e-05, + "loss": 3.6654, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885971095997479e-05, + "loss": 3.6638, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885132501246427e-05, + "loss": 3.6662, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884295544375748e-05, + "loss": 3.6574, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883456949624696e-05, + "loss": 3.6674, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882618354873644e-05, + "loss": 3.6488, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881779760122592e-05, + "loss": 3.6611, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880942803251914e-05, + "loss": 3.6548, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880104208500862e-05, + "loss": 3.657, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.87926561374981e-05, + "loss": 3.6489, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878427018998758e-05, + "loss": 3.6528, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877590062128079e-05, + "loss": 3.6598, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876751467377027e-05, + "loss": 3.6519, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875912872625975e-05, + "loss": 3.6674, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.848881959915161, + "eval_runtime": 303.3404, + "eval_samples_per_second": 1257.963, + "eval_steps_per_second": 39.312, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875074277874923e-05, + "loss": 3.6433, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742373210042436e-05, + "loss": 3.6469, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733987262531916e-05, + "loss": 3.6499, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725601315021396e-05, + "loss": 3.6636, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717215367510876e-05, + "loss": 3.6574, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708829420000356e-05, + "loss": 3.6459, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870045985129357e-05, + "loss": 3.6535, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869207390378305e-05, + "loss": 3.6483, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683687956272525e-05, + "loss": 3.65, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675302008762005e-05, + "loss": 3.6674, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866693244005522e-05, + "loss": 3.6477, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86585464925447e-05, + "loss": 3.6486, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650160545034174e-05, + "loss": 3.6579, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641774597523654e-05, + "loss": 3.6367, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633388650013133e-05, + "loss": 3.648, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862501908130635e-05, + "loss": 3.6407, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861663313379583e-05, + "loss": 3.6499, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860824718628531e-05, + "loss": 3.6519, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859986123877479e-05, + "loss": 3.6387, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591491670068e-05, + "loss": 3.663, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858310572255748e-05, + "loss": 3.6612, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857471977504696e-05, + "loss": 3.6546, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856633382753644e-05, + "loss": 3.6542, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855794788002592e-05, + "loss": 3.6518, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854957831131913e-05, + "loss": 3.6496, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854119236380861e-05, + "loss": 3.6453, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853280641629809e-05, + "loss": 3.6525, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852442046878757e-05, + "loss": 3.651, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851603452127705e-05, + "loss": 3.6408, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8507648573766534e-05, + "loss": 3.6475, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499262626256014e-05, + "loss": 3.6525, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849089305754922e-05, + "loss": 3.6617, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84825071100387e-05, + "loss": 3.6577, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847412116252818e-05, + "loss": 3.6527, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846573521501766e-05, + "loss": 3.6425, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845736564631087e-05, + "loss": 3.6489, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844897969880035e-05, + "loss": 3.6537, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844059375128983e-05, + "loss": 3.6409, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843220780377931e-05, + "loss": 3.6389, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842383823507252e-05, + "loss": 3.639, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415452287562e-05, + "loss": 3.6461, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840706634005148e-05, + "loss": 3.6464, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839868039254097e-05, + "loss": 3.6507, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839029444503045e-05, + "loss": 3.6478, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838190849751993e-05, + "loss": 3.6457, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837352255000941e-05, + "loss": 3.6469, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365152981302616e-05, + "loss": 3.6454, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356767033792096e-05, + "loss": 3.6527, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348381086281576e-05, + "loss": 3.6182, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339995138771056e-05, + "loss": 3.6525, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331625570064265e-05, + "loss": 3.6421, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8323239622553745e-05, + "loss": 3.6575, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314853675043225e-05, + "loss": 3.6393, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306467727532705e-05, + "loss": 3.6411, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829809815882592e-05, + "loss": 3.6291, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.82897122113154e-05, + "loss": 3.6459, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828132626380488e-05, + "loss": 3.6423, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827294031629436e-05, + "loss": 3.6362, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826457074758757e-05, + "loss": 3.6525, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825618480007705e-05, + "loss": 3.6416, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824779885256653e-05, + "loss": 3.6237, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823941290505601e-05, + "loss": 3.6526, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823102695754548e-05, + "loss": 3.63, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.82226573888387e-05, + "loss": 3.6263, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821427144132818e-05, + "loss": 3.6427, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820588549381766e-05, + "loss": 3.6416, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819749954630714e-05, + "loss": 3.6307, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818911359879662e-05, + "loss": 3.6467, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180744030089835e-05, + "loss": 3.6264, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817235808257931e-05, + "loss": 3.6302, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816397213506879e-05, + "loss": 3.6458, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815558618755827e-05, + "loss": 3.6352, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8147216618851484e-05, + "loss": 3.653, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813883067134096e-05, + "loss": 3.6379, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813044472383044e-05, + "loss": 3.6538, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812205877631992e-05, + "loss": 3.6335, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.8113689207613126e-05, + "loss": 3.6499, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810530326010261e-05, + "loss": 3.6334, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809691731259209e-05, + "loss": 3.6339, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808853136508157e-05, + "loss": 3.6412, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808016179637478e-05, + "loss": 3.6429, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807177584886426e-05, + "loss": 3.6426, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806338990135374e-05, + "loss": 3.6499, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805500395384322e-05, + "loss": 3.6251, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.80466180063327e-05, + "loss": 3.6298, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803824843762591e-05, + "loss": 3.6421, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802986249011539e-05, + "loss": 3.6472, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802147654260487e-05, + "loss": 3.6391, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801309059509435e-05, + "loss": 3.646, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004721026387566e-05, + "loss": 3.6413, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996335078877046e-05, + "loss": 3.6433, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987949131366526e-05, + "loss": 3.6399, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979563183856006e-05, + "loss": 3.6314, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971177236345486e-05, + "loss": 3.6446, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962807667638695e-05, + "loss": 3.6465, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954421720128175e-05, + "loss": 3.6382, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946035772617655e-05, + "loss": 3.6359, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937649825107135e-05, + "loss": 3.6229, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929280256400344e-05, + "loss": 3.6397, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920894308889824e-05, + "loss": 3.6493, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912508361379304e-05, + "loss": 3.6368, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904122413868784e-05, + "loss": 3.6393, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895736466358264e-05, + "loss": 3.63, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788736689765148e-05, + "loss": 3.6305, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787898095014096e-05, + "loss": 3.6356, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787059500263044e-05, + "loss": 3.6326, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786220905511992e-05, + "loss": 3.6281, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785383948641313e-05, + "loss": 3.6443, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784545353890261e-05, + "loss": 3.6413, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783706759139209e-05, + "loss": 3.6289, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782868164388157e-05, + "loss": 3.6353, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.6342, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.6435, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.6328, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779515423264322e-05, + "loss": 3.6421, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786784663936433e-05, + "loss": 3.6447, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778398716425913e-05, + "loss": 3.6297, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777002914771912e-05, + "loss": 3.6393, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.77616432002086e-05, + "loss": 3.6294, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775325725269808e-05, + "loss": 3.6355, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774487130518756e-05, + "loss": 3.6359, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773648535767704e-05, + "loss": 3.6276, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.6252, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6381, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6348, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770295794643869e-05, + "loss": 3.6376, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769457199892817e-05, + "loss": 3.62, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6306, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6289, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766943053520035e-05, + "loss": 3.6439, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6358, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6355, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764427269266879e-05, + "loss": 3.6241, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763588674515827e-05, + "loss": 3.6479, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627517176451476e-05, + "loss": 3.6371, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619131228940956e-05, + "loss": 3.6438, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610745281430436e-05, + "loss": 3.6364, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760235933391991e-05, + "loss": 3.6411, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593989765213125e-05, + "loss": 3.635, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585603817702605e-05, + "loss": 3.6481, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757721787019209e-05, + "loss": 3.6228, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.64, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756046235397478e-05, + "loss": 3.6287, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755207640646426e-05, + "loss": 3.6327, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543690458953734e-05, + "loss": 3.6277, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535304511443214e-05, + "loss": 3.6297, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752693494273643e-05, + "loss": 3.6319, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751854899522591e-05, + "loss": 3.63, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751016304771538e-05, + "loss": 3.6392, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.846484661102295, + "eval_runtime": 303.3033, + "eval_samples_per_second": 1258.117, + "eval_steps_per_second": 39.317, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750177710020486e-05, + "loss": 3.6203, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749339115269434e-05, + "loss": 3.6225, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748500520518383e-05, + "loss": 3.6244, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747661925767331e-05, + "loss": 3.6396, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746824968896652e-05, + "loss": 3.6371, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459863741456e-05, + "loss": 3.6209, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745147779394548e-05, + "loss": 3.6297, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744309184643496e-05, + "loss": 3.6262, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743470589892444e-05, + "loss": 3.6326, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742633633021765e-05, + "loss": 3.6406, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741795038270713e-05, + "loss": 3.6254, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740956443519661e-05, + "loss": 3.6272, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740117848768609e-05, + "loss": 3.6329, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392808918979296e-05, + "loss": 3.6153, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738442297146878e-05, + "loss": 3.6242, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737603702395826e-05, + "loss": 3.6158, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736765107644774e-05, + "loss": 3.6269, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735926512893722e-05, + "loss": 3.6292, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735089556023043e-05, + "loss": 3.616, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734250961271991e-05, + "loss": 3.6366, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733412366520939e-05, + "loss": 3.64, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732573771769887e-05, + "loss": 3.6297, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731736814899208e-05, + "loss": 3.6316, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730898220148156e-05, + "loss": 3.6302, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730059625397104e-05, + "loss": 3.6299, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729221030646052e-05, + "loss": 3.6229, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728382435895e-05, + "loss": 3.6268, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727545479024322e-05, + "loss": 3.6319, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.72670688427327e-05, + "loss": 3.6177, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258682895222177e-05, + "loss": 3.6239, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250296947711657e-05, + "loss": 3.6304, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241927379004866e-05, + "loss": 3.6316, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233541431494346e-05, + "loss": 3.6384, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225155483983826e-05, + "loss": 3.63, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216769536473306e-05, + "loss": 3.6192, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208399967766515e-05, + "loss": 3.6244, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200014020255995e-05, + "loss": 3.6293, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191628072745475e-05, + "loss": 3.6148, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183242125234954e-05, + "loss": 3.6173, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717487255652817e-05, + "loss": 3.6186, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716648660901765e-05, + "loss": 3.6182, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715810066150713e-05, + "loss": 3.6262, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714971471399661e-05, + "loss": 3.6277, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714132876648609e-05, + "loss": 3.6272, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.71329591977793e-05, + "loss": 3.6177, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712457325026878e-05, + "loss": 3.6294, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711618730275826e-05, + "loss": 3.6226, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710780135524774e-05, + "loss": 3.6288, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709943178654095e-05, + "loss": 3.5998, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709104583903043e-05, + "loss": 3.6267, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708265989151991e-05, + "loss": 3.6207, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707427394400939e-05, + "loss": 3.6322, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065904375302604e-05, + "loss": 3.6168, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057518427792084e-05, + "loss": 3.6191, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7049132480281564e-05, + "loss": 3.6117, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040746532771044e-05, + "loss": 3.6201, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703237696406425e-05, + "loss": 3.6262, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702399101655373e-05, + "loss": 3.6081, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701560506904321e-05, + "loss": 3.6312, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700721912153269e-05, + "loss": 3.619, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.69988495528259e-05, + "loss": 3.5982, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699046360531538e-05, + "loss": 3.6315, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698207765780486e-05, + "loss": 3.6098, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697369171029434e-05, + "loss": 3.6007, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696532214158756e-05, + "loss": 3.6225, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695693619407704e-05, + "loss": 3.6176, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694855024656652e-05, + "loss": 3.6058, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694016429905599e-05, + "loss": 3.6261, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693179473034921e-05, + "loss": 3.6029, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923408782838687e-05, + "loss": 3.6073, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915022835328167e-05, + "loss": 3.6214, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690663688781764e-05, + "loss": 3.6175, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898267319110856e-05, + "loss": 3.6263, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889881371600336e-05, + "loss": 3.6187, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881495424089815e-05, + "loss": 3.6302, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873109476579295e-05, + "loss": 3.6122, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686473990787251e-05, + "loss": 3.6301, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685635396036199e-05, + "loss": 3.6073, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847968012851464e-05, + "loss": 3.6114, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839582065340944e-05, + "loss": 3.6191, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683121249663416e-05, + "loss": 3.6183, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682282654912364e-05, + "loss": 3.6243, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814440601613113e-05, + "loss": 3.6286, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680605465410259e-05, + "loss": 3.6092, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679766870659207e-05, + "loss": 3.6079, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678929913788529e-05, + "loss": 3.6158, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678091319037477e-05, + "loss": 3.6278, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677252724286425e-05, + "loss": 3.6139, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676414129535373e-05, + "loss": 3.6251, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675577172664694e-05, + "loss": 3.6242, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674738577913642e-05, + "loss": 3.6203, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.67389998316259e-05, + "loss": 3.6163, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673061388411538e-05, + "loss": 3.6106, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672224431540859e-05, + "loss": 3.6219, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671385836789807e-05, + "loss": 3.6216, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670547242038755e-05, + "loss": 3.6209, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669708647287703e-05, + "loss": 3.6111, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6688716904170236e-05, + "loss": 3.6023, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668033095665972e-05, + "loss": 3.6163, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66719450091492e-05, + "loss": 3.6256, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666355906163868e-05, + "loss": 3.6156, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665518949293189e-05, + "loss": 3.6162, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664680354542137e-05, + "loss": 3.6103, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663841759791085e-05, + "loss": 3.6081, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663003165040033e-05, + "loss": 3.6185, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662166208169354e-05, + "loss": 3.6077, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661327613418302e-05, + "loss": 3.6093, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.66048901866725e-05, + "loss": 3.62, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659650423916198e-05, + "loss": 3.6197, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658813467045519e-05, + "loss": 3.6109, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579748722944676e-05, + "loss": 3.6108, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571362775434156e-05, + "loss": 3.609, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562976827923636e-05, + "loss": 3.6243, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6554607259216845e-05, + "loss": 3.6116, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6546221311706325e-05, + "loss": 3.6225, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537835364195805e-05, + "loss": 3.6211, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6529449416685285e-05, + "loss": 3.6115, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521079847978494e-05, + "loss": 3.614, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512693900467974e-05, + "loss": 3.6125, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504307952957454e-05, + "loss": 3.6122, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495922005446934e-05, + "loss": 3.6202, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487536057936414e-05, + "loss": 3.6026, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479150110425894e-05, + "loss": 3.6045, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470764162915374e-05, + "loss": 3.6153, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646237821540486e-05, + "loss": 3.614, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645400864669807e-05, + "loss": 3.6114, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644562269918755e-05, + "loss": 3.6054, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643723675167703e-05, + "loss": 3.6118, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642885080416651e-05, + "loss": 3.604, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642048123545972e-05, + "loss": 3.6242, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.64120952879492e-05, + "loss": 3.6113, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640370934043868e-05, + "loss": 3.6172, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639532339292816e-05, + "loss": 3.6031, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638693744541764e-05, + "loss": 3.6252, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637856787671085e-05, + "loss": 3.6144, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637018192920033e-05, + "loss": 3.6231, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361795981689815e-05, + "loss": 3.6191, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6353410034179295e-05, + "loss": 3.6176, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6345040465472504e-05, + "loss": 3.6126, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336654517961984e-05, + "loss": 3.6298, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328268570451464e-05, + "loss": 3.6022, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319882622940944e-05, + "loss": 3.6159, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631151305423415e-05, + "loss": 3.6097, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630312710672363e-05, + "loss": 3.6115, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629474115921311e-05, + "loss": 3.6048, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628635521170259e-05, + "loss": 3.609, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.62779856429958e-05, + "loss": 3.608, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626959969548528e-05, + "loss": 3.6153, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626121374797477e-05, + "loss": 3.6147, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8449618816375732, + "eval_runtime": 304.7998, + "eval_samples_per_second": 1251.94, + "eval_steps_per_second": 39.124, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625282780046425e-05, + "loss": 3.6028, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624444185295372e-05, + "loss": 3.6004, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62360559054432e-05, + "loss": 3.6046, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622766995793268e-05, + "loss": 3.6186, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621930038922589e-05, + "loss": 3.6157, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621091444171537e-05, + "loss": 3.602, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620252849420485e-05, + "loss": 3.6085, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619414254669433e-05, + "loss": 3.6041, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618575659918381e-05, + "loss": 3.6093, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617738703047702e-05, + "loss": 3.6144, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169001082966506e-05, + "loss": 3.6104, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160615135455986e-05, + "loss": 3.6044, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152229187945466e-05, + "loss": 3.6165, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143859619238675e-05, + "loss": 3.5939, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135473671728155e-05, + "loss": 3.6036, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6127087724217635e-05, + "loss": 3.5927, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118701776707115e-05, + "loss": 3.6106, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110332208000324e-05, + "loss": 3.6119, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101946260489804e-05, + "loss": 3.5927, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6093560312979284e-05, + "loss": 3.6141, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6085174365468764e-05, + "loss": 3.6218, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607680479676197e-05, + "loss": 3.6079, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606841884925145e-05, + "loss": 3.6116, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.606003290174094e-05, + "loss": 3.6107, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605164695423042e-05, + "loss": 3.6095, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604327738552363e-05, + "loss": 3.6042, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603489143801311e-05, + "loss": 3.6008, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602650549050259e-05, + "loss": 3.6091, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601811954299207e-05, + "loss": 3.5969, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600974997428528e-05, + "loss": 3.6053, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600136402677476e-05, + "loss": 3.6107, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599297807926424e-05, + "loss": 3.6132, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598459213175372e-05, + "loss": 3.6097, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597622256304693e-05, + "loss": 3.6156, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596783661553641e-05, + "loss": 3.5963, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595945066802589e-05, + "loss": 3.6057, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595106472051537e-05, + "loss": 3.611, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594269515180858e-05, + "loss": 3.5907, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593430920429806e-05, + "loss": 3.5998, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592592325678754e-05, + "loss": 3.5984, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591753730927702e-05, + "loss": 3.596, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.59091513617665e-05, + "loss": 3.6044, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590078179305971e-05, + "loss": 3.6096, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589239584554919e-05, + "loss": 3.6061, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588400989803867e-05, + "loss": 3.602, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587562395052815e-05, + "loss": 3.6071, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586725438182136e-05, + "loss": 3.6, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585886843431085e-05, + "loss": 3.6077, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585048248680033e-05, + "loss": 3.5839, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584209653928981e-05, + "loss": 3.6063, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583371059177929e-05, + "loss": 3.5977, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5825341023072496e-05, + "loss": 3.6136, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.5816955075561976e-05, + "loss": 3.5956, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5808569128051456e-05, + "loss": 3.5941, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5800183180540936e-05, + "loss": 3.5918, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.5791813611834145e-05, + "loss": 3.6018, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.5783427664323625e-05, + "loss": 3.6069, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5775041716813105e-05, + "loss": 3.5868, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766655769302585e-05, + "loss": 3.6111, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.57582862005958e-05, + "loss": 3.6013, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574990025308528e-05, + "loss": 3.576, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574151430557476e-05, + "loss": 3.6084, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573312835806424e-05, + "loss": 3.589, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572475878935745e-05, + "loss": 3.5842, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571637284184693e-05, + "loss": 3.598, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.570798689433641e-05, + "loss": 3.5997, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.569960094682589e-05, + "loss": 3.5911, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.56912313781191e-05, + "loss": 3.6072, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568284543060858e-05, + "loss": 3.5791, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567445948309806e-05, + "loss": 3.5877, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566607353558754e-05, + "loss": 3.6033, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565768758807702e-05, + "loss": 3.6013, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.5649318019370234e-05, + "loss": 3.6037, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640932071859714e-05, + "loss": 3.5996, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632546124349194e-05, + "loss": 3.6057, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5624160176838674e-05, + "loss": 3.5919, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561579060813188e-05, + "loss": 3.6086, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560740466062136e-05, + "loss": 3.5891, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559901871311084e-05, + "loss": 3.5893, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559063276560032e-05, + "loss": 3.595, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558226319689353e-05, + "loss": 3.6018, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557387724938301e-05, + "loss": 3.6029, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556549130187249e-05, + "loss": 3.6075, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555710535436197e-05, + "loss": 3.5893, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554873578565519e-05, + "loss": 3.584, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554034983814467e-05, + "loss": 3.5985, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553196389063415e-05, + "loss": 3.6098, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552357794312362e-05, + "loss": 3.5941, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551520837441684e-05, + "loss": 3.6049, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550682242690632e-05, + "loss": 3.6057, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.54984364793958e-05, + "loss": 3.5986, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.549005053188527e-05, + "loss": 3.5963, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548166458437475e-05, + "loss": 3.5895, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473295015667966e-05, + "loss": 3.6045, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464909068157446e-05, + "loss": 3.6032, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456523120646926e-05, + "loss": 3.5993, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5448137173136406e-05, + "loss": 3.5942, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543976760442962e-05, + "loss": 3.5824, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431381656919095e-05, + "loss": 3.5959, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5422995709408575e-05, + "loss": 3.6049, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5414609761898055e-05, + "loss": 3.5945, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540624019319127e-05, + "loss": 3.5986, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397854245680744e-05, + "loss": 3.5893, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389468298170224e-05, + "loss": 3.5903, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5381082350659704e-05, + "loss": 3.596, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537271278195291e-05, + "loss": 3.5931, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.53643268344424e-05, + "loss": 3.5875, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535594088693188e-05, + "loss": 3.5988, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534755493942136e-05, + "loss": 3.598, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533918537071457e-05, + "loss": 3.5903, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533079942320405e-05, + "loss": 3.5948, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532241347569353e-05, + "loss": 3.5882, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531402752818301e-05, + "loss": 3.6041, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530564158067249e-05, + "loss": 3.5919, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.52972720119657e-05, + "loss": 3.6018, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528888606445518e-05, + "loss": 3.6003, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528050011694466e-05, + "loss": 3.5929, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5272130548237866e-05, + "loss": 3.5965, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526374460072735e-05, + "loss": 3.5917, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525535865321683e-05, + "loss": 3.5921, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524697270570631e-05, + "loss": 3.5981, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523858675819579e-05, + "loss": 3.5848, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.523020081068527e-05, + "loss": 3.5865, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522181486317475e-05, + "loss": 3.5946, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521342891566423e-05, + "loss": 3.5916, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520505934695744e-05, + "loss": 3.5935, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519667339944692e-05, + "loss": 3.5863, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.51882874519364e-05, + "loss": 3.5889, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517990150442588e-05, + "loss": 3.5878, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517153193571909e-05, + "loss": 3.6058, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516314598820857e-05, + "loss": 3.59, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515476004069805e-05, + "loss": 3.5994, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514637409318753e-05, + "loss": 3.583, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513800452448075e-05, + "loss": 3.6007, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512961857697023e-05, + "loss": 3.5962, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5121232629459707e-05, + "loss": 3.6007, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5112846681949187e-05, + "loss": 3.6017, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104477113242396e-05, + "loss": 3.5965, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5096091165731876e-05, + "loss": 3.5973, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087705218221356e-05, + "loss": 3.6029, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079319270710836e-05, + "loss": 3.5883, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070949702004045e-05, + "loss": 3.5957, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062563754493525e-05, + "loss": 3.5921, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5054177806983005e-05, + "loss": 3.5909, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045791859472484e-05, + "loss": 3.5854, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.50374222907657e-05, + "loss": 3.594, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502903634325518e-05, + "loss": 3.5872, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502065039574466e-05, + "loss": 3.5919, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501226444823414e-05, + "loss": 3.5948, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8441388607025146, + "eval_runtime": 318.1415, + "eval_samples_per_second": 1199.438, + "eval_steps_per_second": 37.483, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500387850072362e-05, + "loss": 3.5925, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499550893201683e-05, + "loss": 3.5782, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498712298450631e-05, + "loss": 3.5858, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497873703699579e-05, + "loss": 3.5974, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497035108948527e-05, + "loss": 3.593, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496198152077848e-05, + "loss": 3.5854, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495359557326796e-05, + "loss": 3.5943, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494520962575744e-05, + "loss": 3.5841, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4936823678246925e-05, + "loss": 3.5871, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4928454109540134e-05, + "loss": 3.5932, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4920068162029614e-05, + "loss": 3.5964, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4911682214519094e-05, + "loss": 3.5824, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903296267008574e-05, + "loss": 3.5965, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489492669830178e-05, + "loss": 3.5704, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488654075079126e-05, + "loss": 3.5851, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487815480328074e-05, + "loss": 3.5765, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486976885577022e-05, + "loss": 3.5877, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486139928706343e-05, + "loss": 3.5922, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485301333955291e-05, + "loss": 3.574, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484462739204239e-05, + "loss": 3.5918, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483624144453188e-05, + "loss": 3.6026, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482787187582509e-05, + "loss": 3.5882, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481948592831457e-05, + "loss": 3.5927, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481109998080405e-05, + "loss": 3.5917, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480271403329352e-05, + "loss": 3.5919, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.4794344464586737e-05, + "loss": 3.5855, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.4785958517076217e-05, + "loss": 3.5815, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777572569565697e-05, + "loss": 3.5937, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476918662205517e-05, + "loss": 3.5802, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476080067454465e-05, + "loss": 3.5854, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475241472703413e-05, + "loss": 3.5962, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4744045158327345e-05, + "loss": 3.5921, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735659210816825e-05, + "loss": 3.5886, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727273263306305e-05, + "loss": 3.5993, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718887315795785e-05, + "loss": 3.5806, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710517747088994e-05, + "loss": 3.5872, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4702131799578474e-05, + "loss": 3.5904, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693745852067954e-05, + "loss": 3.5741, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685359904557434e-05, + "loss": 3.5818, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4676990335850643e-05, + "loss": 3.5803, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466860438834012e-05, + "loss": 3.5754, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.46602184408296e-05, + "loss": 3.5851, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465183249331908e-05, + "loss": 3.5921, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464344654580857e-05, + "loss": 3.5873, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463507697710178e-05, + "loss": 3.5827, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462669102959126e-05, + "loss": 3.5903, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461830508208074e-05, + "loss": 3.5784, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460991913457022e-05, + "loss": 3.5879, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.46015331870597e-05, + "loss": 3.5699, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459316361835291e-05, + "loss": 3.5839, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458477767084239e-05, + "loss": 3.578, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457639172333187e-05, + "loss": 3.5953, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456800577582135e-05, + "loss": 3.5788, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455963620711456e-05, + "loss": 3.5745, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455125025960404e-05, + "loss": 3.5743, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454286431209352e-05, + "loss": 3.5812, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534478364583004e-05, + "loss": 3.5918, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452610879587621e-05, + "loss": 3.5654, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451772284836569e-05, + "loss": 3.5954, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450933690085517e-05, + "loss": 3.5814, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450095095334465e-05, + "loss": 3.5596, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449258138463786e-05, + "loss": 3.5902, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448419543712734e-05, + "loss": 3.568, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447580948961682e-05, + "loss": 3.5648, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.44674235421063e-05, + "loss": 3.5755, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445905397339951e-05, + "loss": 3.5834, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445066802588899e-05, + "loss": 3.5773, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444228207837847e-05, + "loss": 3.5798, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443389613086796e-05, + "loss": 3.5644, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4425526562161166e-05, + "loss": 3.5687, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4417140614650646e-05, + "loss": 3.582, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408754667140126e-05, + "loss": 3.5855, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400368719629606e-05, + "loss": 3.5868, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4391999150922815e-05, + "loss": 3.5801, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.4383613203412295e-05, + "loss": 3.5901, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375227255901775e-05, + "loss": 3.5748, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4366841308391255e-05, + "loss": 3.5856, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358471739684464e-05, + "loss": 3.5753, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4350085792173944e-05, + "loss": 3.572, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4341699844663424e-05, + "loss": 3.58, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433331389715291e-05, + "loss": 3.5759, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432494432844612e-05, + "loss": 3.5864, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.43165583809356e-05, + "loss": 3.5899, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430817243342508e-05, + "loss": 3.5752, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429978648591456e-05, + "loss": 3.5607, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429141691720777e-05, + "loss": 3.5798, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428303096969725e-05, + "loss": 3.5865, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427464502218673e-05, + "loss": 3.5799, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426625907467621e-05, + "loss": 3.5843, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425788950596942e-05, + "loss": 3.589, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.42495035584589e-05, + "loss": 3.5764, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424111761094838e-05, + "loss": 3.5801, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4232731663437865e-05, + "loss": 3.5738, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224345715927345e-05, + "loss": 3.5872, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4215976147220554e-05, + "loss": 3.5832, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.4207590199710034e-05, + "loss": 3.5806, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4199204252199514e-05, + "loss": 3.5734, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419083468349272e-05, + "loss": 3.5664, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.41824487359822e-05, + "loss": 3.5773, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417406278847168e-05, + "loss": 3.588, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416567684096116e-05, + "loss": 3.58, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415730727225437e-05, + "loss": 3.5751, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414892132474385e-05, + "loss": 3.5745, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414053537723333e-05, + "loss": 3.5726, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413214942972282e-05, + "loss": 3.5779, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.41237634822123e-05, + "loss": 3.5782, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411539391350551e-05, + "loss": 3.5705, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410700796599499e-05, + "loss": 3.5781, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409862201848447e-05, + "loss": 3.5814, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409023607097395e-05, + "loss": 3.5739, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.4081866502267156e-05, + "loss": 3.5736, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.4073480554756636e-05, + "loss": 3.5711, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065094607246116e-05, + "loss": 3.5835, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056708659735596e-05, + "loss": 3.5776, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.4048339091028805e-05, + "loss": 3.5782, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.4039953143518285e-05, + "loss": 3.5806, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403156719600777e-05, + "loss": 3.58, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402319762730098e-05, + "loss": 3.5791, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401481167979046e-05, + "loss": 3.5738, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400642573227994e-05, + "loss": 3.5763, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399803978476942e-05, + "loss": 3.578, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.39896538372589e-05, + "loss": 3.5661, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3981267889748374e-05, + "loss": 3.5736, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3972881942237854e-05, + "loss": 3.5718, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.3964495994727334e-05, + "loss": 3.5759, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395612642602054e-05, + "loss": 3.5763, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394774047851002e-05, + "loss": 3.5688, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393935453099951e-05, + "loss": 3.5683, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393096858348899e-05, + "loss": 3.5703, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.39225990147822e-05, + "loss": 3.5865, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391421306727168e-05, + "loss": 3.5742, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390582711976116e-05, + "loss": 3.5785, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389744117225064e-05, + "loss": 3.5657, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388907160354385e-05, + "loss": 3.5822, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388068565603333e-05, + "loss": 3.5806, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387229970852281e-05, + "loss": 3.5803, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386391376101229e-05, + "loss": 3.5816, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.38555441923055e-05, + "loss": 3.5789, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384715824479498e-05, + "loss": 3.5854, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3838772297284463e-05, + "loss": 3.586, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383038634977394e-05, + "loss": 3.5679, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382201678106715e-05, + "loss": 3.579, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381363083355663e-05, + "loss": 3.5725, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380524488604611e-05, + "loss": 3.575, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379685893853559e-05, + "loss": 3.5683, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.37884893698288e-05, + "loss": 3.5748, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378010342231828e-05, + "loss": 3.5694, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377171747480776e-05, + "loss": 3.5751, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376333152729724e-05, + "loss": 3.575, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.845292091369629, + "eval_runtime": 313.1961, + "eval_samples_per_second": 1218.377, + "eval_steps_per_second": 38.075, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375496195859045e-05, + "loss": 3.586, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374657601107993e-05, + "loss": 3.5606, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373819006356942e-05, + "loss": 3.569, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.37298041160589e-05, + "loss": 3.5808, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721434547352106e-05, + "loss": 3.5736, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713048599841586e-05, + "loss": 3.571, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3704662652331066e-05, + "loss": 3.5745, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696276704820546e-05, + "loss": 3.5658, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3687890757310026e-05, + "loss": 3.5669, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679521188603235e-05, + "loss": 3.5781, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3671135241092715e-05, + "loss": 3.5751, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3662749293582195e-05, + "loss": 3.5693, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654363346071675e-05, + "loss": 3.5818, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3645993777364884e-05, + "loss": 3.5515, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3637607829854364e-05, + "loss": 3.569, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362922188234385e-05, + "loss": 3.5564, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362083593483333e-05, + "loss": 3.5755, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361246636612654e-05, + "loss": 3.5692, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360408041861602e-05, + "loss": 3.5616, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.35956944711055e-05, + "loss": 3.5692, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358730852359498e-05, + "loss": 3.588, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357893895488819e-05, + "loss": 3.5702, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357055300737767e-05, + "loss": 3.5732, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356216705986715e-05, + "loss": 3.5772, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355378111235663e-05, + "loss": 3.5764, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354541154364984e-05, + "loss": 3.5664, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353702559613932e-05, + "loss": 3.5652, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528639648628804e-05, + "loss": 3.5747, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520253701118284e-05, + "loss": 3.5606, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511884132411493e-05, + "loss": 3.5656, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350349818490097e-05, + "loss": 3.5768, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349511223739045e-05, + "loss": 3.5767, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348672628987993e-05, + "loss": 3.5729, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347835672117314e-05, + "loss": 3.5789, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346997077366262e-05, + "loss": 3.5645, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.34615848261521e-05, + "loss": 3.57, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345319887864158e-05, + "loss": 3.5722, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344482930993479e-05, + "loss": 3.5524, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343644336242427e-05, + "loss": 3.5684, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342805741491376e-05, + "loss": 3.5607, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341967146740324e-05, + "loss": 3.5568, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341128551989272e-05, + "loss": 3.5692, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340291595118593e-05, + "loss": 3.5801, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339453000367541e-05, + "loss": 3.5636, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338614405616489e-05, + "loss": 3.5658, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337775810865437e-05, + "loss": 3.5716, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369388539947576e-05, + "loss": 3.5632, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3361002592437056e-05, + "loss": 3.5704, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352616644926536e-05, + "loss": 3.5533, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3344230697416016e-05, + "loss": 3.564, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335844749905496e-05, + "loss": 3.5641, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332747518119871e-05, + "loss": 3.5772, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331908923368819e-05, + "loss": 3.5649, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331070328617767e-05, + "loss": 3.5578, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330231733866715e-05, + "loss": 3.5573, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329394776996036e-05, + "loss": 3.5618, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328556182244984e-05, + "loss": 3.5735, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327717587493932e-05, + "loss": 3.5506, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.32687899274288e-05, + "loss": 3.5744, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326042035872201e-05, + "loss": 3.5648, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325203441121149e-05, + "loss": 3.5477, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324364846370097e-05, + "loss": 3.5698, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323526251619045e-05, + "loss": 3.5534, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226892947483665e-05, + "loss": 3.5495, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218506999973145e-05, + "loss": 3.5538, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3210121052462625e-05, + "loss": 3.5683, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.32017351049521e-05, + "loss": 3.5615, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193365536245314e-05, + "loss": 3.5574, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184979588734794e-05, + "loss": 3.5544, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176593641224274e-05, + "loss": 3.5514, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316820769371375e-05, + "loss": 3.5625, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315982174620323e-05, + "loss": 3.5679, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315145217749644e-05, + "loss": 3.5662, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314306622998592e-05, + "loss": 3.5701, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.31346802824754e-05, + "loss": 3.5661, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312629433496488e-05, + "loss": 3.5595, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.31179247662581e-05, + "loss": 3.5682, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310953881874757e-05, + "loss": 3.561, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310115287123705e-05, + "loss": 3.5587, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309276692372653e-05, + "loss": 3.5566, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308439735501975e-05, + "loss": 3.5624, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307601140750922e-05, + "loss": 3.5717, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.30676254599987e-05, + "loss": 3.5715, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305923951248818e-05, + "loss": 3.5622, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305085356497766e-05, + "loss": 3.5451, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304248399627087e-05, + "loss": 3.5626, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303409804876036e-05, + "loss": 3.5671, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302571210124984e-05, + "loss": 3.5656, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301732615373932e-05, + "loss": 3.562, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3008956585032526e-05, + "loss": 3.5728, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000570637522006e-05, + "loss": 3.5614, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2992184690011486e-05, + "loss": 3.5624, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983798742500966e-05, + "loss": 3.5593, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975429173794175e-05, + "loss": 3.5696, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2967043226283655e-05, + "loss": 3.5668, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958657278773135e-05, + "loss": 3.5676, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2950271331262615e-05, + "loss": 3.5539, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2941901762555824e-05, + "loss": 3.5516, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293351581504531e-05, + "loss": 3.5574, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292512986753479e-05, + "loss": 3.5695, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291674392002427e-05, + "loss": 3.5633, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290837435131748e-05, + "loss": 3.5586, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289998840380696e-05, + "loss": 3.5567, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289160245629644e-05, + "loss": 3.5556, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288321650878592e-05, + "loss": 3.5619, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287484694007913e-05, + "loss": 3.5579, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286646099256861e-05, + "loss": 3.5561, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285807504505809e-05, + "loss": 3.5639, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284968909754757e-05, + "loss": 3.5629, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284131952884078e-05, + "loss": 3.5551, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283293358133026e-05, + "loss": 3.5589, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824547633819744e-05, + "loss": 3.5549, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2816161686309224e-05, + "loss": 3.5663, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280779211760243e-05, + "loss": 3.562, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279940617009191e-05, + "loss": 3.5624, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279102022258139e-05, + "loss": 3.5593, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278263427507087e-05, + "loss": 3.566, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277426470636408e-05, + "loss": 3.5606, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276587875885356e-05, + "loss": 3.553, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275749281134304e-05, + "loss": 3.5617, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274910686383252e-05, + "loss": 3.5584, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274073729512573e-05, + "loss": 3.5501, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273235134761521e-05, + "loss": 3.5556, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.27239654001047e-05, + "loss": 3.558, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271557945259418e-05, + "loss": 3.5578, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270720988388739e-05, + "loss": 3.5525, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269882393637687e-05, + "loss": 3.5563, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269043798886635e-05, + "loss": 3.5512, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268205204135583e-05, + "loss": 3.5561, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2673682472649036e-05, + "loss": 3.5698, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2665296525138516e-05, + "loss": 3.5584, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2656910577627996e-05, + "loss": 3.565, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648524630117476e-05, + "loss": 3.5499, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640138682606956e-05, + "loss": 3.5664, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631769113900165e-05, + "loss": 3.5636, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262338316638965e-05, + "loss": 3.5661, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261499721887913e-05, + "loss": 3.5618, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260661127136861e-05, + "loss": 3.5617, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259824170266182e-05, + "loss": 3.5702, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.25898557551513e-05, + "loss": 3.5664, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258146980764078e-05, + "loss": 3.5542, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257308386013026e-05, + "loss": 3.558, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256471429142347e-05, + "loss": 3.5576, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255632834391295e-05, + "loss": 3.5581, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254794239640243e-05, + "loss": 3.5503, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253955644889191e-05, + "loss": 3.5603, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253118688018512e-05, + "loss": 3.5493, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522800932674605e-05, + "loss": 3.5635, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514414985164085e-05, + "loss": 3.5534, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8444786071777344, + "eval_runtime": 303.5773, + "eval_samples_per_second": 1256.982, + "eval_steps_per_second": 39.282, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.2506029037653565e-05, + "loss": 3.5624, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2497659468946774e-05, + "loss": 3.5451, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489273521436254e-05, + "loss": 3.5512, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.2480887573925734e-05, + "loss": 3.5646, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.2472501626415214e-05, + "loss": 3.5594, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246413205770842e-05, + "loss": 3.5555, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.24557461101979e-05, + "loss": 3.5513, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244736016268738e-05, + "loss": 3.5493, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243897421517686e-05, + "loss": 3.5513, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243060464647007e-05, + "loss": 3.5625, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242221869895956e-05, + "loss": 3.5596, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241383275144904e-05, + "loss": 3.5558, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240544680393852e-05, + "loss": 3.5621, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239707723523173e-05, + "loss": 3.5398, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238869128772121e-05, + "loss": 3.5499, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238030534021069e-05, + "loss": 3.5437, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237191939270017e-05, + "loss": 3.5568, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236354982399338e-05, + "loss": 3.5494, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235516387648286e-05, + "loss": 3.55, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234677792897234e-05, + "loss": 3.5535, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233839198146182e-05, + "loss": 3.5688, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2330022412755026e-05, + "loss": 3.5567, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232163646524451e-05, + "loss": 3.5548, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231325051773399e-05, + "loss": 3.5569, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230486457022347e-05, + "loss": 3.5663, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229649500151668e-05, + "loss": 3.5431, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228810905400616e-05, + "loss": 3.5504, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227972310649564e-05, + "loss": 3.5603, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227133715898512e-05, + "loss": 3.5424, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2262951211474595e-05, + "loss": 3.5506, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225458164276781e-05, + "loss": 3.5581, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224619569525729e-05, + "loss": 3.5617, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223780974774677e-05, + "loss": 3.5581, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222942380023625e-05, + "loss": 3.5618, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2221054231529466e-05, + "loss": 3.5477, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2212668284018946e-05, + "loss": 3.5576, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220428233650842e-05, + "loss": 3.5534, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.21958963889979e-05, + "loss": 3.5387, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2187526820291115e-05, + "loss": 3.5545, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2179140872780595e-05, + "loss": 3.5428, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217075492527007e-05, + "loss": 3.5432, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216236897775955e-05, + "loss": 3.551, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2153999409052764e-05, + "loss": 3.563, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2145613461542244e-05, + "loss": 3.5464, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213722751403172e-05, + "loss": 3.5554, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2128841566521204e-05, + "loss": 3.5536, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2120455619010684e-05, + "loss": 3.5498, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211208605030389e-05, + "loss": 3.5518, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210370010279337e-05, + "loss": 3.5371, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209531415528285e-05, + "loss": 3.5491, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208692820777233e-05, + "loss": 3.5484, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207855863906554e-05, + "loss": 3.5587, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.207017269155502e-05, + "loss": 3.5502, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.20617867440445e-05, + "loss": 3.5369, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205340079653398e-05, + "loss": 3.5388, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204503122782719e-05, + "loss": 3.5442, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203664528031667e-05, + "loss": 3.5627, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202825933280616e-05, + "loss": 3.5339, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201987338529564e-05, + "loss": 3.5573, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201150381658885e-05, + "loss": 3.5522, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2003117869078327e-05, + "loss": 3.5304, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1994731921567807e-05, + "loss": 3.5524, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1986345974057287e-05, + "loss": 3.5416, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1977976405350496e-05, + "loss": 3.5328, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969590457839976e-05, + "loss": 3.5343, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1961204510329456e-05, + "loss": 3.5568, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1952818562818935e-05, + "loss": 3.544, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944448994112145e-05, + "loss": 3.5391, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1936063046601625e-05, + "loss": 3.5341, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1927677099091104e-05, + "loss": 3.5396, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191929115158059e-05, + "loss": 3.5463, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191090520407007e-05, + "loss": 3.5511, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190253563536328e-05, + "loss": 3.5482, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189414968785276e-05, + "loss": 3.5525, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188576374034224e-05, + "loss": 3.5492, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187737779283172e-05, + "loss": 3.5505, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186900822412493e-05, + "loss": 3.548, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186062227661441e-05, + "loss": 3.5421, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185223632910389e-05, + "loss": 3.542, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184385038159337e-05, + "loss": 3.5436, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183546443408285e-05, + "loss": 3.5465, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182709486537606e-05, + "loss": 3.5517, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.1818708917865545e-05, + "loss": 3.5603, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1810322970355025e-05, + "loss": 3.5448, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801937022844505e-05, + "loss": 3.5284, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793567454137714e-05, + "loss": 3.5445, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1785181506627194e-05, + "loss": 3.5504, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1776795559116674e-05, + "loss": 3.5527, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1768409611606154e-05, + "loss": 3.5414, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.176004004289936e-05, + "loss": 3.5575, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175165409538884e-05, + "loss": 3.547, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174326814787832e-05, + "loss": 3.5432, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.17348822003678e-05, + "loss": 3.5416, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172651263166101e-05, + "loss": 3.557, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.17181266841505e-05, + "loss": 3.5472, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170974073663998e-05, + "loss": 3.5532, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170135478912946e-05, + "loss": 3.5387, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169298522042267e-05, + "loss": 3.5368, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168459927291215e-05, + "loss": 3.5421, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167621332540163e-05, + "loss": 3.5517, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166782737789111e-05, + "loss": 3.5485, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1659457809184317e-05, + "loss": 3.5443, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.1651071861673796e-05, + "loss": 3.5371, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.1642685914163276e-05, + "loss": 3.5402, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634299966652756e-05, + "loss": 3.5498, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1625930397945965e-05, + "loss": 3.5395, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161754445043545e-05, + "loss": 3.539, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160915850292493e-05, + "loss": 3.5463, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160077255541441e-05, + "loss": 3.5473, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159240298670762e-05, + "loss": 3.5411, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.15840170391971e-05, + "loss": 3.5444, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157563109168658e-05, + "loss": 3.5365, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156724514417606e-05, + "loss": 3.5507, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155887557546927e-05, + "loss": 3.5483, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155048962795875e-05, + "loss": 3.5406, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154210368044823e-05, + "loss": 3.5488, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.153371773293771e-05, + "loss": 3.5511, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152534816423092e-05, + "loss": 3.5442, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1516962216720406e-05, + "loss": 3.5388, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1508576269209886e-05, + "loss": 3.5476, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1500190321699366e-05, + "loss": 3.5401, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1491820752992575e-05, + "loss": 3.5353, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483434805482055e-05, + "loss": 3.5407, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1475048857971535e-05, + "loss": 3.5408, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1466662910461015e-05, + "loss": 3.5451, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1458293341754224e-05, + "loss": 3.5347, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1449907394243704e-05, + "loss": 3.5455, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.1441521446733184e-05, + "loss": 3.5377, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1433135499222664e-05, + "loss": 3.5396, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142476593051587e-05, + "loss": 3.5476, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141637998300536e-05, + "loss": 3.5466, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140799403549484e-05, + "loss": 3.5452, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139960808798432e-05, + "loss": 3.534, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139123851927753e-05, + "loss": 3.5501, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.138285257176701e-05, + "loss": 3.5463, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137446662425649e-05, + "loss": 3.5469, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136608067674597e-05, + "loss": 3.5476, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135771110803918e-05, + "loss": 3.5472, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134932516052866e-05, + "loss": 3.557, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134093921301814e-05, + "loss": 3.5515, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133255326550762e-05, + "loss": 3.5399, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.1324183696800826e-05, + "loss": 3.5424, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131579774929031e-05, + "loss": 3.5409, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130741180177979e-05, + "loss": 3.5413, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129902585426927e-05, + "loss": 3.5384, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129065628556248e-05, + "loss": 3.5444, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128227033805196e-05, + "loss": 3.5337, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127388439054144e-05, + "loss": 3.5483, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265498443030915e-05, + "loss": 3.5379, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.8452062606811523, + "eval_runtime": 303.3263, + "eval_samples_per_second": 1258.022, + "eval_steps_per_second": 39.314, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125712887432413e-05, + "loss": 3.5142, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124874292681361e-05, + "loss": 3.5356, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124035697930309e-05, + "loss": 3.5319, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1231971031792564e-05, + "loss": 3.5481, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122360146308578e-05, + "loss": 3.5477, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121521551557526e-05, + "loss": 3.5409, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120682956806475e-05, + "loss": 3.5349, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119844362055422e-05, + "loss": 3.5335, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1190074051847436e-05, + "loss": 3.5418, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181688104336916e-05, + "loss": 3.5423, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117330215682639e-05, + "loss": 3.5441, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116491620931587e-05, + "loss": 3.5394, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1156546640609085e-05, + "loss": 3.5484, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1148160693098565e-05, + "loss": 3.5216, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113977474558804e-05, + "loss": 3.5334, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113138879807752e-05, + "loss": 3.53, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1123019229370734e-05, + "loss": 3.5393, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1114633281860214e-05, + "loss": 3.537, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106247334349694e-05, + "loss": 3.5353, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1097861386839174e-05, + "loss": 3.5349, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1089475439328654e-05, + "loss": 3.5539, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108110587062186e-05, + "loss": 3.5412, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107271992311134e-05, + "loss": 3.5354, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.106433397560082e-05, + "loss": 3.5451, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.10559480280903e-05, + "loss": 3.5489, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104757845938351e-05, + "loss": 3.5315, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103919251187299e-05, + "loss": 3.5331, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103080656436247e-05, + "loss": 3.5453, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102242061685195e-05, + "loss": 3.5248, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101405104814517e-05, + "loss": 3.5359, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100566510063465e-05, + "loss": 3.5395, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099727915312413e-05, + "loss": 3.5487, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098889320561361e-05, + "loss": 3.5411, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980523636906816e-05, + "loss": 3.5432, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0972137689396296e-05, + "loss": 3.5354, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0963751741885776e-05, + "loss": 3.5433, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0955365794375256e-05, + "loss": 3.5398, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0946996225668465e-05, + "loss": 3.522, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0938610278157945e-05, + "loss": 3.5385, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930224330647425e-05, + "loss": 3.524, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0921838383136905e-05, + "loss": 3.5323, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091346881443012e-05, + "loss": 3.5325, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.09050828669196e-05, + "loss": 3.5441, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089669691940908e-05, + "loss": 3.5347, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088831097189856e-05, + "loss": 3.5345, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087994140319177e-05, + "loss": 3.5426, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087155545568125e-05, + "loss": 3.53, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086316950817073e-05, + "loss": 3.5421, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085478356066021e-05, + "loss": 3.5236, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084641399195342e-05, + "loss": 3.5291, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.08380280444429e-05, + "loss": 3.5369, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082964209693238e-05, + "loss": 3.5397, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082125614942186e-05, + "loss": 3.5363, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0812886580715075e-05, + "loss": 3.5212, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804500633204555e-05, + "loss": 3.5288, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796114685694035e-05, + "loss": 3.5249, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.0787728738183515e-05, + "loss": 3.5497, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.0779359169476724e-05, + "loss": 3.518, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.0770973221966204e-05, + "loss": 3.5408, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.0762587274455684e-05, + "loss": 3.5336, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754201326945164e-05, + "loss": 3.5152, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074583175823837e-05, + "loss": 3.5354, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073744581072785e-05, + "loss": 3.5282, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072905986321733e-05, + "loss": 3.516, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072067391570681e-05, + "loss": 3.5218, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071230434700003e-05, + "loss": 3.5427, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070391839948951e-05, + "loss": 3.5287, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069553245197899e-05, + "loss": 3.5265, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068714650446847e-05, + "loss": 3.5197, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067876055695795e-05, + "loss": 3.5216, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067039098825116e-05, + "loss": 3.5318, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066200504074064e-05, + "loss": 3.5348, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065361909323012e-05, + "loss": 3.5334, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.06452331457196e-05, + "loss": 3.5393, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.0636863577012806e-05, + "loss": 3.5368, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.0628477629502286e-05, + "loss": 3.5316, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0620091681991766e-05, + "loss": 3.5313, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061170573448125e-05, + "loss": 3.5283, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060333616577446e-05, + "loss": 3.5289, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059495021826394e-05, + "loss": 3.5326, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058656427075342e-05, + "loss": 3.5296, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.05781783232429e-05, + "loss": 3.5376, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056980875453611e-05, + "loss": 3.537, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056142280702559e-05, + "loss": 3.5321, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055303685951507e-05, + "loss": 3.5167, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054465091200455e-05, + "loss": 3.5251, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053628134329776e-05, + "loss": 3.5396, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052789539578724e-05, + "loss": 3.5366, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051950944827672e-05, + "loss": 3.5314, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511139879569932e-05, + "loss": 3.5426, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502753932059412e-05, + "loss": 3.5318, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494367984548892e-05, + "loss": 3.5309, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485982037038376e-05, + "loss": 3.5274, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477612468331585e-05, + "loss": 3.5382, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469226520821065e-05, + "loss": 3.5301, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460840573310545e-05, + "loss": 3.5412, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452454625800025e-05, + "loss": 3.5174, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444085057093237e-05, + "loss": 3.531, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435699109582717e-05, + "loss": 3.5244, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427313162072197e-05, + "loss": 3.5347, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418927214561677e-05, + "loss": 3.5402, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410557645854886e-05, + "loss": 3.5256, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402171698344366e-05, + "loss": 3.5262, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393785750833846e-05, + "loss": 3.5261, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038539980332333e-05, + "loss": 3.5333, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037703023461654e-05, + "loss": 3.5205, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036864428710602e-05, + "loss": 3.5278, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.03602583395955e-05, + "loss": 3.5324, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351872392084978e-05, + "loss": 3.5299, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.034350282337819e-05, + "loss": 3.5293, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033511687586767e-05, + "loss": 3.5318, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.032673092835715e-05, + "loss": 3.5169, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031834498084663e-05, + "loss": 3.5367, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030997541213984e-05, + "loss": 3.5301, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030158946462932e-05, + "loss": 3.5264, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.02932035171188e-05, + "loss": 3.5346, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284817569608283e-05, + "loss": 3.5373, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276448000901492e-05, + "loss": 3.5278, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268062053390972e-05, + "loss": 3.5231, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259676105880452e-05, + "loss": 3.5306, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251290158369932e-05, + "loss": 3.5256, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242920589663144e-05, + "loss": 3.5225, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234534642152624e-05, + "loss": 3.523, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226148694642104e-05, + "loss": 3.5276, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217762747131584e-05, + "loss": 3.5297, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209393178424793e-05, + "loss": 3.5214, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0201007230914273e-05, + "loss": 3.5281, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192621283403753e-05, + "loss": 3.523, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184235335893237e-05, + "loss": 3.5285, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175865767186446e-05, + "loss": 3.5308, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167479819675926e-05, + "loss": 3.5316, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0159093872165406e-05, + "loss": 3.5313, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150707924654886e-05, + "loss": 3.5209, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142338355948098e-05, + "loss": 3.5302, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0133952408437578e-05, + "loss": 3.5355, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125566460927058e-05, + "loss": 3.5346, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117180513416538e-05, + "loss": 3.5334, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108810944709747e-05, + "loss": 3.5293, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100424997199227e-05, + "loss": 3.5447, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0092039049688707e-05, + "loss": 3.5313, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083653102178184e-05, + "loss": 3.5272, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.00752835334714e-05, + "loss": 3.5276, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.006689758596088e-05, + "loss": 3.5246, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005851163845036e-05, + "loss": 3.5251, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050125690939836e-05, + "loss": 3.52, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041756122233052e-05, + "loss": 3.5338, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033370174722532e-05, + "loss": 3.5187, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002498422721201e-05, + "loss": 3.5312, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016598279701485e-05, + "loss": 3.5251, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.00082287109947e-05, + "loss": 3.5285, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.8465096950531006, + "eval_runtime": 306.2759, + "eval_samples_per_second": 1245.906, + "eval_steps_per_second": 38.935, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.999984276348418e-05, + "loss": 3.5188, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991456815973657e-05, + "loss": 3.5172, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983070868463137e-05, + "loss": 3.5311, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974701299756353e-05, + "loss": 3.5332, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966315352245833e-05, + "loss": 3.5284, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957929404735306e-05, + "loss": 3.5194, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.994954345722479e-05, + "loss": 3.5195, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941173888518005e-05, + "loss": 3.5198, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9932787941007485e-05, + "loss": 3.5347, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992440199349696e-05, + "loss": 3.5264, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991601604598644e-05, + "loss": 3.5296, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907646477279654e-05, + "loss": 3.5337, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.989926052976913e-05, + "loss": 3.5113, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989087458225861e-05, + "loss": 3.5153, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988248863474809e-05, + "loss": 3.5143, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874119066041307e-05, + "loss": 3.5229, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986573311853078e-05, + "loss": 3.5217, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985734717102026e-05, + "loss": 3.5248, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9848961223509743e-05, + "loss": 3.5176, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840591654802952e-05, + "loss": 3.5418, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832205707292432e-05, + "loss": 3.5254, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823819759781912e-05, + "loss": 3.525, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815433812271392e-05, + "loss": 3.5262, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807064243564605e-05, + "loss": 3.5378, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9798678296054085e-05, + "loss": 3.5162, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790292348543565e-05, + "loss": 3.5211, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781906401033045e-05, + "loss": 3.5271, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773520453522524e-05, + "loss": 3.5126, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765150884815734e-05, + "loss": 3.5203, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756764937305214e-05, + "loss": 3.5237, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748378989794693e-05, + "loss": 3.5352, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739993042284177e-05, + "loss": 3.526, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731623473577386e-05, + "loss": 3.53, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723237526066866e-05, + "loss": 3.5246, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714851578556346e-05, + "loss": 3.525, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706465631045826e-05, + "loss": 3.5277, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698096062339038e-05, + "loss": 3.5109, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689710114828518e-05, + "loss": 3.5224, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681324167317998e-05, + "loss": 3.5097, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672938219807478e-05, + "loss": 3.5188, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664568651100687e-05, + "loss": 3.5183, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656182703590167e-05, + "loss": 3.5302, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647796756079647e-05, + "loss": 3.5209, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.963941080856913e-05, + "loss": 3.5194, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963102486105861e-05, + "loss": 3.5278, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962265529235182e-05, + "loss": 3.5175, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.96142693448413e-05, + "loss": 3.5279, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960588339733078e-05, + "loss": 3.5076, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959749744982026e-05, + "loss": 3.5167, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589127881113472e-05, + "loss": 3.5226, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580741933602952e-05, + "loss": 3.5265, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572355986092432e-05, + "loss": 3.5226, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9563970038581912e-05, + "loss": 3.5032, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955560046987512e-05, + "loss": 3.5198, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.95472145223646e-05, + "loss": 3.5103, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538828574854084e-05, + "loss": 3.5348, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530442627343564e-05, + "loss": 3.5076, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522073058636773e-05, + "loss": 3.5279, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513687111126253e-05, + "loss": 3.5161, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505301163615733e-05, + "loss": 3.5031, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496915216105213e-05, + "loss": 3.522, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488545647398426e-05, + "loss": 3.5156, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480159699887906e-05, + "loss": 3.4986, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471773752377385e-05, + "loss": 3.5065, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463387804866865e-05, + "loss": 3.5286, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9455018236160075e-05, + "loss": 3.5136, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446632288649554e-05, + "loss": 3.5098, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438246341139038e-05, + "loss": 3.5097, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429860393628518e-05, + "loss": 3.506, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421490824921727e-05, + "loss": 3.5151, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413104877411207e-05, + "loss": 3.5241, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404718929900687e-05, + "loss": 3.5182, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396332982390167e-05, + "loss": 3.5275, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.938796341368338e-05, + "loss": 3.5187, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937957746617286e-05, + "loss": 3.5213, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937119151866234e-05, + "loss": 3.5124, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.936280557115182e-05, + "loss": 3.5197, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354436002445028e-05, + "loss": 3.5187, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9346050054934508e-05, + "loss": 3.5109, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.933766410742399e-05, + "loss": 3.5157, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.932927815991347e-05, + "loss": 3.525, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932090859120668e-05, + "loss": 3.5268, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.931252264369616e-05, + "loss": 3.5145, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.930413669618564e-05, + "loss": 3.5, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.929575074867512e-05, + "loss": 3.5146, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287381179968333e-05, + "loss": 3.5249, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278995232457813e-05, + "loss": 3.5254, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270609284947293e-05, + "loss": 3.5148, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262223337436773e-05, + "loss": 3.5291, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253853768729982e-05, + "loss": 3.5184, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245467821219462e-05, + "loss": 3.5128, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237081873708945e-05, + "loss": 3.5157, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228695926198425e-05, + "loss": 3.5227, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220326357491634e-05, + "loss": 3.5158, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211940409981114e-05, + "loss": 3.5294, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203554462470594e-05, + "loss": 3.5073, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195168514960074e-05, + "loss": 3.5122, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9186798946253287e-05, + "loss": 3.5119, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178412998742767e-05, + "loss": 3.5215, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170027051232246e-05, + "loss": 3.5214, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9161641103721726e-05, + "loss": 3.5161, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9153255156211206e-05, + "loss": 3.5099, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9144885587504415e-05, + "loss": 3.5127, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.91364996399939e-05, + "loss": 3.5222, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912811369248338e-05, + "loss": 3.5028, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911972774497286e-05, + "loss": 3.5147, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111358176266068e-05, + "loss": 3.5204, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102972228755548e-05, + "loss": 3.5167, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094586281245028e-05, + "loss": 3.5145, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086200333734504e-05, + "loss": 3.5195, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907783076502772e-05, + "loss": 3.5058, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.90694448175172e-05, + "loss": 3.5204, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.906105887000668e-05, + "loss": 3.519, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052672922496153e-05, + "loss": 3.5144, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.904430335378937e-05, + "loss": 3.5178, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9035917406278853e-05, + "loss": 3.5227, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.902754783757206e-05, + "loss": 3.5162, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.901916189006154e-05, + "loss": 3.5121, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.901077594255102e-05, + "loss": 3.5148, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.90023899950405e-05, + "loss": 3.5122, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994004047529978e-05, + "loss": 3.5038, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985618100019458e-05, + "loss": 3.5111, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977232152508938e-05, + "loss": 3.511, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8968846204998418e-05, + "loss": 3.519, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960476636291627e-05, + "loss": 3.506, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952090688781107e-05, + "loss": 3.5161, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.894370474127059e-05, + "loss": 3.5066, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.893531879376007e-05, + "loss": 3.5138, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892694922505328e-05, + "loss": 3.5135, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891856327754276e-05, + "loss": 3.5234, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.891017733003224e-05, + "loss": 3.5166, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.890179138252172e-05, + "loss": 3.51, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893421813814932e-05, + "loss": 3.5126, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888503586630441e-05, + "loss": 3.5169, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887664991879389e-05, + "loss": 3.5224, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.886826397128337e-05, + "loss": 3.5195, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885989440257658e-05, + "loss": 3.5182, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885150845506606e-05, + "loss": 3.5279, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884312250755554e-05, + "loss": 3.5184, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834736560045024e-05, + "loss": 3.515, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826366991338233e-05, + "loss": 3.5113, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817981043827713e-05, + "loss": 3.5162, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809595096317193e-05, + "loss": 3.5122, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801209148806673e-05, + "loss": 3.5029, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792839580099885e-05, + "loss": 3.5185, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784453632589365e-05, + "loss": 3.5073, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776067685078845e-05, + "loss": 3.5182, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767681737568325e-05, + "loss": 3.5113, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759312168861534e-05, + "loss": 3.5112, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8481805324554443, + "eval_runtime": 305.2029, + "eval_samples_per_second": 1250.286, + "eval_steps_per_second": 39.072, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750926221351014e-05, + "loss": 3.5022, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742540273840494e-05, + "loss": 3.5071, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734154326329978e-05, + "loss": 3.5197, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725784757623187e-05, + "loss": 3.5147, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717398810112667e-05, + "loss": 3.5164, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709012862602147e-05, + "loss": 3.5062, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700626915091627e-05, + "loss": 3.5056, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.869225734638484e-05, + "loss": 3.5063, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868387139887432e-05, + "loss": 3.5183, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.86754854513638e-05, + "loss": 3.5135, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866709950385328e-05, + "loss": 3.5131, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658729935146488e-05, + "loss": 3.5188, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650343987635968e-05, + "loss": 3.4997, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641958040125448e-05, + "loss": 3.5048, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863357209261493e-05, + "loss": 3.5071, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862520252390814e-05, + "loss": 3.4985, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.861681657639762e-05, + "loss": 3.5106, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.86084306288871e-05, + "loss": 3.5087, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.860004468137658e-05, + "loss": 3.5024, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591675112669793e-05, + "loss": 3.5326, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583289165159273e-05, + "loss": 3.51, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574903217648753e-05, + "loss": 3.5136, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566517270138233e-05, + "loss": 3.5118, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855814770143144e-05, + "loss": 3.5205, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854976175392092e-05, + "loss": 3.5036, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.85413758064104e-05, + "loss": 3.506, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532989858899885e-05, + "loss": 3.5116, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524620290193094e-05, + "loss": 3.5046, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516234342682574e-05, + "loss": 3.505, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507848395172054e-05, + "loss": 3.5046, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499462447661534e-05, + "loss": 3.5257, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491092878954746e-05, + "loss": 3.5115, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482706931444226e-05, + "loss": 3.5137, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474320983933706e-05, + "loss": 3.5133, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465935036423186e-05, + "loss": 3.5113, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457565467716395e-05, + "loss": 3.5132, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449179520205875e-05, + "loss": 3.497, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440793572695355e-05, + "loss": 3.5064, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843240762518484e-05, + "loss": 3.4935, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424038056478048e-05, + "loss": 3.5081, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415652108967528e-05, + "loss": 3.5037, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407266161457008e-05, + "loss": 3.5158, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398880213946488e-05, + "loss": 3.5086, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.83905106452397e-05, + "loss": 3.5062, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.838212469772918e-05, + "loss": 3.5142, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837373875021866e-05, + "loss": 3.5058, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836535280270814e-05, + "loss": 3.5096, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835698323400135e-05, + "loss": 3.4982, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834859728649083e-05, + "loss": 3.5022, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834021133898031e-05, + "loss": 3.5084, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331825391469792e-05, + "loss": 3.5094, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323455822763e-05, + "loss": 3.5136, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831506987525248e-05, + "loss": 3.4879, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830668392774196e-05, + "loss": 3.5086, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829829798023144e-05, + "loss": 3.4909, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289928411524654e-05, + "loss": 3.5222, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281542464014134e-05, + "loss": 3.4947, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273156516503614e-05, + "loss": 3.5137, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264770568993094e-05, + "loss": 3.505, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256401000286303e-05, + "loss": 3.4913, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248015052775783e-05, + "loss": 3.5041, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239629105265263e-05, + "loss": 3.5037, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231243157754746e-05, + "loss": 3.4876, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222873589047955e-05, + "loss": 3.4934, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214487641537435e-05, + "loss": 3.5111, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206101694026915e-05, + "loss": 3.503, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197715746516395e-05, + "loss": 3.4992, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189346177809607e-05, + "loss": 3.4961, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180960230299087e-05, + "loss": 3.4897, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172574282788567e-05, + "loss": 3.5035, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164188335278047e-05, + "loss": 3.5057, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155818766571256e-05, + "loss": 3.5071, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147432819060736e-05, + "loss": 3.5154, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139046871550216e-05, + "loss": 3.5031, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130660924039696e-05, + "loss": 3.5099, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812229135533291e-05, + "loss": 3.4961, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811390540782239e-05, + "loss": 3.5087, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810551946031187e-05, + "loss": 3.502, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809713351280135e-05, + "loss": 3.4973, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808874756529083e-05, + "loss": 3.5042, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808037799658404e-05, + "loss": 3.5074, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807199204907352e-05, + "loss": 3.5137, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063606101563e-05, + "loss": 3.5046, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055220154052474e-05, + "loss": 3.488, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804685058534569e-05, + "loss": 3.4948, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803846463783517e-05, + "loss": 3.5142, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803007869032465e-05, + "loss": 3.5107, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021692742814126e-05, + "loss": 3.5049, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013323174107342e-05, + "loss": 3.5116, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004937226596822e-05, + "loss": 3.5098, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996551279086302e-05, + "loss": 3.4961, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798816533157578e-05, + "loss": 3.4999, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979795762868995e-05, + "loss": 3.5118, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971409815358475e-05, + "loss": 3.5033, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963023867847948e-05, + "loss": 3.5145, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954637920337428e-05, + "loss": 3.4964, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946268351630644e-05, + "loss": 3.4978, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937882404120124e-05, + "loss": 3.501, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.79294964566096e-05, + "loss": 3.5072, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792111050909908e-05, + "loss": 3.5076, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912740940392296e-05, + "loss": 3.5028, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790435499288177e-05, + "loss": 3.4948, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789596904537125e-05, + "loss": 3.4972, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887583097860732e-05, + "loss": 3.5137, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787921352915395e-05, + "loss": 3.4894, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787082758164342e-05, + "loss": 3.4949, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.78624416341329e-05, + "loss": 3.5109, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785405568662238e-05, + "loss": 3.5041, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845686117915597e-05, + "loss": 3.4963, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837300170405074e-05, + "loss": 3.5046, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828914222894554e-05, + "loss": 3.4977, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820528275384034e-05, + "loss": 3.5077, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812158706677243e-05, + "loss": 3.5007, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803772759166723e-05, + "loss": 3.5012, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795386811656203e-05, + "loss": 3.5072, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787000864145686e-05, + "loss": 3.5121, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777864767424263e-05, + "loss": 3.5021, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.777026172673211e-05, + "loss": 3.497, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776187577922159e-05, + "loss": 3.5023, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775348983171107e-05, + "loss": 3.4978, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745103884200548e-05, + "loss": 3.492, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736717936690028e-05, + "loss": 3.4993, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728331989179507e-05, + "loss": 3.4973, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719946041668987e-05, + "loss": 3.5052, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711576472962197e-05, + "loss": 3.4934, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703190525451676e-05, + "loss": 3.5046, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694804577941156e-05, + "loss": 3.4891, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768641863043064e-05, + "loss": 3.5019, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767804906172385e-05, + "loss": 3.4986, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766966311421333e-05, + "loss": 3.5089, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766127716670281e-05, + "loss": 3.5051, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765289121919229e-05, + "loss": 3.5027, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.76445216504855e-05, + "loss": 3.4951, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763613570297498e-05, + "loss": 3.5002, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762774975546446e-05, + "loss": 3.5093, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761936380795394e-05, + "loss": 3.5105, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761099423924715e-05, + "loss": 3.5083, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760260829173663e-05, + "loss": 3.5129, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759422234422611e-05, + "loss": 3.5021, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585836396715593e-05, + "loss": 3.5024, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577466828008803e-05, + "loss": 3.4988, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569080880498283e-05, + "loss": 3.5023, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560694932987762e-05, + "loss": 3.5011, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552308985477242e-05, + "loss": 3.4867, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543939416770455e-05, + "loss": 3.5069, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535553469259935e-05, + "loss": 3.4958, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527167521749415e-05, + "loss": 3.503, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518781574238895e-05, + "loss": 3.4955, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510412005532104e-05, + "loss": 3.5024, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.848186492919922, + "eval_runtime": 324.9783, + "eval_samples_per_second": 1174.205, + "eval_steps_per_second": 36.695, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502026058021584e-05, + "loss": 3.4882, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493640110511064e-05, + "loss": 3.4951, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485254163000547e-05, + "loss": 3.506, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476884594293756e-05, + "loss": 3.5027, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468498646783236e-05, + "loss": 3.5067, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460112699272716e-05, + "loss": 3.4887, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451726751762196e-05, + "loss": 3.4962, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.744335718305541e-05, + "loss": 3.4921, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743497123554489e-05, + "loss": 3.5058, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742658528803437e-05, + "loss": 3.5041, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741819934052385e-05, + "loss": 3.4977, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409829771817058e-05, + "loss": 3.5, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401443824306537e-05, + "loss": 3.4885, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393057876796017e-05, + "loss": 3.4899, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.73846719292855e-05, + "loss": 3.4968, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.737630236057871e-05, + "loss": 3.4889, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736791641306819e-05, + "loss": 3.4944, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735953046555767e-05, + "loss": 3.496, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735114451804715e-05, + "loss": 3.4884, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342774949340362e-05, + "loss": 3.5217, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334389001829842e-05, + "loss": 3.497, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326003054319322e-05, + "loss": 3.5022, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317617106808802e-05, + "loss": 3.4979, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.730924753810201e-05, + "loss": 3.5077, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730086159059149e-05, + "loss": 3.4914, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729247564308097e-05, + "loss": 3.4946, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284089695570454e-05, + "loss": 3.497, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275720126863664e-05, + "loss": 3.4945, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267334179353144e-05, + "loss": 3.4894, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258948231842623e-05, + "loss": 3.4944, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250562284332103e-05, + "loss": 3.5098, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242192715625316e-05, + "loss": 3.4995, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233806768114796e-05, + "loss": 3.4984, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225420820604276e-05, + "loss": 3.5022, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217034873093756e-05, + "loss": 3.4987, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208665304386965e-05, + "loss": 3.4981, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200279356876445e-05, + "loss": 3.4837, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191893409365925e-05, + "loss": 3.4975, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183507461855405e-05, + "loss": 3.4835, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175137893148617e-05, + "loss": 3.494, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166751945638097e-05, + "loss": 3.4891, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158365998127577e-05, + "loss": 3.5031, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149980050617057e-05, + "loss": 3.4983, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714161048191027e-05, + "loss": 3.4901, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.713322453439975e-05, + "loss": 3.5001, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712483858688923e-05, + "loss": 3.4964, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711645263937871e-05, + "loss": 3.4978, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710808307067192e-05, + "loss": 3.4841, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.70996971231614e-05, + "loss": 3.4879, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709131117565088e-05, + "loss": 3.4973, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708292522814036e-05, + "loss": 3.4962, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.707455565943357e-05, + "loss": 3.4982, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.706616971192305e-05, + "loss": 3.478, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705778376441253e-05, + "loss": 3.4974, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704939781690201e-05, + "loss": 3.4772, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704102824819522e-05, + "loss": 3.5078, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032642300684703e-05, + "loss": 3.479, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024256353174183e-05, + "loss": 3.5002, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015870405663663e-05, + "loss": 3.49, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007500836956872e-05, + "loss": 3.4852, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999114889446352e-05, + "loss": 3.4868, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990728941935832e-05, + "loss": 3.4916, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982342994425312e-05, + "loss": 3.4747, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973973425718525e-05, + "loss": 3.4849, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965587478208005e-05, + "loss": 3.4939, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957201530697484e-05, + "loss": 3.493, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948815583186964e-05, + "loss": 3.4839, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940446014480174e-05, + "loss": 3.4832, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932060066969657e-05, + "loss": 3.4815, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923674119459137e-05, + "loss": 3.4868, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915288171948617e-05, + "loss": 3.4916, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906918603241826e-05, + "loss": 3.4908, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898532655731306e-05, + "loss": 3.5029, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890146708220786e-05, + "loss": 3.4952, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881760760710266e-05, + "loss": 3.4963, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873391192003478e-05, + "loss": 3.483, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6865005244492958e-05, + "loss": 3.4939, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856619296982438e-05, + "loss": 3.4924, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848233349471918e-05, + "loss": 3.4828, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839863780765127e-05, + "loss": 3.4939, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683147783325461e-05, + "loss": 3.4933, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.682309188574409e-05, + "loss": 3.5016, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681470593823357e-05, + "loss": 3.4898, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.680633636952678e-05, + "loss": 3.478, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679795042201626e-05, + "loss": 3.4833, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678956447450574e-05, + "loss": 3.4962, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781178526995216e-05, + "loss": 3.4992, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772808958288432e-05, + "loss": 3.4927, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764423010777912e-05, + "loss": 3.5007, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756037063267392e-05, + "loss": 3.4986, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747651115756865e-05, + "loss": 3.4787, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.673928154705008e-05, + "loss": 3.4928, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730895599539564e-05, + "loss": 3.4924, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722509652029044e-05, + "loss": 3.489, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714123704518517e-05, + "loss": 3.5038, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705754135811733e-05, + "loss": 3.4874, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697368188301213e-05, + "loss": 3.4804, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668898224079069e-05, + "loss": 3.49, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668059629328017e-05, + "loss": 3.4968, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672226724573386e-05, + "loss": 3.4951, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663840777062866e-05, + "loss": 3.4917, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665545482955234e-05, + "loss": 3.4803, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664706888204182e-05, + "loss": 3.4831, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638699313335035e-05, + "loss": 3.5025, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630313365824518e-05, + "loss": 3.4763, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.662192741831399e-05, + "loss": 3.489, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661354147080347e-05, + "loss": 3.4953, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605171902096687e-05, + "loss": 3.4898, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596785954586163e-05, + "loss": 3.4834, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588400007075643e-05, + "loss": 3.493, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6580014059565123e-05, + "loss": 3.4859, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657164449085834e-05, + "loss": 3.4898, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563258543347812e-05, + "loss": 3.4875, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554872595837292e-05, + "loss": 3.4874, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546486648326772e-05, + "loss": 3.4956, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538117079619985e-05, + "loss": 3.4991, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.65297475109132e-05, + "loss": 3.493, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652136156340268e-05, + "loss": 3.4828, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651297561589216e-05, + "loss": 3.4874, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504589668381634e-05, + "loss": 3.4865, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496203720871117e-05, + "loss": 3.4777, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487817773360597e-05, + "loss": 3.4917, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479431825850077e-05, + "loss": 3.4817, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471045878339557e-05, + "loss": 3.4937, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462676309632766e-05, + "loss": 3.4809, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454290362122246e-05, + "loss": 3.4918, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445904414611726e-05, + "loss": 3.4775, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643751846710121e-05, + "loss": 3.4898, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642914889839442e-05, + "loss": 3.4831, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.64207629508839e-05, + "loss": 3.4978, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.641237700337338e-05, + "loss": 3.4951, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403991055862858e-05, + "loss": 3.4897, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639562148715607e-05, + "loss": 3.4803, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.638723553964555e-05, + "loss": 3.4892, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637884959213503e-05, + "loss": 3.4951, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.637046364462451e-05, + "loss": 3.4981, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636209407591772e-05, + "loss": 3.4921, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.63537081284072e-05, + "loss": 3.4997, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634532218089668e-05, + "loss": 3.4903, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336936233386163e-05, + "loss": 3.493, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328566664679372e-05, + "loss": 3.485, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320180717168852e-05, + "loss": 3.487, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311794769658332e-05, + "loss": 3.49, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303408822147812e-05, + "loss": 3.4777, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6295039253441024e-05, + "loss": 3.4892, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286653305930504e-05, + "loss": 3.489, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278267358419984e-05, + "loss": 3.485, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269881410909464e-05, + "loss": 3.4835, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261511842202673e-05, + "loss": 3.4844, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.850255250930786, + "eval_runtime": 325.8638, + "eval_samples_per_second": 1171.014, + "eval_steps_per_second": 36.595, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253125894692153e-05, + "loss": 3.4785, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244739947181633e-05, + "loss": 3.4818, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236353999671113e-05, + "loss": 3.4932, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227968052160597e-05, + "loss": 3.4865, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219598483453806e-05, + "loss": 3.4951, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211212535943286e-05, + "loss": 3.4732, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202826588432766e-05, + "loss": 3.4844, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194440640922246e-05, + "loss": 3.4759, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186071072215458e-05, + "loss": 3.4931, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177685124704938e-05, + "loss": 3.4912, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169299177194418e-05, + "loss": 3.4845, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160929608487627e-05, + "loss": 3.4854, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152543660977107e-05, + "loss": 3.474, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144157713466587e-05, + "loss": 3.4769, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135771765956067e-05, + "loss": 3.4837, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612740219724928e-05, + "loss": 3.4797, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611901624973876e-05, + "loss": 3.48, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611063030222824e-05, + "loss": 3.4855, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610224435471772e-05, + "loss": 3.4741, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609387478601093e-05, + "loss": 3.509, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085488838500412e-05, + "loss": 3.4843, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607710289098989e-05, + "loss": 3.4875, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606871694347937e-05, + "loss": 3.4883, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606034737477258e-05, + "loss": 3.4896, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605196142726206e-05, + "loss": 3.4778, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604357547975154e-05, + "loss": 3.488, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603518953224102e-05, + "loss": 3.4824, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026803584730504e-05, + "loss": 3.4833, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018434016023713e-05, + "loss": 3.4719, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010048068513193e-05, + "loss": 3.4847, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001662121002673e-05, + "loss": 3.4974, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993292552295882e-05, + "loss": 3.486, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984906604785365e-05, + "loss": 3.4891, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976520657274845e-05, + "loss": 3.4898, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5968134709764325e-05, + "loss": 3.4816, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959765141057534e-05, + "loss": 3.4893, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951379193547014e-05, + "loss": 3.4705, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942993246036494e-05, + "loss": 3.4845, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934607298525974e-05, + "loss": 3.4682, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926237729819187e-05, + "loss": 3.4824, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917851782308667e-05, + "loss": 3.4784, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909465834798147e-05, + "loss": 3.4904, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901079887287627e-05, + "loss": 3.4854, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892710318580836e-05, + "loss": 3.4767, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588432437107032e-05, + "loss": 3.4894, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.58759384235598e-05, + "loss": 3.4832, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586755247604928e-05, + "loss": 3.4841, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859182907342488e-05, + "loss": 3.4793, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850796959831968e-05, + "loss": 3.4692, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842411012321448e-05, + "loss": 3.4856, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834025064810928e-05, + "loss": 3.4815, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582565549610414e-05, + "loss": 3.4856, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581726954859362e-05, + "loss": 3.4683, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.58088836010831e-05, + "loss": 3.4873, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580049765357258e-05, + "loss": 3.4614, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579212808486579e-05, + "loss": 3.494, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783742137355273e-05, + "loss": 3.4692, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775356189844753e-05, + "loss": 3.4839, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766970242334233e-05, + "loss": 3.4796, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758584294823713e-05, + "loss": 3.4742, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750198347313186e-05, + "loss": 3.4729, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741812399802666e-05, + "loss": 3.484, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573342645229215e-05, + "loss": 3.4605, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725056883585365e-05, + "loss": 3.4688, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716670936074838e-05, + "loss": 3.486, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708284988564318e-05, + "loss": 3.479, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699899041053798e-05, + "loss": 3.4734, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569152947234701e-05, + "loss": 3.474, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568314352483649e-05, + "loss": 3.4647, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567475757732597e-05, + "loss": 3.4731, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566637162981545e-05, + "loss": 3.4799, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565800206110866e-05, + "loss": 3.4794, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564961611359814e-05, + "loss": 3.4912, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564123016608762e-05, + "loss": 3.4811, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632844218577103e-05, + "loss": 3.4869, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624474649870312e-05, + "loss": 3.4688, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616088702359792e-05, + "loss": 3.4792, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607702754849272e-05, + "loss": 3.4815, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599316807338752e-05, + "loss": 3.4687, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590947238631964e-05, + "loss": 3.4859, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582561291121444e-05, + "loss": 3.4774, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574175343610924e-05, + "loss": 3.4866, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565789396100404e-05, + "loss": 3.4771, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557419827393613e-05, + "loss": 3.4647, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5549033879883093e-05, + "loss": 3.4752, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540647932372573e-05, + "loss": 3.4806, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532261984862056e-05, + "loss": 3.4863, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523892416155266e-05, + "loss": 3.4817, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515506468644745e-05, + "loss": 3.4821, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507120521134225e-05, + "loss": 3.4888, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498734573623705e-05, + "loss": 3.4683, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490365004916918e-05, + "loss": 3.482, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481979057406398e-05, + "loss": 3.4787, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473593109895878e-05, + "loss": 3.4779, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465207162385358e-05, + "loss": 3.4899, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456837593678567e-05, + "loss": 3.4776, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448451646168047e-05, + "loss": 3.4678, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440065698657527e-05, + "loss": 3.4771, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543167975114701e-05, + "loss": 3.4814, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542331018244022e-05, + "loss": 3.4822, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.54149242349297e-05, + "loss": 3.4803, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540653828741918e-05, + "loss": 3.4692, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539815233990866e-05, + "loss": 3.472, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538978277120187e-05, + "loss": 3.4887, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538139682369135e-05, + "loss": 3.4645, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537301087618083e-05, + "loss": 3.4736, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536464130747404e-05, + "loss": 3.4801, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535625535996352e-05, + "loss": 3.4797, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347869412453e-05, + "loss": 3.4694, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533948346494248e-05, + "loss": 3.4814, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331113896235693e-05, + "loss": 3.4763, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322727948725173e-05, + "loss": 3.4778, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314342001214653e-05, + "loss": 3.4785, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305956053704133e-05, + "loss": 3.4738, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297586484997342e-05, + "loss": 3.4865, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289200537486825e-05, + "loss": 3.4831, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280830968780034e-05, + "loss": 3.4828, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272445021269514e-05, + "loss": 3.4675, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264059073758994e-05, + "loss": 3.4754, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255673126248474e-05, + "loss": 3.4756, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247287178737954e-05, + "loss": 3.4655, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238901231227434e-05, + "loss": 3.4772, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230515283716914e-05, + "loss": 3.4734, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222129336206397e-05, + "loss": 3.4798, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213759767499606e-05, + "loss": 3.4685, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205373819989086e-05, + "loss": 3.4814, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196987872478566e-05, + "loss": 3.4603, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188601924968046e-05, + "loss": 3.4773, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518023235626126e-05, + "loss": 3.4749, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517184640875074e-05, + "loss": 3.4841, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516346046124022e-05, + "loss": 3.481, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.51550745137297e-05, + "loss": 3.4812, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146704945022908e-05, + "loss": 3.4679, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138318997512388e-05, + "loss": 3.4777, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129933050001868e-05, + "loss": 3.4818, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512154710249135e-05, + "loss": 3.4858, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511317753378456e-05, + "loss": 3.4819, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510479158627404e-05, + "loss": 3.4821, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509640563876352e-05, + "loss": 3.481, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088019691253e-05, + "loss": 3.4838, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079650122546212e-05, + "loss": 3.4725, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071264175035692e-05, + "loss": 3.4752, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062878227525172e-05, + "loss": 3.4781, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054492280014652e-05, + "loss": 3.466, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504612271130786e-05, + "loss": 3.4749, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503773676379734e-05, + "loss": 3.4795, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502935081628682e-05, + "loss": 3.4725, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020964868776305e-05, + "loss": 3.4679, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012595300069514e-05, + "loss": 3.4812, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.852231979370117, + "eval_runtime": 472.5875, + "eval_samples_per_second": 807.451, + "eval_steps_per_second": 25.233, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004209352558994e-05, + "loss": 3.465, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499582340504847e-05, + "loss": 3.4707, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.498743745753795e-05, + "loss": 3.4801, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4979067888831166e-05, + "loss": 3.4773, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970681941320646e-05, + "loss": 3.4861, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962295993810123e-05, + "loss": 3.4629, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953910046299603e-05, + "loss": 3.4709, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945540477592815e-05, + "loss": 3.4645, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4937154530082295e-05, + "loss": 3.4803, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4928768582571775e-05, + "loss": 3.4784, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4920382635061255e-05, + "loss": 3.4673, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4912013066354467e-05, + "loss": 3.4815, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903627118843944e-05, + "loss": 3.4595, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895241171333424e-05, + "loss": 3.4676, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886855223822904e-05, + "loss": 3.4725, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.487848565511612e-05, + "loss": 3.4659, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4870099707605596e-05, + "loss": 3.467, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861713760095076e-05, + "loss": 3.4713, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853327812584556e-05, + "loss": 3.466, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.484495824387777e-05, + "loss": 3.4938, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836572296367245e-05, + "loss": 3.4738, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.482818634885673e-05, + "loss": 3.4726, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.481980040134621e-05, + "loss": 3.4772, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811430832639418e-05, + "loss": 3.4785, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4803044885128898e-05, + "loss": 3.4663, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794658937618378e-05, + "loss": 3.4769, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786272990107858e-05, + "loss": 3.4706, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.477790342140107e-05, + "loss": 3.47, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476951747389055e-05, + "loss": 3.4618, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.476113152638003e-05, + "loss": 3.4707, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752761957673242e-05, + "loss": 3.4878, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.474437601016272e-05, + "loss": 3.4741, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.47359900626522e-05, + "loss": 3.4762, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727604115141682e-05, + "loss": 3.4786, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.471923454643489e-05, + "loss": 3.4696, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.471084859892437e-05, + "loss": 3.4784, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470246265141385e-05, + "loss": 3.4575, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469407670390333e-05, + "loss": 3.4719, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685707135196544e-05, + "loss": 3.4603, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677321187686024e-05, + "loss": 3.4652, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4668935240175504e-05, + "loss": 3.469, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660549292664984e-05, + "loss": 3.4774, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.4652179723958193e-05, + "loss": 3.4722, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.4643793776447673e-05, + "loss": 3.469, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4635407828937153e-05, + "loss": 3.4755, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.4627021881426636e-05, + "loss": 3.4704, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618652312719845e-05, + "loss": 3.4717, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610266365209325e-05, + "loss": 3.4665, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.4601880417698805e-05, + "loss": 3.4572, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593494470188285e-05, + "loss": 3.4751, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4585124901481497e-05, + "loss": 3.467, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4576738953970977e-05, + "loss": 3.4762, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.4568353006460457e-05, + "loss": 3.4589, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559967058949937e-05, + "loss": 3.4728, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551597490243146e-05, + "loss": 3.4533, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.454322792153636e-05, + "loss": 3.4798, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.453484197402584e-05, + "loss": 3.4573, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.452645602651532e-05, + "loss": 3.4662, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.45180700790048e-05, + "loss": 3.4712, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.450968413149428e-05, + "loss": 3.4617, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.450129818398376e-05, + "loss": 3.464, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.449291223647324e-05, + "loss": 3.4689, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448452628896272e-05, + "loss": 3.4554, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.447615672025593e-05, + "loss": 3.4523, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446777077274541e-05, + "loss": 3.4708, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445938482523489e-05, + "loss": 3.4667, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450998877724368e-05, + "loss": 3.4575, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.444262930901758e-05, + "loss": 3.4647, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.443424336150706e-05, + "loss": 3.4514, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4425857413996543e-05, + "loss": 3.4613, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441747146648602e-05, + "loss": 3.4698, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4409101897779232e-05, + "loss": 3.4666, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400715950268712e-05, + "loss": 3.4796, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392330002758192e-05, + "loss": 3.4698, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.438394405524767e-05, + "loss": 3.4795, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375574486540885e-05, + "loss": 3.4562, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367188539030365e-05, + "loss": 3.4686, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.435880259151984e-05, + "loss": 3.4694, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.435041664400932e-05, + "loss": 3.4546, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4342047075302534e-05, + "loss": 3.4765, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4333661127792014e-05, + "loss": 3.466, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325275180281494e-05, + "loss": 3.4733, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4316889232770974e-05, + "loss": 3.4674, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4308519664064186e-05, + "loss": 3.4539, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4300133716553666e-05, + "loss": 3.4658, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4291747769043143e-05, + "loss": 3.4657, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283361821532623e-05, + "loss": 3.475, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427499225282584e-05, + "loss": 3.468, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266606305315315e-05, + "loss": 3.4717, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4258220357804795e-05, + "loss": 3.473, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249834410294275e-05, + "loss": 3.459, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241464841587487e-05, + "loss": 3.4699, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.4233078894076967e-05, + "loss": 3.4632, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4224692946566447e-05, + "loss": 3.4731, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216306999055927e-05, + "loss": 3.4784, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.420793743034914e-05, + "loss": 3.4642, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199551482838616e-05, + "loss": 3.4577, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191165535328096e-05, + "loss": 3.4625, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4182779587817576e-05, + "loss": 3.4682, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417441001911079e-05, + "loss": 3.4746, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416602407160027e-05, + "loss": 3.4635, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.415763812408975e-05, + "loss": 3.4596, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.414925217657923e-05, + "loss": 3.4589, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140882607872438e-05, + "loss": 3.4755, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.413249666036192e-05, + "loss": 3.4532, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.41241107128514e-05, + "loss": 3.4647, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411572476534088e-05, + "loss": 3.4671, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410735519663409e-05, + "loss": 3.4659, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409896924912357e-05, + "loss": 3.4598, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.409058330161305e-05, + "loss": 3.4714, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.408219735410253e-05, + "loss": 3.4642, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073827785395742e-05, + "loss": 3.4628, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065441837885222e-05, + "loss": 3.4688, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4057055890374702e-05, + "loss": 3.4643, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048669942864182e-05, + "loss": 3.4745, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.404030037415739e-05, + "loss": 3.4718, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031930805450607e-05, + "loss": 3.4688, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023544857940087e-05, + "loss": 3.4567, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4015158910429564e-05, + "loss": 3.4664, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006772962919044e-05, + "loss": 3.4622, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998387015408524e-05, + "loss": 3.4526, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3990001067898004e-05, + "loss": 3.4681, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3981615120387484e-05, + "loss": 3.4579, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3973229172876967e-05, + "loss": 3.4677, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964859604170176e-05, + "loss": 3.4595, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956473656659656e-05, + "loss": 3.4686, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3948087709149136e-05, + "loss": 3.4513, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939701761638616e-05, + "loss": 3.4634, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.393133219293183e-05, + "loss": 3.4644, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3922946245421308e-05, + "loss": 3.4668, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3914560297910788e-05, + "loss": 3.4677, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3906174350400265e-05, + "loss": 3.4727, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897804781693477e-05, + "loss": 3.4539, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889418834182957e-05, + "loss": 3.4681, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3881032886672437e-05, + "loss": 3.4724, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3872646939161917e-05, + "loss": 3.4712, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386427737045513e-05, + "loss": 3.4724, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385589142294461e-05, + "loss": 3.4731, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384750547543409e-05, + "loss": 3.4689, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3839119527923566e-05, + "loss": 3.4717, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830749959216782e-05, + "loss": 3.4571, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822364011706262e-05, + "loss": 3.4657, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.381397806419574e-05, + "loss": 3.4627, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.380559211668522e-05, + "loss": 3.4597, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.379722254797843e-05, + "loss": 3.4652, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.378883660046791e-05, + "loss": 3.4628, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.378045065295739e-05, + "loss": 3.4648, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.377206470544687e-05, + "loss": 3.4528, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763695136740083e-05, + "loss": 3.4704, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8541147708892822, + "eval_runtime": 480.852, + "eval_samples_per_second": 793.573, + "eval_steps_per_second": 24.8, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755309189229563e-05, + "loss": 3.4545, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374692324171904e-05, + "loss": 3.4559, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373853729420852e-05, + "loss": 3.4679, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730151346698e-05, + "loss": 3.4691, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721781777991212e-05, + "loss": 3.4677, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713395830480692e-05, + "loss": 3.4572, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3705009882970172e-05, + "loss": 3.4577, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696623935459652e-05, + "loss": 3.4558, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368825436675286e-05, + "loss": 3.4655, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679868419242345e-05, + "loss": 3.47, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671482471731825e-05, + "loss": 3.4554, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663096524221304e-05, + "loss": 3.4695, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654726955514514e-05, + "loss": 3.452, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646341008003994e-05, + "loss": 3.454, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637955060493473e-05, + "loss": 3.4608, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629569112982953e-05, + "loss": 3.4535, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621199544276166e-05, + "loss": 3.4567, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612813596765646e-05, + "loss": 3.4621, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604427649255126e-05, + "loss": 3.4531, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596041701744606e-05, + "loss": 3.4808, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587672133037815e-05, + "loss": 3.4652, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357930256433103e-05, + "loss": 3.4633, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357091661682051e-05, + "loss": 3.4628, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562530669309987e-05, + "loss": 3.4702, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554144721799467e-05, + "loss": 3.4528, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545758774288947e-05, + "loss": 3.4658, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537372826778427e-05, + "loss": 3.4602, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528986879267907e-05, + "loss": 3.4567, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352060093175739e-05, + "loss": 3.4479, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.35122313630506e-05, + "loss": 3.4615, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350384541554008e-05, + "loss": 3.4753, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349545946802956e-05, + "loss": 3.4623, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348708989932277e-05, + "loss": 3.4671, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478703951812252e-05, + "loss": 3.4658, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470318004301732e-05, + "loss": 3.4543, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461932056791212e-05, + "loss": 3.4654, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345356248808442e-05, + "loss": 3.4516, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.34451765405739e-05, + "loss": 3.4558, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343679059306338e-05, + "loss": 3.4495, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.342840464555286e-05, + "loss": 3.452, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420035076846073e-05, + "loss": 3.4586, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411665508139282e-05, + "loss": 3.4653, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403279560628762e-05, + "loss": 3.4604, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394893613118242e-05, + "loss": 3.4571, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386507665607722e-05, + "loss": 3.4638, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3378121718097206e-05, + "loss": 3.4609, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369735770586686e-05, + "loss": 3.4616, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361349823076165e-05, + "loss": 3.4565, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352980254369375e-05, + "loss": 3.4443, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344594306858855e-05, + "loss": 3.4655, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3336208359348334e-05, + "loss": 3.4588, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327822411837814e-05, + "loss": 3.4626, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319452843131027e-05, + "loss": 3.4499, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311066895620507e-05, + "loss": 3.4581, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302680948109987e-05, + "loss": 3.4388, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294311379403196e-05, + "loss": 3.466, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285925431892676e-05, + "loss": 3.4463, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327753948438216e-05, + "loss": 3.4587, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269153536871636e-05, + "loss": 3.4609, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260767589361116e-05, + "loss": 3.445, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252381641850596e-05, + "loss": 3.4502, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243995694340076e-05, + "loss": 3.4644, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235609746829556e-05, + "loss": 3.4421, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227240178122768e-05, + "loss": 3.4396, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3218854230612248e-05, + "loss": 3.4588, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210468283101728e-05, + "loss": 3.4572, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202082335591208e-05, + "loss": 3.4442, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193712766884417e-05, + "loss": 3.4566, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185326819373897e-05, + "loss": 3.4379, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3176940871863377e-05, + "loss": 3.4488, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316855492435286e-05, + "loss": 3.4594, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.316018535564607e-05, + "loss": 3.4549, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315179940813555e-05, + "loss": 3.4637, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314341346062503e-05, + "loss": 3.4586, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.313502751311451e-05, + "loss": 3.4692, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126657944407722e-05, + "loss": 3.446, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118271996897202e-05, + "loss": 3.4606, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310988604938668e-05, + "loss": 3.4604, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310150010187616e-05, + "loss": 3.4403, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309313053316937e-05, + "loss": 3.4642, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.308474458565885e-05, + "loss": 3.4576, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307635863814833e-05, + "loss": 3.4588, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067972690637814e-05, + "loss": 3.4587, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059603121931023e-05, + "loss": 3.4492, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051217174420503e-05, + "loss": 3.4488, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042831226909983e-05, + "loss": 3.4538, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034445279399463e-05, + "loss": 3.4657, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3026075710692675e-05, + "loss": 3.4522, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017689763182155e-05, + "loss": 3.4618, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009303815671635e-05, + "loss": 3.4637, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000917868161115e-05, + "loss": 3.4475, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992548299454324e-05, + "loss": 3.4573, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984162351943804e-05, + "loss": 3.4482, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975776404433284e-05, + "loss": 3.4626, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967390456922764e-05, + "loss": 3.4709, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2959020888215977e-05, + "loss": 3.4472, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950634940705457e-05, + "loss": 3.4513, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942248993194937e-05, + "loss": 3.4492, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933863045684413e-05, + "loss": 3.4573, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292549347697763e-05, + "loss": 3.468, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291710752946711e-05, + "loss": 3.4537, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290872158195659e-05, + "loss": 3.4515, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900352013249798e-05, + "loss": 3.4434, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891966065739278e-05, + "loss": 3.4653, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883580118228758e-05, + "loss": 3.4385, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875194170718238e-05, + "loss": 3.4544, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286682460201145e-05, + "loss": 3.453, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285843865450093e-05, + "loss": 3.4576, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.285005270699041e-05, + "loss": 3.449, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841666759479887e-05, + "loss": 3.459, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.28332971907731e-05, + "loss": 3.4548, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824911243262583e-05, + "loss": 3.4511, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816525295752063e-05, + "loss": 3.4563, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280813934824154e-05, + "loss": 3.4509, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799769779534752e-05, + "loss": 3.4616, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2791383832024232e-05, + "loss": 3.4656, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2783014263317444e-05, + "loss": 3.4541, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774628315806924e-05, + "loss": 3.4452, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766242368296404e-05, + "loss": 3.4521, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757856420785884e-05, + "loss": 3.4547, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274947047327536e-05, + "loss": 3.4431, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274108452576484e-05, + "loss": 3.4542, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273269857825432e-05, + "loss": 3.4444, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724329009547536e-05, + "loss": 3.4571, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715943062037013e-05, + "loss": 3.4469, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707557114526493e-05, + "loss": 3.4549, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699171167015973e-05, + "loss": 3.4446, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690785219505453e-05, + "loss": 3.4486, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682399271994933e-05, + "loss": 3.4563, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2674013324484413e-05, + "loss": 3.4592, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665627376973893e-05, + "loss": 3.4515, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657257808267105e-05, + "loss": 3.4604, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648871860756585e-05, + "loss": 3.4466, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640485913246065e-05, + "loss": 3.4561, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632099965735542e-05, + "loss": 3.4609, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623730397028754e-05, + "loss": 3.4612, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615344449518238e-05, + "loss": 3.4574, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606958502007714e-05, + "loss": 3.4656, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598572554497194e-05, + "loss": 3.4546, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590202985790407e-05, + "loss": 3.4622, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581817038279886e-05, + "loss": 3.4449, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573431090769363e-05, + "loss": 3.455, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565045143258846e-05, + "loss": 3.4492, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255667557455206e-05, + "loss": 3.448, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254828962704154e-05, + "loss": 3.4535, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539903679531015e-05, + "loss": 3.4505, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531517732020495e-05, + "loss": 3.4606, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523148163313708e-05, + "loss": 3.4355, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514762215803188e-05, + "loss": 3.4636, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.85435152053833, + "eval_runtime": 307.2455, + "eval_samples_per_second": 1241.974, + "eval_steps_per_second": 38.813, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506376268292668e-05, + "loss": 3.4425, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497990320782148e-05, + "loss": 3.4452, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248962075207536e-05, + "loss": 3.4577, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481234804564837e-05, + "loss": 3.456, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472848857054317e-05, + "loss": 3.4566, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.24644629095438e-05, + "loss": 3.4462, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456093340837013e-05, + "loss": 3.4418, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244770739332649e-05, + "loss": 3.4478, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243932144581597e-05, + "loss": 3.4562, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.243093549830545e-05, + "loss": 3.4573, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.242256592959866e-05, + "loss": 3.4476, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.241417998208814e-05, + "loss": 3.4527, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.240579403457762e-05, + "loss": 3.443, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397424465870834e-05, + "loss": 3.4418, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238903851836031e-05, + "loss": 3.4503, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238065257084979e-05, + "loss": 3.4399, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237226662333927e-05, + "loss": 3.4451, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363897054632486e-05, + "loss": 3.4528, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355511107121963e-05, + "loss": 3.4404, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347125159611443e-05, + "loss": 3.4664, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338739212100923e-05, + "loss": 3.4566, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330369643394132e-05, + "loss": 3.449, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2321983695883615e-05, + "loss": 3.4515, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313597748373095e-05, + "loss": 3.4621, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305211800862575e-05, + "loss": 3.44, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296842232155784e-05, + "loss": 3.4556, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288456284645264e-05, + "loss": 3.4469, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280070337134744e-05, + "loss": 3.4458, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271684389624224e-05, + "loss": 3.4379, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2263314820917437e-05, + "loss": 3.4509, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2254928873406916e-05, + "loss": 3.4622, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2246542925896396e-05, + "loss": 3.452, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238156978385876e-05, + "loss": 3.4585, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229787409679086e-05, + "loss": 3.4561, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.222140146216857e-05, + "loss": 3.4446, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221301551465805e-05, + "loss": 3.452, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220462956714753e-05, + "loss": 3.4434, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196259998440738e-05, + "loss": 3.4427, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187874050930218e-05, + "loss": 3.4402, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179488103419698e-05, + "loss": 3.4403, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171102155909178e-05, + "loss": 3.4474, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216273258720239e-05, + "loss": 3.4543, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215434663969187e-05, + "loss": 3.449, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214596069218135e-05, + "loss": 3.4459, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213757474467083e-05, + "loss": 3.4533, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212920517596404e-05, + "loss": 3.4482, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120819228453523e-05, + "loss": 3.4516, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112433280943002e-05, + "loss": 3.4449, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2104047333432482e-05, + "loss": 3.4274, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209567776472569e-05, + "loss": 3.4579, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208729181721517e-05, + "loss": 3.4432, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207890586970465e-05, + "loss": 3.4547, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.207051992219413e-05, + "loss": 3.4435, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062150353487344e-05, + "loss": 3.4413, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053764405976824e-05, + "loss": 3.4341, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045394837270033e-05, + "loss": 3.4525, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2037008889759513e-05, + "loss": 3.4389, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2028622942248993e-05, + "loss": 3.4455, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2020236994738476e-05, + "loss": 3.4541, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011851047227956e-05, + "loss": 3.4334, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003465099717436e-05, + "loss": 3.437, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995079152206913e-05, + "loss": 3.4565, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986693204696393e-05, + "loss": 3.4264, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978323635989605e-05, + "loss": 3.4299, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969937688479085e-05, + "loss": 3.4451, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961568119772298e-05, + "loss": 3.4466, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953182172261778e-05, + "loss": 3.4359, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944796224751257e-05, + "loss": 3.4461, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936410277240734e-05, + "loss": 3.4301, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928024329730214e-05, + "loss": 3.4338, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919638382219694e-05, + "loss": 3.4506, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911252434709177e-05, + "loss": 3.4434, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902866487198657e-05, + "loss": 3.4493, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894496918491866e-05, + "loss": 3.4485, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886110970981346e-05, + "loss": 3.4573, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877725023470826e-05, + "loss": 3.4371, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869339075960306e-05, + "loss": 3.4476, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.186096950725352e-05, + "loss": 3.4475, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852583559743e-05, + "loss": 3.4292, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.184419761223248e-05, + "loss": 3.4512, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835828043525688e-05, + "loss": 3.4482, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827442096015168e-05, + "loss": 3.4481, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.181907252730838e-05, + "loss": 3.4455, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.181068657979786e-05, + "loss": 3.4363, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180230063228734e-05, + "loss": 3.4359, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179391468477682e-05, + "loss": 3.4442, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.17855287372663e-05, + "loss": 3.4502, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.177714278975578e-05, + "loss": 3.4452, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.176875684224526e-05, + "loss": 3.4505, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.176037089473474e-05, + "loss": 3.4526, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.175201770483168e-05, + "loss": 3.4398, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174363175732116e-05, + "loss": 3.4456, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173524580981064e-05, + "loss": 3.4353, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172685986230012e-05, + "loss": 3.4555, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.17184739147896e-05, + "loss": 3.4552, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1710087967279085e-05, + "loss": 3.4387, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1701702019768565e-05, + "loss": 3.4378, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169331607225804e-05, + "loss": 3.4363, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1684946503551254e-05, + "loss": 3.4465, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1676560556040734e-05, + "loss": 3.4535, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166817460853021e-05, + "loss": 3.4429, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659805039823426e-05, + "loss": 3.4417, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651419092312906e-05, + "loss": 3.4354, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1643033144802386e-05, + "loss": 3.4496, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.1634647197291862e-05, + "loss": 3.4319, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.1626277628585075e-05, + "loss": 3.4455, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1617891681074555e-05, + "loss": 3.4357, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1609505733564038e-05, + "loss": 3.4505, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1601119786053515e-05, + "loss": 3.4393, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592750217346727e-05, + "loss": 3.4444, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584364269836207e-05, + "loss": 3.4456, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575978322325684e-05, + "loss": 3.4381, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567592374815164e-05, + "loss": 3.4469, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155922280610838e-05, + "loss": 3.443, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.155083685859786e-05, + "loss": 3.4482, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542450911087336e-05, + "loss": 3.454, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.153408134238055e-05, + "loss": 3.4401, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152569539487003e-05, + "loss": 3.442, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151730944735951e-05, + "loss": 3.4363, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150892349984899e-05, + "loss": 3.4456, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.150053755233847e-05, + "loss": 3.4386, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.149215160482795e-05, + "loss": 3.4405, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.148376565731743e-05, + "loss": 3.4311, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.147537970980691e-05, + "loss": 3.4445, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1467010141100117e-05, + "loss": 3.4357, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.14586241935896e-05, + "loss": 3.4484, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.145023824607908e-05, + "loss": 3.4327, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.144185229856856e-05, + "loss": 3.4415, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.143348272986177e-05, + "loss": 3.4427, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.142509678235125e-05, + "loss": 3.4498, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.141671083484073e-05, + "loss": 3.4409, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140832488733021e-05, + "loss": 3.4485, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399955318623422e-05, + "loss": 3.4341, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391569371112902e-05, + "loss": 3.4473, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383183423602382e-05, + "loss": 3.4471, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374797476091862e-05, + "loss": 3.4488, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.136642790738507e-05, + "loss": 3.4474, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1358041959874554e-05, + "loss": 3.4538, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349656012364034e-05, + "loss": 3.4434, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341270064853514e-05, + "loss": 3.4539, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332900496146723e-05, + "loss": 3.4336, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1324514548636203e-05, + "loss": 3.4445, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1316128601125683e-05, + "loss": 3.4397, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1307742653615163e-05, + "loss": 3.441, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299373084908376e-05, + "loss": 3.4368, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1290987137397856e-05, + "loss": 3.437, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1282601189887336e-05, + "loss": 3.4471, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1274215242376812e-05, + "loss": 3.4275, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1265845673670025e-05, + "loss": 3.4543, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.855902671813965, + "eval_runtime": 307.1828, + "eval_samples_per_second": 1242.228, + "eval_steps_per_second": 38.821, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257459726159508e-05, + "loss": 3.4339, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249073778648988e-05, + "loss": 3.4325, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240687831138465e-05, + "loss": 3.4444, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232301883627945e-05, + "loss": 3.4473, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223932314921157e-05, + "loss": 3.4431, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215546367410634e-05, + "loss": 3.4385, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207160419900117e-05, + "loss": 3.4342, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198774472389597e-05, + "loss": 3.4347, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119040490368281e-05, + "loss": 3.4437, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182018956172286e-05, + "loss": 3.4492, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173633008661766e-05, + "loss": 3.4372, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165247061151246e-05, + "loss": 3.4361, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156877492444462e-05, + "loss": 3.4381, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114849154493394e-05, + "loss": 3.4314, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114010559742342e-05, + "loss": 3.439, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131719649912898e-05, + "loss": 3.429, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123350081206107e-05, + "loss": 3.4367, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114964133695587e-05, + "loss": 3.4406, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110657818618507e-05, + "loss": 3.4291, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109819223867455e-05, + "loss": 3.4537, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108982266996776e-05, + "loss": 3.448, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081453101260972e-05, + "loss": 3.4387, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1073067153750452e-05, + "loss": 3.4408, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064681206239932e-05, + "loss": 3.446, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056295258729412e-05, + "loss": 3.4301, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047909311218892e-05, + "loss": 3.4433, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039523363708372e-05, + "loss": 3.4373, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031137416197852e-05, + "loss": 3.4327, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022751468687332e-05, + "loss": 3.4272, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101438189998054e-05, + "loss": 3.4437, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005995952470024e-05, + "loss": 3.4473, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997610004959504e-05, + "loss": 3.4439, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989224057448984e-05, + "loss": 3.449, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980870867545926e-05, + "loss": 3.4412, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972484920035406e-05, + "loss": 3.4348, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964098972524886e-05, + "loss": 3.4433, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955713025014366e-05, + "loss": 3.4361, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947327077503846e-05, + "loss": 3.4291, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938941129993326e-05, + "loss": 3.4292, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930555182482806e-05, + "loss": 3.4305, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922169234972286e-05, + "loss": 3.4364, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913799666265495e-05, + "loss": 3.4413, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905413718754978e-05, + "loss": 3.4399, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0897027771244458e-05, + "loss": 3.4352, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888641823733938e-05, + "loss": 3.4401, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880272255027147e-05, + "loss": 3.4396, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871886307516627e-05, + "loss": 3.4401, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863500360006107e-05, + "loss": 3.4354, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855114412495587e-05, + "loss": 3.4126, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.08467448437888e-05, + "loss": 3.45, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083835889627828e-05, + "loss": 3.4306, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.082997294876776e-05, + "loss": 3.4458, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821587001257236e-05, + "loss": 3.4303, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081321743255045e-05, + "loss": 3.4342, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804831485039932e-05, + "loss": 3.4217, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079646191633314e-05, + "loss": 3.437, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078807596882262e-05, + "loss": 3.4286, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.07796900213121e-05, + "loss": 3.4337, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077130407380158e-05, + "loss": 3.446, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762918126291057e-05, + "loss": 3.4251, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075453217878054e-05, + "loss": 3.4238, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074614623127002e-05, + "loss": 3.4441, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.07377602837595e-05, + "loss": 3.4185, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072939071505271e-05, + "loss": 3.418, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072100476754219e-05, + "loss": 3.4349, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712635198835402e-05, + "loss": 3.4335, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704249251324885e-05, + "loss": 3.4293, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695863303814362e-05, + "loss": 3.4346, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687477356303842e-05, + "loss": 3.4158, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679091408793322e-05, + "loss": 3.4274, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670705461282802e-05, + "loss": 3.4376, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662319513772282e-05, + "loss": 3.4329, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653933566261762e-05, + "loss": 3.4418, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645563997554974e-05, + "loss": 3.4357, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637194428848183e-05, + "loss": 3.4425, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628808481337663e-05, + "loss": 3.4254, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620422533827143e-05, + "loss": 3.44, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0612036586316623e-05, + "loss": 3.4342, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603650638806103e-05, + "loss": 3.421, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595264691295586e-05, + "loss": 3.438, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586878743785066e-05, + "loss": 3.439, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578509175078276e-05, + "loss": 3.4375, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570123227567755e-05, + "loss": 3.443, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561737280057235e-05, + "loss": 3.4219, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553351332546712e-05, + "loss": 3.4256, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544965385036195e-05, + "loss": 3.432, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536579437525675e-05, + "loss": 3.4393, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528193490015155e-05, + "loss": 3.4362, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519807542504635e-05, + "loss": 3.436, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511437973797844e-05, + "loss": 3.4412, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503068405091057e-05, + "loss": 3.4342, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049468245758054e-05, + "loss": 3.4325, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486296510070017e-05, + "loss": 3.4281, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477910562559497e-05, + "loss": 3.4422, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469524615048977e-05, + "loss": 3.4414, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461138667538457e-05, + "loss": 3.4299, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452752720027937e-05, + "loss": 3.4247, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444366772517416e-05, + "loss": 3.4271, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043599720381063e-05, + "loss": 3.4322, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042761125630011e-05, + "loss": 3.4438, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041922530878959e-05, + "loss": 3.4288, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.041083936127907e-05, + "loss": 3.4339, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402469792572278e-05, + "loss": 3.4265, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394083845061758e-05, + "loss": 3.4344, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038569789755124e-05, + "loss": 3.424, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037732832884445e-05, + "loss": 3.4352, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036894238133393e-05, + "loss": 3.4225, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036055643382341e-05, + "loss": 3.4394, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035217048631289e-05, + "loss": 3.4301, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343800917606103e-05, + "loss": 3.4323, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335414970095583e-05, + "loss": 3.4329, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327029022585063e-05, + "loss": 3.4343, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318643075074543e-05, + "loss": 3.4329, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031027350636775e-05, + "loss": 3.4305, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030188755885723e-05, + "loss": 3.4358, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029350161134671e-05, + "loss": 3.4445, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285132042639924e-05, + "loss": 3.4286, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276746095129404e-05, + "loss": 3.4313, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268360147618884e-05, + "loss": 3.4267, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259974200108364e-05, + "loss": 3.431, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025158825259784e-05, + "loss": 3.4287, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024320230508732e-05, + "loss": 3.4297, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234816357576804e-05, + "loss": 3.421, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226446788870016e-05, + "loss": 3.4302, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218060841359493e-05, + "loss": 3.4272, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209674893848973e-05, + "loss": 3.432, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201288946338453e-05, + "loss": 3.4196, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192902998827933e-05, + "loss": 3.4332, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184517051317413e-05, + "loss": 3.4305, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176131103806896e-05, + "loss": 3.4387, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167745156296373e-05, + "loss": 3.4309, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159375587589585e-05, + "loss": 3.4376, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150989640079065e-05, + "loss": 3.4224, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142603692568545e-05, + "loss": 3.4393, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134217745058025e-05, + "loss": 3.4387, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125848176351237e-05, + "loss": 3.4389, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117462228840717e-05, + "loss": 3.4399, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109076281330197e-05, + "loss": 3.4387, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100690333819674e-05, + "loss": 3.4339, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092320765112886e-05, + "loss": 3.4402, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083934817602366e-05, + "loss": 3.4247, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075548870091846e-05, + "loss": 3.4346, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067162922581326e-05, + "loss": 3.4277, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.005879335387454e-05, + "loss": 3.4333, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050423785167748e-05, + "loss": 3.4257, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042037837657228e-05, + "loss": 3.4269, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003365189014671e-05, + "loss": 3.4337, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002526594263619e-05, + "loss": 3.4211, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.00168963739294e-05, + "loss": 3.4423, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8573269844055176, + "eval_runtime": 320.1372, + "eval_samples_per_second": 1191.961, + "eval_steps_per_second": 37.25, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.000851042641888e-05, + "loss": 3.4208, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.000012447890836e-05, + "loss": 3.4261, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.999173853139784e-05, + "loss": 3.4283, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.998335258388732e-05, + "loss": 3.4335, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.99749666363768e-05, + "loss": 3.4337, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996658068886628e-05, + "loss": 3.4248, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995819474135576e-05, + "loss": 3.4306, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994982517264897e-05, + "loss": 3.4261, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.994143922513845e-05, + "loss": 3.427, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9933069656431665e-05, + "loss": 3.4391, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924683708921145e-05, + "loss": 3.4248, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991629776141062e-05, + "loss": 3.4268, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.99079118139001e-05, + "loss": 3.427, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989952586638958e-05, + "loss": 3.4186, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989113991887906e-05, + "loss": 3.4286, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988275397136854e-05, + "loss": 3.4177, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.987436802385802e-05, + "loss": 3.4255, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865998455151234e-05, + "loss": 3.4324, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857612507640713e-05, + "loss": 3.4183, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849226560130193e-05, + "loss": 3.4392, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9840840612619673e-05, + "loss": 3.4402, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.983248742271662e-05, + "loss": 3.4298, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9824101475206095e-05, + "loss": 3.4259, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815715527695575e-05, + "loss": 3.4347, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807329580185055e-05, + "loss": 3.4262, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798943632674535e-05, + "loss": 3.4286, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790557685164015e-05, + "loss": 3.4273, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782171737653495e-05, + "loss": 3.4248, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773785790142975e-05, + "loss": 3.4211, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765416221436187e-05, + "loss": 3.4257, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757030273925667e-05, + "loss": 3.4336, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748644326415147e-05, + "loss": 3.4367, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740274757708356e-05, + "loss": 3.4366, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731888810197836e-05, + "loss": 3.4304, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.972350286268732e-05, + "loss": 3.4208, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.97151169151768e-05, + "loss": 3.4338, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706730967666276e-05, + "loss": 3.4263, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698345020155756e-05, + "loss": 3.4194, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689959072645236e-05, + "loss": 3.4192, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681573125134716e-05, + "loss": 3.4171, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.967320355642793e-05, + "loss": 3.4234, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.966483398772114e-05, + "loss": 3.4294, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.965644804021062e-05, + "loss": 3.4337, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648062092700097e-05, + "loss": 3.4273, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639676145189577e-05, + "loss": 3.4262, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631290197679057e-05, + "loss": 3.4314, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622904250168537e-05, + "loss": 3.4273, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.961451830265802e-05, + "loss": 3.4279, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.96061323551475e-05, + "loss": 3.4029, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959776278644071e-05, + "loss": 3.4384, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.958937683893019e-05, + "loss": 3.4221, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958099089141967e-05, + "loss": 3.4349, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572621322712882e-05, + "loss": 3.4188, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564235375202362e-05, + "loss": 3.4197, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9555849427691842e-05, + "loss": 3.4116, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954747985898505e-05, + "loss": 3.4279, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953909391147453e-05, + "loss": 3.4206, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953070796396401e-05, + "loss": 3.4221, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952232201645349e-05, + "loss": 3.4325, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513936068942974e-05, + "loss": 3.4184, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950555012143245e-05, + "loss": 3.41, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949716417392193e-05, + "loss": 3.4361, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948877822641141e-05, + "loss": 3.41, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480408657704623e-05, + "loss": 3.4063, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472022710194103e-05, + "loss": 3.4258, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463653141487316e-05, + "loss": 3.4229, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455267193976796e-05, + "loss": 3.4171, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446881246466276e-05, + "loss": 3.4218, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438495298955752e-05, + "loss": 3.4071, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430109351445232e-05, + "loss": 3.4153, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421723403934712e-05, + "loss": 3.4282, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413337456424195e-05, + "loss": 3.4197, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404951508913675e-05, + "loss": 3.4324, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396598319010617e-05, + "loss": 3.4237, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388212371500097e-05, + "loss": 3.4345, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379826423989574e-05, + "loss": 3.4156, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371440476479057e-05, + "loss": 3.4284, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936307090777227e-05, + "loss": 3.422, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935468496026175e-05, + "loss": 3.4126, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346299012751226e-05, + "loss": 3.4285, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337913065240706e-05, + "loss": 3.431, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932954349653392e-05, + "loss": 3.4233, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321157549023398e-05, + "loss": 3.4326, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312771601512878e-05, + "loss": 3.4086, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304385654002358e-05, + "loss": 3.4143, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295999706491838e-05, + "loss": 3.4249, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287630137785047e-05, + "loss": 3.4274, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279244190274527e-05, + "loss": 3.4253, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927085824276401e-05, + "loss": 3.4281, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.926247229525349e-05, + "loss": 3.4277, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.92541027265467e-05, + "loss": 3.4246, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924571677903618e-05, + "loss": 3.4228, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923733083152566e-05, + "loss": 3.4171, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922894488401514e-05, + "loss": 3.4348, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922055893650462e-05, + "loss": 3.4262, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.92121729889941e-05, + "loss": 3.4242, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203803420287312e-05, + "loss": 3.4182, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195417472776792e-05, + "loss": 3.4156, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9187031525266272e-05, + "loss": 3.4184, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178645577755752e-05, + "loss": 3.4338, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170259630245228e-05, + "loss": 3.4215, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916187368273471e-05, + "loss": 3.4238, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153504114027924e-05, + "loss": 3.4166, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145118166517404e-05, + "loss": 3.4203, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913673221900688e-05, + "loss": 3.4199, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912834627149636e-05, + "loss": 3.4204, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.911996032398584e-05, + "loss": 3.4112, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.911157437647532e-05, + "loss": 3.4301, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103188428964804e-05, + "loss": 3.4229, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094802481454284e-05, + "loss": 3.4193, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086432912747493e-05, + "loss": 3.4192, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078046965236973e-05, + "loss": 3.4274, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069661017726453e-05, + "loss": 3.4231, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061275070215933e-05, + "loss": 3.4192, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052905501509145e-05, + "loss": 3.4252, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044519553998625e-05, + "loss": 3.4328, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036133606488105e-05, + "loss": 3.4159, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027764037781314e-05, + "loss": 3.4278, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019378090270794e-05, + "loss": 3.4134, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9010992142760274e-05, + "loss": 3.4219, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002606195249758e-05, + "loss": 3.4176, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994220247739234e-05, + "loss": 3.4152, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985834300228714e-05, + "loss": 3.4147, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977448352718194e-05, + "loss": 3.4213, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969062405207674e-05, + "loss": 3.4212, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960692836500883e-05, + "loss": 3.4197, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952306888990366e-05, + "loss": 3.4092, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943920941479846e-05, + "loss": 3.4204, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935534993969326e-05, + "loss": 3.4184, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927149046458806e-05, + "loss": 3.4284, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918763098948286e-05, + "loss": 3.4203, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910377151437763e-05, + "loss": 3.4247, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8901991203927243e-05, + "loss": 3.4141, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889362163522046e-05, + "loss": 3.4313, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888523568770994e-05, + "loss": 3.427, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8876849740199415e-05, + "loss": 3.4265, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868463792688895e-05, + "loss": 3.428, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860094223982108e-05, + "loss": 3.4273, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851708276471588e-05, + "loss": 3.4241, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843322328961067e-05, + "loss": 3.4303, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8834936381450547e-05, + "loss": 3.4134, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882658319154749e-05, + "loss": 3.4256, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881819724403697e-05, + "loss": 3.4185, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880981129652645e-05, + "loss": 3.4207, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880142534901593e-05, + "loss": 3.4137, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793039401505412e-05, + "loss": 3.4166, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878465345399489e-05, + "loss": 3.4227, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.877626750648437e-05, + "loss": 3.4161, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876788155897385e-05, + "loss": 3.4292, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.85945463180542, + "eval_runtime": 316.6651, + "eval_samples_per_second": 1205.03, + "eval_steps_per_second": 37.658, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.875951199026706e-05, + "loss": 3.4074, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751126042756538e-05, + "loss": 3.4139, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.874274009524602e-05, + "loss": 3.417, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.87343541477355e-05, + "loss": 3.4293, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726000957832443e-05, + "loss": 3.4234, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717615010321923e-05, + "loss": 3.4124, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709229062811403e-05, + "loss": 3.4215, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700843115300883e-05, + "loss": 3.4156, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692457167790363e-05, + "loss": 3.4162, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684087599083575e-05, + "loss": 3.4326, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675701651573055e-05, + "loss": 3.412, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667315704062535e-05, + "loss": 3.4135, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865892975655201e-05, + "loss": 3.4261, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865054380904149e-05, + "loss": 3.4037, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642157861530975e-05, + "loss": 3.4166, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633771914020455e-05, + "loss": 3.408, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625385966509935e-05, + "loss": 3.4158, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617016397803144e-05, + "loss": 3.4198, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608630450292624e-05, + "loss": 3.4075, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600244502782104e-05, + "loss": 3.4269, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591858555271584e-05, + "loss": 3.4296, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858350536536853e-05, + "loss": 3.4219, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857511941785801e-05, + "loss": 3.4201, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566733470347485e-05, + "loss": 3.4198, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558347522836965e-05, + "loss": 3.4183, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8549961575326445e-05, + "loss": 3.4146, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854157562781593e-05, + "loss": 3.42, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853318968030541e-05, + "loss": 3.4178, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852480373279489e-05, + "loss": 3.4084, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516434164088097e-05, + "loss": 3.4155, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508048216577577e-05, + "loss": 3.4198, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499662269067057e-05, + "loss": 3.431, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491276321556537e-05, + "loss": 3.4262, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848290675284975e-05, + "loss": 3.4219, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847452080533923e-05, + "loss": 3.4118, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846613485782871e-05, + "loss": 3.4153, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845774891031819e-05, + "loss": 3.4203, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449362962807666e-05, + "loss": 3.4087, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440977015297146e-05, + "loss": 3.4093, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.843259106778663e-05, + "loss": 3.4053, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.842422149907984e-05, + "loss": 3.4168, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841585193037305e-05, + "loss": 3.4155, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.840746598286253e-05, + "loss": 3.4202, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839908003535201e-05, + "loss": 3.4169, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.839069408784149e-05, + "loss": 3.4157, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.838230814033097e-05, + "loss": 3.4172, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837392219282045e-05, + "loss": 3.4144, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365552624113663e-05, + "loss": 3.4228, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835716667660314e-05, + "loss": 3.3897, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834878072909262e-05, + "loss": 3.4223, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.83403947815821e-05, + "loss": 3.4111, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332008834071583e-05, + "loss": 3.4258, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323622886561063e-05, + "loss": 3.4102, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315236939050543e-05, + "loss": 3.4102, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830685099154002e-05, + "loss": 3.4003, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829849780163696e-05, + "loss": 3.4166, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290111854126445e-05, + "loss": 3.4149, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281725906615925e-05, + "loss": 3.4078, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273339959105405e-05, + "loss": 3.4229, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264954011594885e-05, + "loss": 3.4108, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256568064084365e-05, + "loss": 3.3929, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824818211657384e-05, + "loss": 3.4254, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823979616906332e-05, + "loss": 3.4015, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231426600356537e-05, + "loss": 3.3978, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223040652846017e-05, + "loss": 3.4136, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214654705335493e-05, + "loss": 3.4114, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206268757824973e-05, + "loss": 3.4046, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197882810314453e-05, + "loss": 3.4159, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189496862803933e-05, + "loss": 3.3982, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181110915293413e-05, + "loss": 3.4022, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172741346586626e-05, + "loss": 3.4158, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164355399076106e-05, + "loss": 3.4095, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8155969451565586e-05, + "loss": 3.423, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147583504055066e-05, + "loss": 3.411, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139213935348275e-05, + "loss": 3.4221, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8130827987837755e-05, + "loss": 3.4065, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122442040327238e-05, + "loss": 3.4229, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114056092816718e-05, + "loss": 3.4073, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105670145306198e-05, + "loss": 3.4059, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097284197795674e-05, + "loss": 3.415, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088898250285154e-05, + "loss": 3.418, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080528681578367e-05, + "loss": 3.4145, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072142734067847e-05, + "loss": 3.424, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063756786557327e-05, + "loss": 3.3962, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055370839046807e-05, + "loss": 3.4034, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046984891536287e-05, + "loss": 3.4141, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038598944025767e-05, + "loss": 3.4187, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030212996515247e-05, + "loss": 3.412, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021827049004727e-05, + "loss": 3.4192, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801345748029794e-05, + "loss": 3.4155, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005087911591148e-05, + "loss": 3.4177, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996701964080628e-05, + "loss": 3.4123, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988316016570108e-05, + "loss": 3.4045, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979930069059588e-05, + "loss": 3.4222, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971544121549068e-05, + "loss": 3.4184, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963158174038548e-05, + "loss": 3.4124, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795477222652803e-05, + "loss": 3.4102, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946386279017508e-05, + "loss": 3.4034, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793801671031072e-05, + "loss": 3.411, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.79296307628002e-05, + "loss": 3.4219, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921244815289677e-05, + "loss": 3.409, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791285886777916e-05, + "loss": 3.4154, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904489299072373e-05, + "loss": 3.4059, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896119730365582e-05, + "loss": 3.4083, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887733782855062e-05, + "loss": 3.4133, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879347835344542e-05, + "loss": 3.4079, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.787096188783402e-05, + "loss": 3.4018, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862592319127234e-05, + "loss": 3.419, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854206371616714e-05, + "loss": 3.4154, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845820424106194e-05, + "loss": 3.4033, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837434476595674e-05, + "loss": 3.4105, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782904852908515e-05, + "loss": 3.4113, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.782066258157463e-05, + "loss": 3.4174, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812276634064114e-05, + "loss": 3.4064, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803907065357326e-05, + "loss": 3.4184, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795521117846803e-05, + "loss": 3.4218, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787135170336283e-05, + "loss": 3.4028, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778765601629495e-05, + "loss": 3.415, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770379654118975e-05, + "loss": 3.4041, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7761993706608455e-05, + "loss": 3.4123, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753607759097935e-05, + "loss": 3.4109, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745221811587415e-05, + "loss": 3.4037, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736835864076895e-05, + "loss": 3.4017, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728449916566375e-05, + "loss": 3.4132, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720063969055855e-05, + "loss": 3.4098, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711694400349068e-05, + "loss": 3.4125, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703308452838548e-05, + "loss": 3.4005, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7694922505328027e-05, + "loss": 3.4051, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686536557817507e-05, + "loss": 3.408, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678150610306984e-05, + "loss": 3.4183, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669764662796464e-05, + "loss": 3.4134, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661378715285944e-05, + "loss": 3.4156, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7652992767775424e-05, + "loss": 3.4001, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644623199068636e-05, + "loss": 3.4234, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636237251558116e-05, + "loss": 3.4113, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762786768285133e-05, + "loss": 3.4183, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619481735340805e-05, + "loss": 3.4146, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611095787830285e-05, + "loss": 3.4179, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760270984031977e-05, + "loss": 3.4126, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759432389280925e-05, + "loss": 3.423, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758593794529873e-05, + "loss": 3.3997, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757755199778821e-05, + "loss": 3.4165, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756916605027769e-05, + "loss": 3.4068, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756081286037463e-05, + "loss": 3.4109, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.755242691286411e-05, + "loss": 3.4031, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754404096535359e-05, + "loss": 3.4073, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753565501784307e-05, + "loss": 3.4078, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752726907033255e-05, + "loss": 3.4077, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751888312282203e-05, + "loss": 3.4145, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8599934577941895, + "eval_runtime": 312.3238, + "eval_samples_per_second": 1221.78, + "eval_steps_per_second": 38.182, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.751049717531151e-05, + "loss": 3.4025, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502111227800986e-05, + "loss": 3.4021, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493741659094202e-05, + "loss": 3.4042, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485355711583682e-05, + "loss": 3.4188, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7476969764073162e-05, + "loss": 3.4172, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746858381656264e-05, + "loss": 3.3994, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.746021424785585e-05, + "loss": 3.4093, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745182830034533e-05, + "loss": 3.4048, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.744344235283481e-05, + "loss": 3.4073, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435072784128024e-05, + "loss": 3.4195, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426686836617504e-05, + "loss": 3.4032, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418300889106984e-05, + "loss": 3.4061, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740991494159646e-05, + "loss": 3.4152, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740152899408594e-05, + "loss": 3.3946, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393143046575423e-05, + "loss": 3.4054, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384757099064903e-05, + "loss": 3.3964, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376371151554383e-05, + "loss": 3.4062, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368001582847592e-05, + "loss": 3.4105, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359615635337072e-05, + "loss": 3.3955, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351229687826552e-05, + "loss": 3.4177, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342843740316032e-05, + "loss": 3.4183, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334490550412977e-05, + "loss": 3.4122, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326104602902457e-05, + "loss": 3.409, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317718655391934e-05, + "loss": 3.4092, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309332707881414e-05, + "loss": 3.4119, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7300946760370894e-05, + "loss": 3.4034, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292560812860377e-05, + "loss": 3.4039, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284174865349857e-05, + "loss": 3.4115, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275788917839337e-05, + "loss": 3.3973, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267419349132546e-05, + "loss": 3.4056, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259033401622026e-05, + "loss": 3.4103, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250647454111506e-05, + "loss": 3.4137, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242261506600986e-05, + "loss": 3.4204, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.72338919378942e-05, + "loss": 3.4115, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722550599038368e-05, + "loss": 3.4024, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721712004287316e-05, + "loss": 3.4054, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208734095362638e-05, + "loss": 3.4121, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200348147852115e-05, + "loss": 3.3973, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7191962200341595e-05, + "loss": 3.3992, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183576252831078e-05, + "loss": 3.4006, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717520668412429e-05, + "loss": 3.4017, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.71668371154175e-05, + "loss": 3.4082, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715845116790698e-05, + "loss": 3.4105, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.715006522039646e-05, + "loss": 3.4109, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.714167927288594e-05, + "loss": 3.4016, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.713329332537542e-05, + "loss": 3.4109, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.71249073778649e-05, + "loss": 3.4054, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711652143035438e-05, + "loss": 3.4106, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710813548284386e-05, + "loss": 3.3836, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.709976591413707e-05, + "loss": 3.4103, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709137996662655e-05, + "loss": 3.4029, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7082994019116032e-05, + "loss": 3.4174, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074608071605512e-05, + "loss": 3.4009, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706623850289872e-05, + "loss": 3.3996, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.70578525553882e-05, + "loss": 3.3923, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704946660787768e-05, + "loss": 3.3994, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041097039170893e-05, + "loss": 3.4097, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032711091660373e-05, + "loss": 3.3932, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024325144149853e-05, + "loss": 3.4149, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7015939196639333e-05, + "loss": 3.3998, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007553249128813e-05, + "loss": 3.3797, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999167301618293e-05, + "loss": 3.4148, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.699078135410777e-05, + "loss": 3.3922, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982411785400986e-05, + "loss": 3.3861, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974025837890465e-05, + "loss": 3.4057, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965656269183675e-05, + "loss": 3.4021, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957270321673155e-05, + "loss": 3.3925, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6948884374162634e-05, + "loss": 3.409, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6940498426652114e-05, + "loss": 3.3865, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932112479141594e-05, + "loss": 3.3914, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923726531631074e-05, + "loss": 3.4049, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915356962924287e-05, + "loss": 3.4039, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6906971015413767e-05, + "loss": 3.4084, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898585067903243e-05, + "loss": 3.4026, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890199120392723e-05, + "loss": 3.4116, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688182955168594e-05, + "loss": 3.3981, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873443604175416e-05, + "loss": 3.4133, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865057656664896e-05, + "loss": 3.3931, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856671709154376e-05, + "loss": 3.3958, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848285761643856e-05, + "loss": 3.4063, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839899814133336e-05, + "loss": 3.4027, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831530245426548e-05, + "loss": 3.4081, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823144297916028e-05, + "loss": 3.4124, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6814758350405508e-05, + "loss": 3.3913, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806372402894988e-05, + "loss": 3.3897, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6797986455384468e-05, + "loss": 3.401, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789616886677677e-05, + "loss": 3.4107, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781230939167157e-05, + "loss": 3.3988, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677284499165664e-05, + "loss": 3.4097, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676445904414612e-05, + "loss": 3.4079, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.675608947543933e-05, + "loss": 3.409, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.674770352792881e-05, + "loss": 3.4009, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673931758041829e-05, + "loss": 3.3967, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.673093163290777e-05, + "loss": 3.4099, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.672254568539725e-05, + "loss": 3.4056, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.671415973788673e-05, + "loss": 3.4062, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.670579016917994e-05, + "loss": 3.3972, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669740422166942e-05, + "loss": 3.3917, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689018274158898e-05, + "loss": 3.4016, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680632326648378e-05, + "loss": 3.4114, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672246379137858e-05, + "loss": 3.4012, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666386043162734e-05, + "loss": 3.4032, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.665547448411682e-05, + "loss": 3.397, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664710491541003e-05, + "loss": 3.3969, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663871896789951e-05, + "loss": 3.4061, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663033302038899e-05, + "loss": 3.3947, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662194707287847e-05, + "loss": 3.3955, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613577504171683e-05, + "loss": 3.4056, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605191556661163e-05, + "loss": 3.4055, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596805609150643e-05, + "loss": 3.3972, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588419661640123e-05, + "loss": 3.3989, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580033714129603e-05, + "loss": 3.3975, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657164776661908e-05, + "loss": 3.4101, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563261819108562e-05, + "loss": 3.3969, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6554875871598042e-05, + "loss": 3.4091, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546522681694984e-05, + "loss": 3.4081, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538136734184464e-05, + "loss": 3.3997, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6529767165477673e-05, + "loss": 3.3998, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521381217967156e-05, + "loss": 3.3973, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6512995270456636e-05, + "loss": 3.3998, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504609322946116e-05, + "loss": 3.4027, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496223375435596e-05, + "loss": 3.3916, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487837427925076e-05, + "loss": 3.3937, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479451480414553e-05, + "loss": 3.4012, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471065532904033e-05, + "loss": 3.4016, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.646269596419725e-05, + "loss": 3.3996, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454310016686725e-05, + "loss": 3.3936, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6445924069176205e-05, + "loss": 3.3993, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437538121665685e-05, + "loss": 3.3928, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429152174155165e-05, + "loss": 3.4116, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420766226644645e-05, + "loss": 3.3991, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412380279134125e-05, + "loss": 3.406, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6403994331623605e-05, + "loss": 3.39, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395624762916817e-05, + "loss": 3.4107, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387238815406297e-05, + "loss": 3.4008, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6378869246699507e-05, + "loss": 3.4099, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370483299188986e-05, + "loss": 3.4079, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.636209735167847e-05, + "loss": 3.4031, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.635371140416795e-05, + "loss": 3.4022, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634532545665743e-05, + "loss": 3.4155, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6336939509146906e-05, + "loss": 3.3903, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328553561636386e-05, + "loss": 3.4049, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320167614125866e-05, + "loss": 3.397, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.631179804541908e-05, + "loss": 3.3998, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630341209790856e-05, + "loss": 3.3947, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629502615039804e-05, + "loss": 3.3968, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628664020288752e-05, + "loss": 3.3944, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278254255377e-05, + "loss": 3.405, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6269884686670208e-05, + "loss": 3.4003, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.861694097518921, + "eval_runtime": 314.7613, + "eval_samples_per_second": 1212.319, + "eval_steps_per_second": 37.886, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261498739159688e-05, + "loss": 3.3911, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625311279164917e-05, + "loss": 3.3896, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.624472684413865e-05, + "loss": 3.3931, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623634089662813e-05, + "loss": 3.4075, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6227987706725072e-05, + "loss": 3.4067, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219601759214552e-05, + "loss": 3.3904, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211215811704032e-05, + "loss": 3.4001, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202829864193512e-05, + "loss": 3.3956, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194443916682992e-05, + "loss": 3.3957, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.61860743479762e-05, + "loss": 3.4041, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617768840046568e-05, + "loss": 3.3977, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616930245295516e-05, + "loss": 3.3929, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.616091650544464e-05, + "loss": 3.4059, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152530557934125e-05, + "loss": 3.3832, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144144610423605e-05, + "loss": 3.3958, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135758662913084e-05, + "loss": 3.3836, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612737271540256e-05, + "loss": 3.4, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119003146695774e-05, + "loss": 3.402, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110617199185254e-05, + "loss": 3.3821, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102231251674733e-05, + "loss": 3.4047, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6093845304164213e-05, + "loss": 3.4091, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085492114261155e-05, + "loss": 3.4001, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077106166750635e-05, + "loss": 3.4, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068720219240115e-05, + "loss": 3.4018, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060334271729595e-05, + "loss": 3.4009, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051948324219078e-05, + "loss": 3.3937, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043562376708558e-05, + "loss": 3.3913, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035176429198035e-05, + "loss": 3.4001, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026790481687515e-05, + "loss": 3.3874, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018420912980727e-05, + "loss": 3.3956, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010034965470207e-05, + "loss": 3.4022, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001649017959687e-05, + "loss": 3.4067, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993263070449167e-05, + "loss": 3.4028, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598489350174238e-05, + "loss": 3.4078, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976507554231856e-05, + "loss": 3.3898, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968121606721336e-05, + "loss": 3.3972, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959735659210816e-05, + "loss": 3.403, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951349711700296e-05, + "loss": 3.3829, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594296376418978e-05, + "loss": 3.3932, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593457781667926e-05, + "loss": 3.3895, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592620824797247e-05, + "loss": 3.3906, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591783867926568e-05, + "loss": 3.3941, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909452731755157e-05, + "loss": 3.4019, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590106678424464e-05, + "loss": 3.3972, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.589268083673412e-05, + "loss": 3.3942, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.58842948892236e-05, + "loss": 3.3983, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587590894171308e-05, + "loss": 3.3918, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586752299420256e-05, + "loss": 3.4026, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585915342549577e-05, + "loss": 3.3779, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.585076747798525e-05, + "loss": 3.3985, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842381530474733e-05, + "loss": 3.3898, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5833995582964213e-05, + "loss": 3.4063, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582560963545369e-05, + "loss": 3.3917, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581722368794317e-05, + "loss": 3.3871, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580883774043265e-05, + "loss": 3.3824, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.580046817172586e-05, + "loss": 3.3936, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792098603019074e-05, + "loss": 3.4013, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783712655508554e-05, + "loss": 3.3851, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775326707998034e-05, + "loss": 3.4032, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.576694076048751e-05, + "loss": 3.3935, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575855481297699e-05, + "loss": 3.3709, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575016886546647e-05, + "loss": 3.4041, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741799296759687e-05, + "loss": 3.3849, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733413349249163e-05, + "loss": 3.3772, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725027401738643e-05, + "loss": 3.3923, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716641454228123e-05, + "loss": 3.3944, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708271885521332e-05, + "loss": 3.3847, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5699885938010812e-05, + "loss": 3.3999, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691499990500296e-05, + "loss": 3.3731, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683114042989776e-05, + "loss": 3.3832, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674744474282985e-05, + "loss": 3.3977, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666358526772465e-05, + "loss": 3.3946, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5657972579261945e-05, + "loss": 3.3951, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649586631751424e-05, + "loss": 3.3939, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641217063044637e-05, + "loss": 3.3983, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5632831115534117e-05, + "loss": 3.3881, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624445168023597e-05, + "loss": 3.4039, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616059220513077e-05, + "loss": 3.387, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607673273002557e-05, + "loss": 3.3834, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599287325492037e-05, + "loss": 3.3934, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5590901377981513e-05, + "loss": 3.3961, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582515430470997e-05, + "loss": 3.396, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557414586176421e-05, + "loss": 3.4028, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556575991425369e-05, + "loss": 3.3847, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557373966743166e-05, + "loss": 3.3793, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5548988019232646e-05, + "loss": 3.3907, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540618450525858e-05, + "loss": 3.4027, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.553223250301534e-05, + "loss": 3.3877, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5523846555504818e-05, + "loss": 3.3975, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515460607994298e-05, + "loss": 3.4016, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507074660483778e-05, + "loss": 3.3957, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498705091776987e-05, + "loss": 3.3929, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490319144266467e-05, + "loss": 3.3852, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548193319675595e-05, + "loss": 3.4012, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547354724924543e-05, + "loss": 3.3981, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546516130173491e-05, + "loss": 3.3946, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545679173302812e-05, + "loss": 3.3883, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.54484057855176e-05, + "loss": 3.3804, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.544001983800708e-05, + "loss": 3.3916, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.543163389049656e-05, + "loss": 3.4005, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423247942986043e-05, + "loss": 3.3902, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5414861995475522e-05, + "loss": 3.3934, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406476047965e-05, + "loss": 3.387, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.539809010045448e-05, + "loss": 3.3876, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.538972053174769e-05, + "loss": 3.3941, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.538133458423717e-05, + "loss": 3.3893, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5372965015530384e-05, + "loss": 3.3842, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364579068019864e-05, + "loss": 3.3953, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356193120509344e-05, + "loss": 3.3932, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534780717299882e-05, + "loss": 3.3855, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.53394212254883e-05, + "loss": 3.3923, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533103527797778e-05, + "loss": 3.3856, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322665709270996e-05, + "loss": 3.3992, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314279761760473e-05, + "loss": 3.3869, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5305893814249953e-05, + "loss": 3.3959, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297507866739433e-05, + "loss": 3.4, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289121919228913e-05, + "loss": 3.3897, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5280752350522122e-05, + "loss": 3.3923, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5272366403011605e-05, + "loss": 3.3898, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263980455501085e-05, + "loss": 3.3876, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255594507990565e-05, + "loss": 3.3943, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247208560480045e-05, + "loss": 3.383, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238822612969525e-05, + "loss": 3.3843, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230436665459003e-05, + "loss": 3.3918, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222067096752216e-05, + "loss": 3.3883, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213681149241696e-05, + "loss": 3.3887, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205295201731174e-05, + "loss": 3.3845, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196909254220654e-05, + "loss": 3.3852, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188539685513866e-05, + "loss": 3.3861, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180153738003346e-05, + "loss": 3.4023, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171767790492825e-05, + "loss": 3.3872, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163381842982304e-05, + "loss": 3.399, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5154995895471784e-05, + "loss": 3.382, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146609947961266e-05, + "loss": 3.3967, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138224000450746e-05, + "loss": 3.392, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129854431743957e-05, + "loss": 3.3981, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121468484233437e-05, + "loss": 3.3994, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113082536722917e-05, + "loss": 3.3935, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104696589212397e-05, + "loss": 3.3954, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096310641701877e-05, + "loss": 3.3981, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087924694191355e-05, + "loss": 3.3827, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079555125484567e-05, + "loss": 3.3943, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071169177974049e-05, + "loss": 3.3895, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062783230463529e-05, + "loss": 3.3886, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054397282953006e-05, + "loss": 3.3841, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046011335442487e-05, + "loss": 3.3896, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.50376417667357e-05, + "loss": 3.3848, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.502925581922518e-05, + "loss": 3.3883, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020869871714658e-05, + "loss": 3.3921, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.863065004348755, + "eval_runtime": 307.6248, + "eval_samples_per_second": 1240.443, + "eval_steps_per_second": 38.765, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012483924204138e-05, + "loss": 3.3895, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004097976693618e-05, + "loss": 3.3783, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995712029183098e-05, + "loss": 3.3843, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987326081672578e-05, + "loss": 3.3948, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4978956512965789e-05, + "loss": 3.3919, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970570565455268e-05, + "loss": 3.3839, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.496218461794475e-05, + "loss": 3.3924, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.495379867043423e-05, + "loss": 3.384, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.494541272292371e-05, + "loss": 3.3844, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.493704315421692e-05, + "loss": 3.3928, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.49286572067064e-05, + "loss": 3.3935, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.492027125919588e-05, + "loss": 3.3832, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.491188531168536e-05, + "loss": 3.3963, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903499364174839e-05, + "loss": 3.3693, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895113416664319e-05, + "loss": 3.3855, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886727469153799e-05, + "loss": 3.3754, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.487834152164328e-05, + "loss": 3.3892, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.486997195293649e-05, + "loss": 3.3935, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.486158600542597e-05, + "loss": 3.3748, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853200057915451e-05, + "loss": 3.392, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844814110404931e-05, + "loss": 3.401, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836460920501875e-05, + "loss": 3.3873, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828074972991354e-05, + "loss": 3.3914, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819689025480834e-05, + "loss": 3.3914, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811303077970313e-05, + "loss": 3.393, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4802917130459793e-05, + "loss": 3.3854, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794531182949273e-05, + "loss": 3.3831, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786145235438753e-05, + "loss": 3.391, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4777759287928234e-05, + "loss": 3.3757, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769389719221443e-05, + "loss": 3.3831, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761003771710923e-05, + "loss": 3.3967, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752617824200405e-05, + "loss": 3.3934, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744231876689885e-05, + "loss": 3.3896, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735862307983096e-05, + "loss": 3.4004, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727476360472576e-05, + "loss": 3.382, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719090412962056e-05, + "loss": 3.3862, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710704465451536e-05, + "loss": 3.3881, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702318517941015e-05, + "loss": 3.3747, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4693932570430494e-05, + "loss": 3.3855, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685546622919974e-05, + "loss": 3.3805, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677160675409454e-05, + "loss": 3.3774, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668807485506397e-05, + "loss": 3.3865, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660421537995877e-05, + "loss": 3.393, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652035590485359e-05, + "loss": 3.3891, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643649642974839e-05, + "loss": 3.3829, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635263695464315e-05, + "loss": 3.3914, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4626877747953797e-05, + "loss": 3.3811, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618491800443277e-05, + "loss": 3.3902, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610122231736487e-05, + "loss": 3.371, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601736284225967e-05, + "loss": 3.3867, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593350336715447e-05, + "loss": 3.3802, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4584964389204927e-05, + "loss": 3.3973, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576578441694407e-05, + "loss": 3.3808, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568192494183889e-05, + "loss": 3.3772, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559806546673369e-05, + "loss": 3.3751, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551420599162845e-05, + "loss": 3.3803, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543067409259789e-05, + "loss": 3.3929, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534681461749269e-05, + "loss": 3.369, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.452629551423875e-05, + "loss": 3.397, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.451790956672823e-05, + "loss": 3.3824, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.450952361921771e-05, + "loss": 3.361, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.450113767170719e-05, + "loss": 3.3928, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492768103000401e-05, + "loss": 3.3721, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484382155489881e-05, + "loss": 3.3666, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4475996207979361e-05, + "loss": 3.3762, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467610260468843e-05, + "loss": 3.3866, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459240691762052e-05, + "loss": 3.379, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450854744251532e-05, + "loss": 3.3819, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442468796741013e-05, + "loss": 3.3687, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434082849230493e-05, + "loss": 3.3706, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425713280523704e-05, + "loss": 3.3836, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417327333013184e-05, + "loss": 3.3901, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4408941385502664e-05, + "loss": 3.3845, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400555437992142e-05, + "loss": 3.3821, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392185869285355e-05, + "loss": 3.3911, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4383799921774835e-05, + "loss": 3.3795, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375413974264315e-05, + "loss": 3.3887, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367028026753793e-05, + "loss": 3.3777, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358642079243273e-05, + "loss": 3.3761, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350256131732753e-05, + "loss": 3.3854, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341870184222233e-05, + "loss": 3.3781, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333500615515444e-05, + "loss": 3.39, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325114668004924e-05, + "loss": 3.3947, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316728720494405e-05, + "loss": 3.3775, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308342772983885e-05, + "loss": 3.3642, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299956825473365e-05, + "loss": 3.3816, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291587256766576e-05, + "loss": 3.3885, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283201309256056e-05, + "loss": 3.3811, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274815361745536e-05, + "loss": 3.3864, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266429414235016e-05, + "loss": 3.391, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258059845528227e-05, + "loss": 3.3831, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249673898017706e-05, + "loss": 3.3843, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241287950507186e-05, + "loss": 3.3759, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232902002996668e-05, + "loss": 3.392, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224532434289877e-05, + "loss": 3.3851, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216146486779359e-05, + "loss": 3.3872, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4207760539268839e-05, + "loss": 3.3778, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199374591758319e-05, + "loss": 3.3725, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.419100502305153e-05, + "loss": 3.3803, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.418261907554101e-05, + "loss": 3.3915, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417423312803049e-05, + "loss": 3.3833, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.416584718051997e-05, + "loss": 3.3788, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157461233009448e-05, + "loss": 3.3808, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.414909166430266e-05, + "loss": 3.3777, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.414070571679214e-05, + "loss": 3.3826, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132319769281622e-05, + "loss": 3.3824, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4123933821771098e-05, + "loss": 3.3745, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115547874260578e-05, + "loss": 3.3834, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107178305553792e-05, + "loss": 3.3851, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4098792358043269e-05, + "loss": 3.3771, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.409040641053275e-05, + "loss": 3.3785, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.408202046302223e-05, + "loss": 3.3796, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.407363451551171e-05, + "loss": 3.3877, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.406524856800119e-05, + "loss": 3.3804, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056878999294401e-05, + "loss": 3.382, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048493051783881e-05, + "loss": 3.3856, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040107104273361e-05, + "loss": 3.3844, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031737535566572e-05, + "loss": 3.3835, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023351588056052e-05, + "loss": 3.3779, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4014965640545532e-05, + "loss": 3.381, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006579693035014e-05, + "loss": 3.383, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998193745524494e-05, + "loss": 3.3712, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989807798013973e-05, + "loss": 3.379, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981421850503452e-05, + "loss": 3.3771, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973035902992932e-05, + "loss": 3.3791, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964666334286144e-05, + "loss": 3.3805, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956280386775624e-05, + "loss": 3.3756, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947894439265102e-05, + "loss": 3.3733, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939508491754582e-05, + "loss": 3.3776, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931122544244062e-05, + "loss": 3.393, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3922736596733544e-05, + "loss": 3.3783, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914350649223024e-05, + "loss": 3.3857, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905964701712504e-05, + "loss": 3.3725, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897595133005715e-05, + "loss": 3.3863, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889225564298924e-05, + "loss": 3.3832, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880839616788405e-05, + "loss": 3.3869, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872453669277885e-05, + "loss": 3.3873, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864067721767365e-05, + "loss": 3.3831, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855698153060576e-05, + "loss": 3.39, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847312205550056e-05, + "loss": 3.3901, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838926258039536e-05, + "loss": 3.3723, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830540310529016e-05, + "loss": 3.3856, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822154363018498e-05, + "loss": 3.3794, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813768415507978e-05, + "loss": 3.3801, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805398846801187e-05, + "loss": 3.3738, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797012899290668e-05, + "loss": 3.3807, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788626951780148e-05, + "loss": 3.375, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780241004269628e-05, + "loss": 3.3803, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771855056759107e-05, + "loss": 3.3779, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8630282878875732, + "eval_runtime": 304.4929, + "eval_samples_per_second": 1253.202, + "eval_steps_per_second": 39.163, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763485488052319e-05, + "loss": 3.384, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375511591934553e-05, + "loss": 3.3695, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374672997183501e-05, + "loss": 3.3752, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373834402432449e-05, + "loss": 3.3855, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.372995807681397e-05, + "loss": 3.3791, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721572129303451e-05, + "loss": 3.3777, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713186181792928e-05, + "loss": 3.3822, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704800234282408e-05, + "loss": 3.3737, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.369641428677189e-05, + "loss": 3.3727, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688061096868831e-05, + "loss": 3.3847, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679675149358313e-05, + "loss": 3.3785, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671289201847793e-05, + "loss": 3.3762, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3662903254337273e-05, + "loss": 3.3881, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654517306826753e-05, + "loss": 3.3567, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646131359316231e-05, + "loss": 3.3752, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.363774541180571e-05, + "loss": 3.365, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.362935946429519e-05, + "loss": 3.3839, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621006274392134e-05, + "loss": 3.3788, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612620326881614e-05, + "loss": 3.3674, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604234379371094e-05, + "loss": 3.3771, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3595848431860576e-05, + "loss": 3.3954, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587478863153785e-05, + "loss": 3.3794, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579092915643265e-05, + "loss": 3.3803, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3570706968132746e-05, + "loss": 3.3838, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562321020622226e-05, + "loss": 3.3836, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3553935073111703e-05, + "loss": 3.3715, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545549125601185e-05, + "loss": 3.373, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537163178090665e-05, + "loss": 3.3811, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528777230580144e-05, + "loss": 3.366, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520407661873355e-05, + "loss": 3.3761, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512021714362835e-05, + "loss": 3.3846, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503635766852315e-05, + "loss": 3.385, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495249819341795e-05, + "loss": 3.383, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486880250635006e-05, + "loss": 3.3879, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478494303124486e-05, + "loss": 3.372, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470108355613968e-05, + "loss": 3.3759, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461722408103447e-05, + "loss": 3.3815, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453336460592927e-05, + "loss": 3.3611, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3444950513082407e-05, + "loss": 3.3801, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436580944375618e-05, + "loss": 3.37, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428194996865098e-05, + "loss": 3.3664, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419809049354578e-05, + "loss": 3.3755, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411423101844056e-05, + "loss": 3.3884, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403037154333536e-05, + "loss": 3.3732, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394651206823016e-05, + "loss": 3.3738, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386265259312498e-05, + "loss": 3.3796, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377879311801978e-05, + "loss": 3.3693, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369509743095187e-05, + "loss": 3.3813, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361140174388401e-05, + "loss": 3.3615, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3352754226877878e-05, + "loss": 3.3745, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.334436827936736e-05, + "loss": 3.3727, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.333598233185684e-05, + "loss": 3.3873, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.332759638434632e-05, + "loss": 3.3747, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.33192104368358e-05, + "loss": 3.3666, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.331082448932528e-05, + "loss": 3.3634, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330245492061849e-05, + "loss": 3.3701, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.329406897310797e-05, + "loss": 3.3835, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.328568302559745e-05, + "loss": 3.3642, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277297078086932e-05, + "loss": 3.3818, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268911130576411e-05, + "loss": 3.3733, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260525183065888e-05, + "loss": 3.357, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325213923555537e-05, + "loss": 3.3816, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.324375328804485e-05, + "loss": 3.3648, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235400098141793e-05, + "loss": 3.3589, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227014150631273e-05, + "loss": 3.3655, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218628203120753e-05, + "loss": 3.3785, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210242255610233e-05, + "loss": 3.3697, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3201856308099711e-05, + "loss": 3.3655, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193486739392924e-05, + "loss": 3.3657, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185100791882404e-05, + "loss": 3.3626, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176714844371885e-05, + "loss": 3.3705, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168328896861362e-05, + "loss": 3.3776, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3159942949350842e-05, + "loss": 3.374, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151573380644056e-05, + "loss": 3.3784, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143187433133532e-05, + "loss": 3.3742, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134801485623014e-05, + "loss": 3.3688, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126415538112494e-05, + "loss": 3.3785, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118029590601974e-05, + "loss": 3.3725, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109660021895185e-05, + "loss": 3.3679, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101274074384665e-05, + "loss": 3.3676, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3092888126874145e-05, + "loss": 3.3717, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084502179363625e-05, + "loss": 3.3805, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076132610656835e-05, + "loss": 3.3816, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067746663146315e-05, + "loss": 3.3724, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059360715635795e-05, + "loss": 3.355, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3050974768125277e-05, + "loss": 3.3714, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042605199418486e-05, + "loss": 3.3779, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034219251907968e-05, + "loss": 3.3758, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025833304397448e-05, + "loss": 3.371, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017447356886928e-05, + "loss": 3.3839, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009061409376408e-05, + "loss": 3.3747, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3000691840669618e-05, + "loss": 3.3729, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992305893159098e-05, + "loss": 3.3671, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2983919945648578e-05, + "loss": 3.3804, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975550376941789e-05, + "loss": 3.3771, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967164429431269e-05, + "loss": 3.3795, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958778481920749e-05, + "loss": 3.3638, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.295039253441023e-05, + "loss": 3.3655, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.294202296570344e-05, + "loss": 3.3688, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933637018192921e-05, + "loss": 3.3789, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925251070682401e-05, + "loss": 3.3733, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2916865123171881e-05, + "loss": 3.371, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908479175661361e-05, + "loss": 3.3706, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900109606954572e-05, + "loss": 3.3686, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891723659444052e-05, + "loss": 3.3742, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883337711933532e-05, + "loss": 3.3696, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874951764423012e-05, + "loss": 3.367, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866582195716223e-05, + "loss": 3.3747, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858196248205703e-05, + "loss": 3.3737, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849810300695184e-05, + "loss": 3.3643, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841424353184661e-05, + "loss": 3.3703, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833038405674141e-05, + "loss": 3.3683, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824652458163623e-05, + "loss": 3.3771, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816266510653102e-05, + "loss": 3.3714, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807896941946312e-05, + "loss": 3.3729, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799510994435793e-05, + "loss": 3.3731, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791125046925273e-05, + "loss": 3.3791, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782755478218486e-05, + "loss": 3.3734, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774369530707964e-05, + "loss": 3.3652, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2765983583197444e-05, + "loss": 3.3749, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757597635686924e-05, + "loss": 3.3695, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749211688176404e-05, + "loss": 3.3622, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2740825740665885e-05, + "loss": 3.3669, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732439793155365e-05, + "loss": 3.3693, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724053845644842e-05, + "loss": 3.3702, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715684276938056e-05, + "loss": 3.3657, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707298329427536e-05, + "loss": 3.3682, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2698912381917016e-05, + "loss": 3.3649, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690526434406494e-05, + "loss": 3.3682, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682140486895974e-05, + "loss": 3.3826, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2673754539385454e-05, + "loss": 3.3686, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665368591874934e-05, + "loss": 3.3791, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2656982644364416e-05, + "loss": 3.363, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648613075657625e-05, + "loss": 3.3772, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640227128147105e-05, + "loss": 3.3745, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631857559440316e-05, + "loss": 3.3781, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623471611929796e-05, + "loss": 3.3744, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615085664419277e-05, + "loss": 3.3733, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606699716908757e-05, + "loss": 3.3834, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598313769398237e-05, + "loss": 3.3779, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2589927821887717e-05, + "loss": 3.365, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581558253180928e-05, + "loss": 3.3713, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573172305670408e-05, + "loss": 3.3703, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564786358159888e-05, + "loss": 3.3711, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.255640041064937e-05, + "loss": 3.3637, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548014463138846e-05, + "loss": 3.3729, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539644894432059e-05, + "loss": 3.3623, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.253125894692154e-05, + "loss": 3.3763, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.252287299941102e-05, + "loss": 3.3635, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8652987480163574, + "eval_runtime": 341.8635, + "eval_samples_per_second": 1116.209, + "eval_steps_per_second": 34.882, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514487051900497e-05, + "loss": 3.3747, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506117483193711e-05, + "loss": 3.3605, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.249773153568319e-05, + "loss": 3.3641, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489345588172669e-05, + "loss": 3.3764, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.248095964066215e-05, + "loss": 3.3726, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472573693151629e-05, + "loss": 3.368, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464187745641109e-05, + "loss": 3.3633, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455801798130589e-05, + "loss": 3.3647, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.244741585062007e-05, + "loss": 3.3637, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439062660717012e-05, + "loss": 3.3752, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430676713206492e-05, + "loss": 3.3712, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422290765695972e-05, + "loss": 3.3714, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2413904818185452e-05, + "loss": 3.3745, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2405518870674932e-05, + "loss": 3.3538, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397132923164412e-05, + "loss": 3.3642, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388746975653892e-05, + "loss": 3.3577, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.238036102814337e-05, + "loss": 3.3707, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371991459436583e-05, + "loss": 3.3648, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363605511926063e-05, + "loss": 3.3628, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355219564415543e-05, + "loss": 3.3666, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2346833616905023e-05, + "loss": 3.3836, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338480427001966e-05, + "loss": 3.3729, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330094479491446e-05, + "loss": 3.3684, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321708531980926e-05, + "loss": 3.3719, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313322584470404e-05, + "loss": 3.3831, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304936636959886e-05, + "loss": 3.3561, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296550689449366e-05, + "loss": 3.3633, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288164741938844e-05, + "loss": 3.3743, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279778794428324e-05, + "loss": 3.3549, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271409225721536e-05, + "loss": 3.3638, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263023278211016e-05, + "loss": 3.3736, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254637330700496e-05, + "loss": 3.3761, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246251383189976e-05, + "loss": 3.3708, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2237881814483187e-05, + "loss": 3.3783, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229495866972667e-05, + "loss": 3.3624, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221109919462147e-05, + "loss": 3.3711, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212723971951627e-05, + "loss": 3.3678, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204338024441107e-05, + "loss": 3.3536, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2195968455734318e-05, + "loss": 3.3705, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187582508223798e-05, + "loss": 3.3577, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179196560713278e-05, + "loss": 3.3591, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170810613202758e-05, + "loss": 3.3661, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162424665692237e-05, + "loss": 3.3775, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154038718181717e-05, + "loss": 3.3599, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145652770671197e-05, + "loss": 3.3685, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137283201964408e-05, + "loss": 3.3685, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2128897254453888e-05, + "loss": 3.3659, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.212051130694337e-05, + "loss": 3.3678, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112141738236579e-05, + "loss": 3.3524, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103755790726059e-05, + "loss": 3.3677, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.209536984321554e-05, + "loss": 3.3624, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208698389570502e-05, + "loss": 3.3748, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078597948194499e-05, + "loss": 3.3671, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070212000683979e-05, + "loss": 3.353, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.206182605317346e-05, + "loss": 3.3538, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.205345648446667e-05, + "loss": 3.3601, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045070536956151e-05, + "loss": 3.3771, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036684589445631e-05, + "loss": 3.3533, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028298641935111e-05, + "loss": 3.3698, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.201991269442459e-05, + "loss": 3.3638, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011526746914071e-05, + "loss": 3.3467, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.200314079940355e-05, + "loss": 3.371, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994754851893029e-05, + "loss": 3.3587, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986385283186242e-05, + "loss": 3.3505, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978015714479452e-05, + "loss": 3.3519, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969629766968932e-05, + "loss": 3.3735, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961243819458412e-05, + "loss": 3.36, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952857871947892e-05, + "loss": 3.3553, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944488303241105e-05, + "loss": 3.3532, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936102355730585e-05, + "loss": 3.3552, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927716408220063e-05, + "loss": 3.3609, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919330460709543e-05, + "loss": 3.3678, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1910960892002755e-05, + "loss": 3.3644, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902574944492234e-05, + "loss": 3.3685, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894188996981714e-05, + "loss": 3.3649, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885803049471195e-05, + "loss": 3.3679, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1877417101960675e-05, + "loss": 3.3646, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869047533253886e-05, + "loss": 3.3603, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860661585743366e-05, + "loss": 3.3577, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852275638232846e-05, + "loss": 3.3625, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1843889690722324e-05, + "loss": 3.3642, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835503743211806e-05, + "loss": 3.365, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827134174505017e-05, + "loss": 3.3747, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818748226994497e-05, + "loss": 3.361, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810362279483977e-05, + "loss": 3.3444, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801976331973456e-05, + "loss": 3.3614, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793606763266667e-05, + "loss": 3.3686, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785220815756149e-05, + "loss": 3.3677, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1776834868245627e-05, + "loss": 3.3585, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768448920735107e-05, + "loss": 3.3747, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760062973224587e-05, + "loss": 3.3667, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751693404517798e-05, + "loss": 3.3614, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743307457007278e-05, + "loss": 3.3595, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.173492150949676e-05, + "loss": 3.3718, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.172653556198624e-05, + "loss": 3.3648, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718165993279449e-05, + "loss": 3.3697, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.170978004576893e-05, + "loss": 3.3568, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170139409825841e-05, + "loss": 3.3556, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693008150747888e-05, + "loss": 3.3597, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168462220323737e-05, + "loss": 3.3694, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.167623625572685e-05, + "loss": 3.3638, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.166785030821633e-05, + "loss": 3.361, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.165948073950954e-05, + "loss": 3.3568, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.165109479199902e-05, + "loss": 3.3597, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.16427088444885e-05, + "loss": 3.3671, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634322896977979e-05, + "loss": 3.3568, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.162593694946746e-05, + "loss": 3.3574, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1617567380760671e-05, + "loss": 3.366, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609181433250151e-05, + "loss": 3.3646, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1600795485739631e-05, + "loss": 3.3609, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592409538229111e-05, + "loss": 3.3614, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584023590718591e-05, + "loss": 3.356, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1575654022011804e-05, + "loss": 3.366, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567268074501282e-05, + "loss": 3.3645, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1558882126990762e-05, + "loss": 3.3591, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1550496179480244e-05, + "loss": 3.369, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542110231969722e-05, + "loss": 3.3692, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533740663262933e-05, + "loss": 3.3626, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525354715752414e-05, + "loss": 3.3572, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516968768241893e-05, + "loss": 3.3646, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508582820731372e-05, + "loss": 3.3582, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500213252024585e-05, + "loss": 3.3523, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1491827304514065e-05, + "loss": 3.3611, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483441357003543e-05, + "loss": 3.3593, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475055409493025e-05, + "loss": 3.3639, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466685840786236e-05, + "loss": 3.3509, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458299893275716e-05, + "loss": 3.3634, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449913945765196e-05, + "loss": 3.3559, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441527998254675e-05, + "loss": 3.3582, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433142050744155e-05, + "loss": 3.3675, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424772482037366e-05, + "loss": 3.3629, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416386534526846e-05, + "loss": 3.3662, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408000587016326e-05, + "loss": 3.3528, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399614639505806e-05, + "loss": 3.3673, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391228691995286e-05, + "loss": 3.3651, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1382859123288497e-05, + "loss": 3.3663, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1374473175777978e-05, + "loss": 3.3669, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366087228267457e-05, + "loss": 3.3652, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1357701280756937e-05, + "loss": 3.3761, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349315333246417e-05, + "loss": 3.3667, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1340929385735898e-05, + "loss": 3.3544, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1332559817029107e-05, + "loss": 3.3614, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324173869518587e-05, + "loss": 3.3606, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1315787922008069e-05, + "loss": 3.3569, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1307401974497547e-05, + "loss": 3.3554, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299016026987027e-05, + "loss": 3.3641, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129064645828024e-05, + "loss": 3.3545, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128226051076972e-05, + "loss": 3.3677, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1273874563259198e-05, + "loss": 3.3548, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.8652238845825195, + "eval_runtime": 353.2607, + "eval_samples_per_second": 1080.197, + "eval_steps_per_second": 33.757, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.126548861574868e-05, + "loss": 3.3212, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.125710266823816e-05, + "loss": 3.3546, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1248716720727638e-05, + "loss": 3.3512, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1240330773217118e-05, + "loss": 3.3656, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.123196120451033e-05, + "loss": 3.3653, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1223591635803541e-05, + "loss": 3.3593, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1215205688293021e-05, + "loss": 3.3543, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1206819740782501e-05, + "loss": 3.3537, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198433793271981e-05, + "loss": 3.3617, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190064224565193e-05, + "loss": 3.3634, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1181678277054672e-05, + "loss": 3.3608, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173292329544152e-05, + "loss": 3.3583, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1164906382033633e-05, + "loss": 3.3688, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1156536813326844e-05, + "loss": 3.3454, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148150865816322e-05, + "loss": 3.3549, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1139764918305804e-05, + "loss": 3.3494, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131378970795284e-05, + "loss": 3.3599, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123009402088495e-05, + "loss": 3.3558, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114623454577975e-05, + "loss": 3.3538, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106237507067455e-05, + "loss": 3.3536, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1097851559556935e-05, + "loss": 3.375, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089481990850145e-05, + "loss": 3.3609, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081096043339625e-05, + "loss": 3.3541, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1072710095829105e-05, + "loss": 3.3637, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064324148318585e-05, + "loss": 3.3705, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1055938200808065e-05, + "loss": 3.3508, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1047552253297545e-05, + "loss": 3.3526, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039166305787025e-05, + "loss": 3.3659, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1030780358276505e-05, + "loss": 3.3454, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022410789569716e-05, + "loss": 3.3554, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014024842059196e-05, + "loss": 3.3584, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1005638894548676e-05, + "loss": 3.37, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997252947038156e-05, + "loss": 3.3606, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0988883378331368e-05, + "loss": 3.3642, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980497430820848e-05, + "loss": 3.3552, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972111483310326e-05, + "loss": 3.3622, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963725535799806e-05, + "loss": 3.3603, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0955339588289288e-05, + "loss": 3.3437, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0946970019582499e-05, + "loss": 3.3595, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0938584072071977e-05, + "loss": 3.345, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930198124561459e-05, + "loss": 3.3521, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0921812177050939e-05, + "loss": 3.3533, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.091344260834415e-05, + "loss": 3.3666, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.090505666083363e-05, + "loss": 3.3546, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.089667071332311e-05, + "loss": 3.3543, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888284765812588e-05, + "loss": 3.3647, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.087989881830207e-05, + "loss": 3.3502, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.087151287079155e-05, + "loss": 3.3651, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.086314330208476e-05, + "loss": 3.3437, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.085475735457424e-05, + "loss": 3.3508, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.084637140706372e-05, + "loss": 3.3567, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.08379854595532e-05, + "loss": 3.3624, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.082959951204268e-05, + "loss": 3.3615, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.082121356453216e-05, + "loss": 3.3415, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.081282761702164e-05, + "loss": 3.3481, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080445804831485e-05, + "loss": 3.346, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.079607210080433e-05, + "loss": 3.3702, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.078768615329381e-05, + "loss": 3.3423, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.077930020578329e-05, + "loss": 3.3622, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.077091425827277e-05, + "loss": 3.3545, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.076252831076225e-05, + "loss": 3.3374, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.075414236325173e-05, + "loss": 3.3598, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0745772794544943e-05, + "loss": 3.3522, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737386847034421e-05, + "loss": 3.3362, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729000899523901e-05, + "loss": 3.3438, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720614952013381e-05, + "loss": 3.3618, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712245383306593e-05, + "loss": 3.3496, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703859435796072e-05, + "loss": 3.3482, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695473488285553e-05, + "loss": 3.3437, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687087540775033e-05, + "loss": 3.3437, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0678701593264512e-05, + "loss": 3.3515, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670332024557724e-05, + "loss": 3.3578, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0661946077047204e-05, + "loss": 3.3537, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0653560129536684e-05, + "loss": 3.3604, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645174182026162e-05, + "loss": 3.3562, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0636804613319375e-05, + "loss": 3.3544, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0628418665808855e-05, + "loss": 3.3548, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620032718298335e-05, + "loss": 3.3509, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0611646770787815e-05, + "loss": 3.3501, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603260823277295e-05, + "loss": 3.3547, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0594874875766774e-05, + "loss": 3.3509, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0586488928256254e-05, + "loss": 3.3585, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578119359549465e-05, + "loss": 3.3597, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0569733412038945e-05, + "loss": 3.3511, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0561347464528425e-05, + "loss": 3.3371, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0552961517017905e-05, + "loss": 3.3464, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0544591948311116e-05, + "loss": 3.3631, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0536206000800598e-05, + "loss": 3.3584, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0527820053290076e-05, + "loss": 3.3518, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0519434105779556e-05, + "loss": 3.3656, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511048158269036e-05, + "loss": 3.3549, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502678589562248e-05, + "loss": 3.3526, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494292642051726e-05, + "loss": 3.35, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0485906694541208e-05, + "loss": 3.3614, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0477520747030688e-05, + "loss": 3.3546, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469134799520166e-05, + "loss": 3.365, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0460765230813379e-05, + "loss": 3.3395, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452379283302859e-05, + "loss": 3.3538, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0443993335792339e-05, + "loss": 3.3497, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435607388281819e-05, + "loss": 3.3586, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427221440771299e-05, + "loss": 3.3611, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.041885187206451e-05, + "loss": 3.3472, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.041046592455399e-05, + "loss": 3.3504, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.040207997704347e-05, + "loss": 3.3504, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.039369402953295e-05, + "loss": 3.3595, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.038530808202243e-05, + "loss": 3.3447, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.037693851331564e-05, + "loss": 3.3497, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.036855256580512e-05, + "loss": 3.3551, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.03601666182946e-05, + "loss": 3.3518, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.035178067078408e-05, + "loss": 3.3505, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.034339472327356e-05, + "loss": 3.3536, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033500877576304e-05, + "loss": 3.3422, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326639207056252e-05, + "loss": 3.3602, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.031825325954573e-05, + "loss": 3.354, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.030986731203521e-05, + "loss": 3.35, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0301481364524692e-05, + "loss": 3.3592, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.029309541701417e-05, + "loss": 3.36, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0284725848307381e-05, + "loss": 3.3521, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0276339900796863e-05, + "loss": 3.3453, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0267953953286343e-05, + "loss": 3.3547, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0259568005775821e-05, + "loss": 3.3473, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251182058265301e-05, + "loss": 3.3449, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0242812489558514e-05, + "loss": 3.3476, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0234426542047992e-05, + "loss": 3.3507, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226040594537473e-05, + "loss": 3.3535, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0217654647026953e-05, + "loss": 3.3442, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209285078320164e-05, + "loss": 3.3552, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0200899130809644e-05, + "loss": 3.3463, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0192513183299124e-05, + "loss": 3.3512, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184127235788604e-05, + "loss": 3.3547, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0175741288278082e-05, + "loss": 3.3524, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0167355340767564e-05, + "loss": 3.3571, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0158969393257044e-05, + "loss": 3.3467, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0150599824550255e-05, + "loss": 3.3541, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142213877039735e-05, + "loss": 3.354, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0133844308332945e-05, + "loss": 3.36, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125458360822427e-05, + "loss": 3.3581, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117072413311907e-05, + "loss": 3.355, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0108686465801385e-05, + "loss": 3.3671, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100300518290865e-05, + "loss": 3.3537, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0091914570780347e-05, + "loss": 3.3487, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0083528623269825e-05, + "loss": 3.3519, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075159054563036e-05, + "loss": 3.3503, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0066773107052518e-05, + "loss": 3.3479, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0058387159541998e-05, + "loss": 3.3449, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050001212031476e-05, + "loss": 3.3552, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0041631643324688e-05, + "loss": 3.3437, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033245695814168e-05, + "loss": 3.3559, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0024859748303647e-05, + "loss": 3.3487, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0016473800793128e-05, + "loss": 3.3528, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.8671226501464844, + "eval_runtime": 305.1671, + "eval_samples_per_second": 1250.433, + "eval_steps_per_second": 39.077, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008087853282608e-05, + "loss": 3.3441, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.999701905772088e-06, + "loss": 3.3436, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.991315958261566e-06, + "loss": 3.3538, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.982930010751048e-06, + "loss": 3.3596, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.974560442044259e-06, + "loss": 3.3516, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966174494533739e-06, + "loss": 3.3441, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.957788547023219e-06, + "loss": 3.3467, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.949402599512699e-06, + "loss": 3.3436, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.94103303080591e-06, + "loss": 3.3567, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.93264708329539e-06, + "loss": 3.3487, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92426113578487e-06, + "loss": 3.3533, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91587518827435e-06, + "loss": 3.3593, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.90748924076383e-06, + "loss": 3.338, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.89910329325331e-06, + "loss": 3.3389, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.89071734574279e-06, + "loss": 3.341, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.882331398232269e-06, + "loss": 3.3484, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87397820832921e-06, + "loss": 3.3481, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86559226081869e-06, + "loss": 3.35, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857206313308172e-06, + "loss": 3.343, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.848820365797652e-06, + "loss": 3.3657, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.840450797090863e-06, + "loss": 3.3507, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832064849580343e-06, + "loss": 3.3478, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.823678902069823e-06, + "loss": 3.3517, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.815292954559301e-06, + "loss": 3.3648, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.806907007048783e-06, + "loss": 3.3416, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.798521059538263e-06, + "loss": 3.3485, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.790151490831474e-06, + "loss": 3.3511, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.781765543320954e-06, + "loss": 3.3387, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.773379595810434e-06, + "loss": 3.3462, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.764993648299914e-06, + "loss": 3.3481, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.756607700789394e-06, + "loss": 3.3613, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748221753278873e-06, + "loss": 3.35, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.739852184572084e-06, + "loss": 3.3543, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.731466237061564e-06, + "loss": 3.3508, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723080289551044e-06, + "loss": 3.3481, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.714694342040524e-06, + "loss": 3.3525, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.706308394530004e-06, + "loss": 3.3373, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.697922447019484e-06, + "loss": 3.3502, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.689536499508964e-06, + "loss": 3.337, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681166930802175e-06, + "loss": 3.3454, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.672780983291656e-06, + "loss": 3.3425, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.664395035781135e-06, + "loss": 3.3597, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656009088270615e-06, + "loss": 3.3465, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.647623140760095e-06, + "loss": 3.3451, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.639237193249575e-06, + "loss": 3.3521, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.630851245739055e-06, + "loss": 3.3439, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.622481677032267e-06, + "loss": 3.3542, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614112108325478e-06, + "loss": 3.3323, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.605726160814956e-06, + "loss": 3.3431, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.597340213304438e-06, + "loss": 3.3492, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.588954265793918e-06, + "loss": 3.3518, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.580568318283396e-06, + "loss": 3.3491, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572182370772876e-06, + "loss": 3.3303, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.563796423262358e-06, + "loss": 3.345, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.555426854555568e-06, + "loss": 3.3339, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.547040907045048e-06, + "loss": 3.3604, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.538654959534528e-06, + "loss": 3.3361, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.530269012024008e-06, + "loss": 3.3529, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.521883064513486e-06, + "loss": 3.341, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.513497117002968e-06, + "loss": 3.3305, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.505111169492448e-06, + "loss": 3.3505, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.496725221981928e-06, + "loss": 3.3431, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.48837203207887e-06, + "loss": 3.3248, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.47998608456835e-06, + "loss": 3.3352, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.47160013705783e-06, + "loss": 3.3541, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.463214189547311e-06, + "loss": 3.342, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.45482824203679e-06, + "loss": 3.3371, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.446458673330002e-06, + "loss": 3.3367, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438072725819482e-06, + "loss": 3.336, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.42968677830896e-06, + "loss": 3.3401, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.42130083079844e-06, + "loss": 3.3517, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.412931262091653e-06, + "loss": 3.3416, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.404545314581133e-06, + "loss": 3.3525, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.39615936707061e-06, + "loss": 3.3427, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.387773419560092e-06, + "loss": 3.3511, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.379387472049572e-06, + "loss": 3.3402, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.37100152453905e-06, + "loss": 3.3449, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.362631955832263e-06, + "loss": 3.3443, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.354246008321743e-06, + "loss": 3.34, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.345860060811223e-06, + "loss": 3.3423, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.337474113300703e-06, + "loss": 3.3492, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329104544593914e-06, + "loss": 3.3516, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.320718597083394e-06, + "loss": 3.3412, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.312332649572875e-06, + "loss": 3.3295, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.303946702062354e-06, + "loss": 3.3408, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.295577133355564e-06, + "loss": 3.3529, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287191185845046e-06, + "loss": 3.3522, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.278805238334524e-06, + "loss": 3.3425, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.270419290824004e-06, + "loss": 3.3561, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262033343313484e-06, + "loss": 3.3461, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.253663774606697e-06, + "loss": 3.3385, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.245277827096175e-06, + "loss": 3.3416, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.236891879585657e-06, + "loss": 3.3506, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.228505932075137e-06, + "loss": 3.3445, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220136363368347e-06, + "loss": 3.3546, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.211750415857827e-06, + "loss": 3.3362, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.203364468347307e-06, + "loss": 3.3376, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.194978520836787e-06, + "loss": 3.3411, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.186608952129998e-06, + "loss": 3.3504, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.178223004619478e-06, + "loss": 3.3488, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.169837057108958e-06, + "loss": 3.3427, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.161451109598438e-06, + "loss": 3.3391, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153081540891649e-06, + "loss": 3.3417, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.144695593381129e-06, + "loss": 3.3519, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.13630964587061e-06, + "loss": 3.3301, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.127923698360089e-06, + "loss": 3.3406, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.1195541296533e-06, + "loss": 3.3484, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.111168182142781e-06, + "loss": 3.3436, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.102782234632261e-06, + "loss": 3.3413, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.09439628712174e-06, + "loss": 3.3478, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.08601033961122e-06, + "loss": 3.3352, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.077640770904432e-06, + "loss": 3.3444, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.06925482339391e-06, + "loss": 3.3451, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.060868875883392e-06, + "loss": 3.3406, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.052482928372872e-06, + "loss": 3.3483, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044096980862352e-06, + "loss": 3.3517, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.035727412155562e-06, + "loss": 3.3453, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.027341464645042e-06, + "loss": 3.3399, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.018955517134522e-06, + "loss": 3.3416, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.010569569624002e-06, + "loss": 3.3389, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002183622113482e-06, + "loss": 3.3337, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.993814053406693e-06, + "loss": 3.3379, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.985428105896173e-06, + "loss": 3.3383, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977042158385653e-06, + "loss": 3.3465, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.968656210875133e-06, + "loss": 3.3347, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.960286642168345e-06, + "loss": 3.3443, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.951900694657825e-06, + "loss": 3.3349, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.943514747147304e-06, + "loss": 3.3423, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.935128799636783e-06, + "loss": 3.3419, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.926742852126265e-06, + "loss": 3.3512, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.918356904615743e-06, + "loss": 3.3451, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.909970957105223e-06, + "loss": 3.3397, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.901601388398436e-06, + "loss": 3.3418, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.893215440887916e-06, + "loss": 3.3455, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.884829493377394e-06, + "loss": 3.3496, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.876443545866876e-06, + "loss": 3.3474, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868057598356356e-06, + "loss": 3.3489, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.859688029649565e-06, + "loss": 3.3563, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.851302082139046e-06, + "loss": 3.3444, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.842916134628526e-06, + "loss": 3.3429, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.834530187118006e-06, + "loss": 3.339, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826144239607485e-06, + "loss": 3.3444, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.817758292096966e-06, + "loss": 3.3408, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.809388723390177e-06, + "loss": 3.3323, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801002775879657e-06, + "loss": 3.3465, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.792616828369137e-06, + "loss": 3.3356, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.784230880858617e-06, + "loss": 3.3461, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.775844933348097e-06, + "loss": 3.3368, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.767475364641308e-06, + "loss": 3.3407, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8684656620025635, + "eval_runtime": 308.7115, + "eval_samples_per_second": 1236.077, + "eval_steps_per_second": 38.628, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.759105795934518e-06, + "loss": 3.3312, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.750719848424e-06, + "loss": 3.3374, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.74233390091348e-06, + "loss": 3.3479, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.733947953402958e-06, + "loss": 3.3444, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.72557838469617e-06, + "loss": 3.3465, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.71719243718565e-06, + "loss": 3.3356, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.708806489675129e-06, + "loss": 3.3346, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.70042054216461e-06, + "loss": 3.3348, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.692050973457821e-06, + "loss": 3.348, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.683665025947301e-06, + "loss": 3.3423, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.675279078436781e-06, + "loss": 3.341, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.666893130926261e-06, + "loss": 3.3466, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.658507183415741e-06, + "loss": 3.3287, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.65012123590522e-06, + "loss": 3.3337, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.641751667198432e-06, + "loss": 3.337, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.633365719687912e-06, + "loss": 3.3287, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.624979772177392e-06, + "loss": 3.3401, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.616593824666872e-06, + "loss": 3.3387, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.608207877156352e-06, + "loss": 3.3312, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.599821929645832e-06, + "loss": 3.3617, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.591452360939044e-06, + "loss": 3.3412, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.583066413428523e-06, + "loss": 3.3388, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.574680465918002e-06, + "loss": 3.3407, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.566294518407484e-06, + "loss": 3.3512, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.557908570896962e-06, + "loss": 3.3322, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.549522623386442e-06, + "loss": 3.3379, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.541136675875922e-06, + "loss": 3.3402, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.532750728365402e-06, + "loss": 3.3345, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.524381159658613e-06, + "loss": 3.3347, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.515995212148093e-06, + "loss": 3.3354, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.507609264637575e-06, + "loss": 3.3558, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.499223317127053e-06, + "loss": 3.3412, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.490853748420265e-06, + "loss": 3.3439, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.482467800909745e-06, + "loss": 3.3437, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.474081853399224e-06, + "loss": 3.3424, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.465695905888704e-06, + "loss": 3.3416, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.457309958378185e-06, + "loss": 3.328, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.448924010867665e-06, + "loss": 3.3384, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.440538063357143e-06, + "loss": 3.3252, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.432168494650356e-06, + "loss": 3.3389, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.423782547139836e-06, + "loss": 3.3324, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.415396599629314e-06, + "loss": 3.3466, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.407010652118796e-06, + "loss": 3.3362, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.398624704608276e-06, + "loss": 3.3352, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.390238757097756e-06, + "loss": 3.344, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.381852809587234e-06, + "loss": 3.336, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.373466862076716e-06, + "loss": 3.34, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.365097293369926e-06, + "loss": 3.3279, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.356711345859405e-06, + "loss": 3.3343, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.348325398348886e-06, + "loss": 3.3389, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.339939450838366e-06, + "loss": 3.3421, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.331553503327846e-06, + "loss": 3.3457, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.323167555817324e-06, + "loss": 3.3178, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.314781608306806e-06, + "loss": 3.3385, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.306412039600017e-06, + "loss": 3.3201, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.298026092089497e-06, + "loss": 3.3512, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.289640144578977e-06, + "loss": 3.3296, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.281254197068457e-06, + "loss": 3.3406, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.272868249557937e-06, + "loss": 3.3369, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.264482302047417e-06, + "loss": 3.3226, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.256112733340627e-06, + "loss": 3.3348, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.247726785830107e-06, + "loss": 3.3337, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.239340838319587e-06, + "loss": 3.3175, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.230954890809067e-06, + "loss": 3.326, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.222585322102278e-06, + "loss": 3.342, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.21419937459176e-06, + "loss": 3.3323, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.205813427081238e-06, + "loss": 3.3283, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.197427479570718e-06, + "loss": 3.3298, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.189041532060198e-06, + "loss": 3.3221, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.180655584549678e-06, + "loss": 3.3336, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.172286015842889e-06, + "loss": 3.3366, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.16390006833237e-06, + "loss": 3.3346, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.15551412082185e-06, + "loss": 3.3464, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.147128173311329e-06, + "loss": 3.335, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.138758604604541e-06, + "loss": 3.3435, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.130372657094021e-06, + "loss": 3.3292, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.121986709583501e-06, + "loss": 3.3393, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.113600762072981e-06, + "loss": 3.3331, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.105214814562461e-06, + "loss": 3.3312, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.09682886705194e-06, + "loss": 3.3355, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.088459298345152e-06, + "loss": 3.3379, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.080073350834632e-06, + "loss": 3.3443, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.071687403324112e-06, + "loss": 3.3342, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.063301455813591e-06, + "loss": 3.3203, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.054931887106802e-06, + "loss": 3.3254, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.046545939596282e-06, + "loss": 3.3451, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.038159992085762e-06, + "loss": 3.3411, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.029774044575242e-06, + "loss": 3.3355, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.021404475868453e-06, + "loss": 3.3416, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.013018528357933e-06, + "loss": 3.3425, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.004632580847415e-06, + "loss": 3.3279, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.996246633336893e-06, + "loss": 3.3301, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.987860685826373e-06, + "loss": 3.3419, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.979491117119585e-06, + "loss": 3.3335, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.971105169609065e-06, + "loss": 3.3454, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.962719222098543e-06, + "loss": 3.3276, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.954333274588025e-06, + "loss": 3.3316, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.945947327077505e-06, + "loss": 3.3331, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.937577758370716e-06, + "loss": 3.3382, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.929191810860196e-06, + "loss": 3.3406, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.920805863349676e-06, + "loss": 3.3347, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.912419915839154e-06, + "loss": 3.3276, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.904050347132367e-06, + "loss": 3.3307, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.895664399621846e-06, + "loss": 3.3475, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.887278452111326e-06, + "loss": 3.3223, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.878892504600806e-06, + "loss": 3.3276, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.870506557090286e-06, + "loss": 3.3409, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.862136988383497e-06, + "loss": 3.3355, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.853751040872979e-06, + "loss": 3.3311, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.845365093362457e-06, + "loss": 3.3354, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.836979145851937e-06, + "loss": 3.328, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.82860957714515e-06, + "loss": 3.3378, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.820223629634628e-06, + "loss": 3.3315, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.811837682124108e-06, + "loss": 3.3308, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.80345173461359e-06, + "loss": 3.34, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.79506578710307e-06, + "loss": 3.3457, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.786696218396278e-06, + "loss": 3.3338, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.77831027088576e-06, + "loss": 3.3317, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.76992432337524e-06, + "loss": 3.3341, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.761538375864718e-06, + "loss": 3.3292, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.753152428354198e-06, + "loss": 3.3221, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.74478285964741e-06, + "loss": 3.3315, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.73639691213689e-06, + "loss": 3.3289, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.72801096462637e-06, + "loss": 3.3366, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.71962501711585e-06, + "loss": 3.325, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.711255448409061e-06, + "loss": 3.3375, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.702869500898541e-06, + "loss": 3.3212, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.694483553388021e-06, + "loss": 3.3333, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.686097605877501e-06, + "loss": 3.3324, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.677728037170714e-06, + "loss": 3.34, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.669342089660192e-06, + "loss": 3.3401, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.660956142149672e-06, + "loss": 3.3374, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.652570194639152e-06, + "loss": 3.3266, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.644184247128634e-06, + "loss": 3.3326, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.635798299618112e-06, + "loss": 3.3425, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.627412352107592e-06, + "loss": 3.3428, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.6190264045970726e-06, + "loss": 3.3404, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.6106568358902825e-06, + "loss": 3.345, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.602287267183494e-06, + "loss": 3.3328, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.593901319672975e-06, + "loss": 3.334, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.585515372162455e-06, + "loss": 3.3312, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.577129424651934e-06, + "loss": 3.3355, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.568759855945146e-06, + "loss": 3.3339, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.560373908434626e-06, + "loss": 3.3203, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.551987960924106e-06, + "loss": 3.3377, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.5436020134135855e-06, + "loss": 3.3292, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.535232444706797e-06, + "loss": 3.3351, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.526846497196277e-06, + "loss": 3.327, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.518460549685756e-06, + "loss": 3.3356, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.8682570457458496, + "eval_runtime": 306.3963, + "eval_samples_per_second": 1245.417, + "eval_steps_per_second": 38.92, + "step": 2594880 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7943164260679025e+18, + "trial_name": null, + "trial_params": null +}