diff --git "a/checkpoint-2365920/trainer_state.json" "b/checkpoint-2365920/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2365920/trainer_state.json" @@ -0,0 +1,27993 @@ +{ + "best_metric": 3.842529535293579, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/3/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2365920, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 11.0296, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8182, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1941, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9832, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8117, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6987, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.597, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5325, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4388, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4063, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3457, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3048, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2634, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1972, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1771, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1302, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1068, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0772, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0387, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0144, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9993, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.971, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 4.9413, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9205, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9122, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8863, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8577, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 4.8489, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8257, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8134, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.7984, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 4.7846, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7735, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7557, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7519, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7498, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7265, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6902, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.696, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6747, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6796, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6667, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6572, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6377, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6469, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6301, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6294, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.618, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5962, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5964, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5995, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5806, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5695, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5615, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5587, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5444, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5637, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5297, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5409, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5325, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5066, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5137, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5047, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4899, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4824, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4991, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4769, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4716, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4594, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4721, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4776, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4624, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4556, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.46, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4584, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4476, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4309, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4366, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4265, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4231, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4153, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4188, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4251, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4156, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3888, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3978, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4012, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.3967, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3898, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3854, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3808, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3682, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3748, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3748, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3639, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3751, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.3548, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3542, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3522, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3498, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3554, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3387, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3365, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3324, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3361, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3192, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3118, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3214, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3254, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3186, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.316, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3047, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.315, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.2984, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3057, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3052, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3076, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2955, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2931, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2944, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.2966, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2837, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2848, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2838, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2858, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2682, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2658, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2702, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2729, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2644, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2776, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2682, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2546, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2594, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887672526129106e-05, + "loss": 4.269, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.2613, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2556, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2464, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2536, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2592, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.246, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2375, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2425, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2373, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2345, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87845125962828e-05, + "loss": 4.2411, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877612664877228e-05, + "loss": 4.2302, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2319, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2288, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2247, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.192929267883301, + "eval_runtime": 305.4189, + "eval_samples_per_second": 1249.402, + "eval_steps_per_second": 39.045, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2128, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2199, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2278, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2188, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.2178, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2125, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869229993127454e-05, + "loss": 4.2088, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683913983764027e-05, + "loss": 4.1968, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675544415057236e-05, + "loss": 4.2223, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667158467546716e-05, + "loss": 4.2052, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658772520036196e-05, + "loss": 4.2146, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650386572525676e-05, + "loss": 4.2112, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.1924, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.1935, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.1902, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.1827, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.1894, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.181, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.1766, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1999, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1842, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856655985502793e-05, + "loss": 4.1758, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855817390751741e-05, + "loss": 4.1736, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1877, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1647, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.162, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1672, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.1657, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.1593, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1593, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1612, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1662, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1494, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1601, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.165, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1597, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1341, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1422, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1378, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1441, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1376, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1446, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1325, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1425, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1417, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1415, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1395, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1199, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.132, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1371, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1302, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1248, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.116, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1232, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1079, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1355, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1133, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1259, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.125, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.1139, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1082, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.0967, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.0943, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1128, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1018, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.098, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.0889, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.1071, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1095, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815581221504977e-05, + "loss": 4.1051, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814742626753924e-05, + "loss": 4.0989, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.109, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1058, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.1053, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0878, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0983, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0917, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0896, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.0871, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0908, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.1007, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.095, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0715, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.0795, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0846, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0849, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0832, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0799, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0789, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.066, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0771, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0771, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.072, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0825, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0724, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0659, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0696, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0717, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0748, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.0648, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0588, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0594, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.068, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.052, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0441, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.059, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0615, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.0531, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.056, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0503, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0585, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0453, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0521, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.0577, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0586, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777022241760315e-05, + "loss": 4.0483, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0476, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0514, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0538, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0391, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.0495, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0413, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0536, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0333, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694798026419666e-05, + "loss": 4.0332, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686412078909146e-05, + "loss": 4.0379, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7678026131398626e-05, + "loss": 4.0394, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.7669640183888106e-05, + "loss": 4.0346, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766127061518132e-05, + "loss": 4.0518, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528846676708e-05, + "loss": 4.04, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764449872016028e-05, + "loss": 4.0308, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763611277264976e-05, + "loss": 4.0322, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0478, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761935725643245e-05, + "loss": 4.0406, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761097130892193e-05, + "loss": 4.0355, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760258536141141e-05, + "loss": 4.0295, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.0374, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.75858298451941e-05, + "loss": 4.0391, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0313, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.0257, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.0285, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552302433955756e-05, + "loss": 4.0255, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.0217, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0356, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0233, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0257, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0233, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.0198, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.024447917938232, + "eval_runtime": 304.6013, + "eval_samples_per_second": 1252.756, + "eval_steps_per_second": 39.15, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.007, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0178, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0304, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0194, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0233, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0147, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0175, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0007, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0252, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.021, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0167, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0235, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.0023, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0037, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 4.0118, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 3.9938, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.002, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 3.9973, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9964, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0225, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 4.0016, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0025, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 3.9929, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0105, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.986, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9911, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 3.9914, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9974, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9871, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9876, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.994, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723375108018211e-05, + "loss": 3.9984, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 3.9792, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9931, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9962, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720022366894376e-05, + "loss": 3.9908, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.971, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9812, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.9687, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716669625770541e-05, + "loss": 3.9846, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715831031019489e-05, + "loss": 3.9786, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9845, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9751, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133168846467065e-05, + "loss": 3.9805, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124782898956545e-05, + "loss": 3.9841, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9857, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.9827, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099641435228714e-05, + "loss": 3.961, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091255487718194e-05, + "loss": 3.9752, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.9871, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9704, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706613040279409e-05, + "loss": 3.9714, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705774445528357e-05, + "loss": 3.9662, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704935850777306e-05, + "loss": 3.9702, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704097256026254e-05, + "loss": 3.9575, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703258661275202e-05, + "loss": 3.9804, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.70242006652415e-05, + "loss": 3.9693, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701581471773098e-05, + "loss": 3.9729, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700742877022045e-05, + "loss": 3.9813, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699905920151367e-05, + "loss": 3.9517, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699067325400315e-05, + "loss": 3.9671, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9604, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.9567, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696553179027532e-05, + "loss": 3.9495, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69571458427648e-05, + "loss": 3.9643, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694875989525428e-05, + "loss": 3.9599, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694037394774376e-05, + "loss": 3.9531, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693200437903697e-05, + "loss": 3.9441, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692361843152645e-05, + "loss": 3.9655, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9702, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9615, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689847696779862e-05, + "loss": 3.9609, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890091020288095e-05, + "loss": 3.9685, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881705072777575e-05, + "loss": 3.965, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.9673, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686494955656027e-05, + "loss": 3.9455, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685656360904975e-05, + "loss": 3.9623, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684817766153923e-05, + "loss": 3.959, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683979171402871e-05, + "loss": 3.9503, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831422145321926e-05, + "loss": 3.9552, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.68230361978114e-05, + "loss": 3.955, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681465025030088e-05, + "loss": 3.9674, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680626430279036e-05, + "loss": 3.9573, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679789473408357e-05, + "loss": 3.9365, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678950878657305e-05, + "loss": 3.9435, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678112283906253e-05, + "loss": 3.9513, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677273689155201e-05, + "loss": 3.9542, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676436732284522e-05, + "loss": 3.9514, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755981375334704e-05, + "loss": 3.9453, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747595427824184e-05, + "loss": 3.9483, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739209480313664e-05, + "loss": 3.9371, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673083991160687e-05, + "loss": 3.9507, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672245396409635e-05, + "loss": 3.9446, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671406801658583e-05, + "loss": 3.9454, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670569844787904e-05, + "loss": 3.9563, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669731250036852e-05, + "loss": 3.9483, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688926552858e-05, + "loss": 3.9383, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668054060534748e-05, + "loss": 3.9435, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667215465783696e-05, + "loss": 3.9427, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666378508913017e-05, + "loss": 3.9481, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665539914161966e-05, + "loss": 3.9417, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664701319410914e-05, + "loss": 3.9358, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663862724659862e-05, + "loss": 3.9319, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66302412990881e-05, + "loss": 3.9451, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662185535157758e-05, + "loss": 3.9313, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661346940406706e-05, + "loss": 3.922, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660509983536027e-05, + "loss": 3.9346, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659671388784975e-05, + "loss": 3.9394, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658832794033923e-05, + "loss": 3.9287, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579941992828707e-05, + "loss": 3.9402, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571556045318187e-05, + "loss": 3.9265, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563170097807667e-05, + "loss": 3.9401, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554800529100876e-05, + "loss": 3.9256, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546414581590356e-05, + "loss": 3.9276, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538028634079836e-05, + "loss": 3.9445, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652964268656932e-05, + "loss": 3.9394, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652127311786253e-05, + "loss": 3.9305, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651288717035201e-05, + "loss": 3.9327, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650450122284149e-05, + "loss": 3.9288, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649611527533097e-05, + "loss": 3.9351, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648772932782045e-05, + "loss": 3.9232, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647934338030993e-05, + "loss": 3.9336, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470957432799404e-05, + "loss": 3.9257, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462571485288884e-05, + "loss": 3.9361, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.64542019165821e-05, + "loss": 3.9157, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644581596907158e-05, + "loss": 3.9248, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643743002156106e-05, + "loss": 3.9201, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642904407405054e-05, + "loss": 3.9258, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420674505343756e-05, + "loss": 3.9205, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412288557833236e-05, + "loss": 3.9403, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403918989126445e-05, + "loss": 3.9279, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395533041615925e-05, + "loss": 3.9219, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387147094105405e-05, + "loss": 3.9149, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637876114659488e-05, + "loss": 3.9334, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637037519908436e-05, + "loss": 3.9307, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636198925157384e-05, + "loss": 3.9272, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635360330406332e-05, + "loss": 3.9197, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.63452173565528e-05, + "loss": 3.9251, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336847787846014e-05, + "loss": 3.9278, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328461840335494e-05, + "loss": 3.9222, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320075892824974e-05, + "loss": 3.9167, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311689945314454e-05, + "loss": 3.9214, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630332037660766e-05, + "loss": 3.919, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629493442909714e-05, + "loss": 3.9108, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628656486039035e-05, + "loss": 3.9247, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627817891287983e-05, + "loss": 3.9217, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626979296536931e-05, + "loss": 3.9163, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626140701785879e-05, + "loss": 3.9134, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6253037449152e-05, + "loss": 3.9092, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.951061248779297, + "eval_runtime": 305.5686, + "eval_samples_per_second": 1248.79, + "eval_steps_per_second": 39.026, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624465150164148e-05, + "loss": 3.9128, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623626555413097e-05, + "loss": 3.9105, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622787960662045e-05, + "loss": 3.9246, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621949365910993e-05, + "loss": 3.9129, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621110771159941e-05, + "loss": 3.9219, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202738142892616e-05, + "loss": 3.907, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194352195382096e-05, + "loss": 3.9142, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185966247871576e-05, + "loss": 3.8972, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177580300361056e-05, + "loss": 3.9227, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169194352850536e-05, + "loss": 3.9164, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.914, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.9201, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144052889122705e-05, + "loss": 3.8996, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135666941612185e-05, + "loss": 3.9021, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127280994101665e-05, + "loss": 3.9112, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611889504659115e-05, + "loss": 3.8979, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611050909908063e-05, + "loss": 3.8961, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610213953037384e-05, + "loss": 3.8965, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609375358286332e-05, + "loss": 3.898, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.60853676353528e-05, + "loss": 3.9247, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.9027, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.9021, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606020979282124e-05, + "loss": 3.8986, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051823845310714e-05, + "loss": 3.907, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604345427660393e-05, + "loss": 3.8917, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603506832909341e-05, + "loss": 3.8926, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602668238158289e-05, + "loss": 3.8954, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601829643407237e-05, + "loss": 3.903, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600991048656185e-05, + "loss": 3.8862, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001540917855065e-05, + "loss": 3.8938, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599315497034454e-05, + "loss": 3.8938, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598476902283402e-05, + "loss": 3.9016, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.59763830753235e-05, + "loss": 3.8896, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596799712781298e-05, + "loss": 3.8945, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595962755910619e-05, + "loss": 3.8971, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595124161159567e-05, + "loss": 3.8972, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594285566408515e-05, + "loss": 3.8785, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593446971657463e-05, + "loss": 3.8895, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592608376906411e-05, + "loss": 3.874, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591769782155359e-05, + "loss": 3.8921, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590931187404307e-05, + "loss": 3.8816, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900925926532554e-05, + "loss": 3.8941, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589255635782576e-05, + "loss": 3.8861, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588417041031524e-05, + "loss": 3.8849, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587578446280472e-05, + "loss": 3.8939, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.58673985152942e-05, + "loss": 3.8916, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585902894658741e-05, + "loss": 3.889, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585065937788062e-05, + "loss": 3.8755, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58422734303701e-05, + "loss": 3.8785, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583388748285958e-05, + "loss": 3.8957, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.8818, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581713196664228e-05, + "loss": 3.8781, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580874601913176e-05, + "loss": 3.8776, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580036007162124e-05, + "loss": 3.8826, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579197412411072e-05, + "loss": 3.8667, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.8877, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.8806, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576681628157916e-05, + "loss": 3.8848, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.889, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750060765361846e-05, + "loss": 3.8678, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741674817851326e-05, + "loss": 3.8721, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733305249144535e-05, + "loss": 3.8783, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724919301634015e-05, + "loss": 3.8672, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716533354123495e-05, + "loss": 3.8634, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.8745, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.8755, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569137551159194e-05, + "loss": 3.8664, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568300594288515e-05, + "loss": 3.8585, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567461999537463e-05, + "loss": 3.875, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566623404786411e-05, + "loss": 3.8819, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565784810035359e-05, + "loss": 3.8721, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8788, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8831, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563270663662576e-05, + "loss": 3.8815, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562432068911524e-05, + "loss": 3.8858, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8606, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8767, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599179225387415e-05, + "loss": 3.8771, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590793277876895e-05, + "loss": 3.8643, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8773, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.8696, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.882, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555724948783481e-05, + "loss": 3.8751, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554886354032429e-05, + "loss": 3.8537, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8627, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.8659, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.8691, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551533612908594e-05, + "loss": 3.8712, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550696656037915e-05, + "loss": 3.8599, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8672, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8575, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8674, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8593, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.8662, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8771, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.8666, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543989535909872e-05, + "loss": 3.8578, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8637, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8622, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8691, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540636794786037e-05, + "loss": 3.8618, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539798200034985e-05, + "loss": 3.8573, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8502, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.8693, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.8484, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.8464, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8544, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8586, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.8511, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330910799069426e-05, + "loss": 3.8668, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8505, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8554, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8543, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8466, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8708, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8625, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8572, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8563, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8482, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.8605, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238698134061164e-05, + "loss": 3.8478, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230312186550644e-05, + "loss": 3.8628, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221926239040124e-05, + "loss": 3.846, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213540291529604e-05, + "loss": 3.856, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520517072282281e-05, + "loss": 3.846, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.8487, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.844, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518001288029125e-05, + "loss": 3.8516, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517164331158447e-05, + "loss": 3.8462, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516325736407395e-05, + "loss": 3.865, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8543, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514648546905291e-05, + "loss": 3.8492, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513809952154239e-05, + "loss": 3.8368, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512971357403187e-05, + "loss": 3.8588, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.8542, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511295805781456e-05, + "loss": 3.8573, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510457211030404e-05, + "loss": 3.8462, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509618616279352e-05, + "loss": 3.8484, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.8548, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079430646576206e-05, + "loss": 3.8532, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8422, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506265875155517e-05, + "loss": 3.8488, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505427280404465e-05, + "loss": 3.8441, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.8383, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.8518, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8538, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8418, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8379, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500398987658899e-05, + "loss": 3.8454, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.909972906112671, + "eval_runtime": 308.3464, + "eval_samples_per_second": 1237.54, + "eval_steps_per_second": 38.674, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499560392907847e-05, + "loss": 3.8346, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498721798156795e-05, + "loss": 3.8397, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497883203405743e-05, + "loss": 3.8516, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497044608654691e-05, + "loss": 3.8413, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496206013903639e-05, + "loss": 3.8541, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495367419152587e-05, + "loss": 3.8364, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494528824401535e-05, + "loss": 3.8422, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493690229650483e-05, + "loss": 3.8292, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928532727798047e-05, + "loss": 3.8548, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492014678028752e-05, + "loss": 3.8439, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911760832777e-05, + "loss": 3.8403, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490337488526648e-05, + "loss": 3.8531, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.8283, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8377, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8405, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8296, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861477905321344e-05, + "loss": 3.8291, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853091957810824e-05, + "loss": 3.8281, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844706010300304e-05, + "loss": 3.8332, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836320062789784e-05, + "loss": 3.8511, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827934115279264e-05, + "loss": 3.8347, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481956454657247e-05, + "loss": 3.8327, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481117859906195e-05, + "loss": 3.8322, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480279265155143e-05, + "loss": 3.8396, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8245, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8253, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.826, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476926524031308e-05, + "loss": 3.836, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476087929280256e-05, + "loss": 3.8196, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475249334529205e-05, + "loss": 3.8294, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8291, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473573782907474e-05, + "loss": 3.8346, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.824, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8303, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8305, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8312, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8174, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468543852281535e-05, + "loss": 3.8192, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8104, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.825, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8169, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651911111577e-05, + "loss": 3.8282, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8214, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8226, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8267, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8259, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.46099813740244e-05, + "loss": 3.828, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8143, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8089, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8329, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457645396278605e-05, + "loss": 3.8176, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8144, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.8134, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8203, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45429265515477e-05, + "loss": 3.8013, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8244, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8177, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8201, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8276, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8109, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.8075, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8217, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.7994, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8021, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445909983404996e-05, + "loss": 3.8141, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445071388653944e-05, + "loss": 3.8142, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8028, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.8005, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.8128, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417186475301094e-05, + "loss": 3.8185, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8153, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.814, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.8231, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438365906406274e-05, + "loss": 3.8171, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437527311655222e-05, + "loss": 3.8271, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.8004, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8169, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435013165282439e-05, + "loss": 3.8145, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434174570531388e-05, + "loss": 3.8021, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433335975780336e-05, + "loss": 3.8198, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8088, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431660424158605e-05, + "loss": 3.818, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430821829407553e-05, + "loss": 3.8185, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429983234656501e-05, + "loss": 3.7945, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8048, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283076830347696e-05, + "loss": 3.8025, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274690882837176e-05, + "loss": 3.8117, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266304935326656e-05, + "loss": 3.81, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.8023, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249549419109345e-05, + "loss": 3.8096, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424116347159883e-05, + "loss": 3.7998, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423277752408831e-05, + "loss": 3.8028, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.8012, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216022007871e-05, + "loss": 3.81, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420763606036048e-05, + "loss": 3.8172, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419925011284996e-05, + "loss": 3.8086, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.7995, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418249459663265e-05, + "loss": 3.8038, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417410864912213e-05, + "loss": 3.807, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416572270161161e-05, + "loss": 3.8127, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415733675410109e-05, + "loss": 3.8064, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41489671853943e-05, + "loss": 3.7999, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414058123788378e-05, + "loss": 3.7951, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132195290373266e-05, + "loss": 3.8078, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123809342862746e-05, + "loss": 3.792, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115439774155955e-05, + "loss": 3.7935, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107053826645435e-05, + "loss": 3.7903, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098667879134915e-05, + "loss": 3.8042, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.79, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081912362917604e-05, + "loss": 3.8144, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073526415407084e-05, + "loss": 3.7902, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065140467896564e-05, + "loss": 3.8035, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056754520386044e-05, + "loss": 3.799, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048368572875524e-05, + "loss": 3.7896, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039982625365004e-05, + "loss": 3.8141, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031596677854484e-05, + "loss": 3.8061, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.40232271091477e-05, + "loss": 3.7995, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401484116163718e-05, + "loss": 3.7992, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400645521412666e-05, + "loss": 3.7921, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399806926661613e-05, + "loss": 3.803, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398969969790935e-05, + "loss": 3.7853, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398131375039883e-05, + "loss": 3.8079, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397292780288831e-05, + "loss": 3.7951, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.7972, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956172286671e-05, + "loss": 3.7924, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394778633916048e-05, + "loss": 3.7943, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393940039164996e-05, + "loss": 3.7857, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393101444413944e-05, + "loss": 3.7976, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392264487543265e-05, + "loss": 3.7893, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391425892792213e-05, + "loss": 3.8064, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905872980411606e-05, + "loss": 3.7999, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897487032901086e-05, + "loss": 3.7964, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.7818, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880715137880046e-05, + "loss": 3.8023, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872345569173255e-05, + "loss": 3.798, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863959621662735e-05, + "loss": 3.8015, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.7914, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847187726641695e-05, + "loss": 3.7945, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383881815793491e-05, + "loss": 3.7985, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383043221042439e-05, + "loss": 3.8038, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.7874, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381366031540335e-05, + "loss": 3.7973, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380529074669656e-05, + "loss": 3.7877, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379690479918604e-05, + "loss": 3.7855, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788535230479256e-05, + "loss": 3.8027, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378014928296873e-05, + "loss": 3.7917, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377176333545821e-05, + "loss": 3.7913, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376337738794769e-05, + "loss": 3.7842, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375499144043717e-05, + "loss": 3.7914, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.88553786277771, + "eval_runtime": 320.7264, + "eval_samples_per_second": 1189.771, + "eval_steps_per_second": 37.181, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374660549292665e-05, + "loss": 3.7885, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373821954541613e-05, + "loss": 3.7854, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372983359790561e-05, + "loss": 3.8006, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721464029198824e-05, + "loss": 3.7913, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.3713078081688304e-05, + "loss": 3.7962, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704692134177784e-05, + "loss": 3.7883, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.3696306186667264e-05, + "loss": 3.7855, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.7771, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679550670449953e-05, + "loss": 3.7962, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367116472293943e-05, + "loss": 3.7976, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366277877542891e-05, + "loss": 3.789, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365440920672212e-05, + "loss": 3.798, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7768, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7846, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7905, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.7767, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361249584797326e-05, + "loss": 3.7767, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360410990046274e-05, + "loss": 3.7782, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359572395295222e-05, + "loss": 3.7809, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35873380054417e-05, + "loss": 3.7973, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357896843673491e-05, + "loss": 3.7862, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357058248922439e-05, + "loss": 3.7848, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356219654171387e-05, + "loss": 3.7772, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355381059420335e-05, + "loss": 3.7886, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545441025496556e-05, + "loss": 3.7724, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537055077986036e-05, + "loss": 3.7737, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528669130475516e-05, + "loss": 3.7779, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520283182964996e-05, + "loss": 3.7829, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351191361425821e-05, + "loss": 3.7689, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350352766674769e-05, + "loss": 3.7781, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349514171923717e-05, + "loss": 3.781, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348675577172665e-05, + "loss": 3.7832, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347838620301986e-05, + "loss": 3.7773, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347000025550934e-05, + "loss": 3.7762, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346161430799882e-05, + "loss": 3.78, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.34532283604883e-05, + "loss": 3.7776, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344484241297778e-05, + "loss": 3.7711, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343647284427099e-05, + "loss": 3.7695, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342808689676047e-05, + "loss": 3.7615, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341970094924995e-05, + "loss": 3.7735, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411331380543165e-05, + "loss": 3.77, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402945433032645e-05, + "loss": 3.7788, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394559485522125e-05, + "loss": 3.7709, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386173538011605e-05, + "loss": 3.77, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7802, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369418021794294e-05, + "loss": 3.7751, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3361032074283774e-05, + "loss": 3.7788, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352646126773254e-05, + "loss": 3.7627, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7602, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333589061055594e-05, + "loss": 3.7856, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332750466304542e-05, + "loss": 3.7684, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.33191187155349e-05, + "loss": 3.7661, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7647, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.33023631993176e-05, + "loss": 3.7712, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329397725180708e-05, + "loss": 3.753, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328559130429656e-05, + "loss": 3.7752, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7703, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326883578807925e-05, + "loss": 3.7667, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326044984056873e-05, + "loss": 3.7841, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325206389305821e-05, + "loss": 3.7591, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324369432435142e-05, + "loss": 3.7613, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.32353083768409e-05, + "loss": 3.7752, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322692242933038e-05, + "loss": 3.7553, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321853648181986e-05, + "loss": 3.7549, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.765, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320178096560255e-05, + "loss": 3.7657, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319339501809203e-05, + "loss": 3.7581, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185009070581506e-05, + "loss": 3.7532, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.7598, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.31682535543642e-05, + "loss": 3.7683, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315986760685368e-05, + "loss": 3.7668, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151481659343155e-05, + "loss": 3.7698, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314311209063637e-05, + "loss": 3.7729, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313472614312585e-05, + "loss": 3.7713, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312634019561533e-05, + "loss": 3.7818, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311795424810481e-05, + "loss": 3.7504, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.775, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101198731887506e-05, + "loss": 3.769, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309281278437698e-05, + "loss": 3.7491, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308442683686646e-05, + "loss": 3.7765, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.7613, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067671320649155e-05, + "loss": 3.7718, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305928537313863e-05, + "loss": 3.7719, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305089942562811e-05, + "loss": 3.7505, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.7547, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034143909410804e-05, + "loss": 3.7566, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025757961900284e-05, + "loss": 3.7665, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017372014389764e-05, + "loss": 3.7614, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300900244568298e-05, + "loss": 3.7593, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300061649817245e-05, + "loss": 3.7583, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299223055066193e-05, + "loss": 3.7566, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298384460315141e-05, + "loss": 3.7584, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297547503444463e-05, + "loss": 3.7533, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.29670890869341e-05, + "loss": 3.7666, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.769, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.7687, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7508, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293356167569576e-05, + "loss": 3.7593, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292517572818524e-05, + "loss": 3.7573, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291678978067472e-05, + "loss": 3.7634, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290842021196793e-05, + "loss": 3.7627, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290003426445741e-05, + "loss": 3.757, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289164831694689e-05, + "loss": 3.7487, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288326236943637e-05, + "loss": 3.7612, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874892800729576e-05, + "loss": 3.751, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.2866506853219056e-05, + "loss": 3.7472, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858120905708536e-05, + "loss": 3.7408, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849734958198016e-05, + "loss": 3.759, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284138176829496e-05, + "loss": 3.75, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283299582078444e-05, + "loss": 3.7652, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282460987327393e-05, + "loss": 3.749, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.28162239257634e-05, + "loss": 3.7559, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280783797825288e-05, + "loss": 3.7563, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279945203074236e-05, + "loss": 3.7451, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279106608323184e-05, + "loss": 3.7684, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278268013572132e-05, + "loss": 3.7609, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277431056701453e-05, + "loss": 3.7538, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276592461950401e-05, + "loss": 3.7545, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275753867199349e-05, + "loss": 3.7513, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274915272448297e-05, + "loss": 3.7603, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274078315577618e-05, + "loss": 3.7388, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2732397208265665e-05, + "loss": 3.7636, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.2724011260755145e-05, + "loss": 3.7468, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.2715625313244625e-05, + "loss": 3.7523, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.2707255744537834e-05, + "loss": 3.7519, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.2698869797027314e-05, + "loss": 3.7478, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.2690483849516794e-05, + "loss": 3.7477, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2682097902006274e-05, + "loss": 3.7496, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7501, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7609, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.7524, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264857049076792e-05, + "loss": 3.7546, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264020092206113e-05, + "loss": 3.7364, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.7617, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7517, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261504307952958e-05, + "loss": 3.7558, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7492, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7473, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.7575, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258151566829123e-05, + "loss": 3.7602, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7435, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7518, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.25563742045634e-05, + "loss": 3.7475, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254798825705288e-05, + "loss": 3.7422, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539618688346086e-05, + "loss": 3.7587, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7473, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252284679332505e-05, + "loss": 3.7537, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251446084581453e-05, + "loss": 3.7367, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250607489830401e-05, + "loss": 3.7515, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8704419136047363, + "eval_runtime": 359.2798, + "eval_samples_per_second": 1062.1, + "eval_steps_per_second": 33.191, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249768895079349e-05, + "loss": 3.7448, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248930300328297e-05, + "loss": 3.74, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248091705577245e-05, + "loss": 3.7577, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247253110826193e-05, + "loss": 3.7505, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246414516075141e-05, + "loss": 3.7526, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455759213240885e-05, + "loss": 3.7464, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447373265730365e-05, + "loss": 3.7385, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438987318219845e-05, + "loss": 3.7418, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430617749513054e-05, + "loss": 3.7494, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422231802002534e-05, + "loss": 3.7574, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241384585449202e-05, + "loss": 3.7464, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.24054599069815e-05, + "loss": 3.7573, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397106717078446e-05, + "loss": 3.7403, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388720769567926e-05, + "loss": 3.7388, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380334822057406e-05, + "loss": 3.7495, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371948874546886e-05, + "loss": 3.7347, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236356292703636e-05, + "loss": 3.735, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235517697952584e-05, + "loss": 3.734, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234679103201532e-05, + "loss": 3.7407, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.23384050845048e-05, + "loss": 3.7513, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233003551579801e-05, + "loss": 3.746, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232164956828749e-05, + "loss": 3.7445, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313263620776975e-05, + "loss": 3.7336, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304877673266455e-05, + "loss": 3.7475, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296508104559664e-05, + "loss": 3.7351, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288122157049144e-05, + "loss": 3.7352, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279736209538624e-05, + "loss": 3.7319, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2271350262028104e-05, + "loss": 3.74, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226298069332131e-05, + "loss": 3.7351, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225459474581079e-05, + "loss": 3.7326, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224620879830027e-05, + "loss": 3.7409, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223782285078975e-05, + "loss": 3.7412, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222945328208296e-05, + "loss": 3.7365, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222106733457244e-05, + "loss": 3.7403, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221268138706193e-05, + "loss": 3.737, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220429543955141e-05, + "loss": 3.7363, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219592587084462e-05, + "loss": 3.7347, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.21875399233341e-05, + "loss": 3.7232, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217915397582358e-05, + "loss": 3.7197, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217076802831306e-05, + "loss": 3.7321, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2162398459606267e-05, + "loss": 3.7323, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154012512095746e-05, + "loss": 3.7354, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.733, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137240617074706e-05, + "loss": 3.7314, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.7409, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.7339, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7407, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210371320583636e-05, + "loss": 3.7224, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7161, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208695768961905e-05, + "loss": 3.7474, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207857174210853e-05, + "loss": 3.7332, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207018579459801e-05, + "loss": 3.7231, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7269, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7291, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204504433087018e-05, + "loss": 3.7172, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203665838335966e-05, + "loss": 3.7307, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7325, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7318, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011516919631836e-05, + "loss": 3.7427, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003130972121316e-05, + "loss": 3.718, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.723, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986375455904005e-05, + "loss": 3.7387, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977989508393485e-05, + "loss": 3.7154, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969603560882965e-05, + "loss": 3.7131, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961233992176174e-05, + "loss": 3.7259, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.725, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.7177, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7184, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192770658093782e-05, + "loss": 3.7158, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.19193206334273e-05, + "loss": 3.7347, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191093468591679e-05, + "loss": 3.7286, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190254873840627e-05, + "loss": 3.7293, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189417916969948e-05, + "loss": 3.7322, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188579322218896e-05, + "loss": 3.7307, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187740727467844e-05, + "loss": 3.7441, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186902132716792e-05, + "loss": 3.7149, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186065175846113e-05, + "loss": 3.7357, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185226581095061e-05, + "loss": 3.7306, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184387986344009e-05, + "loss": 3.7141, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183549391592957e-05, + "loss": 3.7349, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.7243, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818738399712256e-05, + "loss": 3.732, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181035245220174e-05, + "loss": 3.7341, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.7163, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179359693598443e-05, + "loss": 3.7114, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178521098847391e-05, + "loss": 3.7186, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177682504096339e-05, + "loss": 3.7307, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.7215, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176006952474608e-05, + "loss": 3.7223, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175168357723556e-05, + "loss": 3.7222, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174329762972504e-05, + "loss": 3.7177, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7225, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172654211350773e-05, + "loss": 3.7164, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171815616599721e-05, + "loss": 3.729, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170977021848669e-05, + "loss": 3.7304, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7304, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7129, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7232, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7235, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667889617345284e-05, + "loss": 3.7266, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659503669834764e-05, + "loss": 3.7248, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651117722324244e-05, + "loss": 3.7159, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.7168, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7216, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7125, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7173, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609187984771644e-05, + "loss": 3.6983, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.724, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7148, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.7247, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7136, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.7206, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155890505731599e-05, + "loss": 3.7204, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155051910980547e-05, + "loss": 3.7054, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.7333, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7226, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.7187, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7228, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.706, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7263, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.7077, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148346428732877e-05, + "loss": 3.7245, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7085, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7175, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7131, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144993687609042e-05, + "loss": 3.7143, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.7136, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.7089, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.716, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7243, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7134, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7228, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.7009, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.7241, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7213, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7173, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7125, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7145, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7168, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7277, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.7046, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7177, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7116, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7067, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7192, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.712, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7166, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.7029, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257141977367114e-05, + "loss": 3.7206, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.859236240386963, + "eval_runtime": 307.2076, + "eval_samples_per_second": 1242.128, + "eval_steps_per_second": 38.817, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7075, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.706, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.7192, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122361456612876e-05, + "loss": 3.7148, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121522861861824e-05, + "loss": 3.7162, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120684267110773e-05, + "loss": 3.7127, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119845672359721e-05, + "loss": 3.7048, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119008715489042e-05, + "loss": 3.7052, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11817012073799e-05, + "loss": 3.7164, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117331525986938e-05, + "loss": 3.7184, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7116, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7194, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7089, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7027, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7121, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.6979, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7023, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.7004, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7081, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108948854237164e-05, + "loss": 3.7136, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7172, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7067, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.6995, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.7116, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.6968, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.7038, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.6973, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.7076, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101406415118815e-05, + "loss": 3.6979, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.702, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997292256167117e-05, + "loss": 3.7028, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7108, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7036, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.7012, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963764844928766e-05, + "loss": 3.7044, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.7002, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.7039, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.6856, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.6886, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6969, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.7017, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7013, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.6992, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.6947, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.7082, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.6973, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086318261121372e-05, + "loss": 3.7155, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085481304250693e-05, + "loss": 3.6873, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6774, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.717, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.6964, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082128563126858e-05, + "loss": 3.696, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.6962, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080451373624754e-05, + "loss": 3.6921, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079614416754075e-05, + "loss": 3.6858, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078775822003023e-05, + "loss": 3.6967, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.6992, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6981, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.7123, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075421442998815e-05, + "loss": 3.687, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074582848247763e-05, + "loss": 3.688, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7074, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6825, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.07206870187498e-05, + "loss": 3.6819, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071230107123928e-05, + "loss": 3.6916, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.6942, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.682, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.6908, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067877366000094e-05, + "loss": 3.6833, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6968, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.7002, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6927, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.7006, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.6996, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.7118, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.6804, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061171883752423e-05, + "loss": 3.7058, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.6942, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6834, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.7011, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578191426285884e-05, + "loss": 3.6954, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6973, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056143591006858e-05, + "loss": 3.7051, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055304996255805e-05, + "loss": 3.6817, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054466401504753e-05, + "loss": 3.6774, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6876, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.6992, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6921, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.6875, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.6854, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.6878, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.689, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6861, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6951, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.7001, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.6963, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6838, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.6931, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.6854, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041895669640839e-05, + "loss": 3.6946, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041057074889787e-05, + "loss": 3.6942, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040218480138735e-05, + "loss": 3.6887, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.6809, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038541290636631e-05, + "loss": 3.6857, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6853, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.6837, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6708, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035188549512796e-05, + "loss": 3.6926, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343515926421177e-05, + "loss": 3.6872, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033512997891065e-05, + "loss": 3.6872, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6792, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031835808388961e-05, + "loss": 3.6955, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.6859, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.676, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.6995, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.692, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276444725140745e-05, + "loss": 3.686, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268058777630225e-05, + "loss": 3.6934, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.6767, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.695, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242917313902394e-05, + "loss": 3.6788, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234531366391874e-05, + "loss": 3.6907, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6783, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6866, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020938990266404e-05, + "loss": 3.6827, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020100395515353e-05, + "loss": 3.6821, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019261800764301e-05, + "loss": 3.6799, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.6797, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.01758624914257e-05, + "loss": 3.6865, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016747654391518e-05, + "loss": 3.692, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015909059640466e-05, + "loss": 3.6791, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.6952, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014233508018735e-05, + "loss": 3.6679, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013394913267683e-05, + "loss": 3.6947, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012556318516631e-05, + "loss": 3.6896, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011717723765579e-05, + "loss": 3.6874, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108807668949e-05, + "loss": 3.6812, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100421721438484e-05, + "loss": 3.6855, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092035773927964e-05, + "loss": 3.6873, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0083649826417444e-05, + "loss": 3.6985, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007528025771065e-05, + "loss": 3.6739, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006689431020013e-05, + "loss": 3.6861, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005850836268961e-05, + "loss": 3.6795, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.6834, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004176922527603e-05, + "loss": 3.6821, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003338327776551e-05, + "loss": 3.6819, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002499733025499e-05, + "loss": 3.6899, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001661138274447e-05, + "loss": 3.6711, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000822543523395e-05, + "loss": 3.6904, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.85294246673584, + "eval_runtime": 307.3127, + "eval_samples_per_second": 1241.703, + "eval_steps_per_second": 38.804, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999983948772343e-05, + "loss": 3.6776, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999145354021292e-05, + "loss": 3.6786, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.99830675927024e-05, + "loss": 3.6858, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997468164519188e-05, + "loss": 3.6837, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996629569768136e-05, + "loss": 3.6904, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995790975017084e-05, + "loss": 3.6792, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994952380266031e-05, + "loss": 3.6769, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941154233953526e-05, + "loss": 3.6781, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932768286443006e-05, + "loss": 3.682, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992438233893248e-05, + "loss": 3.6912, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991599639142196e-05, + "loss": 3.6836, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990761044391144e-05, + "loss": 3.6883, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899240875204655e-05, + "loss": 3.6765, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890854927694135e-05, + "loss": 3.6766, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882468980183615e-05, + "loss": 3.6833, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874083032673095e-05, + "loss": 3.668, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865697085162575e-05, + "loss": 3.6709, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857311137652055e-05, + "loss": 3.6701, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.678, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6817, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832169673924224e-05, + "loss": 3.6883, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823783726413704e-05, + "loss": 3.6786, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815397778903184e-05, + "loss": 3.6702, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9807011831392664e-05, + "loss": 3.6785, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979864226268587e-05, + "loss": 3.6714, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979025631517535e-05, + "loss": 3.675, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978187036766484e-05, + "loss": 3.6651, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977348442015432e-05, + "loss": 3.6786, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976511485144753e-05, + "loss": 3.6733, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975672890393701e-05, + "loss": 3.6703, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974835933523022e-05, + "loss": 3.6724, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.97399733877197e-05, + "loss": 3.6837, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973158744020918e-05, + "loss": 3.6727, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972320149269866e-05, + "loss": 3.6701, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971481554518814e-05, + "loss": 3.6732, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970642959767762e-05, + "loss": 3.677, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96980436501671e-05, + "loss": 3.6716, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968965770265658e-05, + "loss": 3.6581, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968128813394979e-05, + "loss": 3.6617, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967290218643927e-05, + "loss": 3.6663, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966451623892875e-05, + "loss": 3.6713, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965613029141823e-05, + "loss": 3.6723, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964776072271144e-05, + "loss": 3.6707, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963937477520092e-05, + "loss": 3.6683, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.96309888276904e-05, + "loss": 3.6751, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962260288017988e-05, + "loss": 3.6674, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961423331147309e-05, + "loss": 3.6827, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960584736396257e-05, + "loss": 3.6635, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959746141645205e-05, + "loss": 3.6463, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958907546894153e-05, + "loss": 3.6884, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958070590023475e-05, + "loss": 3.6682, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957231995272423e-05, + "loss": 3.6695, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956393400521371e-05, + "loss": 3.667, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6629, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547178488996396e-05, + "loss": 3.6566, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538792541485876e-05, + "loss": 3.6657, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530406593975356e-05, + "loss": 3.6737, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522020646464836e-05, + "loss": 3.6713, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513634698954316e-05, + "loss": 3.6834, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950524875144379e-05, + "loss": 3.6581, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949686280393327e-05, + "loss": 3.6576, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948847685642275e-05, + "loss": 3.6811, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480107287715965e-05, + "loss": 3.6498, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471721340205445e-05, + "loss": 3.6526, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463335392694925e-05, + "loss": 3.6633, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945496582398814e-05, + "loss": 3.6654, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944657987647762e-05, + "loss": 3.6555, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438193928967094e-05, + "loss": 3.6606, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429807981456573e-05, + "loss": 3.6555, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942143841274979e-05, + "loss": 3.6713, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941305246523926e-05, + "loss": 3.6683, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940466651772874e-05, + "loss": 3.667, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939628057021822e-05, + "loss": 3.6719, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938791100151144e-05, + "loss": 3.6718, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937954143280465e-05, + "loss": 3.6815, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9371155485294134e-05, + "loss": 3.6542, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362769537783614e-05, + "loss": 3.6796, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935438359027309e-05, + "loss": 3.6612, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934599764276257e-05, + "loss": 3.6559, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933761169525205e-05, + "loss": 3.6732, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932922574774153e-05, + "loss": 3.668, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932083980023101e-05, + "loss": 3.6701, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312470231524216e-05, + "loss": 3.676, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304084284013696e-05, + "loss": 3.6538, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295698336503176e-05, + "loss": 3.6476, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287312388992656e-05, + "loss": 3.6606, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927894282028587e-05, + "loss": 3.6703, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927055687277535e-05, + "loss": 3.6651, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926217092526483e-05, + "loss": 3.6615, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925378497775431e-05, + "loss": 3.6571, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924539903024379e-05, + "loss": 3.658, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923701308273327e-05, + "loss": 3.6627, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922862713522275e-05, + "loss": 3.6572, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922024118771223e-05, + "loss": 3.6663, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.671, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920350205029865e-05, + "loss": 3.6696, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919511610278813e-05, + "loss": 3.6584, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918673015527761e-05, + "loss": 3.663, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917834420776709e-05, + "loss": 3.6588, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169974639060306e-05, + "loss": 3.6659, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161588691549786e-05, + "loss": 3.6668, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153202744039265e-05, + "loss": 3.6626, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144816796528745e-05, + "loss": 3.6589, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136447227821955e-05, + "loss": 3.6512, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128061280311434e-05, + "loss": 3.6606, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119675332800914e-05, + "loss": 3.6555, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111289385290394e-05, + "loss": 3.6414, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102903437779874e-05, + "loss": 3.6682, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094533869073083e-05, + "loss": 3.6595, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086147921562563e-05, + "loss": 3.6614, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907776197405204e-05, + "loss": 3.6497, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906937602654152e-05, + "loss": 3.6658, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906099007903101e-05, + "loss": 3.6616, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905260413152049e-05, + "loss": 3.6494, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904421818400997e-05, + "loss": 3.6733, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903583223649945e-05, + "loss": 3.6669, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902746266779266e-05, + "loss": 3.6591, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901907672028214e-05, + "loss": 3.6644, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901069077277162e-05, + "loss": 3.6474, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.90023048252611e-05, + "loss": 3.6662, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899395163535804e-05, + "loss": 3.6554, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898556568784752e-05, + "loss": 3.6594, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977179740337e-05, + "loss": 3.6521, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896879379282648e-05, + "loss": 3.6632, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960407845315964e-05, + "loss": 3.6564, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952021897805444e-05, + "loss": 3.653, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943635950294924e-05, + "loss": 3.6529, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352500027844e-05, + "loss": 3.6574, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892688043407761e-05, + "loss": 3.6553, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891849448656709e-05, + "loss": 3.6645, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891010853905657e-05, + "loss": 3.6538, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.8901722591546046e-05, + "loss": 3.6709, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889335302283926e-05, + "loss": 3.6407, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888496707532874e-05, + "loss": 3.6665, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887658112781822e-05, + "loss": 3.6649, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.88681951803077e-05, + "loss": 3.6634, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885982561160092e-05, + "loss": 3.6532, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.88514396640904e-05, + "loss": 3.6565, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884305371657987e-05, + "loss": 3.6568, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883466776906935e-05, + "loss": 3.6767, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826298200362566e-05, + "loss": 3.6469, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817912252852046e-05, + "loss": 3.6574, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880952630534152e-05, + "loss": 3.6526, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801140357831e-05, + "loss": 3.6602, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792787167927944e-05, + "loss": 3.6519, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784401220417424e-05, + "loss": 3.6587, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776015272906904e-05, + "loss": 3.6599, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767629325396384e-05, + "loss": 3.6525, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875924337788587e-05, + "loss": 3.6599, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.848494052886963, + "eval_runtime": 317.0125, + "eval_samples_per_second": 1203.71, + "eval_steps_per_second": 37.617, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875087380917908e-05, + "loss": 3.6479, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874248786166856e-05, + "loss": 3.6495, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873410191415804e-05, + "loss": 3.6616, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872571596664752e-05, + "loss": 3.6583, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871733001913699e-05, + "loss": 3.6626, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870896045043021e-05, + "loss": 3.6529, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870057450291969e-05, + "loss": 3.65, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869218855540916e-05, + "loss": 3.6543, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868380260789864e-05, + "loss": 3.6534, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867541666038812e-05, + "loss": 3.6644, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866703071287761e-05, + "loss": 3.6574, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865864476536709e-05, + "loss": 3.6583, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.86502751966603e-05, + "loss": 3.6598, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864188924914978e-05, + "loss": 3.6421, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863350330163926e-05, + "loss": 3.6576, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862511735412874e-05, + "loss": 3.6432, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861673140661822e-05, + "loss": 3.6435, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.86083454591077e-05, + "loss": 3.6465, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859995951159718e-05, + "loss": 3.6481, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859157356408666e-05, + "loss": 3.6555, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858320399537987e-05, + "loss": 3.6653, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857481804786935e-05, + "loss": 3.6576, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566432100358827e-05, + "loss": 3.6446, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558046152848307e-05, + "loss": 3.6501, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854967658414152e-05, + "loss": 3.6448, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541290636631e-05, + "loss": 3.6475, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853290468912048e-05, + "loss": 3.6414, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852451874160996e-05, + "loss": 3.6563, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851614917290317e-05, + "loss": 3.6424, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850776322539265e-05, + "loss": 3.6451, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849939365668586e-05, + "loss": 3.6424, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849100770917534e-05, + "loss": 3.6573, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848262176166482e-05, + "loss": 3.6488, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.84742358141543e-05, + "loss": 3.6458, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846584986664378e-05, + "loss": 3.6478, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845746391913326e-05, + "loss": 3.6472, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844907797162274e-05, + "loss": 3.6501, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844069202411223e-05, + "loss": 3.635, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432322455405436e-05, + "loss": 3.6353, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423952886698645e-05, + "loss": 3.6397, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415566939188125e-05, + "loss": 3.6426, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407180991677605e-05, + "loss": 3.6457, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398795044167085e-05, + "loss": 3.6452, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390409096656565e-05, + "loss": 3.6479, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8382023149146045e-05, + "loss": 3.6439, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373637201635525e-05, + "loss": 3.6468, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365251254125e-05, + "loss": 3.6553, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356881685418214e-05, + "loss": 3.6399, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348495737907694e-05, + "loss": 3.6215, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834010979039718e-05, + "loss": 3.6594, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331723842886654e-05, + "loss": 3.6421, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832335427417987e-05, + "loss": 3.6447, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831496832666935e-05, + "loss": 3.6455, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830658237915883e-05, + "loss": 3.6364, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829821281045204e-05, + "loss": 3.6315, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828982686294152e-05, + "loss": 3.6385, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281440915431e-05, + "loss": 3.6507, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827305496792047e-05, + "loss": 3.6419, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826466902040995e-05, + "loss": 3.6562, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825628307289943e-05, + "loss": 3.6357, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824789712538892e-05, + "loss": 3.629, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.82395111778784e-05, + "loss": 3.6545, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823114160917161e-05, + "loss": 3.6298, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822275566166109e-05, + "loss": 3.6267, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821436971415057e-05, + "loss": 3.6401, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8206000145443776e-05, + "loss": 3.6377, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197614197933256e-05, + "loss": 3.6317, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189228250422736e-05, + "loss": 3.6351, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180842302912216e-05, + "loss": 3.6303, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172472734205425e-05, + "loss": 3.6438, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164086786694905e-05, + "loss": 3.6451, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155700839184385e-05, + "loss": 3.6419, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814731489167387e-05, + "loss": 3.6458, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813894532296708e-05, + "loss": 3.6451, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81305757542603e-05, + "loss": 3.655, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812218980674977e-05, + "loss": 3.6325, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811380385923925e-05, + "loss": 3.6546, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810541791172873e-05, + "loss": 3.6342, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809703196421821e-05, + "loss": 3.635, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808864601670769e-05, + "loss": 3.643, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808026006919717e-05, + "loss": 3.6447, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807187412168665e-05, + "loss": 3.6464, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806350455297986e-05, + "loss": 3.6504, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805511860546934e-05, + "loss": 3.6281, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046732657958826e-05, + "loss": 3.6262, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038363089252035e-05, + "loss": 3.6359, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029977141741515e-05, + "loss": 3.6471, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021591194230995e-05, + "loss": 3.6363, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013205246720475e-05, + "loss": 3.6371, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004819299209955e-05, + "loss": 3.6374, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996449730503164e-05, + "loss": 3.635, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7988063782992644e-05, + "loss": 3.6347, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979677835482124e-05, + "loss": 3.6336, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971291887971604e-05, + "loss": 3.6417, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962905940461084e-05, + "loss": 3.6458, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795453637175429e-05, + "loss": 3.6486, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794615042424377e-05, + "loss": 3.6337, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793776447673326e-05, + "loss": 3.6355, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792937852922274e-05, + "loss": 3.6376, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792099258171222e-05, + "loss": 3.64, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791262301300543e-05, + "loss": 3.6424, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790423706549491e-05, + "loss": 3.6395, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789585111798439e-05, + "loss": 3.6331, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788746517047387e-05, + "loss": 3.6263, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787907922296335e-05, + "loss": 3.6394, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787069327545283e-05, + "loss": 3.6302, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786230732794231e-05, + "loss": 3.6149, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785393775923552e-05, + "loss": 3.6373, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845568190528726e-05, + "loss": 3.6439, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783718224301821e-05, + "loss": 3.6334, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782879629550769e-05, + "loss": 3.6272, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782041034799717e-05, + "loss": 3.637, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781202440048665e-05, + "loss": 3.6369, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780363845297613e-05, + "loss": 3.6264, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795252505465606e-05, + "loss": 3.6499, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778688293675882e-05, + "loss": 3.6438, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77784969892483e-05, + "loss": 3.6324, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777011104173778e-05, + "loss": 3.638, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761725094227255e-05, + "loss": 3.6271, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753339146716735e-05, + "loss": 3.6397, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774496957800995e-05, + "loss": 3.632, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773658363049943e-05, + "loss": 3.6342, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772819768298891e-05, + "loss": 3.6286, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771981173547839e-05, + "loss": 3.6391, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771142578796787e-05, + "loss": 3.6342, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770303984045735e-05, + "loss": 3.6306, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769465389294683e-05, + "loss": 3.6277, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768626794543631e-05, + "loss": 3.6339, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767789837672952e-05, + "loss": 3.63, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766952880802273e-05, + "loss": 3.6409, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766114286051221e-05, + "loss": 3.6329, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765275691300169e-05, + "loss": 3.6442, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764437096549117e-05, + "loss": 3.6174, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763598501798065e-05, + "loss": 3.6453, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627599070470135e-05, + "loss": 3.6379, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619213122959615e-05, + "loss": 3.6379, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610827175449095e-05, + "loss": 3.6318, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602457606742304e-05, + "loss": 3.6311, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594071659231784e-05, + "loss": 3.6339, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585685711721264e-05, + "loss": 3.655, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577299764210744e-05, + "loss": 3.621, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756893019550395e-05, + "loss": 3.6364, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756054424799343e-05, + "loss": 3.6297, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755215830048291e-05, + "loss": 3.634, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754378873177612e-05, + "loss": 3.629, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.75354027842656e-05, + "loss": 3.636, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752701683675509e-05, + "loss": 3.6347, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751863088924457e-05, + "loss": 3.6328, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751024494173405e-05, + "loss": 3.6327, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8461601734161377, + "eval_runtime": 314.3363, + "eval_samples_per_second": 1213.958, + "eval_steps_per_second": 37.937, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750185899422353e-05, + "loss": 3.6247, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749347304671301e-05, + "loss": 3.6254, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748508709920249e-05, + "loss": 3.636, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747670115169197e-05, + "loss": 3.6393, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746831520418144e-05, + "loss": 3.6389, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745992925667092e-05, + "loss": 3.6306, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745155968796414e-05, + "loss": 3.6272, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744317374045362e-05, + "loss": 3.6274, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743478779294309e-05, + "loss": 3.6305, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742640184543257e-05, + "loss": 3.6406, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741801589792206e-05, + "loss": 3.6333, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740962995041154e-05, + "loss": 3.6363, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401260381704747e-05, + "loss": 3.6393, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392874434194226e-05, + "loss": 3.6162, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384488486683706e-05, + "loss": 3.6378, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376102539173186e-05, + "loss": 3.6155, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367732970466395e-05, + "loss": 3.6215, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359347022955875e-05, + "loss": 3.6229, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350961075445355e-05, + "loss": 3.6242, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342575127934835e-05, + "loss": 3.6325, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334189180424315e-05, + "loss": 3.6395, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325803232913795e-05, + "loss": 3.6342, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317417285403275e-05, + "loss": 3.6227, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309031337892755e-05, + "loss": 3.6219, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730066176918597e-05, + "loss": 3.6294, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729227582167545e-05, + "loss": 3.6228, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728388987416493e-05, + "loss": 3.6193, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727552030545814e-05, + "loss": 3.6335, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726713435794762e-05, + "loss": 3.6154, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.72587484104371e-05, + "loss": 3.6267, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725036246292658e-05, + "loss": 3.6185, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724197651541606e-05, + "loss": 3.6318, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723359056790554e-05, + "loss": 3.6302, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722520462039502e-05, + "loss": 3.6206, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72168186728845e-05, + "loss": 3.6269, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720844910417771e-05, + "loss": 3.619, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720006315666719e-05, + "loss": 3.6286, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191677209156676e-05, + "loss": 3.6173, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183291261646155e-05, + "loss": 3.61, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174938071743094e-05, + "loss": 3.6161, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166552124232574e-05, + "loss": 3.6237, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158166176722054e-05, + "loss": 3.6194, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149780229211534e-05, + "loss": 3.6194, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141394281701014e-05, + "loss": 3.6238, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133008334190493e-05, + "loss": 3.6226, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124622386679973e-05, + "loss": 3.6253, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116236439169453e-05, + "loss": 3.6364, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710786687046266e-05, + "loss": 3.6175, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709948092295214e-05, + "loss": 3.5965, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709109497544163e-05, + "loss": 3.6374, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.70827090279311e-05, + "loss": 3.6188, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707433945922432e-05, + "loss": 3.6239, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706596989051753e-05, + "loss": 3.6207, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705758394300701e-05, + "loss": 3.6155, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704919799549649e-05, + "loss": 3.6077, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704081204798597e-05, + "loss": 3.6127, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032442479279176e-05, + "loss": 3.6321, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024056531768656e-05, + "loss": 3.617, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015670584258136e-05, + "loss": 3.6343, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007284636747616e-05, + "loss": 3.6152, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998898689237096e-05, + "loss": 3.6041, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990512741726576e-05, + "loss": 3.6301, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982126794216056e-05, + "loss": 3.6151, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973740846705536e-05, + "loss": 3.6009, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696537127799875e-05, + "loss": 3.6185, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956985330488225e-05, + "loss": 3.6163, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948599382977705e-05, + "loss": 3.6102, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940213435467185e-05, + "loss": 3.6126, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.69318438667604e-05, + "loss": 3.6084, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923457919249874e-05, + "loss": 3.6226, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915071971739354e-05, + "loss": 3.6259, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906686024228834e-05, + "loss": 3.6157, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689830007671832e-05, + "loss": 3.6253, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.68899141292078e-05, + "loss": 3.6221, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688152818169728e-05, + "loss": 3.6343, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687315861299049e-05, + "loss": 3.6124, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686477266547997e-05, + "loss": 3.634, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685638671796945e-05, + "loss": 3.6123, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684800077045893e-05, + "loss": 3.6105, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683961482294841e-05, + "loss": 3.6266, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683122887543789e-05, + "loss": 3.6179, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682284292792737e-05, + "loss": 3.6262, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681447335922058e-05, + "loss": 3.6288, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680608741171006e-05, + "loss": 3.6078, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679770146419954e-05, + "loss": 3.6033, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678931551668902e-05, + "loss": 3.6118, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780945947982234e-05, + "loss": 3.6282, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772560000471714e-05, + "loss": 3.6113, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764174052961194e-05, + "loss": 3.6165, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755788105450674e-05, + "loss": 3.6189, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747402157940154e-05, + "loss": 3.6064, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739016210429634e-05, + "loss": 3.6171, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730630262919114e-05, + "loss": 3.611, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672224431540859e-05, + "loss": 3.6206, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.67138747467018e-05, + "loss": 3.6218, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670550517799501e-05, + "loss": 3.6286, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669711923048449e-05, + "loss": 3.6109, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668873328297397e-05, + "loss": 3.6179, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668034733546345e-05, + "loss": 3.6126, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667196138795294e-05, + "loss": 3.6195, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666359181924615e-05, + "loss": 3.623, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665520587173563e-05, + "loss": 3.6144, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664681992422511e-05, + "loss": 3.6142, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663843397671459e-05, + "loss": 3.6059, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663004802920406e-05, + "loss": 3.6145, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662167846049728e-05, + "loss": 3.6097, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661329251298676e-05, + "loss": 3.5943, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660490656547623e-05, + "loss": 3.6169, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659652061796571e-05, + "loss": 3.6188, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658813467045519e-05, + "loss": 3.612, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579748722944676e-05, + "loss": 3.6075, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571362775434156e-05, + "loss": 3.6147, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562976827923636e-05, + "loss": 3.6153, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6554607259216845e-05, + "loss": 3.6019, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654623769051006e-05, + "loss": 3.6303, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537851742999535e-05, + "loss": 3.6194, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6529465795489015e-05, + "loss": 3.6116, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6521079847978494e-05, + "loss": 3.6194, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512693900467974e-05, + "loss": 3.6056, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6504324331761184e-05, + "loss": 3.6191, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495938384250663e-05, + "loss": 3.6127, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487552436740143e-05, + "loss": 3.6084, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647916648922963e-05, + "loss": 3.6103, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647078054171911e-05, + "loss": 3.6146, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646239459420859e-05, + "loss": 3.6147, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645400864669807e-05, + "loss": 3.6065, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644562269918755e-05, + "loss": 3.6099, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643725313048076e-05, + "loss": 3.6077, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642886718297024e-05, + "loss": 3.6078, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642049761426345e-05, + "loss": 3.6237, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641211166675293e-05, + "loss": 3.6116, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640372571924241e-05, + "loss": 3.621, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639533977173189e-05, + "loss": 3.5929, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638695382422137e-05, + "loss": 3.627, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637856787671085e-05, + "loss": 3.616, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637018192920033e-05, + "loss": 3.6164, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361795981689815e-05, + "loss": 3.6119, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6353426412983024e-05, + "loss": 3.6064, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6345040465472504e-05, + "loss": 3.6148, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336654517961984e-05, + "loss": 3.6319, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6328268570451464e-05, + "loss": 3.6021, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319882622940944e-05, + "loss": 3.6154, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631149667543042e-05, + "loss": 3.606, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.63031107279199e-05, + "loss": 3.6118, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629474115921311e-05, + "loss": 3.61, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628635521170259e-05, + "loss": 3.614, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277969264192066e-05, + "loss": 3.6136, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626958331668155e-05, + "loss": 3.6157, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626119736917103e-05, + "loss": 3.6099, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.844151020050049, + "eval_runtime": 303.9418, + "eval_samples_per_second": 1255.474, + "eval_steps_per_second": 39.234, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625282780046425e-05, + "loss": 3.6039, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624444185295372e-05, + "loss": 3.6042, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.62360559054432e-05, + "loss": 3.6166, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622766995793268e-05, + "loss": 3.6133, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621930038922589e-05, + "loss": 3.6191, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621091444171537e-05, + "loss": 3.6087, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620252849420485e-05, + "loss": 3.6054, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619414254669433e-05, + "loss": 3.6109, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618575659918381e-05, + "loss": 3.6053, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617737065167329e-05, + "loss": 3.6145, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169001082966506e-05, + "loss": 3.615, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160615135455986e-05, + "loss": 3.6186, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152245566749195e-05, + "loss": 3.6175, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143859619238675e-05, + "loss": 3.5957, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135473671728155e-05, + "loss": 3.6149, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127087724217635e-05, + "loss": 3.594, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118701776707115e-05, + "loss": 3.6017, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110315829196595e-05, + "loss": 3.6039, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101929881686075e-05, + "loss": 3.6014, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093543934175555e-05, + "loss": 3.6089, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085157986665035e-05, + "loss": 3.6207, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076772039154515e-05, + "loss": 3.6106, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068402470447724e-05, + "loss": 3.606, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060016522937204e-05, + "loss": 3.6037, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051630575426684e-05, + "loss": 3.6057, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604324462791617e-05, + "loss": 3.6002, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603485868040565e-05, + "loss": 3.5973, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602647273289513e-05, + "loss": 3.6139, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601810316418834e-05, + "loss": 3.599, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600971721667782e-05, + "loss": 3.6038, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60013312691673e-05, + "loss": 3.5991, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599296170046051e-05, + "loss": 3.6121, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598457575294999e-05, + "loss": 3.6024, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597618980543947e-05, + "loss": 3.6046, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596780385792895e-05, + "loss": 3.606, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595941791041843e-05, + "loss": 3.6002, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595103196290791e-05, + "loss": 3.6108, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594264601539739e-05, + "loss": 3.5918, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593426006788687e-05, + "loss": 3.5917, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925890499180084e-05, + "loss": 3.5951, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591750455166956e-05, + "loss": 3.6037, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590911860415904e-05, + "loss": 3.5995, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590073265664852e-05, + "loss": 3.6011, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892346709138e-05, + "loss": 3.6031, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588396076162748e-05, + "loss": 3.6024, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587557481411696e-05, + "loss": 3.6036, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586718886660644e-05, + "loss": 3.6116, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858819297899646e-05, + "loss": 3.5998, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850433350389126e-05, + "loss": 3.5794, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842047402878606e-05, + "loss": 3.6158, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583366145536809e-05, + "loss": 3.6001, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.58252918866613e-05, + "loss": 3.6004, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581692231795451e-05, + "loss": 3.5994, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580853637044399e-05, + "loss": 3.5956, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580015042293347e-05, + "loss": 3.5874, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579176447542295e-05, + "loss": 3.5927, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578339490671616e-05, + "loss": 3.6152, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577500895920564e-05, + "loss": 3.5974, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576662301169512e-05, + "loss": 3.614, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57582370641846e-05, + "loss": 3.5967, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574985111667408e-05, + "loss": 3.5815, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741481547967296e-05, + "loss": 3.6108, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733095600456775e-05, + "loss": 3.5945, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724709652946255e-05, + "loss": 3.5823, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716323705435735e-05, + "loss": 3.5968, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707937757925215e-05, + "loss": 3.5939, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699551810414695e-05, + "loss": 3.5895, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691165862904175e-05, + "loss": 3.5952, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5682796294197384e-05, + "loss": 3.5897, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674410346686864e-05, + "loss": 3.5975, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666024399176344e-05, + "loss": 3.6046, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657638451665824e-05, + "loss": 3.5968, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649252504155304e-05, + "loss": 3.6038, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640866556644784e-05, + "loss": 3.6024, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632480609134264e-05, + "loss": 3.6152, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624094661623744e-05, + "loss": 3.5927, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561574147172069e-05, + "loss": 3.6128, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560735552421017e-05, + "loss": 3.5921, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559896957669965e-05, + "loss": 3.5913, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559058362918913e-05, + "loss": 3.6019, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558219768167861e-05, + "loss": 3.5986, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557381173416809e-05, + "loss": 3.6048, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556542578665756e-05, + "loss": 3.6097, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555703983914704e-05, + "loss": 3.5915, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554868664924399e-05, + "loss": 3.5826, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554030070173347e-05, + "loss": 3.5901, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553191475422295e-05, + "loss": 3.6094, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523528806712434e-05, + "loss": 3.5896, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515142859201914e-05, + "loss": 3.5996, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550677329049512e-05, + "loss": 3.5988, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.54983873429846e-05, + "loss": 3.5852, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549000139547408e-05, + "loss": 3.5956, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548161544796356e-05, + "loss": 3.5927, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473229500453036e-05, + "loss": 3.5981, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546485993174625e-05, + "loss": 3.6065, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545647398423573e-05, + "loss": 3.6074, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544808803672521e-05, + "loss": 3.5925, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439702089214685e-05, + "loss": 3.5958, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543131614170417e-05, + "loss": 3.5912, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542293019419365e-05, + "loss": 3.6001, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541456062548686e-05, + "loss": 3.5996, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540617467797634e-05, + "loss": 3.5934, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539778873046582e-05, + "loss": 3.5947, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.53894027829553e-05, + "loss": 3.5854, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538103321424851e-05, + "loss": 3.5965, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537264726673799e-05, + "loss": 3.5908, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536426131922747e-05, + "loss": 3.5764, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535587537171695e-05, + "loss": 3.5978, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534750580301016e-05, + "loss": 3.5971, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533911985549964e-05, + "loss": 3.5923, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330733907989125e-05, + "loss": 3.5878, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322347960478605e-05, + "loss": 3.5961, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313978391771814e-05, + "loss": 3.5955, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305592444261294e-05, + "loss": 3.5831, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297206496750774e-05, + "loss": 3.6064, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288820549240254e-05, + "loss": 3.5986, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280434601729734e-05, + "loss": 3.5934, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527206503302294e-05, + "loss": 3.5998, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526367908551242e-05, + "loss": 3.5882, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52552931380019e-05, + "loss": 3.5973, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524692356929511e-05, + "loss": 3.5963, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523853762178459e-05, + "loss": 3.5902, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523015167427408e-05, + "loss": 3.5903, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522176572676356e-05, + "loss": 3.595, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521337977925304e-05, + "loss": 3.5952, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520499383174252e-05, + "loss": 3.5861, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196607884232e-05, + "loss": 3.5878, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518823831552521e-05, + "loss": 3.5908, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517985236801469e-05, + "loss": 3.5863, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517146642050417e-05, + "loss": 3.6055, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516308047299365e-05, + "loss": 3.5922, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515469452548313e-05, + "loss": 3.6047, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514630857797261e-05, + "loss": 3.5713, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513792263046209e-05, + "loss": 3.6065, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512953668295157e-05, + "loss": 3.5913, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121167114244776e-05, + "loss": 3.6021, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511278116673426e-05, + "loss": 3.5934, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510439521922374e-05, + "loss": 3.5822, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509600927171322e-05, + "loss": 3.5974, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508763970300643e-05, + "loss": 3.6157, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507925375549591e-05, + "loss": 3.5787, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507086780798539e-05, + "loss": 3.5957, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506248186047487e-05, + "loss": 3.5891, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505411229176808e-05, + "loss": 3.5909, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504574272306129e-05, + "loss": 3.5902, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503735677555077e-05, + "loss": 3.5946, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.5883, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502058488052973e-05, + "loss": 3.5954, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501219893301922e-05, + "loss": 3.5921, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.842529535293579, + "eval_runtime": 305.9765, + "eval_samples_per_second": 1247.125, + "eval_steps_per_second": 38.974, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.50038129855087e-05, + "loss": 3.5917, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499542703799817e-05, + "loss": 3.5793, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498704109048765e-05, + "loss": 3.5976, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497865514297713e-05, + "loss": 3.5976, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497026919546661e-05, + "loss": 3.5961, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496189962675982e-05, + "loss": 3.5914, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.49535136792493e-05, + "loss": 3.5947, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494512773173878e-05, + "loss": 3.5897, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493674178422826e-05, + "loss": 3.5873, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492835583671774e-05, + "loss": 3.5934, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491996988920722e-05, + "loss": 3.6008, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911600320500435e-05, + "loss": 3.5957, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903230751793644e-05, + "loss": 3.5994, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894844804283124e-05, + "loss": 3.5776, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886458856772604e-05, + "loss": 3.595, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878072909262084e-05, + "loss": 3.5758, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869686961751564e-05, + "loss": 3.584, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861301014241043e-05, + "loss": 3.5803, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852915066730523e-05, + "loss": 3.5811, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844529119220003e-05, + "loss": 3.5868, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483614317170948e-05, + "loss": 3.6011, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482775722419896e-05, + "loss": 3.5929, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481937127668844e-05, + "loss": 3.5884, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481100170798165e-05, + "loss": 3.5859, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480261576047113e-05, + "loss": 3.5897, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479422981296062e-05, + "loss": 3.5813, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47858438654501e-05, + "loss": 3.575, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477747429674331e-05, + "loss": 3.5933, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476908834923279e-05, + "loss": 3.5789, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476070240172227e-05, + "loss": 3.5845, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475231645421175e-05, + "loss": 3.585, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474394688550496e-05, + "loss": 3.592, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473556093799444e-05, + "loss": 3.5825, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472717499048392e-05, + "loss": 3.5875, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47187890429734e-05, + "loss": 3.5868, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471040309546288e-05, + "loss": 3.5811, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470201714795236e-05, + "loss": 3.5948, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469363120044184e-05, + "loss": 3.5695, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468524525293132e-05, + "loss": 3.5788, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467687568422453e-05, + "loss": 3.5757, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668489736714006e-05, + "loss": 3.5816, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660103789203486e-05, + "loss": 3.5807, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651717841692966e-05, + "loss": 3.5856, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643331894182446e-05, + "loss": 3.587, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634962325475655e-05, + "loss": 3.5814, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626576377965135e-05, + "loss": 3.5827, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618190430454615e-05, + "loss": 3.5936, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609804482944095e-05, + "loss": 3.5802, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601418535433575e-05, + "loss": 3.5607, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459304896672679e-05, + "loss": 3.5962, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458466301921627e-05, + "loss": 3.5837, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457627707170575e-05, + "loss": 3.5787, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456789112419523e-05, + "loss": 3.5839, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455950517668471e-05, + "loss": 3.577, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455113560797792e-05, + "loss": 3.5718, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.45427496604674e-05, + "loss": 3.571, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453436371295688e-05, + "loss": 3.5964, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452597776544636e-05, + "loss": 3.5785, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451759181793584e-05, + "loss": 3.6004, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450920587042532e-05, + "loss": 3.5812, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.45008199229148e-05, + "loss": 3.5594, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449245035420801e-05, + "loss": 3.5914, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484064406697495e-05, + "loss": 3.576, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475678459186975e-05, + "loss": 3.5662, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467292511676455e-05, + "loss": 3.5751, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458906564165935e-05, + "loss": 3.5771, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450520616655415e-05, + "loss": 3.571, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442151047948624e-05, + "loss": 3.5802, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433765100438104e-05, + "loss": 3.5672, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425379152927584e-05, + "loss": 3.5816, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4416993205417064e-05, + "loss": 3.585, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440862363671027e-05, + "loss": 3.5789, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440023768919975e-05, + "loss": 3.5854, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439185174168923e-05, + "loss": 3.5827, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438346579417871e-05, + "loss": 3.5966, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437507984666819e-05, + "loss": 3.5762, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436671027796141e-05, + "loss": 3.5901, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435832433045089e-05, + "loss": 3.579, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434993838294037e-05, + "loss": 3.5724, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434155243542984e-05, + "loss": 3.5884, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433316648791932e-05, + "loss": 3.5746, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43247805404088e-05, + "loss": 3.5869, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431639459289828e-05, + "loss": 3.5911, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430800864538776e-05, + "loss": 3.577, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299655455484706e-05, + "loss": 3.5602, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291269507974186e-05, + "loss": 3.5723, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282883560463666e-05, + "loss": 3.5874, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4274497612953146e-05, + "loss": 3.5738, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266111665442626e-05, + "loss": 3.579, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257725717932106e-05, + "loss": 3.5816, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249356149225315e-05, + "loss": 3.5674, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4240970201714795e-05, + "loss": 3.5796, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232584254204275e-05, + "loss": 3.5727, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224198306693755e-05, + "loss": 3.5834, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215828737986964e-05, + "loss": 3.5852, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207442790476444e-05, + "loss": 3.5879, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199056842965924e-05, + "loss": 3.5737, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190670895455404e-05, + "loss": 3.5775, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182284947944884e-05, + "loss": 3.5794, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.41739153792381e-05, + "loss": 3.5792, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416552943172758e-05, + "loss": 3.5839, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415714348421706e-05, + "loss": 3.5752, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414875753670654e-05, + "loss": 3.5743, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414038796799975e-05, + "loss": 3.5701, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413200202048923e-05, + "loss": 3.5778, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412361607297871e-05, + "loss": 3.5726, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411523012546819e-05, + "loss": 3.5604, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.41068605567614e-05, + "loss": 3.5755, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409847460925088e-05, + "loss": 3.5822, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409008866174036e-05, + "loss": 3.5689, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408170271422984e-05, + "loss": 3.5735, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407331676671932e-05, + "loss": 3.5715, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4064930819208804e-05, + "loss": 3.5813, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056544871698284e-05, + "loss": 3.5703, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048158924187764e-05, + "loss": 3.5823, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039789355480973e-05, + "loss": 3.5788, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031403407970453e-05, + "loss": 3.5826, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402301746045993e-05, + "loss": 3.5802, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401463151294941e-05, + "loss": 3.5708, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400626194424262e-05, + "loss": 3.5781, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.39978759967321e-05, + "loss": 3.5786, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398949004922158e-05, + "loss": 3.5737, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398110410171106e-05, + "loss": 3.5716, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397273453300427e-05, + "loss": 3.573, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396434858549376e-05, + "loss": 3.5789, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395596263798324e-05, + "loss": 3.5692, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394757669047272e-05, + "loss": 3.5716, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.39391907429622e-05, + "loss": 3.568, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393082117425541e-05, + "loss": 3.569, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392243522674489e-05, + "loss": 3.5858, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391404927923437e-05, + "loss": 3.5743, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390566333172385e-05, + "loss": 3.5885, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389727738421332e-05, + "loss": 3.5596, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.38888914367028e-05, + "loss": 3.5823, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880521867996016e-05, + "loss": 3.5804, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872135920485496e-05, + "loss": 3.5806, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863749972974976e-05, + "loss": 3.5769, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855364025464456e-05, + "loss": 3.5641, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846978077953936e-05, + "loss": 3.5783, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838592130443416e-05, + "loss": 3.5939, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830206182932896e-05, + "loss": 3.5635, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3821820235422376e-05, + "loss": 3.5758, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813450666715585e-05, + "loss": 3.5748, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805081098008794e-05, + "loss": 3.5734, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379671152930201e-05, + "loss": 3.5758, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378832558179149e-05, + "loss": 3.5764, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377993963428097e-05, + "loss": 3.5712, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377155368677045e-05, + "loss": 3.5783, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376316773925993e-05, + "loss": 3.5727, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.843351364135742, + "eval_runtime": 303.3513, + "eval_samples_per_second": 1257.918, + "eval_steps_per_second": 39.311, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375478179174941e-05, + "loss": 3.5703, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374639584423889e-05, + "loss": 3.5628, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373800989672837e-05, + "loss": 3.5793, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372962394921785e-05, + "loss": 3.5833, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372125438051106e-05, + "loss": 3.5731, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371286843300054e-05, + "loss": 3.5745, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370448248549002e-05, + "loss": 3.5738, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.36960965379795e-05, + "loss": 3.5732, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368772696927271e-05, + "loss": 3.5648, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367934102176219e-05, + "loss": 3.5796, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367095507425167e-05, + "loss": 3.5805, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366256912674115e-05, + "loss": 3.5786, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365421593683809e-05, + "loss": 3.5858, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364582998932757e-05, + "loss": 3.5573, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363744404181705e-05, + "loss": 3.572, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362905809430653e-05, + "loss": 3.5609, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362067214679601e-05, + "loss": 3.5712, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361228619928549e-05, + "loss": 3.5652, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360390025177497e-05, + "loss": 3.564, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359551430426445e-05, + "loss": 3.564, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358712835675393e-05, + "loss": 3.5884, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357875878804714e-05, + "loss": 3.576, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357037284053662e-05, + "loss": 3.5687, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.35619868930261e-05, + "loss": 3.5691, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355360094551558e-05, + "loss": 3.5754, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.35452313768088e-05, + "loss": 3.5603, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353684542929828e-05, + "loss": 3.5576, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352845948178776e-05, + "loss": 3.5761, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352007353427724e-05, + "loss": 3.5637, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351168758676672e-05, + "loss": 3.5619, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503318018059926e-05, + "loss": 3.569, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3494948449353135e-05, + "loss": 3.5712, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486562501842615e-05, + "loss": 3.5675, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478176554332095e-05, + "loss": 3.5713, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469790606821575e-05, + "loss": 3.5668, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461404659311055e-05, + "loss": 3.571, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453018711800535e-05, + "loss": 3.575, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344463276429002e-05, + "loss": 3.5501, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.34362468167795e-05, + "loss": 3.5603, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342787724807271e-05, + "loss": 3.5596, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341949130056219e-05, + "loss": 3.5642, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341110535305167e-05, + "loss": 3.5645, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340271940554115e-05, + "loss": 3.57, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339434983683436e-05, + "loss": 3.5642, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338596388932384e-05, + "loss": 3.5665, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337757794181332e-05, + "loss": 3.565, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33691919943028e-05, + "loss": 3.5732, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336080604679228e-05, + "loss": 3.567, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335242009928176e-05, + "loss": 3.5445, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344050530574975e-05, + "loss": 3.5779, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335664583064455e-05, + "loss": 3.5679, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332727863555393e-05, + "loss": 3.565, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331889268804341e-05, + "loss": 3.5635, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331050674053289e-05, + "loss": 3.5591, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302137171826104e-05, + "loss": 3.5544, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329375122431558e-05, + "loss": 3.5558, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328536527680506e-05, + "loss": 3.5753, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327697932929454e-05, + "loss": 3.5571, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268609760587746e-05, + "loss": 3.5821, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260223813077226e-05, + "loss": 3.5681, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325183786556671e-05, + "loss": 3.5455, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324345191805619e-05, + "loss": 3.5704, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.32350823493494e-05, + "loss": 3.557, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322669640183888e-05, + "loss": 3.5492, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321831045432836e-05, + "loss": 3.5558, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320992450681784e-05, + "loss": 3.56, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320155493811105e-05, + "loss": 3.5598, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319316899060053e-05, + "loss": 3.5612, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318478304309001e-05, + "loss": 3.5495, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317639709557949e-05, + "loss": 3.5645, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316801114806897e-05, + "loss": 3.5696, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315964157936218e-05, + "loss": 3.5633, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151255631851666e-05, + "loss": 3.5661, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3142869684341146e-05, + "loss": 3.5659, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134483736830626e-05, + "loss": 3.5765, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126097789320106e-05, + "loss": 3.5567, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3117728220613315e-05, + "loss": 3.5713, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109342273102795e-05, + "loss": 3.5665, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3100956325592275e-05, + "loss": 3.5559, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092570378081755e-05, + "loss": 3.5696, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084200809374964e-05, + "loss": 3.5591, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3075814861864444e-05, + "loss": 3.5697, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067428914353924e-05, + "loss": 3.5734, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059042966843404e-05, + "loss": 3.5628, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305067339813662e-05, + "loss": 3.5455, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.30422874506261e-05, + "loss": 3.5543, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303390150311558e-05, + "loss": 3.5662, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302551555560506e-05, + "loss": 3.5612, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301712960809454e-05, + "loss": 3.561, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300876003938775e-05, + "loss": 3.5633, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300037409187723e-05, + "loss": 3.5564, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299198814436671e-05, + "loss": 3.5565, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298360219685619e-05, + "loss": 3.5587, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297521624934567e-05, + "loss": 3.5636, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296683030183515e-05, + "loss": 3.5678, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295844435432463e-05, + "loss": 3.5733, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295007478561784e-05, + "loss": 3.5526, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294168883810732e-05, + "loss": 3.5593, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.29333028905968e-05, + "loss": 3.565, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2924916943086285e-05, + "loss": 3.5609, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916530995575764e-05, + "loss": 3.5687, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908161426868974e-05, + "loss": 3.5597, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2899775479358454e-05, + "loss": 3.5569, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891389531847933e-05, + "loss": 3.5549, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883003584337413e-05, + "loss": 3.5644, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874617636826887e-05, + "loss": 3.5564, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.28662480681201e-05, + "loss": 3.5392, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285786212060958e-05, + "loss": 3.5617, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2849476173099056e-05, + "loss": 3.5654, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841090225588536e-05, + "loss": 3.5557, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283272065688175e-05, + "loss": 3.5544, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282433470937124e-05, + "loss": 3.5537, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281594876186071e-05, + "loss": 3.5633, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280756281435019e-05, + "loss": 3.5552, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279919324564341e-05, + "loss": 3.5608, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279080729813289e-05, + "loss": 3.5673, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278242135062236e-05, + "loss": 3.5641, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277403540311184e-05, + "loss": 3.5625, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276564945560132e-05, + "loss": 3.5557, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.27572635080908e-05, + "loss": 3.5607, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274889393938401e-05, + "loss": 3.5597, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274050799187349e-05, + "loss": 3.5538, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732122044362976e-05, + "loss": 3.5589, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723736096852456e-05, + "loss": 3.5555, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715366528145665e-05, + "loss": 3.5609, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2706980580635145e-05, + "loss": 3.5522, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698594633124625e-05, + "loss": 3.556, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690208685614105e-05, + "loss": 3.5505, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2681822738103585e-05, + "loss": 3.5537, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673453169396794e-05, + "loss": 3.5703, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665067221886274e-05, + "loss": 3.5573, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656681274375754e-05, + "loss": 3.5702, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648295326865234e-05, + "loss": 3.541, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2639909379354714e-05, + "loss": 3.5639, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263153981064793e-05, + "loss": 3.5667, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262315386313741e-05, + "loss": 3.562, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261476791562689e-05, + "loss": 3.5591, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260638196811637e-05, + "loss": 3.5471, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259801239940958e-05, + "loss": 3.5659, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258962645189906e-05, + "loss": 3.5766, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258124050438854e-05, + "loss": 3.5503, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257285455687802e-05, + "loss": 3.5545, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.25644686093675e-05, + "loss": 3.5618, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255609904066071e-05, + "loss": 3.5558, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.2547729471953917e-05, + "loss": 3.5563, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539343524443397e-05, + "loss": 3.5614, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253095757693288e-05, + "loss": 3.5509, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252257162942236e-05, + "loss": 3.565, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251418568191184e-05, + "loss": 3.5518, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8435354232788086, + "eval_runtime": 306.0375, + "eval_samples_per_second": 1246.877, + "eval_steps_per_second": 38.966, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250579973440132e-05, + "loss": 3.5528, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.24974137868908e-05, + "loss": 3.5489, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248902783938028e-05, + "loss": 3.5617, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248064189186976e-05, + "loss": 3.5677, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247227232316297e-05, + "loss": 3.56, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246388637565245e-05, + "loss": 3.5576, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245550042814193e-05, + "loss": 3.5554, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244711448063141e-05, + "loss": 3.5554, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243874491192462e-05, + "loss": 3.5475, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.24303589644141e-05, + "loss": 3.5681, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242197301690358e-05, + "loss": 3.5614, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241358706939306e-05, + "loss": 3.5621, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405233879490006e-05, + "loss": 3.5719, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2396847931979486e-05, + "loss": 3.5397, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388461984468966e-05, + "loss": 3.5584, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380076036958446e-05, + "loss": 3.5443, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2371690089447926e-05, + "loss": 3.554, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363304141937406e-05, + "loss": 3.5428, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2354918194426886e-05, + "loss": 3.5526, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346532246916366e-05, + "loss": 3.5446, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338162678209575e-05, + "loss": 3.5712, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329776730699055e-05, + "loss": 3.559, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321390783188535e-05, + "loss": 3.5529, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313004835678015e-05, + "loss": 3.5523, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304618888167495e-05, + "loss": 3.5628, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229624931946071e-05, + "loss": 3.5432, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228786337195019e-05, + "loss": 3.542, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2279477424439664e-05, + "loss": 3.5604, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271091476929144e-05, + "loss": 3.5478, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2262705529418623e-05, + "loss": 3.5465, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225433596071184e-05, + "loss": 3.5527, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224596639200505e-05, + "loss": 3.5538, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223758044449453e-05, + "loss": 3.5554, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222919449698401e-05, + "loss": 3.551, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222080854947349e-05, + "loss": 3.5467, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221242260196297e-05, + "loss": 3.5602, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220403665445245e-05, + "loss": 3.5562, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219565070694193e-05, + "loss": 3.5345, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218726475943141e-05, + "loss": 3.5454, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217887881192089e-05, + "loss": 3.5424, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.21705092432141e-05, + "loss": 3.5448, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216212329570358e-05, + "loss": 3.5499, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215373734819306e-05, + "loss": 3.5554, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214535140068254e-05, + "loss": 3.5458, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2136981831975746e-05, + "loss": 3.5479, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128595884465226e-05, + "loss": 3.555, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120209936954706e-05, + "loss": 3.5534, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211182398944419e-05, + "loss": 3.5524, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210343804193367e-05, + "loss": 3.5288, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209506847322688e-05, + "loss": 3.5581, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208668252571636e-05, + "loss": 3.5554, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207829657820584e-05, + "loss": 3.5468, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206991063069532e-05, + "loss": 3.5473, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.20615246831848e-05, + "loss": 3.5476, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205315511447801e-05, + "loss": 3.5315, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204476916696749e-05, + "loss": 3.5419, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203638321945697e-05, + "loss": 3.5599, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202799727194645e-05, + "loss": 3.5461, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201961132443593e-05, + "loss": 3.5636, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201122537692541e-05, + "loss": 3.5518, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200283942941489e-05, + "loss": 3.5303, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994469860708106e-05, + "loss": 3.5561, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986083913197586e-05, + "loss": 3.5385, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977697965687066e-05, + "loss": 3.5357, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969312018176546e-05, + "loss": 3.5383, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1960942449469755e-05, + "loss": 3.5476, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952556501959235e-05, + "loss": 3.5405, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944170554448715e-05, + "loss": 3.5398, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1935784606938195e-05, + "loss": 3.5337, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927398659427675e-05, + "loss": 3.5512, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919029090720884e-05, + "loss": 3.5533, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910643143210364e-05, + "loss": 3.55, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902257195699844e-05, + "loss": 3.5491, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1893871248189324e-05, + "loss": 3.5532, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885485300678804e-05, + "loss": 3.5574, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187711573197202e-05, + "loss": 3.5489, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.18687297844615e-05, + "loss": 3.5484, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186034383695097e-05, + "loss": 3.5487, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185195788944045e-05, + "loss": 3.5431, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184357194192993e-05, + "loss": 3.5503, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183520237322315e-05, + "loss": 3.5455, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182681642571262e-05, + "loss": 3.5528, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.18184304782021e-05, + "loss": 3.5614, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181004453069158e-05, + "loss": 3.5459, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.18016749619848e-05, + "loss": 3.5281, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179328901447428e-05, + "loss": 3.5401, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178490306696376e-05, + "loss": 3.5485, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177651711945324e-05, + "loss": 3.5429, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176814755074645e-05, + "loss": 3.5457, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175976160323593e-05, + "loss": 3.5512, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175137565572541e-05, + "loss": 3.5356, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174298970821489e-05, + "loss": 3.5408, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1734620139508096e-05, + "loss": 3.5425, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1726234191997576e-05, + "loss": 3.5495, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1717848244487056e-05, + "loss": 3.5495, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1709462296976536e-05, + "loss": 3.5617, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170109272826975e-05, + "loss": 3.5349, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169270678075923e-05, + "loss": 3.5443, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168432083324871e-05, + "loss": 3.5493, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167593488573819e-05, + "loss": 3.5455, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166754893822767e-05, + "loss": 3.5556, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165917936952088e-05, + "loss": 3.5391, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165079342201036e-05, + "loss": 3.54, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164240747449984e-05, + "loss": 3.5388, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163402152698932e-05, + "loss": 3.5493, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.16256355794788e-05, + "loss": 3.5372, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161726601077201e-05, + "loss": 3.53, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160888006326149e-05, + "loss": 3.5427, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160049411575097e-05, + "loss": 3.5455, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592108168240456e-05, + "loss": 3.5404, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1583738599533665e-05, + "loss": 3.5453, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575352652023145e-05, + "loss": 3.5327, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1566966704512625e-05, + "loss": 3.5506, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1558580757002105e-05, + "loss": 3.5393, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550211188295314e-05, + "loss": 3.544, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1541825240784794e-05, + "loss": 3.5516, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1533439293274274e-05, + "loss": 3.5532, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525053345763754e-05, + "loss": 3.5432, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516667398253234e-05, + "loss": 3.5385, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508281450742714e-05, + "loss": 3.5472, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149991188203592e-05, + "loss": 3.5431, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149152593452541e-05, + "loss": 3.5362, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148313998701489e-05, + "loss": 3.5464, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147475403950437e-05, + "loss": 3.5397, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146638447079758e-05, + "loss": 3.5421, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145799852328706e-05, + "loss": 3.5367, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144961257577654e-05, + "loss": 3.5425, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144122662826602e-05, + "loss": 3.5373, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143285705955923e-05, + "loss": 3.5366, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142447111204871e-05, + "loss": 3.5537, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141608516453819e-05, + "loss": 3.5455, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140769921702767e-05, + "loss": 3.553, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139931326951715e-05, + "loss": 3.531, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139092732200663e-05, + "loss": 3.5447, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138255775329984e-05, + "loss": 3.5495, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137417180578932e-05, + "loss": 3.5484, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.13657858582788e-05, + "loss": 3.5378, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135739991076828e-05, + "loss": 3.5335, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349013963257756e-05, + "loss": 3.551, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134064439455097e-05, + "loss": 3.5598, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133225844704045e-05, + "loss": 3.5375, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1323872499529925e-05, + "loss": 3.5377, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315486552019405e-05, + "loss": 3.5473, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130711698331262e-05, + "loss": 3.5396, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129874741460583e-05, + "loss": 3.5393, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129036146709532e-05, + "loss": 3.547, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.12819755195848e-05, + "loss": 3.5358, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127358957207428e-05, + "loss": 3.5513, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126520362456376e-05, + "loss": 3.5346, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.845522880554199, + "eval_runtime": 308.1685, + "eval_samples_per_second": 1238.254, + "eval_steps_per_second": 38.696, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125681767705323e-05, + "loss": 3.5359, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124843172954271e-05, + "loss": 3.5356, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124004578203219e-05, + "loss": 3.5456, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.12316762133254e-05, + "loss": 3.5524, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122329026581488e-05, + "loss": 3.5429, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121490431830436e-05, + "loss": 3.545, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120651837079384e-05, + "loss": 3.5421, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119813242328332e-05, + "loss": 3.5373, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1189762854576535e-05, + "loss": 3.5373, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181376907066015e-05, + "loss": 3.5508, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1172990959555495e-05, + "loss": 3.5459, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164605012044975e-05, + "loss": 3.5474, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115625182214192e-05, + "loss": 3.5558, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.11478658746314e-05, + "loss": 3.5267, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113947992712087e-05, + "loss": 3.5419, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113109397961035e-05, + "loss": 3.5295, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112270803209983e-05, + "loss": 3.5423, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111432208458931e-05, + "loss": 3.526, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110593613707879e-05, + "loss": 3.5372, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109755018956827e-05, + "loss": 3.535, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108916424205775e-05, + "loss": 3.5536, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108079467335097e-05, + "loss": 3.5473, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107240872584045e-05, + "loss": 3.5359, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106402277832993e-05, + "loss": 3.5355, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105563683081941e-05, + "loss": 3.5487, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104726726211262e-05, + "loss": 3.5262, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.10388813146021e-05, + "loss": 3.5267, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103049536709158e-05, + "loss": 3.5478, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102210941958106e-05, + "loss": 3.5293, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101372347207054e-05, + "loss": 3.5321, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005353903363746e-05, + "loss": 3.5354, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099698433465696e-05, + "loss": 3.5372, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098859838714644e-05, + "loss": 3.543, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098021243963592e-05, + "loss": 3.5304, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.09718264921254e-05, + "loss": 3.5355, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096344054461488e-05, + "loss": 3.5433, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095505459710436e-05, + "loss": 3.5435, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094666864959384e-05, + "loss": 3.518, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093828270208332e-05, + "loss": 3.5333, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092991313337653e-05, + "loss": 3.5229, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092152718586601e-05, + "loss": 3.531, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091314123835549e-05, + "loss": 3.5361, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090475529084497e-05, + "loss": 3.5415, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089636934333445e-05, + "loss": 3.5316, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088799977462766e-05, + "loss": 3.5327, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087961382711714e-05, + "loss": 3.5396, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871227879606627e-05, + "loss": 3.5407, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0862841932096106e-05, + "loss": 3.533, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854472363389316e-05, + "loss": 3.5171, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846086415878796e-05, + "loss": 3.5423, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0837700468368275e-05, + "loss": 3.5418, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0829314520857755e-05, + "loss": 3.5321, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0820944952150965e-05, + "loss": 3.5299, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812559004640444e-05, + "loss": 3.5309, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804173057129924e-05, + "loss": 3.5244, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795787109619404e-05, + "loss": 3.5203, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787417540912614e-05, + "loss": 3.5459, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779031593402093e-05, + "loss": 3.5308, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077064564589158e-05, + "loss": 3.5451, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076225969838106e-05, + "loss": 3.539, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075387375087053e-05, + "loss": 3.5147, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074550418216375e-05, + "loss": 3.5358, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073711823465323e-05, + "loss": 3.5297, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072873228714271e-05, + "loss": 3.524, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072034633963218e-05, + "loss": 3.5175, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.07119767709254e-05, + "loss": 3.5366, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070359082341488e-05, + "loss": 3.5284, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069520487590436e-05, + "loss": 3.5221, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068681892839383e-05, + "loss": 3.5208, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067843298088332e-05, + "loss": 3.5365, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670063412176534e-05, + "loss": 3.5374, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066167746466601e-05, + "loss": 3.5343, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065329151715549e-05, + "loss": 3.5346, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064490556964497e-05, + "loss": 3.5352, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063653600093818e-05, + "loss": 3.5423, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628150053427656e-05, + "loss": 3.5379, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619764105917136e-05, + "loss": 3.5356, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611378158406616e-05, + "loss": 3.5351, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060300858969983e-05, + "loss": 3.5287, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594622642189305e-05, + "loss": 3.5359, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586236694678785e-05, + "loss": 3.5299, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057785074716827e-05, + "loss": 3.5402, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056948117846148e-05, + "loss": 3.5408, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056109523095096e-05, + "loss": 3.5357, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055270928344044e-05, + "loss": 3.5148, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054432333592992e-05, + "loss": 3.5241, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.05359373884194e-05, + "loss": 3.5319, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052755144090888e-05, + "loss": 3.53, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051918187220209e-05, + "loss": 3.5303, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051079592469157e-05, + "loss": 3.5359, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050240997718105e-05, + "loss": 3.5286, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494024029670533e-05, + "loss": 3.5212, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485654460963742e-05, + "loss": 3.5286, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477268513453222e-05, + "loss": 3.5353, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468882565942702e-05, + "loss": 3.5321, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460496618432182e-05, + "loss": 3.544, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452127049725394e-05, + "loss": 3.5243, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443741102214874e-05, + "loss": 3.5308, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435355154704354e-05, + "loss": 3.5342, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0426969207193834e-05, + "loss": 3.5302, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418599638487043e-05, + "loss": 3.5385, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410213690976523e-05, + "loss": 3.5301, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401827743466003e-05, + "loss": 3.5242, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393441795955487e-05, + "loss": 3.5235, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385072227248696e-05, + "loss": 3.5356, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376686279738176e-05, + "loss": 3.5186, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368300332227656e-05, + "loss": 3.5144, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0359914384717136e-05, + "loss": 3.5331, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351544816010348e-05, + "loss": 3.5302, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343158868499828e-05, + "loss": 3.5236, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334772920989308e-05, + "loss": 3.5296, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326386973478788e-05, + "loss": 3.52, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318017404771997e-05, + "loss": 3.5372, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309631457261477e-05, + "loss": 3.5208, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301245509750957e-05, + "loss": 3.5291, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029285956224044e-05, + "loss": 3.5357, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028447361472992e-05, + "loss": 3.5402, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027610404602313e-05, + "loss": 3.528, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026771809851261e-05, + "loss": 3.5238, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025933215100209e-05, + "loss": 3.5333, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.025094620349157e-05, + "loss": 3.5298, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024257663478478e-05, + "loss": 3.5203, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023419068727426e-05, + "loss": 3.531, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022580473976374e-05, + "loss": 3.5262, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021741879225322e-05, + "loss": 3.5287, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020904922354643e-05, + "loss": 3.5247, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020066327603591e-05, + "loss": 3.5241, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192277328525394e-05, + "loss": 3.5281, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0183891381014874e-05, + "loss": 3.5208, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175521812308083e-05, + "loss": 3.5312, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167135864797563e-05, + "loss": 3.5369, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158749917287043e-05, + "loss": 3.5361, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150363969776523e-05, + "loss": 3.5178, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0141978022266003e-05, + "loss": 3.5313, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133608453559215e-05, + "loss": 3.5357, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125222506048695e-05, + "loss": 3.5328, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0116836558538175e-05, + "loss": 3.5231, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108450611027655e-05, + "loss": 3.5194, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100081042320864e-05, + "loss": 3.5348, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091695094810348e-05, + "loss": 3.5429, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083309147299827e-05, + "loss": 3.5241, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0074923199789307e-05, + "loss": 3.5222, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066537252278787e-05, + "loss": 3.5314, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058167683571997e-05, + "loss": 3.5228, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004979811486521e-05, + "loss": 3.5274, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004141216735469e-05, + "loss": 3.537, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003302621984417e-05, + "loss": 3.5177, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002464027233365e-05, + "loss": 3.5374, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001625432482313e-05, + "loss": 3.5216, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000786837731261e-05, + "loss": 3.5247, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.846574544906616, + "eval_runtime": 313.5179, + "eval_samples_per_second": 1217.126, + "eval_steps_per_second": 38.036, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999482429802085e-05, + "loss": 3.5186, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991096482291565e-05, + "loss": 3.5299, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982710534781045e-05, + "loss": 3.5384, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974324587270525e-05, + "loss": 3.5297, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9965955018563734e-05, + "loss": 3.5309, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957569071053214e-05, + "loss": 3.5268, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949183123542694e-05, + "loss": 3.525, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940797176032178e-05, + "loss": 3.5152, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932427607325387e-05, + "loss": 3.5418, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924041659814867e-05, + "loss": 3.5269, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915655712304347e-05, + "loss": 3.5378, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907286143597556e-05, + "loss": 3.5394, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989890019608704e-05, + "loss": 3.5145, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989051424857652e-05, + "loss": 3.5243, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882128301066e-05, + "loss": 3.5191, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987374235355548e-05, + "loss": 3.5202, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986535640604496e-05, + "loss": 3.5189, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985697045853444e-05, + "loss": 3.5186, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984858451102392e-05, + "loss": 3.5191, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.98401985635134e-05, + "loss": 3.5368, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983182899480661e-05, + "loss": 3.5307, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982344304729609e-05, + "loss": 3.5221, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981505709978557e-05, + "loss": 3.5236, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980667115227505e-05, + "loss": 3.5366, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979830158356826e-05, + "loss": 3.5126, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.978991563605774e-05, + "loss": 3.5125, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978152968854722e-05, + "loss": 3.5289, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773143741036703e-05, + "loss": 3.5189, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764757793526183e-05, + "loss": 3.5172, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756388224819392e-05, + "loss": 3.519, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.97480186561126e-05, + "loss": 3.5237, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973963270860208e-05, + "loss": 3.5259, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731246761091565e-05, + "loss": 3.5165, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722860813581045e-05, + "loss": 3.5214, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714474866070525e-05, + "loss": 3.5304, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706088918560005e-05, + "loss": 3.5269, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697702971049485e-05, + "loss": 3.5073, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689317023538965e-05, + "loss": 3.5189, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9680947454832174e-05, + "loss": 3.507, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672561507321657e-05, + "loss": 3.5201, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664175559811137e-05, + "loss": 3.5179, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655789612300617e-05, + "loss": 3.5284, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647420043593826e-05, + "loss": 3.5171, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639034096083306e-05, + "loss": 3.5222, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630648148572786e-05, + "loss": 3.5199, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622262201062266e-05, + "loss": 3.5269, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961387625355175e-05, + "loss": 3.5185, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960550668484496e-05, + "loss": 3.5047, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959712073733444e-05, + "loss": 3.5251, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588734789823918e-05, + "loss": 3.5309, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580348842313395e-05, + "loss": 3.517, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957197927360661e-05, + "loss": 3.5143, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956359332609609e-05, + "loss": 3.5152, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955520737858557e-05, + "loss": 3.5127, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546821431075044e-05, + "loss": 3.5036, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953845186236826e-05, + "loss": 3.5341, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953006591485774e-05, + "loss": 3.5184, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521679967347216e-05, + "loss": 3.532, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513294019836696e-05, + "loss": 3.5227, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9504908072326176e-05, + "loss": 3.5045, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496538503619392e-05, + "loss": 3.5212, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488152556108865e-05, + "loss": 3.5176, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947976660859835e-05, + "loss": 3.5074, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947138066108783e-05, + "loss": 3.5039, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463011092381044e-05, + "loss": 3.5231, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454625144870518e-05, + "loss": 3.5111, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446239197359997e-05, + "loss": 3.5094, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9437853249849477e-05, + "loss": 3.5038, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429467302338957e-05, + "loss": 3.522, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942109773363217e-05, + "loss": 3.5211, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941271178612165e-05, + "loss": 3.5196, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940432583861113e-05, + "loss": 3.5201, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939593989110061e-05, + "loss": 3.5252, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938757032239382e-05, + "loss": 3.5259, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379184374883302e-05, + "loss": 3.5244, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370798427372782e-05, + "loss": 3.5155, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362412479862262e-05, + "loss": 3.5253, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935404291115547e-05, + "loss": 3.5179, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934565696364495e-05, + "loss": 3.5197, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933727101613443e-05, + "loss": 3.5172, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932888506862391e-05, + "loss": 3.5228, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320515499917124e-05, + "loss": 3.5276, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312129552406604e-05, + "loss": 3.5196, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303743604896083e-05, + "loss": 3.5002, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295357657385563e-05, + "loss": 3.5097, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9286988088678773e-05, + "loss": 3.5221, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278602141168256e-05, + "loss": 3.5175, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270216193657736e-05, + "loss": 3.518, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9261830246147216e-05, + "loss": 3.5176, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253444298636696e-05, + "loss": 3.5161, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245074729929905e-05, + "loss": 3.5084, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236688782419385e-05, + "loss": 3.5148, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228302834908865e-05, + "loss": 3.5191, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9219916887398348e-05, + "loss": 3.5177, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211547318691557e-05, + "loss": 3.5303, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203161371181037e-05, + "loss": 3.5131, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194775423670517e-05, + "loss": 3.5172, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186389476159997e-05, + "loss": 3.5198, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917801990745321e-05, + "loss": 3.5172, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916963395994269e-05, + "loss": 3.5239, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916124801243217e-05, + "loss": 3.5147, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915286206492165e-05, + "loss": 3.5091, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914449249621486e-05, + "loss": 3.5091, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913610654870434e-05, + "loss": 3.5216, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912772060119382e-05, + "loss": 3.5069, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.91193346536833e-05, + "loss": 3.5004, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9110948706172782e-05, + "loss": 3.514, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910257913746599e-05, + "loss": 3.5217, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909419318995547e-05, + "loss": 3.5074, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908580724244495e-05, + "loss": 3.5178, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907742129493443e-05, + "loss": 3.5071, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069051726227643e-05, + "loss": 3.5218, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060665778717123e-05, + "loss": 3.507, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052279831206603e-05, + "loss": 3.5155, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9043893883696083e-05, + "loss": 3.5233, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035524314989292e-05, + "loss": 3.5278, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027138367478772e-05, + "loss": 3.5141, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018752419968252e-05, + "loss": 3.5137, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010366472457735e-05, + "loss": 3.5171, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9001996903750944e-05, + "loss": 3.5174, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993610956240424e-05, + "loss": 3.5069, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985225008729904e-05, + "loss": 3.5131, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8976839061219384e-05, + "loss": 3.5163, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968469492512597e-05, + "loss": 3.5184, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960083545002077e-05, + "loss": 3.5102, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951697597491557e-05, + "loss": 3.5083, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943311649981037e-05, + "loss": 3.5099, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8934942081274246e-05, + "loss": 3.5141, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926556133763726e-05, + "loss": 3.5123, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918170186253206e-05, + "loss": 3.5256, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890978423874269e-05, + "loss": 3.5211, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901414670035898e-05, + "loss": 3.5065, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893028722525378e-05, + "loss": 3.5121, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884642775014858e-05, + "loss": 3.5247, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876256827504338e-05, + "loss": 3.5202, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8867870879993818e-05, + "loss": 3.5122, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885950131128703e-05, + "loss": 3.5064, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885111536377651e-05, + "loss": 3.5235, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884272941626599e-05, + "loss": 3.5249, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883434346875547e-05, + "loss": 3.5136, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882597390004868e-05, + "loss": 3.5112, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881758795253816e-05, + "loss": 3.5138, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809202005027643e-05, + "loss": 3.5136, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800832436320852e-05, + "loss": 3.5103, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792446488810332e-05, + "loss": 3.5225, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784060541299812e-05, + "loss": 3.5112, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877567459378929e-05, + "loss": 3.5193, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767288646278768e-05, + "loss": 3.5094, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8758902698768248e-05, + "loss": 3.5068, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8470776081085205, + "eval_runtime": 302.8388, + "eval_samples_per_second": 1260.047, + "eval_steps_per_second": 39.377, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750516751257728e-05, + "loss": 3.5075, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742130803747208e-05, + "loss": 3.5183, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733744856236688e-05, + "loss": 3.5227, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725375287529897e-05, + "loss": 3.5131, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871698934001938e-05, + "loss": 3.5183, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870860339250886e-05, + "loss": 3.5144, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870021744499834e-05, + "loss": 3.5089, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869184787629155e-05, + "loss": 3.5017, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868346192878103e-05, + "loss": 3.5276, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867507598127051e-05, + "loss": 3.5145, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866669003375999e-05, + "loss": 3.5231, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658304086249473e-05, + "loss": 3.5192, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8649950896346418e-05, + "loss": 3.5084, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864156494883589e-05, + "loss": 3.5058, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863317900132537e-05, + "loss": 3.5096, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862479305381485e-05, + "loss": 3.5018, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616407106304334e-05, + "loss": 3.507, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608021158793814e-05, + "loss": 3.5063, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599635211283294e-05, + "loss": 3.5027, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591249263772774e-05, + "loss": 3.5276, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8582879695065983e-05, + "loss": 3.5159, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574493747555463e-05, + "loss": 3.5096, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566107800044943e-05, + "loss": 3.5078, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557721852534426e-05, + "loss": 3.5245, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549352283827635e-05, + "loss": 3.4967, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8540966336317115e-05, + "loss": 3.4999, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532580388806595e-05, + "loss": 3.5124, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524194441296075e-05, + "loss": 3.508, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8515824872589288e-05, + "loss": 3.5018, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507438925078768e-05, + "loss": 3.5058, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499069356371977e-05, + "loss": 3.5112, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490683408861457e-05, + "loss": 3.5171, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482297461350937e-05, + "loss": 3.5028, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8473911513840417e-05, + "loss": 3.5099, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465525566329897e-05, + "loss": 3.5148, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845713961881938e-05, + "loss": 3.5123, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844875367130886e-05, + "loss": 3.4963, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844036772379834e-05, + "loss": 3.503, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843199815509155e-05, + "loss": 3.4982, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842361220758103e-05, + "loss": 3.5064, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841522626007051e-05, + "loss": 3.5022, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840684031255999e-05, + "loss": 3.5125, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839845436504947e-05, + "loss": 3.5024, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839008479634268e-05, + "loss": 3.5064, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.838169884883216e-05, + "loss": 3.5102, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837331290132164e-05, + "loss": 3.5115, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836492695381112e-05, + "loss": 3.5102, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356557385104334e-05, + "loss": 3.4889, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348171437593814e-05, + "loss": 3.5101, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339785490083294e-05, + "loss": 3.5121, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331399542572774e-05, + "loss": 3.5068, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323029973865983e-05, + "loss": 3.5044, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314644026355463e-05, + "loss": 3.497, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306258078844943e-05, + "loss": 3.5033, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8297872131334423e-05, + "loss": 3.4871, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289502562627635e-05, + "loss": 3.5206, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281116615117115e-05, + "loss": 3.5055, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272730667606595e-05, + "loss": 3.5185, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264344720096075e-05, + "loss": 3.5118, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8255975151389284e-05, + "loss": 3.4896, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247589203878767e-05, + "loss": 3.5077, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239203256368247e-05, + "loss": 3.5065, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8230817308857727e-05, + "loss": 3.4929, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.82224313613472e-05, + "loss": 3.4904, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214061792640416e-05, + "loss": 3.5104, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205675845129896e-05, + "loss": 3.4999, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197289897619373e-05, + "loss": 3.496, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8188903950108853e-05, + "loss": 3.4901, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180518002598333e-05, + "loss": 3.5097, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817214843389155e-05, + "loss": 3.506, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163762486381022e-05, + "loss": 3.5062, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155376538870505e-05, + "loss": 3.5044, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8146990591359985e-05, + "loss": 3.5154, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81386210226532e-05, + "loss": 3.5096, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130235075142674e-05, + "loss": 3.5146, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121849127632154e-05, + "loss": 3.4984, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113463180121634e-05, + "loss": 3.5123, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105093611414847e-05, + "loss": 3.5039, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096707663904326e-05, + "loss": 3.5061, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088321716393806e-05, + "loss": 3.5054, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8079935768883286e-05, + "loss": 3.5055, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071549821372766e-05, + "loss": 3.5152, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063180252665975e-05, + "loss": 3.5078, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805479430515546e-05, + "loss": 3.4877, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804640835764494e-05, + "loss": 3.4957, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803802241013442e-05, + "loss": 3.5056, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.80296364626239e-05, + "loss": 3.5039, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021266893917108e-05, + "loss": 3.5079, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8012880946406588e-05, + "loss": 3.5039, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004494998896068e-05, + "loss": 3.5011, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799610905138555e-05, + "loss": 3.4917, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798773948267876e-05, + "loss": 3.5022, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797935353516824e-05, + "loss": 3.505, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797096758765772e-05, + "loss": 3.5076, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.79625816401472e-05, + "loss": 3.5133, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954212071440412e-05, + "loss": 3.5056, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7945826123929892e-05, + "loss": 3.4986, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937440176419372e-05, + "loss": 3.5085, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929054228908852e-05, + "loss": 3.5041, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792068466020206e-05, + "loss": 3.5088, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791229871269154e-05, + "loss": 3.5011, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790391276518102e-05, + "loss": 3.4964, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895526817670505e-05, + "loss": 3.4972, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887140870159985e-05, + "loss": 3.5102, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7878771301453194e-05, + "loss": 3.4946, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870385353942674e-05, + "loss": 3.4855, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7861999406432154e-05, + "loss": 3.5031, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853613458921634e-05, + "loss": 3.5058, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845243890214846e-05, + "loss": 3.4938, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7836857942704326e-05, + "loss": 3.5048, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828471995193806e-05, + "loss": 3.4947, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820086047683286e-05, + "loss": 3.506, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811716478976495e-05, + "loss": 3.4967, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803330531465975e-05, + "loss": 3.4994, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779494458395546e-05, + "loss": 3.5114, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786558636444938e-05, + "loss": 3.5155, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778189067738147e-05, + "loss": 3.4972, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7769803120227627e-05, + "loss": 3.4981, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761417172717107e-05, + "loss": 3.5064, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753031225206587e-05, + "loss": 3.5036, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.77446616564998e-05, + "loss": 3.4915, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773627570898928e-05, + "loss": 3.5024, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772788976147876e-05, + "loss": 3.4981, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771950381396824e-05, + "loss": 3.5101, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771113424526145e-05, + "loss": 3.494, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770274829775093e-05, + "loss": 3.4955, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694362350240412e-05, + "loss": 3.4967, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7685976402729892e-05, + "loss": 3.5005, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.76776068340231e-05, + "loss": 3.4966, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766922088651258e-05, + "loss": 3.5161, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766083493900206e-05, + "loss": 3.5053, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765244899149154e-05, + "loss": 3.4963, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644079422784753e-05, + "loss": 3.4955, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635693475274233e-05, + "loss": 3.5123, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627307527763713e-05, + "loss": 3.5077, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7618921580253193e-05, + "loss": 3.4981, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610552011546402e-05, + "loss": 3.4936, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602166064035882e-05, + "loss": 3.5105, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7593780116525366e-05, + "loss": 3.5098, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585394169014846e-05, + "loss": 3.5012, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577024600308055e-05, + "loss": 3.4996, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568638652797535e-05, + "loss": 3.5024, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560252705287015e-05, + "loss": 3.4976, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7551883136580227e-05, + "loss": 3.4965, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543497189069707e-05, + "loss": 3.5126, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535111241559187e-05, + "loss": 3.4978, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526725294048667e-05, + "loss": 3.5046, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518339346538147e-05, + "loss": 3.496, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7509953399027627e-05, + "loss": 3.4938, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.84928035736084, + "eval_runtime": 302.9274, + "eval_samples_per_second": 1259.678, + "eval_steps_per_second": 39.366, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501567451517103e-05, + "loss": 3.4907, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493181504006583e-05, + "loss": 3.5018, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7484795556496063e-05, + "loss": 3.5126, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476409608985543e-05, + "loss": 3.5013, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468040040278752e-05, + "loss": 3.5057, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459654092768232e-05, + "loss": 3.4988, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451268145257712e-05, + "loss": 3.5, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7442882197747192e-05, + "loss": 3.4875, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434512629040405e-05, + "loss": 3.5113, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426126681529885e-05, + "loss": 3.5065, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417740734019365e-05, + "loss": 3.5027, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409354786508845e-05, + "loss": 3.5086, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7400985217802054e-05, + "loss": 3.4971, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392599270291537e-05, + "loss": 3.4932, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384213322781017e-05, + "loss": 3.5028, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7375827375270497e-05, + "loss": 3.4848, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367441427759977e-05, + "loss": 3.4932, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359055480249457e-05, + "loss": 3.4925, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350669532738937e-05, + "loss": 3.4907, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342283585228417e-05, + "loss": 3.5155, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733391401652163e-05, + "loss": 3.5008, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732552806901111e-05, + "loss": 3.5013, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731714212150059e-05, + "loss": 3.4921, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730875617399007e-05, + "loss": 3.5084, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300386605283278e-05, + "loss": 3.4814, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292000657772758e-05, + "loss": 3.4908, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283614710262238e-05, + "loss": 3.4938, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727522876275172e-05, + "loss": 3.499, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726685919404493e-05, + "loss": 3.4904, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725847324653441e-05, + "loss": 3.4918, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725010367782762e-05, + "loss": 3.5012, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.72417177303171e-05, + "loss": 3.5024, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233331782806583e-05, + "loss": 3.4872, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7224945835296063e-05, + "loss": 3.4987, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216559887785543e-05, + "loss": 3.5006, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208173940275023e-05, + "loss": 3.4983, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199787992764503e-05, + "loss": 3.484, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191402045253983e-05, + "loss": 3.494, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183032476547192e-05, + "loss": 3.4819, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174646529036675e-05, + "loss": 3.4963, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166260581526155e-05, + "loss": 3.4903, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7157874634015635e-05, + "loss": 3.5021, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149505065308844e-05, + "loss": 3.4906, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141119117798324e-05, + "loss": 3.4917, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132733170287804e-05, + "loss": 3.4974, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124347222777284e-05, + "loss": 3.5035, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711596127526676e-05, + "loss": 3.4966, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107591706559977e-05, + "loss": 3.477, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099205759049456e-05, + "loss": 3.4929, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7090819811538936e-05, + "loss": 3.503, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082433864028413e-05, + "loss": 3.4903, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707406429532163e-05, + "loss": 3.4905, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706567834781111e-05, + "loss": 3.488, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705729240030059e-05, + "loss": 3.4886, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7048906452790062e-05, + "loss": 3.4767, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040536884083278e-05, + "loss": 3.5037, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032150936572758e-05, + "loss": 3.4955, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7023764989062234e-05, + "loss": 3.5008, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015379041551714e-05, + "loss": 3.5046, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700700947284493e-05, + "loss": 3.4783, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699862352533441e-05, + "loss": 3.493, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990237577823883e-05, + "loss": 3.4891, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6981851630313367e-05, + "loss": 3.4818, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973482061606583e-05, + "loss": 3.4785, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965096114096056e-05, + "loss": 3.4954, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956710166585536e-05, + "loss": 3.4907, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948324219075016e-05, + "loss": 3.4833, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.693995465036823e-05, + "loss": 3.4742, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931568702857708e-05, + "loss": 3.4964, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923182755347188e-05, + "loss": 3.4973, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914796807836668e-05, + "loss": 3.4915, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906427239129884e-05, + "loss": 3.4927, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898041291619357e-05, + "loss": 3.5047, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889655344108837e-05, + "loss": 3.4972, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688126939659832e-05, + "loss": 3.5026, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687289982789153e-05, + "loss": 3.4848, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686451388038101e-05, + "loss": 3.4999, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685612793287049e-05, + "loss": 3.4955, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684774198535997e-05, + "loss": 3.4898, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683935603784945e-05, + "loss": 3.4986, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6830986469142662e-05, + "loss": 3.4929, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682260052163214e-05, + "loss": 3.5044, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681421457412162e-05, + "loss": 3.4937, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.68058286266111e-05, + "loss": 3.4755, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679745905790431e-05, + "loss": 3.4821, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678907311039379e-05, + "loss": 3.4918, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678068716288327e-05, + "loss": 3.4938, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772301215372754e-05, + "loss": 3.4944, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6763915267862234e-05, + "loss": 3.4905, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755545699155443e-05, + "loss": 3.4874, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747159751644923e-05, + "loss": 3.4809, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6738773804134403e-05, + "loss": 3.4903, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730387856623883e-05, + "loss": 3.4863, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722018287917095e-05, + "loss": 3.497, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713632340406575e-05, + "loss": 3.5006, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705246392896055e-05, + "loss": 3.4969, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6696860445385535e-05, + "loss": 3.4865, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688490876678744e-05, + "loss": 3.4962, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680104929168224e-05, + "loss": 3.4904, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671718981657708e-05, + "loss": 3.4972, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663333034147188e-05, + "loss": 3.4901, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6654963465440397e-05, + "loss": 3.4865, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646577517929877e-05, + "loss": 3.4821, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638191570419357e-05, + "loss": 3.4968, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6629805622908837e-05, + "loss": 3.4852, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662143605420205e-05, + "loss": 3.4755, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661305010669153e-05, + "loss": 3.484, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660466415918101e-05, + "loss": 3.4954, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659627821167049e-05, + "loss": 3.4807, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6587908642963698e-05, + "loss": 3.4968, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579522695453178e-05, + "loss": 3.4798, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657113674794266e-05, + "loss": 3.4952, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656275080043214e-05, + "loss": 3.4829, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655438123172535e-05, + "loss": 3.4821, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654599528421483e-05, + "loss": 3.5018, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653760933670431e-05, + "loss": 3.4999, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652922338919379e-05, + "loss": 3.4868, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6520853820487003e-05, + "loss": 3.4868, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512467872976483e-05, + "loss": 3.4904, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504081925465963e-05, + "loss": 3.4918, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495695977955443e-05, + "loss": 3.4818, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648732640924865e-05, + "loss": 3.4913, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647894046173813e-05, + "loss": 3.4843, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470554514227615e-05, + "loss": 3.4948, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462168566717095e-05, + "loss": 3.4777, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6453798998010304e-05, + "loss": 3.4888, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445413050499784e-05, + "loss": 3.4826, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437027102989264e-05, + "loss": 3.4872, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428641155478744e-05, + "loss": 3.4863, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420271586771956e-05, + "loss": 3.5044, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6411885639261436e-05, + "loss": 3.491, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403499691750916e-05, + "loss": 3.4867, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395113744240396e-05, + "loss": 3.4783, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6386744175533605e-05, + "loss": 3.4984, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378358228023085e-05, + "loss": 3.4947, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.636997228051257e-05, + "loss": 3.4886, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636158633300205e-05, + "loss": 3.4814, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635320038549153e-05, + "loss": 3.4953, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6344830816784738e-05, + "loss": 3.4966, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336444869274218e-05, + "loss": 3.4881, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328058921763698e-05, + "loss": 3.4888, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319672974253177e-05, + "loss": 3.4895, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.631130340554639e-05, + "loss": 3.4864, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630291745803587e-05, + "loss": 3.4797, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629454788932908e-05, + "loss": 3.496, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628616194181856e-05, + "loss": 3.4908, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627777599430804e-05, + "loss": 3.4912, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269390046797522e-05, + "loss": 3.4833, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261004099287002e-05, + "loss": 3.4788, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.850958824157715, + "eval_runtime": 305.6648, + "eval_samples_per_second": 1248.397, + "eval_steps_per_second": 39.013, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252618151776482e-05, + "loss": 3.4878, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244232204265962e-05, + "loss": 3.4888, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6235846256755435e-05, + "loss": 3.4985, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622747668804865e-05, + "loss": 3.4873, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621909074053813e-05, + "loss": 3.4983, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6210704793027608e-05, + "loss": 3.483, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202318845517088e-05, + "loss": 3.4875, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6193949276810304e-05, + "loss": 3.4755, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185563329299784e-05, + "loss": 3.4992, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617717738178926e-05, + "loss": 3.4932, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616879143427874e-05, + "loss": 3.4909, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160421865571956e-05, + "loss": 3.4934, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152052296865165e-05, + "loss": 3.4844, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143666349354645e-05, + "loss": 3.4818, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135280401844125e-05, + "loss": 3.4909, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6126894454333605e-05, + "loss": 3.4773, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611850850682308e-05, + "loss": 3.4793, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611012255931256e-05, + "loss": 3.4773, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.610173661180204e-05, + "loss": 3.4801, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.609335066429152e-05, + "loss": 3.5054, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608498109558473e-05, + "loss": 3.4858, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076595148074214e-05, + "loss": 3.4875, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068209200563694e-05, + "loss": 3.4842, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6059823253053174e-05, + "loss": 3.4907, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051453684346383e-05, + "loss": 3.4742, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043067736835863e-05, + "loss": 3.4769, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6034681789325343e-05, + "loss": 3.4822, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026295841814823e-05, + "loss": 3.4912, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6017926273108035e-05, + "loss": 3.4741, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009540325597515e-05, + "loss": 3.4819, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001154378086995e-05, + "loss": 3.4816, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5992784809380204e-05, + "loss": 3.4912, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984398861869684e-05, + "loss": 3.4798, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976012914359167e-05, + "loss": 3.4844, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967626966848647e-05, + "loss": 3.4845, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959241019338127e-05, + "loss": 3.4884, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5950855071827607e-05, + "loss": 3.4701, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942469124317087e-05, + "loss": 3.4822, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934099555610296e-05, + "loss": 3.4686, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925713608099776e-05, + "loss": 3.4849, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917327660589256e-05, + "loss": 3.4761, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590894171307874e-05, + "loss": 3.4887, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590057214437195e-05, + "loss": 3.481, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589218619686143e-05, + "loss": 3.4764, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588380024935091e-05, + "loss": 3.4887, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587541430184039e-05, + "loss": 3.4861, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586702835432987e-05, + "loss": 3.4842, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585865878562308e-05, + "loss": 3.4711, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585027283811256e-05, + "loss": 3.477, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584188689060204e-05, + "loss": 3.4905, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583350094309152e-05, + "loss": 3.4803, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582513137438473e-05, + "loss": 3.4756, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581674542687421e-05, + "loss": 3.4763, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808359479363693e-05, + "loss": 3.4777, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5799973531853173e-05, + "loss": 3.4649, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791603963146382e-05, + "loss": 3.4859, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783218015635862e-05, + "loss": 3.4828, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5774832068125342e-05, + "loss": 3.4874, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766446120614822e-05, + "loss": 3.4882, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758076551908035e-05, + "loss": 3.4699, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5749690604397515e-05, + "loss": 3.4744, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741304656886995e-05, + "loss": 3.4817, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5732918709376475e-05, + "loss": 3.4711, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724549140669684e-05, + "loss": 3.4699, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716163193159164e-05, + "loss": 3.4787, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5707777245648647e-05, + "loss": 3.4806, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699391298138127e-05, + "loss": 3.4694, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691021729431336e-05, + "loss": 3.465, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682635781920816e-05, + "loss": 3.4801, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674249834410296e-05, + "loss": 3.4852, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5665863886899776e-05, + "loss": 3.4765, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565749431819299e-05, + "loss": 3.4826, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649108370682468e-05, + "loss": 3.4917, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5640722423171948e-05, + "loss": 3.485, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632336475661428e-05, + "loss": 3.4931, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5623966906954637e-05, + "loss": 3.4685, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615580959444117e-05, + "loss": 3.4849, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.56071950119336e-05, + "loss": 3.485, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559880906442308e-05, + "loss": 3.475, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559043949571629e-05, + "loss": 3.4907, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558205354820577e-05, + "loss": 3.4793, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557366760069525e-05, + "loss": 3.4887, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556528165318473e-05, + "loss": 3.4843, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5556912084477942e-05, + "loss": 3.4628, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548526136967422e-05, + "loss": 3.4738, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540140189456902e-05, + "loss": 3.4761, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5531754241946382e-05, + "loss": 3.4811, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523368294435862e-05, + "loss": 3.4833, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551499872572907e-05, + "loss": 3.4754, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5506612778218554e-05, + "loss": 3.477, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498226830708034e-05, + "loss": 3.469, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5489840883197514e-05, + "loss": 3.4787, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481471314490723e-05, + "loss": 3.4724, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473085366980203e-05, + "loss": 3.4847, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464699419469683e-05, + "loss": 3.4899, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545631347195916e-05, + "loss": 3.4836, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5447943903252376e-05, + "loss": 3.4727, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439557955741856e-05, + "loss": 3.4846, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431172008231336e-05, + "loss": 3.4771, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542278606072081e-05, + "loss": 3.4859, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414416492014025e-05, + "loss": 3.4783, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406030544503508e-05, + "loss": 3.4747, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397644596992988e-05, + "loss": 3.4677, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538925864948246e-05, + "loss": 3.4884, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5380889080775677e-05, + "loss": 3.4686, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372503133265157e-05, + "loss": 3.4658, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364117185754633e-05, + "loss": 3.4708, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5355731238244113e-05, + "loss": 3.4801, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534736166953733e-05, + "loss": 3.4695, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533897572202681e-05, + "loss": 3.4879, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5330589774516282e-05, + "loss": 3.4694, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322203827005762e-05, + "loss": 3.4764, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5313834258298978e-05, + "loss": 3.4772, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530544831078846e-05, + "loss": 3.4664, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297062363277935e-05, + "loss": 3.4903, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288676415767415e-05, + "loss": 3.4871, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280290468256895e-05, + "loss": 3.4783, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5271920899550107e-05, + "loss": 3.4769, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263534952039587e-05, + "loss": 3.4733, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255149004529067e-05, + "loss": 3.4814, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5246763057018547e-05, + "loss": 3.4686, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238393488311756e-05, + "loss": 3.4829, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230007540801236e-05, + "loss": 3.4681, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221621593290716e-05, + "loss": 3.4788, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.52132356457802e-05, + "loss": 3.4715, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520486607707341e-05, + "loss": 3.4748, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519648012956289e-05, + "loss": 3.4701, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518809418205237e-05, + "loss": 3.475, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517970823454185e-05, + "loss": 3.4705, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.517133866583506e-05, + "loss": 3.4908, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516295271832454e-05, + "loss": 3.4819, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.515456677081402e-05, + "loss": 3.4763, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.51461808233035e-05, + "loss": 3.4648, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.513781125459671e-05, + "loss": 3.4868, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512942530708619e-05, + "loss": 3.4819, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512103935957567e-05, + "loss": 3.4811, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511265341206515e-05, + "loss": 3.472, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104283843358362e-05, + "loss": 3.4801, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5095897895847842e-05, + "loss": 3.4843, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087511948337322e-05, + "loss": 3.4801, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079126000826802e-05, + "loss": 3.4744, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507075643212001e-05, + "loss": 3.4793, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062370484609494e-05, + "loss": 3.4744, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5053984537098974e-05, + "loss": 3.4709, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045614968392184e-05, + "loss": 3.4811, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037229020881663e-05, + "loss": 3.4836, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5028843073371143e-05, + "loss": 3.4759, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020457125860623e-05, + "loss": 3.4684, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012071178350103e-05, + "loss": 3.4741, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.853104829788208, + "eval_runtime": 309.9748, + "eval_samples_per_second": 1231.039, + "eval_steps_per_second": 38.471, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003685230839587e-05, + "loss": 3.4697, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995299283329067e-05, + "loss": 3.4783, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4986913335818547e-05, + "loss": 3.4848, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978527388308027e-05, + "loss": 3.4747, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970157819601236e-05, + "loss": 3.4873, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961771872090716e-05, + "loss": 3.4711, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953385924580196e-05, + "loss": 3.4724, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4944999977069676e-05, + "loss": 3.4639, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936630408362888e-05, + "loss": 3.4888, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928244460852368e-05, + "loss": 3.4804, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4919858513341848e-05, + "loss": 3.475, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911472565831324e-05, + "loss": 3.4855, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490310299712454e-05, + "loss": 3.4703, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489471704961402e-05, + "loss": 3.4727, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.48863311021035e-05, + "loss": 3.4779, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4877945154592977e-05, + "loss": 3.4655, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869559207082457e-05, + "loss": 3.4665, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861173259571937e-05, + "loss": 3.4663, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852787312061417e-05, + "loss": 3.4727, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844401364550897e-05, + "loss": 3.4885, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483603179584411e-05, + "loss": 3.4755, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482764584833359e-05, + "loss": 3.4735, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481925990082307e-05, + "loss": 3.474, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481087395331255e-05, + "loss": 3.4792, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802504384605758e-05, + "loss": 3.4649, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479411843709524e-05, + "loss": 3.4658, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478573248958472e-05, + "loss": 3.4662, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.47773465420742e-05, + "loss": 3.4778, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476897697336741e-05, + "loss": 3.4619, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476059102585689e-05, + "loss": 3.4708, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475220507834637e-05, + "loss": 3.4732, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4743835509639583e-05, + "loss": 3.4787, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735449562129063e-05, + "loss": 3.4681, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727063614618543e-05, + "loss": 3.474, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4718677667108023e-05, + "loss": 3.4714, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710291719597503e-05, + "loss": 3.4755, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470190577208698e-05, + "loss": 3.464, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693519824576463e-05, + "loss": 3.467, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685150255869675e-05, + "loss": 3.4572, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676764308359155e-05, + "loss": 3.4721, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.466837836084863e-05, + "loss": 3.4642, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.465999241333811e-05, + "loss": 3.4761, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651622844631324e-05, + "loss": 3.4696, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643236897120804e-05, + "loss": 3.4692, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4634850949610284e-05, + "loss": 3.4755, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626465002099764e-05, + "loss": 3.4736, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618095433392976e-05, + "loss": 3.4744, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609709485882453e-05, + "loss": 3.4623, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601323538371933e-05, + "loss": 3.4587, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4592937590861416e-05, + "loss": 3.4809, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458456802215463e-05, + "loss": 3.4684, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576182074644105e-05, + "loss": 3.4653, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4567796127133585e-05, + "loss": 3.4656, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559410179623065e-05, + "loss": 3.4681, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551040610916278e-05, + "loss": 3.4518, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542654663405758e-05, + "loss": 3.4746, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534268715895238e-05, + "loss": 3.4731, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4525882768384718e-05, + "loss": 3.4722, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517513199677927e-05, + "loss": 3.4786, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509127252167407e-05, + "loss": 3.4619, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500741304656887e-05, + "loss": 3.4598, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492355357146367e-05, + "loss": 3.4752, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448398578843958e-05, + "loss": 3.4533, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447559984092906e-05, + "loss": 3.4581, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446721389341854e-05, + "loss": 3.4672, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445882794590802e-05, + "loss": 3.4699, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445045837720123e-05, + "loss": 3.4574, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444207242969071e-05, + "loss": 3.4555, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443368648218019e-05, + "loss": 3.4671, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442530053466967e-05, + "loss": 3.4696, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441693096596288e-05, + "loss": 3.4689, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440854501845236e-05, + "loss": 3.4676, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440015907094184e-05, + "loss": 3.4795, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439177312343132e-05, + "loss": 3.4722, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383403554724533e-05, + "loss": 3.484, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375017607214013e-05, + "loss": 3.4563, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366631659703493e-05, + "loss": 3.476, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358245712192973e-05, + "loss": 3.4723, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434987614348618e-05, + "loss": 3.4612, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341490195975665e-05, + "loss": 3.481, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333104248465145e-05, + "loss": 3.467, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324718300954625e-05, + "loss": 3.4743, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316348732247834e-05, + "loss": 3.4765, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4307962784737314e-05, + "loss": 3.4541, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299576837226794e-05, + "loss": 3.4633, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291190889716274e-05, + "loss": 3.4613, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4282821321009486e-05, + "loss": 3.4714, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274435373498966e-05, + "loss": 3.4717, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266049425988446e-05, + "loss": 3.4635, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257663478477926e-05, + "loss": 3.4651, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249293909771135e-05, + "loss": 3.46, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424090796226062e-05, + "loss": 3.462, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.42325220147501e-05, + "loss": 3.4634, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422413606723958e-05, + "loss": 3.475, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215766498532788e-05, + "loss": 3.4794, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207380551022268e-05, + "loss": 3.4712, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4198994603511748e-05, + "loss": 3.4615, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190608656001228e-05, + "loss": 3.4702, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.418223908729444e-05, + "loss": 3.467, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417385313978392e-05, + "loss": 3.476, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.41654671922734e-05, + "loss": 3.4688, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157081244762876e-05, + "loss": 3.462, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414871167605609e-05, + "loss": 3.4593, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140325728545572e-05, + "loss": 3.4712, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4131939781035052e-05, + "loss": 3.4589, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412355383352453e-05, + "loss": 3.457, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411518426481774e-05, + "loss": 3.4548, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410679831730722e-05, + "loss": 3.4687, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.40984123697967e-05, + "loss": 3.4536, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409002642228618e-05, + "loss": 3.4792, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081656853579394e-05, + "loss": 3.456, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073270906068874e-05, + "loss": 3.4684, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406488495855835e-05, + "loss": 3.4652, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405649901104783e-05, + "loss": 3.4533, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048129442341043e-05, + "loss": 3.4782, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4039743494830526e-05, + "loss": 3.4769, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031357547320003e-05, + "loss": 3.464, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4022971599809482e-05, + "loss": 3.4645, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014602031102695e-05, + "loss": 3.4616, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400621608359217e-05, + "loss": 3.4705, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3997830136081655e-05, + "loss": 3.4531, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989444188571135e-05, + "loss": 3.4733, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981074619864347e-05, + "loss": 3.4622, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972688672353824e-05, + "loss": 3.4649, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964302724843304e-05, + "loss": 3.4603, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3955916777332784e-05, + "loss": 3.4638, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947547208625996e-05, + "loss": 3.4565, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939161261115476e-05, + "loss": 3.4643, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930775313604956e-05, + "loss": 3.46, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922389366094436e-05, + "loss": 3.476, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914019797387645e-05, + "loss": 3.471, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905633849877125e-05, + "loss": 3.4662, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897247902366605e-05, + "loss": 3.4539, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388886195485609e-05, + "loss": 3.4737, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880492386149298e-05, + "loss": 3.4693, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872106438638778e-05, + "loss": 3.4675, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863720491128258e-05, + "loss": 3.4578, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855334543617737e-05, + "loss": 3.4686, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384696497491095e-05, + "loss": 3.4711, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383857902740043e-05, + "loss": 3.4735, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383019307988991e-05, + "loss": 3.4596, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382180713237939e-05, + "loss": 3.4697, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.38134375636726e-05, + "loss": 3.4594, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380505161616208e-05, + "loss": 3.4584, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796682047455295e-05, + "loss": 3.4732, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378829609994477e-05, + "loss": 3.468, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.377991015243425e-05, + "loss": 3.4641, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377152420492373e-05, + "loss": 3.4569, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376313825741321e-05, + "loss": 3.4643, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8544275760650635, + "eval_runtime": 304.8553, + "eval_samples_per_second": 1251.712, + "eval_steps_per_second": 39.117, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375475230990269e-05, + "loss": 3.463, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374636636239217e-05, + "loss": 3.4626, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3737996793685384e-05, + "loss": 3.4748, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729610846174864e-05, + "loss": 3.4671, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721224898664343e-05, + "loss": 3.4702, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3712838951153823e-05, + "loss": 3.4644, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.37044530036433e-05, + "loss": 3.4597, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696083434936513e-05, + "loss": 3.4536, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687697487425996e-05, + "loss": 3.4729, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679311539915476e-05, + "loss": 3.4724, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3670925592404952e-05, + "loss": 3.4648, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662556023698165e-05, + "loss": 3.4738, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654186454991374e-05, + "loss": 3.4582, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3645800507480857e-05, + "loss": 3.4601, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637414559970337e-05, + "loss": 3.4673, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629028612459817e-05, + "loss": 3.4527, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620642664949297e-05, + "loss": 3.4545, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612256717438774e-05, + "loss": 3.4553, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3603870769928254e-05, + "loss": 3.4591, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595484822417734e-05, + "loss": 3.4764, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358711525371095e-05, + "loss": 3.4658, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3578729306200426e-05, + "loss": 3.4636, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570343358689906e-05, + "loss": 3.4573, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3561957411179386e-05, + "loss": 3.4699, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553587842472595e-05, + "loss": 3.4532, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545201894962075e-05, + "loss": 3.4561, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.353681594745156e-05, + "loss": 3.4568, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352844637874477e-05, + "loss": 3.4638, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520060431234247e-05, + "loss": 3.4503, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511674483723727e-05, + "loss": 3.4604, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503288536213207e-05, + "loss": 3.4653, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349491896750642e-05, + "loss": 3.4662, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.34865330199959e-05, + "loss": 3.4602, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.347814707248538e-05, + "loss": 3.4598, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346976112497486e-05, + "loss": 3.462, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346137517746434e-05, + "loss": 3.4604, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345298922995382e-05, + "loss": 3.4557, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.34446032824433e-05, + "loss": 3.4544, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436233713736512e-05, + "loss": 3.448, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3427847766225992e-05, + "loss": 3.4602, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419461818715472e-05, + "loss": 3.4547, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411075871204952e-05, + "loss": 3.4641, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340270630249816e-05, + "loss": 3.4585, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339432035498764e-05, + "loss": 3.4546, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338593440747712e-05, + "loss": 3.4658, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377548459966604e-05, + "loss": 3.4583, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369178891259813e-05, + "loss": 3.464, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3360792943749293e-05, + "loss": 3.4497, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352406996238773e-05, + "loss": 3.4471, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334402104872825e-05, + "loss": 3.4728, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3335651480021466e-05, + "loss": 3.4558, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327265532510946e-05, + "loss": 3.4527, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3318879585000426e-05, + "loss": 3.4537, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310493637489902e-05, + "loss": 3.457, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302124068783115e-05, + "loss": 3.4389, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3293738121272595e-05, + "loss": 3.4622, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285352173762075e-05, + "loss": 3.46, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3276966226251555e-05, + "loss": 3.4562, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268596657544767e-05, + "loss": 3.4727, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260210710034247e-05, + "loss": 3.4501, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3251824762523724e-05, + "loss": 3.4503, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243438815013204e-05, + "loss": 3.4628, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323506924630642e-05, + "loss": 3.4451, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.32266832987959e-05, + "loss": 3.4475, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218297351285376e-05, + "loss": 3.4553, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3209911403774856e-05, + "loss": 3.4583, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.320154183506807e-05, + "loss": 3.448, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319315588755755e-05, + "loss": 3.4449, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3184769940047028e-05, + "loss": 3.4509, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176383992536508e-05, + "loss": 3.4563, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316801442382972e-05, + "loss": 3.4584, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159628476319197e-05, + "loss": 3.4595, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151242528808677e-05, + "loss": 3.4643, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3142856581298157e-05, + "loss": 3.4634, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134487012591373e-05, + "loss": 3.4731, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.312610106508085e-05, + "loss": 3.446, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311771511757033e-05, + "loss": 3.4663, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310932917005981e-05, + "loss": 3.461, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310095960135302e-05, + "loss": 3.4446, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.30925736538425e-05, + "loss": 3.4716, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084187706331982e-05, + "loss": 3.4537, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3075801758821462e-05, + "loss": 3.4641, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.306743219011467e-05, + "loss": 3.4666, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305904624260415e-05, + "loss": 3.446, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305066029509363e-05, + "loss": 3.4489, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304227434758311e-05, + "loss": 3.449, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3033904778876323e-05, + "loss": 3.4604, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025518831365803e-05, + "loss": 3.4586, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017132883855283e-05, + "loss": 3.4537, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008746936344763e-05, + "loss": 3.4502, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000377367637972e-05, + "loss": 3.4514, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2991991420127452e-05, + "loss": 3.4529, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983605472616936e-05, + "loss": 3.4478, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975235903910145e-05, + "loss": 3.4661, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2966849956399625e-05, + "loss": 3.4654, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958464008889105e-05, + "loss": 3.4668, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950078061378585e-05, + "loss": 3.4474, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2941708492671797e-05, + "loss": 3.4589, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933322545161277e-05, + "loss": 3.4549, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2924936597650757e-05, + "loss": 3.4604, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916550650140237e-05, + "loss": 3.4575, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908181081433446e-05, + "loss": 3.4552, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2899795133922926e-05, + "loss": 3.4469, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891409186412406e-05, + "loss": 3.4568, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.288302323890189e-05, + "loss": 3.45, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.28746536701951e-05, + "loss": 3.4463, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286626772268458e-05, + "loss": 3.441, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2857881775174058e-05, + "loss": 3.457, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849495827663538e-05, + "loss": 3.4481, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284112625895675e-05, + "loss": 3.4658, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283274031144623e-05, + "loss": 3.4466, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282435436393571e-05, + "loss": 3.4566, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281596841642519e-05, + "loss": 3.4572, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.28075988477184e-05, + "loss": 3.4427, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279921290020788e-05, + "loss": 3.4678, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279082695269736e-05, + "loss": 3.4642, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782441005186843e-05, + "loss": 3.4529, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774071436480052e-05, + "loss": 3.4533, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2765685488969532e-05, + "loss": 3.4522, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757299541459012e-05, + "loss": 3.458, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2748913593948492e-05, + "loss": 3.438, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740544025241704e-05, + "loss": 3.4606, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732158077731184e-05, + "loss": 3.4483, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2723772130220664e-05, + "loss": 3.4512, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715386182710144e-05, + "loss": 3.4545, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707016614003353e-05, + "loss": 3.4519, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698630666492833e-05, + "loss": 3.4508, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690244718982313e-05, + "loss": 3.4513, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2681858771471797e-05, + "loss": 3.4514, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673489202765006e-05, + "loss": 3.4616, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665103255254486e-05, + "loss": 3.4561, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656717307743966e-05, + "loss": 3.4579, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648331360233446e-05, + "loss": 3.4399, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2639961791526658e-05, + "loss": 3.4643, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631575844016138e-05, + "loss": 3.4559, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623189896505618e-05, + "loss": 3.4544, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2614803948995095e-05, + "loss": 3.4496, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606434380288307e-05, + "loss": 3.4545, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598048432777787e-05, + "loss": 3.4633, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589662485267267e-05, + "loss": 3.4609, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581276537756747e-05, + "loss": 3.4476, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257290696904996e-05, + "loss": 3.4562, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256452102153944e-05, + "loss": 3.4534, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255613507402892e-05, + "loss": 3.4457, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2547749126518396e-05, + "loss": 3.463, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539379557811612e-05, + "loss": 3.4547, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.253099361030109e-05, + "loss": 3.4587, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522607662790568e-05, + "loss": 3.4404, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514221715280048e-05, + "loss": 3.4558, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8558597564697266, + "eval_runtime": 306.2655, + "eval_samples_per_second": 1245.948, + "eval_steps_per_second": 38.937, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250585214657326e-05, + "loss": 3.4522, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249746619906274e-05, + "loss": 3.4492, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248908025155222e-05, + "loss": 3.4622, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.24806943040417e-05, + "loss": 3.4577, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472324735334913e-05, + "loss": 3.4591, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246393878782439e-05, + "loss": 3.4522, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245555284031387e-05, + "loss": 3.4438, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244716689280335e-05, + "loss": 3.448, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2438797324096565e-05, + "loss": 3.4569, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430411376586042e-05, + "loss": 3.4632, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422025429075522e-05, + "loss": 3.4515, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413639481565002e-05, + "loss": 3.4614, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405286291661943e-05, + "loss": 3.4504, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2396900344151427e-05, + "loss": 3.4425, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388514396640907e-05, + "loss": 3.4612, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380128449130387e-05, + "loss": 3.4417, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2371742501619863e-05, + "loss": 3.4437, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363356554109343e-05, + "loss": 3.4425, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2354970606598823e-05, + "loss": 3.4496, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346584659088303e-05, + "loss": 3.4599, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338215090381516e-05, + "loss": 3.4564, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2329829142870996e-05, + "loss": 3.4557, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321443195360476e-05, + "loss": 3.4452, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313057247849956e-05, + "loss": 3.4562, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304687679143165e-05, + "loss": 3.4457, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296301731632645e-05, + "loss": 3.4462, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2287915784122128e-05, + "loss": 3.4443, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279529836611608e-05, + "loss": 3.4518, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271160267904817e-05, + "loss": 3.4463, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2262774320394297e-05, + "loss": 3.4436, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254388372883777e-05, + "loss": 3.4543, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224601880417699e-05, + "loss": 3.4534, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223763285666647e-05, + "loss": 3.448, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222924690915595e-05, + "loss": 3.4501, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222086096164543e-05, + "loss": 3.4487, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221247501413491e-05, + "loss": 3.4495, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220408906662439e-05, + "loss": 3.4497, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.219570311911387e-05, + "loss": 3.4365, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187317171603346e-05, + "loss": 3.4347, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217894760289656e-05, + "loss": 3.4472, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.217056165538604e-05, + "loss": 3.4465, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162175707875518e-05, + "loss": 3.4517, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215380613916873e-05, + "loss": 3.4471, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214542019165821e-05, + "loss": 3.4436, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.213703424414769e-05, + "loss": 3.4542, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212864829663717e-05, + "loss": 3.45, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120278727930383e-05, + "loss": 3.4561, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2111892780419863e-05, + "loss": 3.4381, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103506832909343e-05, + "loss": 3.4303, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209512088539882e-05, + "loss": 3.4627, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2086751316692035e-05, + "loss": 3.4481, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078365369181515e-05, + "loss": 3.4411, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2069979421670992e-05, + "loss": 3.4443, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061593474160472e-05, + "loss": 3.4434, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053223905453684e-05, + "loss": 3.4327, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2044837957943164e-05, + "loss": 3.4476, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036452010432644e-05, + "loss": 3.4503, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028066062922124e-05, + "loss": 3.4482, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019680115411604e-05, + "loss": 3.4579, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011294167901084e-05, + "loss": 3.4369, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2002908220390564e-05, + "loss": 3.4402, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994538651683773e-05, + "loss": 3.4562, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986152704173253e-05, + "loss": 3.4309, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1977766756662736e-05, + "loss": 3.4326, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969380809152216e-05, + "loss": 3.4417, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961011240445425e-05, + "loss": 3.446, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952625292934905e-05, + "loss": 3.4349, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944239345424385e-05, + "loss": 3.4386, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1935853397913865e-05, + "loss": 3.435, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927483829207078e-05, + "loss": 3.4511, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919097881696558e-05, + "loss": 3.4457, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1910711934186038e-05, + "loss": 3.4461, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902325986675518e-05, + "loss": 3.4539, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1893956417968727e-05, + "loss": 3.4504, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885570470458207e-05, + "loss": 3.4651, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187718452294769e-05, + "loss": 3.4354, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186879857543717e-05, + "loss": 3.4548, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186042900673038e-05, + "loss": 3.4507, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185204305921986e-05, + "loss": 3.4328, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184365711170934e-05, + "loss": 3.4579, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183527116419882e-05, + "loss": 3.4424, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.182690159549203e-05, + "loss": 3.4525, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181851564798151e-05, + "loss": 3.4535, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181012970047099e-05, + "loss": 3.4364, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1801743752960468e-05, + "loss": 3.4324, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179337418425368e-05, + "loss": 3.4395, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178498823674316e-05, + "loss": 3.4502, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776602289232644e-05, + "loss": 3.4442, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.176821634172212e-05, + "loss": 3.441, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.17598303942116e-05, + "loss": 3.4413, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175144444670108e-05, + "loss": 3.4406, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174305849919056e-05, + "loss": 3.4427, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173468893048377e-05, + "loss": 3.438, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726302982973253e-05, + "loss": 3.4538, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1717917035462733e-05, + "loss": 3.4538, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709531087952212e-05, + "loss": 3.4532, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170116151924542e-05, + "loss": 3.4366, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.16927755717349e-05, + "loss": 3.449, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168438962422438e-05, + "loss": 3.4455, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167600367671386e-05, + "loss": 3.4487, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667634108007074e-05, + "loss": 3.4472, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659248160496554e-05, + "loss": 3.4395, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1650862212986034e-05, + "loss": 3.4392, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642476265475514e-05, + "loss": 3.4431, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634106696768723e-05, + "loss": 3.4373, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1625720749258206e-05, + "loss": 3.4428, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617334801747686e-05, + "loss": 3.4229, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1608948854237166e-05, + "loss": 3.4479, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600579285530375e-05, + "loss": 3.4382, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592193338019855e-05, + "loss": 3.4499, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1583807390509335e-05, + "loss": 3.4348, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575421442998815e-05, + "loss": 3.448, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567051874292028e-05, + "loss": 3.4478, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1558665926781508e-05, + "loss": 3.4293, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550279979270987e-05, + "loss": 3.4574, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1541894031760467e-05, + "loss": 3.4496, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533524463053677e-05, + "loss": 3.442, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152513851554316e-05, + "loss": 3.447, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151675256803264e-05, + "loss": 3.4328, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150836662052212e-05, + "loss": 3.4531, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.149999705181533e-05, + "loss": 3.4329, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149161110430481e-05, + "loss": 3.4479, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148322515679429e-05, + "loss": 3.4355, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.147483920928377e-05, + "loss": 3.4441, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146646964057698e-05, + "loss": 3.4409, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145808369306646e-05, + "loss": 3.4404, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144969774555594e-05, + "loss": 3.4408, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144131179804542e-05, + "loss": 3.4367, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143294222933863e-05, + "loss": 3.4432, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424556281828114e-05, + "loss": 3.4499, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416170334317594e-05, + "loss": 3.4415, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140778438680707e-05, + "loss": 3.4502, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399414818100283e-05, + "loss": 3.4294, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391028870589763e-05, + "loss": 3.4526, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382642923079242e-05, + "loss": 3.4488, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374256975568722e-05, + "loss": 3.4428, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1365887406861935e-05, + "loss": 3.438, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357501459351415e-05, + "loss": 3.4468, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349115511840895e-05, + "loss": 3.4478, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134072956433037e-05, + "loss": 3.4527, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332359995623584e-05, + "loss": 3.433, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1323974048113067e-05, + "loss": 3.448, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315588100602544e-05, + "loss": 3.4395, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307202153092024e-05, + "loss": 3.4372, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1298832584385236e-05, + "loss": 3.4474, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290446636874716e-05, + "loss": 3.4434, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282060689364193e-05, + "loss": 3.448, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127369112065741e-05, + "loss": 3.4309, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126530517314689e-05, + "loss": 3.4469, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.857816219329834, + "eval_runtime": 315.6741, + "eval_samples_per_second": 1208.813, + "eval_steps_per_second": 37.776, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125691922563637e-05, + "loss": 3.4437, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248533278125845e-05, + "loss": 3.4386, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240147330615325e-05, + "loss": 3.4492, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1231761383104805e-05, + "loss": 3.446, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223391814398018e-05, + "loss": 3.4463, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215005866887497e-05, + "loss": 3.4439, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1206619919376977e-05, + "loss": 3.4332, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198233971866457e-05, + "loss": 3.4359, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1189864403159666e-05, + "loss": 3.4469, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181478455649146e-05, + "loss": 3.4505, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.117309250813863e-05, + "loss": 3.442, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.116470656062811e-05, + "loss": 3.4498, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115635337072505e-05, + "loss": 3.443, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114796742321453e-05, + "loss": 3.4325, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.113958147570401e-05, + "loss": 3.4443, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113119552819349e-05, + "loss": 3.4293, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112280958068297e-05, + "loss": 3.4345, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111442363317245e-05, + "loss": 3.4322, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110603768566193e-05, + "loss": 3.4378, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109765173815141e-05, + "loss": 3.4477, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.108928216944462e-05, + "loss": 3.4516, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.10808962219341e-05, + "loss": 3.4411, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072510274423583e-05, + "loss": 3.4342, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064124326913063e-05, + "loss": 3.4471, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1055754758206272e-05, + "loss": 3.4312, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047368810695752e-05, + "loss": 3.438, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1038982863185232e-05, + "loss": 3.431, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1030596915674712e-05, + "loss": 3.443, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022227346967925e-05, + "loss": 3.4302, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1013841399457405e-05, + "loss": 3.438, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005471830750614e-05, + "loss": 3.4393, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997085883240094e-05, + "loss": 3.4482, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0988699935729574e-05, + "loss": 3.4372, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980313988219054e-05, + "loss": 3.4362, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0971928040708537e-05, + "loss": 3.4371, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963542093198017e-05, + "loss": 3.4375, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955156145687494e-05, + "loss": 3.4401, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0946770198176974e-05, + "loss": 3.4213, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938400629470186e-05, + "loss": 3.4264, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930014681959666e-05, + "loss": 3.4328, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0921628734449146e-05, + "loss": 3.44, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913242786938626e-05, + "loss": 3.4376, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090487321823184e-05, + "loss": 3.4361, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089648727072132e-05, + "loss": 3.4306, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888101323210795e-05, + "loss": 3.4458, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0879715375700275e-05, + "loss": 3.4322, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087134580699349e-05, + "loss": 3.4513, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0862959859482967e-05, + "loss": 3.424, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854573911972447e-05, + "loss": 3.4167, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846187964461927e-05, + "loss": 3.4543, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083781839575514e-05, + "loss": 3.4352, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829432448244616e-05, + "loss": 3.4342, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.08210465007341e-05, + "loss": 3.4367, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0812676932027312e-05, + "loss": 3.4293, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804290984516792e-05, + "loss": 3.4231, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079590503700627e-05, + "loss": 3.4339, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078751908949575e-05, + "loss": 3.439, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077913314198523e-05, + "loss": 3.4403, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077074719447471e-05, + "loss": 3.4487, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762361246964192e-05, + "loss": 3.4269, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0753975299453672e-05, + "loss": 3.4284, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074560573074688e-05, + "loss": 3.4493, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073721978323636e-05, + "loss": 3.4204, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072883383572584e-05, + "loss": 3.4232, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072044788821532e-05, + "loss": 3.4309, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712078319508533e-05, + "loss": 3.434, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0703692371998013e-05, + "loss": 3.4218, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695306424487493e-05, + "loss": 3.4314, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0686920476976973e-05, + "loss": 3.4233, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0678550908270182e-05, + "loss": 3.4371, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670164960759662e-05, + "loss": 3.4387, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0661779013249146e-05, + "loss": 3.4337, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653393065738622e-05, + "loss": 3.4413, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645023497031835e-05, + "loss": 3.4401, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0636637549521315e-05, + "loss": 3.4531, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628251602010794e-05, + "loss": 3.4226, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.061986565450027e-05, + "loss": 3.4486, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611496085793487e-05, + "loss": 3.4371, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603110138282967e-05, + "loss": 3.4259, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0594724190772443e-05, + "loss": 3.4433, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586338243261923e-05, + "loss": 3.4374, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0577968674555136e-05, + "loss": 3.4413, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569582727044616e-05, + "loss": 3.4473, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561196779534096e-05, + "loss": 3.4232, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0552827210827308e-05, + "loss": 3.4207, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544457642120517e-05, + "loss": 3.431, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536071694609997e-05, + "loss": 3.4403, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0527685747099477e-05, + "loss": 3.4349, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051929979958896e-05, + "loss": 3.429, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.051091385207844e-05, + "loss": 3.4263, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502527904567917e-05, + "loss": 3.4306, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494141957057397e-05, + "loss": 3.4308, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0485756009546877e-05, + "loss": 3.4307, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047738644084009e-05, + "loss": 3.4401, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046900049332957e-05, + "loss": 3.4438, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.046061454581905e-05, + "loss": 3.4411, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045222859830853e-05, + "loss": 3.4285, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0443859029601742e-05, + "loss": 3.4388, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043548946089495e-05, + "loss": 3.4299, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042710351338443e-05, + "loss": 3.4389, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0418717565873914e-05, + "loss": 3.4378, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.041033161836339e-05, + "loss": 3.4357, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.040194567085287e-05, + "loss": 3.4254, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039355972334235e-05, + "loss": 3.4279, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038517377583183e-05, + "loss": 3.4321, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037678782832131e-05, + "loss": 3.4277, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368418259614523e-05, + "loss": 3.4185, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360032312104003e-05, + "loss": 3.4379, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0351646364593483e-05, + "loss": 3.4311, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343260417082963e-05, + "loss": 3.4355, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0334890848376172e-05, + "loss": 3.4228, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0326504900865652e-05, + "loss": 3.4425, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318118953355132e-05, + "loss": 3.4329, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0309733005844615e-05, + "loss": 3.4192, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301363437137825e-05, + "loss": 3.4426, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0292977489627304e-05, + "loss": 3.4391, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0284591542116784e-05, + "loss": 3.4305, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276205594606264e-05, + "loss": 3.4388, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0267836025899477e-05, + "loss": 3.4232, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025946645719269e-05, + "loss": 3.4418, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251080509682166e-05, + "loss": 3.4232, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0242694562171646e-05, + "loss": 3.4347, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234308614661126e-05, + "loss": 3.426, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0225922667150606e-05, + "loss": 3.4318, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217536719640086e-05, + "loss": 3.4288, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020915077212957e-05, + "loss": 3.4275, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0200764824619046e-05, + "loss": 3.4259, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192395255912258e-05, + "loss": 3.4286, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184025687205467e-05, + "loss": 3.4336, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0175639739694947e-05, + "loss": 3.4407, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016725379218443e-05, + "loss": 3.4277, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015886784467391e-05, + "loss": 3.4449, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015048189716339e-05, + "loss": 3.4188, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.014209594965287e-05, + "loss": 3.4426, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0133710002142347e-05, + "loss": 3.4369, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125324054631827e-05, + "loss": 3.4324, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011695448592504e-05, + "loss": 3.4261, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.010856853841452e-05, + "loss": 3.4362, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100182590904e-05, + "loss": 3.4357, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.009179664339348e-05, + "loss": 3.4445, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083427074686692e-05, + "loss": 3.4226, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007504112717617e-05, + "loss": 3.4344, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0066655179665648e-05, + "loss": 3.4282, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058285610958864e-05, + "loss": 3.4319, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0049899663448344e-05, + "loss": 3.4308, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.004151371593782e-05, + "loss": 3.433, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.00331277684273e-05, + "loss": 3.4412, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0024758199720513e-05, + "loss": 3.4182, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016372252209993e-05, + "loss": 3.437, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.858814001083374, + "eval_runtime": 304.3605, + "eval_samples_per_second": 1253.747, + "eval_steps_per_second": 39.181, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008019062306935e-05, + "loss": 3.43, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999633114796415e-05, + "loss": 3.4319, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991247167285895e-05, + "loss": 3.4356, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9982861219775375e-05, + "loss": 3.4329, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974475272264855e-05, + "loss": 3.439, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966105703558067e-05, + "loss": 3.4303, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9957719756047547e-05, + "loss": 3.4251, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949333808537027e-05, + "loss": 3.4284, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9940947861026507e-05, + "loss": 3.4333, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932561913515987e-05, + "loss": 3.4426, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924175966005463e-05, + "loss": 3.4333, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9915790018494947e-05, + "loss": 3.4369, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990742044978816e-05, + "loss": 3.4287, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.989903450227764e-05, + "loss": 3.4235, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890648554767116e-05, + "loss": 3.4376, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882262607256596e-05, + "loss": 3.4184, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9873876659746076e-05, + "loss": 3.4238, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865490712235556e-05, + "loss": 3.4229, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985710476472504e-05, + "loss": 3.4283, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984871881721452e-05, + "loss": 3.4329, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840349248507728e-05, + "loss": 3.4423, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9831963300997208e-05, + "loss": 3.4295, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823577353486688e-05, + "loss": 3.4252, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815191405976168e-05, + "loss": 3.4318, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9806838216073113e-05, + "loss": 3.4261, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979845226856259e-05, + "loss": 3.4269, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979006632105207e-05, + "loss": 3.4183, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978168037354155e-05, + "loss": 3.4335, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977329442603103e-05, + "loss": 3.4245, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976490847852051e-05, + "loss": 3.4225, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756538909813722e-05, + "loss": 3.4274, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748152962303202e-05, + "loss": 3.4395, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973976701479268e-05, + "loss": 3.4274, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973138106728216e-05, + "loss": 3.4232, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972299511977164e-05, + "loss": 3.4262, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9714609172261118e-05, + "loss": 3.4308, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.97062232247506e-05, + "loss": 3.4257, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969783727724008e-05, + "loss": 3.4163, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689467708533294e-05, + "loss": 3.417, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.968108176102277e-05, + "loss": 3.422, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967269581351225e-05, + "loss": 3.4284, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966430986600173e-05, + "loss": 3.4269, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9655940297294943e-05, + "loss": 3.4268, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647554349784423e-05, + "loss": 3.4217, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639168402273903e-05, + "loss": 3.4322, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9630782454763383e-05, + "loss": 3.4234, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622396507252863e-05, + "loss": 3.4385, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614010559742343e-05, + "loss": 3.421, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605624612231823e-05, + "loss": 3.4026, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597238664721303e-05, + "loss": 3.4446, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9588869096014515e-05, + "loss": 3.4218, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580483148503995e-05, + "loss": 3.426, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572113579797204e-05, + "loss": 3.4233, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563727632286684e-05, + "loss": 3.4184, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555341684776164e-05, + "loss": 3.4132, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9546955737265647e-05, + "loss": 3.4217, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538569789755124e-05, + "loss": 3.4314, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530183842244604e-05, + "loss": 3.4281, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9521814273537816e-05, + "loss": 3.4396, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513428326027296e-05, + "loss": 3.416, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505042378516776e-05, + "loss": 3.4163, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496656431006256e-05, + "loss": 3.439, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488270483495736e-05, + "loss": 3.41, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.947990091478895e-05, + "loss": 3.4086, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471514967278425e-05, + "loss": 3.4196, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463129019767905e-05, + "loss": 3.4242, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9454743072257385e-05, + "loss": 3.4145, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446357124746865e-05, + "loss": 3.4192, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943797117723635e-05, + "loss": 3.4135, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942958522972583e-05, + "loss": 3.4278, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421199282215305e-05, + "loss": 3.4263, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9412829713508517e-05, + "loss": 3.4249, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404443765997997e-05, + "loss": 3.4311, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396057818487477e-05, + "loss": 3.4307, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387671870976957e-05, + "loss": 3.4399, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937930230227017e-05, + "loss": 3.4136, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937091635475965e-05, + "loss": 3.436, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.936253040724913e-05, + "loss": 3.4226, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354144459738606e-05, + "loss": 3.4162, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.934577489103182e-05, + "loss": 3.4339, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337388943521302e-05, + "loss": 3.4271, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932900299601078e-05, + "loss": 3.4272, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.932061704850026e-05, + "loss": 3.4368, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931224747979347e-05, + "loss": 3.4125, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930386153228295e-05, + "loss": 3.4069, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295491963576164e-05, + "loss": 3.4216, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287106016065644e-05, + "loss": 3.4303, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9278720068555123e-05, + "loss": 3.4259, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.92703341210446e-05, + "loss": 3.4212, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.926194817353408e-05, + "loss": 3.4151, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925356222602356e-05, + "loss": 3.4186, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.924517627851304e-05, + "loss": 3.4246, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9236790331002523e-05, + "loss": 3.417, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228420762295732e-05, + "loss": 3.4292, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220034814785212e-05, + "loss": 3.4338, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9211665246078425e-05, + "loss": 3.432, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.92032792985679e-05, + "loss": 3.4202, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9194893351057385e-05, + "loss": 3.4252, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186507403546865e-05, + "loss": 3.4202, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178121456036345e-05, + "loss": 3.4271, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169735508525825e-05, + "loss": 3.4255, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161349561015305e-05, + "loss": 3.4256, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9152979992308514e-05, + "loss": 3.4185, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144610423601726e-05, + "loss": 3.4121, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136224476091206e-05, + "loss": 3.4249, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9127838528580686e-05, + "loss": 3.4174, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119452581070166e-05, + "loss": 3.4057, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111066633559646e-05, + "loss": 3.4275, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102680686049126e-05, + "loss": 3.4215, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094294738538606e-05, + "loss": 3.4239, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9085908791028086e-05, + "loss": 3.4104, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077539222321298e-05, + "loss": 3.4268, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069153274810778e-05, + "loss": 3.4256, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9060767327300255e-05, + "loss": 3.4104, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052381379789735e-05, + "loss": 3.4339, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044011811082947e-05, + "loss": 3.4308, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035625863572427e-05, + "loss": 3.4214, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027239916061907e-05, + "loss": 3.4256, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9018853968551387e-05, + "loss": 3.4108, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.90104843998446e-05, + "loss": 3.4294, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.900209845233408e-05, + "loss": 3.4167, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8993712504823556e-05, + "loss": 3.4213, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.898532655731304e-05, + "loss": 3.4146, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897694060980252e-05, + "loss": 3.4245, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8968554662292e-05, + "loss": 3.4197, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896016871478148e-05, + "loss": 3.417, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895178276727096e-05, + "loss": 3.4159, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894341319856417e-05, + "loss": 3.421, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893502725105365e-05, + "loss": 3.4191, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926641303543132e-05, + "loss": 3.4286, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891825535603261e-05, + "loss": 3.4197, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.890988578732582e-05, + "loss": 3.4353, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.89014998398153e-05, + "loss": 3.4061, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889311389230478e-05, + "loss": 3.4288, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8884744323597993e-05, + "loss": 3.4284, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8876358376087473e-05, + "loss": 3.4234, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8867972428576953e-05, + "loss": 3.4162, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859586481066433e-05, + "loss": 3.4234, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851216912359642e-05, + "loss": 3.4224, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8842830964849122e-05, + "loss": 3.4402, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8834445017338602e-05, + "loss": 3.4139, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826059069828082e-05, + "loss": 3.4224, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8817689501121294e-05, + "loss": 3.415, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809303553610774e-05, + "loss": 3.4261, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8800917606100254e-05, + "loss": 3.4172, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792531658589734e-05, + "loss": 3.424, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784162089882947e-05, + "loss": 3.4245, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8775776142372427e-05, + "loss": 3.4172, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767390194861907e-05, + "loss": 3.4233, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.860321283340454, + "eval_runtime": 307.2727, + "eval_samples_per_second": 1241.864, + "eval_steps_per_second": 38.809, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759004247351383e-05, + "loss": 3.4125, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750618299840863e-05, + "loss": 3.418, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742232352330343e-05, + "loss": 3.428, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8733846404819823e-05, + "loss": 3.4238, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725460457309303e-05, + "loss": 3.4293, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717107267406248e-05, + "loss": 3.4208, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8708721319895728e-05, + "loss": 3.4153, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700335372385205e-05, + "loss": 3.4197, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8691949424874685e-05, + "loss": 3.4199, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683563477364165e-05, + "loss": 3.4307, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675177529853648e-05, + "loss": 3.4228, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8666791582343128e-05, + "loss": 3.4253, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658422013636337e-05, + "loss": 3.4282, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650036066125817e-05, + "loss": 3.4077, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8641650118615297e-05, + "loss": 3.4257, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633264171104777e-05, + "loss": 3.4096, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8624878223594257e-05, + "loss": 3.4113, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861649227608374e-05, + "loss": 3.4134, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608106328573217e-05, + "loss": 3.414, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8599720381062697e-05, + "loss": 3.4233, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.859135081235591e-05, + "loss": 3.434, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8582964864845386e-05, + "loss": 3.4252, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574578917334866e-05, + "loss": 3.4162, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856619296982435e-05, + "loss": 3.4167, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.855783977992129e-05, + "loss": 3.4152, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854945383241077e-05, + "loss": 3.4183, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854106788490025e-05, + "loss": 3.4082, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853268193738973e-05, + "loss": 3.4267, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.852429598987921e-05, + "loss": 3.4119, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8515926421172423e-05, + "loss": 3.4145, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507540473661903e-05, + "loss": 3.4122, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8499154526151383e-05, + "loss": 3.4281, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.849076857864086e-05, + "loss": 3.4193, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848238263113034e-05, + "loss": 3.4148, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847399668361982e-05, + "loss": 3.4154, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8465610736109303e-05, + "loss": 3.4171, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457224788598783e-05, + "loss": 3.4203, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8448855219891992e-05, + "loss": 3.4072, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.844046927238147e-05, + "loss": 3.4074, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432099703674684e-05, + "loss": 3.4089, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8423713756164164e-05, + "loss": 3.4129, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415327808653644e-05, + "loss": 3.4156, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8406941861143124e-05, + "loss": 3.4165, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398572292436333e-05, + "loss": 3.4169, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390186344925813e-05, + "loss": 3.4156, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8381800397415293e-05, + "loss": 3.416, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8373414449904773e-05, + "loss": 3.4229, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365028502394256e-05, + "loss": 3.4115, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8356642554883736e-05, + "loss": 3.3915, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348256607373216e-05, + "loss": 3.4308, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8339870659862693e-05, + "loss": 3.4107, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331501091155905e-05, + "loss": 3.4176, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323115143645385e-05, + "loss": 3.4174, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8314745574938598e-05, + "loss": 3.4066, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306359627428078e-05, + "loss": 3.4027, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8297973679917558e-05, + "loss": 3.4091, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289587732407038e-05, + "loss": 3.4237, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281201784896514e-05, + "loss": 3.4147, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8272832216189727e-05, + "loss": 3.4273, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.826444626867921e-05, + "loss": 3.4122, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.825606032116869e-05, + "loss": 3.4018, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8247674373658167e-05, + "loss": 3.4269, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239288426147646e-05, + "loss": 3.402, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.823091885744086e-05, + "loss": 3.3997, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.822253290993034e-05, + "loss": 3.4129, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.821414696241982e-05, + "loss": 3.4082, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.82057610149093e-05, + "loss": 3.4057, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819737506739878e-05, + "loss": 3.4071, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818898911988826e-05, + "loss": 3.4051, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818060317237774e-05, + "loss": 3.4168, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172233603670948e-05, + "loss": 3.4197, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8163847656160428e-05, + "loss": 3.414, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815546170864991e-05, + "loss": 3.4203, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814707576113939e-05, + "loss": 3.4184, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.81387061924326e-05, + "loss": 3.4298, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813032024492208e-05, + "loss": 3.4067, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.812195067621529e-05, + "loss": 3.4274, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8113564728704773e-05, + "loss": 3.4098, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105178781194252e-05, + "loss": 3.408, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8096792833683732e-05, + "loss": 3.4173, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8088406886173212e-05, + "loss": 3.4165, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.808003731746642e-05, + "loss": 3.4226, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.80716513699559e-05, + "loss": 3.4239, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806326542244538e-05, + "loss": 3.4029, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8054879474934865e-05, + "loss": 3.3995, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046509906228074e-05, + "loss": 3.4122, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038123958717554e-05, + "loss": 3.4204, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8029738011207034e-05, + "loss": 3.4094, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021352063696514e-05, + "loss": 3.4109, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.801296611618599e-05, + "loss": 3.4102, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8004580168675474e-05, + "loss": 3.41, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996194221164954e-05, + "loss": 3.4087, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7987808273654434e-05, + "loss": 3.4066, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979438704947643e-05, + "loss": 3.4184, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971069136240855e-05, + "loss": 3.4218, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7962683188730335e-05, + "loss": 3.4232, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.795429724121982e-05, + "loss": 3.4113, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7945911293709295e-05, + "loss": 3.4132, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937525346198775e-05, + "loss": 3.4116, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929139398688255e-05, + "loss": 3.4149, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7920753451177735e-05, + "loss": 3.4145, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912367503667215e-05, + "loss": 3.4154, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7903997934960427e-05, + "loss": 3.4086, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7895611987449907e-05, + "loss": 3.4006, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7887226039939387e-05, + "loss": 3.4183, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7878840092428867e-05, + "loss": 3.4064, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870454144918347e-05, + "loss": 3.3945, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862084576211556e-05, + "loss": 3.4136, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7853698628701036e-05, + "loss": 3.4195, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.784531268119052e-05, + "loss": 3.4087, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.783692673368e-05, + "loss": 3.4023, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7828540786169476e-05, + "loss": 3.4119, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820154838658956e-05, + "loss": 3.4136, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7811768891148436e-05, + "loss": 3.4, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803382943637916e-05, + "loss": 3.4248, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779502975373486e-05, + "loss": 3.4215, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778664380622434e-05, + "loss": 3.407, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777825785871382e-05, + "loss": 3.4152, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7769871911203297e-05, + "loss": 3.405, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.776150234249651e-05, + "loss": 3.4181, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775311639498599e-05, + "loss": 3.4098, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.7744730447475473e-05, + "loss": 3.4093, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773634449996495e-05, + "loss": 3.4056, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772795855245443e-05, + "loss": 3.4153, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771957260494391e-05, + "loss": 3.4106, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771118665743339e-05, + "loss": 3.4074, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770280070992287e-05, + "loss": 3.4036, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694431141216082e-05, + "loss": 3.4102, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686061572509295e-05, + "loss": 3.4084, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767767562499877e-05, + "loss": 3.4181, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766928967748825e-05, + "loss": 3.412, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766090372997773e-05, + "loss": 3.4226, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765251778246721e-05, + "loss": 3.3976, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764413183495669e-05, + "loss": 3.4213, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7635762266249903e-05, + "loss": 3.415, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627376318739383e-05, + "loss": 3.4129, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7618990371228863e-05, + "loss": 3.4081, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7610604423718343e-05, + "loss": 3.411, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602218476207823e-05, + "loss": 3.4123, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7593848907501036e-05, + "loss": 3.4303, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585462959990516e-05, + "loss": 3.4017, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577077012479996e-05, + "loss": 3.4144, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568691064969476e-05, + "loss": 3.4095, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560305117458952e-05, + "loss": 3.4109, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7551919169948432e-05, + "loss": 3.4057, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543533222437912e-05, + "loss": 3.4173, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535163653731128e-05, + "loss": 3.4131, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7526777706220605e-05, + "loss": 3.4114, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518391758710084e-05, + "loss": 3.4114, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8628783226013184, + "eval_runtime": 306.5729, + "eval_samples_per_second": 1244.699, + "eval_steps_per_second": 38.898, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510022190003297e-05, + "loss": 3.405, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501636242492774e-05, + "loss": 3.4084, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493250294982257e-05, + "loss": 3.4161, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7484864347471737e-05, + "loss": 3.4166, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476478399961217e-05, + "loss": 3.4172, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468108831254426e-05, + "loss": 3.411, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7459722883743906e-05, + "loss": 3.4069, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451336936233386e-05, + "loss": 3.4083, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7442950988722866e-05, + "loss": 3.4097, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7434565041212346e-05, + "loss": 3.4213, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.742617909370183e-05, + "loss": 3.4124, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7417793146191306e-05, + "loss": 3.4141, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7409423577484518e-05, + "loss": 3.4207, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7401037629973998e-05, + "loss": 3.395, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7392651682463478e-05, + "loss": 3.4182, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384265734952958e-05, + "loss": 3.3961, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7375879787442438e-05, + "loss": 3.402, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736751021873565e-05, + "loss": 3.4032, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735912427122513e-05, + "loss": 3.4058, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7350738323714607e-05, + "loss": 3.4128, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7342352376204087e-05, + "loss": 3.4188, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7333966428693567e-05, + "loss": 3.4168, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732558048118305e-05, + "loss": 3.4049, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.731719453367253e-05, + "loss": 3.4042, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730882496496574e-05, + "loss": 3.4105, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730043901745522e-05, + "loss": 3.4052, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.72920530699447e-05, + "loss": 3.4009, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.728366712243418e-05, + "loss": 3.4179, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.727528117492366e-05, + "loss": 3.3974, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.726691160621687e-05, + "loss": 3.4073, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725852565870635e-05, + "loss": 3.3999, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.725013971119583e-05, + "loss": 3.416, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724175376368531e-05, + "loss": 3.4131, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233367816174788e-05, + "loss": 3.402, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7224981868664268e-05, + "loss": 3.4075, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.721659592115375e-05, + "loss": 3.4016, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720820997364323e-05, + "loss": 3.4126, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719984040493644e-05, + "loss": 3.4005, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7191470836229653e-05, + "loss": 3.3932, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183084888719133e-05, + "loss": 3.3968, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7174698941208613e-05, + "loss": 3.4088, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166312993698093e-05, + "loss": 3.4024, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7157943424991305e-05, + "loss": 3.4043, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149557477480785e-05, + "loss": 3.4048, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.714117152997026e-05, + "loss": 3.4063, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713278558245974e-05, + "loss": 3.4073, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.712439963494922e-05, + "loss": 3.4177, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116013687438705e-05, + "loss": 3.3991, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7107627739928185e-05, + "loss": 3.3803, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099258171221394e-05, + "loss": 3.4178, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7090872223710874e-05, + "loss": 3.4008, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7082486276200354e-05, + "loss": 3.4075, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074100328689834e-05, + "loss": 3.4047, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7065730759983046e-05, + "loss": 3.3996, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057344812472526e-05, + "loss": 3.3922, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7048958864962006e-05, + "loss": 3.3955, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040572917451486e-05, + "loss": 3.4178, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032186969940966e-05, + "loss": 3.4016, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7023817401234175e-05, + "loss": 3.4204, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701543145372366e-05, + "loss": 3.4024, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700704550621314e-05, + "loss": 3.3897, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998659558702615e-05, + "loss": 3.4153, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990273611192095e-05, + "loss": 3.3987, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6981904042485308e-05, + "loss": 3.3845, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6973518094974788e-05, + "loss": 3.4015, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965132147464267e-05, + "loss": 3.399, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6956746199953747e-05, + "loss": 3.3949, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6948360252443227e-05, + "loss": 3.3977, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6939974304932707e-05, + "loss": 3.3951, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6931588357422187e-05, + "loss": 3.4042, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923202409911667e-05, + "loss": 3.4106, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6914832841204876e-05, + "loss": 3.4001, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.690644689369436e-05, + "loss": 3.4112, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.689806094618384e-05, + "loss": 3.4082, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.688969137747705e-05, + "loss": 3.4184, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.688132180877026e-05, + "loss": 3.3979, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6872935861259738e-05, + "loss": 3.4184, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.686454991374922e-05, + "loss": 3.3976, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.68561639662387e-05, + "loss": 3.3978, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684777801872818e-05, + "loss": 3.4131, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.683939207121766e-05, + "loss": 3.4049, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683100612370714e-05, + "loss": 3.4129, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6822620176196618e-05, + "loss": 3.4131, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681425060748983e-05, + "loss": 3.3938, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6805864659979313e-05, + "loss": 3.3889, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797495091272522e-05, + "loss": 3.3972, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789109143762002e-05, + "loss": 3.413, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6780723196251482e-05, + "loss": 3.3982, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772337248740962e-05, + "loss": 3.4014, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6763951301230442e-05, + "loss": 3.404, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6755581732523655e-05, + "loss": 3.3909, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747195785013135e-05, + "loss": 3.4037, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6738809837502615e-05, + "loss": 3.3957, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.673042388999209e-05, + "loss": 3.4085, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.672203794248157e-05, + "loss": 3.4096, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6713668373774784e-05, + "loss": 3.4164, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705282426264267e-05, + "loss": 3.3991, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6696896478753744e-05, + "loss": 3.407, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688510531243224e-05, + "loss": 3.3979, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680124583732704e-05, + "loss": 3.4058, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6671755015025916e-05, + "loss": 3.406, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663369067515393e-05, + "loss": 3.4022, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6654983120004876e-05, + "loss": 3.401, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6646597172494356e-05, + "loss": 3.3912, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638211224983836e-05, + "loss": 3.4023, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6629841656277045e-05, + "loss": 3.3996, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621455708766525e-05, + "loss": 3.3811, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613069761256005e-05, + "loss": 3.4041, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6604683813745485e-05, + "loss": 3.4056, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596297866234968e-05, + "loss": 3.3989, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6587911918724448e-05, + "loss": 3.3928, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6579542350017657e-05, + "loss": 3.4015, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571156402507137e-05, + "loss": 3.4051, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6562770454996617e-05, + "loss": 3.3899, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554384507486097e-05, + "loss": 3.4155, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6545998559975577e-05, + "loss": 3.4087, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6537612612465057e-05, + "loss": 3.3998, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529226664954537e-05, + "loss": 3.4061, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652087347505148e-05, + "loss": 3.3925, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651248752754096e-05, + "loss": 3.4067, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.650410158003044e-05, + "loss": 3.3996, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6495715632519922e-05, + "loss": 3.3961, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.64873296850094e-05, + "loss": 3.3971, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647894373749888e-05, + "loss": 3.3995, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6470557789988358e-05, + "loss": 3.4053, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462171842477838e-05, + "loss": 3.3936, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6453802273771047e-05, + "loss": 3.3988, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.644541632626053e-05, + "loss": 3.3951, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437046757553743e-05, + "loss": 3.3974, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.642866081004322e-05, + "loss": 3.4095, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.64202748625327e-05, + "loss": 3.4039, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641188891502218e-05, + "loss": 3.4112, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640350296751166e-05, + "loss": 3.383, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639511702000114e-05, + "loss": 3.4148, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6386731072490623e-05, + "loss": 3.4055, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378361503783832e-05, + "loss": 3.4026, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6369975556273312e-05, + "loss": 3.3996, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6361589608762792e-05, + "loss": 3.3952, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353203661252272e-05, + "loss": 3.4048, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6344817713741752e-05, + "loss": 3.4181, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336431766231232e-05, + "loss": 3.3917, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328062197524444e-05, + "loss": 3.4054, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6319676250013924e-05, + "loss": 3.3977, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.63112903025034e-05, + "loss": 3.4007, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630290435499288e-05, + "loss": 3.3989, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629451840748236e-05, + "loss": 3.4032, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6286148838775577e-05, + "loss": 3.4038, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6277762891265053e-05, + "loss": 3.4025, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6269376943754533e-05, + "loss": 3.3993, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.863363027572632, + "eval_runtime": 309.6615, + "eval_samples_per_second": 1232.284, + "eval_steps_per_second": 38.51, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6260990996244013e-05, + "loss": 3.3921, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6252605048733493e-05, + "loss": 3.398, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6244235480026705e-05, + "loss": 3.406, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6235849532516185e-05, + "loss": 3.4037, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6227463585005665e-05, + "loss": 3.4078, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219077637495145e-05, + "loss": 3.4006, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6210708068788354e-05, + "loss": 3.396, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202322121277834e-05, + "loss": 3.4028, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6193936173767314e-05, + "loss": 3.3969, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6185550226256794e-05, + "loss": 3.4065, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6177164278746278e-05, + "loss": 3.4057, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6168778331235758e-05, + "loss": 3.4083, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6160408762528967e-05, + "loss": 3.4086, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152022815018447e-05, + "loss": 3.3859, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6143636867507927e-05, + "loss": 3.4075, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135250919997407e-05, + "loss": 3.3865, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6126864972486887e-05, + "loss": 3.3931, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6118479024976366e-05, + "loss": 3.3945, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6110093077465846e-05, + "loss": 3.3918, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6101707129955326e-05, + "loss": 3.3996, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093337561248535e-05, + "loss": 3.4123, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6084967992541748e-05, + "loss": 3.4013, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607658204503123e-05, + "loss": 3.3989, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068196097520708e-05, + "loss": 3.3979, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6059810150010188e-05, + "loss": 3.3984, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.60514405813034e-05, + "loss": 3.3941, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6043054633792877e-05, + "loss": 3.3875, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.603466868628236e-05, + "loss": 3.4071, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.602628273877184e-05, + "loss": 3.3907, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.601789679126132e-05, + "loss": 3.3946, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.600952722255453e-05, + "loss": 3.3931, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.600114127504401e-05, + "loss": 3.4052, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.599275532753349e-05, + "loss": 3.3962, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.598436938002297e-05, + "loss": 3.3992, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5975983432512452e-05, + "loss": 3.3972, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5967597485001932e-05, + "loss": 3.3936, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959211537491412e-05, + "loss": 3.403, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.595082558998089e-05, + "loss": 3.387, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.59424560212741e-05, + "loss": 3.386, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593407007376358e-05, + "loss": 3.3874, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.592568412625306e-05, + "loss": 3.3976, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.591729817874254e-05, + "loss": 3.3927, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5908928610035754e-05, + "loss": 3.3962, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5900542662525234e-05, + "loss": 3.3969, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.589215671501471e-05, + "loss": 3.3969, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588377076750419e-05, + "loss": 3.3948, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.587538481999367e-05, + "loss": 3.404, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5866998872483154e-05, + "loss": 3.3922, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5858612924972633e-05, + "loss": 3.3716, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5850243356265843e-05, + "loss": 3.4089, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5841857408755323e-05, + "loss": 3.3935, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5833471461244803e-05, + "loss": 3.3941, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5825085513734282e-05, + "loss": 3.3936, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5816715945027495e-05, + "loss": 3.391, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808329997516975e-05, + "loss": 3.3835, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5799944050006455e-05, + "loss": 3.3865, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5791558102495935e-05, + "loss": 3.4088, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783172154985415e-05, + "loss": 3.3915, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5774802586278624e-05, + "loss": 3.4109, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5766416638768107e-05, + "loss": 3.3912, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5758030691257587e-05, + "loss": 3.3763, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5749644743747067e-05, + "loss": 3.4063, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741258796236544e-05, + "loss": 3.3878, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5732889227529756e-05, + "loss": 3.3781, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5724503280019236e-05, + "loss": 3.3897, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5716117332508716e-05, + "loss": 3.3886, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5707731384998196e-05, + "loss": 3.3836, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5699345437487676e-05, + "loss": 3.3911, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5690959489977156e-05, + "loss": 3.3861, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5682573542466636e-05, + "loss": 3.3916, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674187594956116e-05, + "loss": 3.3995, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5665818026249325e-05, + "loss": 3.3916, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.565744845754254e-05, + "loss": 3.3994, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649062510032017e-05, + "loss": 3.3973, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5640676562521497e-05, + "loss": 3.4089, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5632290615010977e-05, + "loss": 3.3903, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5623921046304186e-05, + "loss": 3.4085, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.561553509879367e-05, + "loss": 3.3879, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.560714915128315e-05, + "loss": 3.3883, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.559876320377263e-05, + "loss": 3.3978, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.559039363506584e-05, + "loss": 3.3952, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.558200768755532e-05, + "loss": 3.4011, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.55736217400448e-05, + "loss": 3.4058, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.556523579253428e-05, + "loss": 3.3854, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5556849845023762e-05, + "loss": 3.376, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.554848027631697e-05, + "loss": 3.386, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.554009432880645e-05, + "loss": 3.4044, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.553170838129593e-05, + "loss": 3.3854, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552332243378541e-05, + "loss": 3.3954, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551493648627489e-05, + "loss": 3.3951, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5506566917568103e-05, + "loss": 3.3829, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5498180970057583e-05, + "loss": 3.3905, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5489795022547063e-05, + "loss": 3.3881, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5481409075036543e-05, + "loss": 3.3929, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.547302312752602e-05, + "loss": 3.4044, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5464653558819232e-05, + "loss": 3.4034, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5456267611308716e-05, + "loss": 3.3905, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5447881663798192e-05, + "loss": 3.3934, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5439495716287672e-05, + "loss": 3.3872, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.5431109768777152e-05, + "loss": 3.399, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5422740200070365e-05, + "loss": 3.3948, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.541435425255984e-05, + "loss": 3.3902, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5405968305049325e-05, + "loss": 3.3904, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397582357538804e-05, + "loss": 3.3807, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389196410028284e-05, + "loss": 3.394, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5380826841321494e-05, + "loss": 3.3898, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372440893810973e-05, + "loss": 3.3742, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364054946300453e-05, + "loss": 3.3934, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5355668998789933e-05, + "loss": 3.394, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5347283051279417e-05, + "loss": 3.3883, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5338897103768897e-05, + "loss": 3.386, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5330511156258373e-05, + "loss": 3.3892, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322141587551586e-05, + "loss": 3.3945, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5313755640041066e-05, + "loss": 3.3787, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5305369692530546e-05, + "loss": 3.4019, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5296983745020026e-05, + "loss": 3.3972, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5288597797509506e-05, + "loss": 3.3923, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280211849998986e-05, + "loss": 3.3967, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5271842281292198e-05, + "loss": 3.385, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5263456333781675e-05, + "loss": 3.3961, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255070386271156e-05, + "loss": 3.3934, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5246684438760636e-05, + "loss": 3.3869, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238298491250116e-05, + "loss": 3.3874, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5229912543739596e-05, + "loss": 3.3893, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221526596229078e-05, + "loss": 3.3937, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213140648718554e-05, + "loss": 3.3832, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5204771080011768e-05, + "loss": 3.3866, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5196385132501248e-05, + "loss": 3.3879, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188015563794458e-05, + "loss": 3.3842, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.517962961628394e-05, + "loss": 3.4016, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171243668773419e-05, + "loss": 3.3907, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5162857721262899e-05, + "loss": 3.4031, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5154471773752379e-05, + "loss": 3.373, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146085826241857e-05, + "loss": 3.4043, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5137699878731337e-05, + "loss": 3.39, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.512933031002455e-05, + "loss": 3.3982, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5120944362514028e-05, + "loss": 3.3908, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5112558415003508e-05, + "loss": 3.3809, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5104172467492988e-05, + "loss": 3.3971, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.509578651998247e-05, + "loss": 3.4135, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5087416951275679e-05, + "loss": 3.3766, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079031003765159e-05, + "loss": 3.395, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.507064505625464e-05, + "loss": 3.3879, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.506225910874412e-05, + "loss": 3.3884, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.50538731612336e-05, + "loss": 3.3909, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5045503592526811e-05, + "loss": 3.3945, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037117645016291e-05, + "loss": 3.3878, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5028731697505771e-05, + "loss": 3.3936, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.502034574999525e-05, + "loss": 3.3883, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.864386796951294, + "eval_runtime": 305.9588, + "eval_samples_per_second": 1247.197, + "eval_steps_per_second": 38.976, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5011992560092194e-05, + "loss": 3.394, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5003606612581674e-05, + "loss": 3.3834, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995220665071152e-05, + "loss": 3.3973, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4986834717560632e-05, + "loss": 3.3977, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978448770050112e-05, + "loss": 3.3927, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970079201343323e-05, + "loss": 3.3897, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4961693253832803e-05, + "loss": 3.3932, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953307306322285e-05, + "loss": 3.3896, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4944921358811765e-05, + "loss": 3.3884, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936535411301245e-05, + "loss": 3.3937, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928149463790725e-05, + "loss": 3.3992, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4919779895083935e-05, + "loss": 3.3955, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4911393947573415e-05, + "loss": 3.4008, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903008000062895e-05, + "loss": 3.377, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894622052552377e-05, + "loss": 3.3943, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886236105041857e-05, + "loss": 3.3786, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4877866536335066e-05, + "loss": 3.3841, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4869480588824548e-05, + "loss": 3.3842, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861094641314028e-05, + "loss": 3.3815, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4852708693803504e-05, + "loss": 3.3894, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4844322746292986e-05, + "loss": 3.4016, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4835936798782466e-05, + "loss": 3.3933, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4827550851271946e-05, + "loss": 3.3887, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819181282565156e-05, + "loss": 3.3886, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4810795335054636e-05, + "loss": 3.393, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4802425766347849e-05, + "loss": 3.383, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794039818837329e-05, + "loss": 3.3752, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4785653871326807e-05, + "loss": 3.3978, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4777267923816287e-05, + "loss": 3.3801, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4768898355109501e-05, + "loss": 3.3841, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4760512407598978e-05, + "loss": 3.3861, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4752126460088458e-05, + "loss": 3.3938, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.474374051257794e-05, + "loss": 3.3831, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.473535456506742e-05, + "loss": 3.3895, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4726984996360628e-05, + "loss": 3.3857, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.471859904885011e-05, + "loss": 3.3829, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.471021310133959e-05, + "loss": 3.3945, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.470182715382907e-05, + "loss": 3.3728, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469345758512228e-05, + "loss": 3.3808, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.468507163761176e-05, + "loss": 3.3772, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.467668569010124e-05, + "loss": 3.385, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.466829974259072e-05, + "loss": 3.381, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4659913795080202e-05, + "loss": 3.387, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651544226373411e-05, + "loss": 3.3875, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4643158278862893e-05, + "loss": 3.3865, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4634772331352373e-05, + "loss": 3.3846, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626386383841853e-05, + "loss": 3.3952, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4618000436331333e-05, + "loss": 3.3823, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4609614488820811e-05, + "loss": 3.3649, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601244920114024e-05, + "loss": 3.398, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4592858972603504e-05, + "loss": 3.3857, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4584473025092985e-05, + "loss": 3.3814, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576087077582462e-05, + "loss": 3.3851, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4567717508875674e-05, + "loss": 3.381, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4559331561365156e-05, + "loss": 3.3733, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4550945613854633e-05, + "loss": 3.3729, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542559666344113e-05, + "loss": 3.3982, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534173718833594e-05, + "loss": 3.3821, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4525804150126807e-05, + "loss": 3.4039, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4517418202616285e-05, + "loss": 3.3844, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509032255105765e-05, + "loss": 3.3621, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4500646307595245e-05, + "loss": 3.3939, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4492260360084725e-05, + "loss": 3.3792, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4483890791377936e-05, + "loss": 3.3715, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4475504843867416e-05, + "loss": 3.3766, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4467118896356896e-05, + "loss": 3.3815, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4458732948846375e-05, + "loss": 3.3739, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4450363380139586e-05, + "loss": 3.3821, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4441977432629066e-05, + "loss": 3.3716, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4433591485118548e-05, + "loss": 3.3855, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425205537608028e-05, + "loss": 3.3887, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4416819590097508e-05, + "loss": 3.3822, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4408450021390719e-05, + "loss": 3.3879, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400064073880199e-05, + "loss": 3.3882, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4391678126369678e-05, + "loss": 3.398, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383292178859158e-05, + "loss": 3.3825, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.437492261015237e-05, + "loss": 3.3947, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.436653666264185e-05, + "loss": 3.3824, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358150715131329e-05, + "loss": 3.3781, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.434976476762081e-05, + "loss": 3.3924, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.434139519891402e-05, + "loss": 3.3805, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333009251403502e-05, + "loss": 3.3921, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4324623303892981e-05, + "loss": 3.395, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4316237356382461e-05, + "loss": 3.3825, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.430785140887194e-05, + "loss": 3.3642, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299481840165152e-05, + "loss": 3.3754, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291095892654632e-05, + "loss": 3.3907, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.428270994514411e-05, + "loss": 3.3794, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.427432399763359e-05, + "loss": 3.3829, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.426593805012307e-05, + "loss": 3.3862, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.425755210261255e-05, + "loss": 3.3726, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4249166155102032e-05, + "loss": 3.3816, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4240780207591512e-05, + "loss": 3.3773, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232410638884721e-05, + "loss": 3.3849, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224024691374203e-05, + "loss": 3.3933, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4215638743863683e-05, + "loss": 3.3934, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4207252796353163e-05, + "loss": 3.3799, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4198866848842642e-05, + "loss": 3.3832, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4190497280135853e-05, + "loss": 3.3838, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182111332625333e-05, + "loss": 3.3822, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4173725385114813e-05, + "loss": 3.3877, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4165339437604291e-05, + "loss": 3.3825, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4156953490093771e-05, + "loss": 3.3776, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4148583921386984e-05, + "loss": 3.3748, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4140197973876466e-05, + "loss": 3.3852, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4131812026365942e-05, + "loss": 3.3792, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4123426078855422e-05, + "loss": 3.3648, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115056510148636e-05, + "loss": 3.3808, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4106670562638116e-05, + "loss": 3.3884, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4098284615127594e-05, + "loss": 3.3738, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4089898667617074e-05, + "loss": 3.3796, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081512720106554e-05, + "loss": 3.3758, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073143151399765e-05, + "loss": 3.3885, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4064757203889245e-05, + "loss": 3.3751, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4056371256378725e-05, + "loss": 3.3867, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4047985308868205e-05, + "loss": 3.3844, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4039599361357687e-05, + "loss": 3.3867, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4031213413847167e-05, + "loss": 3.3854, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4022827466336647e-05, + "loss": 3.3748, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014457897629857e-05, + "loss": 3.3842, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006071950119337e-05, + "loss": 3.384, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3997686002608817e-05, + "loss": 3.378, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3989300055098297e-05, + "loss": 3.3785, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3980930486391508e-05, + "loss": 3.3782, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3972544538880988e-05, + "loss": 3.3854, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964158591370468e-05, + "loss": 3.3766, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3955772643859946e-05, + "loss": 3.378, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947386696349426e-05, + "loss": 3.3726, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.393901712764264e-05, + "loss": 3.3746, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.393063118013212e-05, + "loss": 3.3914, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922245232621597e-05, + "loss": 3.3801, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3913859285111079e-05, + "loss": 3.3961, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905489716404291e-05, + "loss": 3.3669, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897103768893771e-05, + "loss": 3.3884, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.388871782138325e-05, + "loss": 3.3877, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.388033187387273e-05, + "loss": 3.3875, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3871945926362209e-05, + "loss": 3.3819, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.386357635765542e-05, + "loss": 3.3708, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.38551904101449e-05, + "loss": 3.3851, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.384680446263438e-05, + "loss": 3.3996, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.383841851512386e-05, + "loss": 3.3722, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830032567613341e-05, + "loss": 3.3837, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3821646620102821e-05, + "loss": 3.382, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.381327705139603e-05, + "loss": 3.3796, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3804891103885512e-05, + "loss": 3.3814, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3796505156374992e-05, + "loss": 3.3818, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788119208864472e-05, + "loss": 3.3769, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3779749640157683e-05, + "loss": 3.3841, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3771363692647163e-05, + "loss": 3.3801, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8647375106811523, + "eval_runtime": 303.8286, + "eval_samples_per_second": 1255.942, + "eval_steps_per_second": 39.249, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3762977745136643e-05, + "loss": 3.3763, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3754591797626123e-05, + "loss": 3.3733, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746222228919334e-05, + "loss": 3.3872, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3737836281408813e-05, + "loss": 3.3902, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729450333898295e-05, + "loss": 3.3793, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721064386387775e-05, + "loss": 3.3821, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3712694817680984e-05, + "loss": 3.3819, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3704308870170466e-05, + "loss": 3.3801, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3695922922659946e-05, + "loss": 3.3717, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3687536975149422e-05, + "loss": 3.3878, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3679151027638904e-05, + "loss": 3.3897, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3670781458932116e-05, + "loss": 3.3845, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3662395511421596e-05, + "loss": 3.3923, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654009563911075e-05, + "loss": 3.3624, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3645623616400555e-05, + "loss": 3.3819, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3637237668890035e-05, + "loss": 3.3686, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3628868100183249e-05, + "loss": 3.3771, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3620482152672725e-05, + "loss": 3.3733, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612096205162205e-05, + "loss": 3.3705, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3603710257651687e-05, + "loss": 3.3749, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3595324310141167e-05, + "loss": 3.3953, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3586954741434376e-05, + "loss": 3.3842, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3578568793923858e-05, + "loss": 3.377, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3570182846413338e-05, + "loss": 3.3774, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3561796898902818e-05, + "loss": 3.3859, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3553427330196028e-05, + "loss": 3.372, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545041382685508e-05, + "loss": 3.3661, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3536655435174988e-05, + "loss": 3.3864, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3528269487664468e-05, + "loss": 3.372, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3519899918957679e-05, + "loss": 3.3692, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3511513971447159e-05, + "loss": 3.3772, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.350312802393664e-05, + "loss": 3.3799, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.349474207642612e-05, + "loss": 3.3775, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.348637250771933e-05, + "loss": 3.3787, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3477986560208811e-05, + "loss": 3.3747, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3469600612698291e-05, + "loss": 3.3799, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461214665187771e-05, + "loss": 3.3835, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3452828717677251e-05, + "loss": 3.3605, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3444459148970462e-05, + "loss": 3.3701, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3436073201459942e-05, + "loss": 3.3696, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3427687253949422e-05, + "loss": 3.3711, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3419301306438904e-05, + "loss": 3.3732, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3410931737732113e-05, + "loss": 3.3795, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3402545790221593e-05, + "loss": 3.374, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394159842711074e-05, + "loss": 3.3793, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.338577389520055e-05, + "loss": 3.3754, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.337738794769003e-05, + "loss": 3.3827, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3369002000179512e-05, + "loss": 3.3738, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3360616052668992e-05, + "loss": 3.3547, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3352246483962203e-05, + "loss": 3.3861, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3343860536451683e-05, + "loss": 3.3768, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3335474588941163e-05, + "loss": 3.3763, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3327088641430643e-05, + "loss": 3.3722, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3318702693920123e-05, + "loss": 3.3716, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3310333125213334e-05, + "loss": 3.3642, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3301947177702814e-05, + "loss": 3.3667, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3293561230192295e-05, + "loss": 3.3853, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285175282681775e-05, + "loss": 3.37, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3276805713974984e-05, + "loss": 3.3925, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268419766464466e-05, + "loss": 3.3806, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260033818953946e-05, + "loss": 3.3551, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3251647871443426e-05, + "loss": 3.3824, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243278302736637e-05, + "loss": 3.3659, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3234892355226117e-05, + "loss": 3.3641, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226506407715597e-05, + "loss": 3.3659, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3218120460205077e-05, + "loss": 3.3694, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3209734512694558e-05, + "loss": 3.3696, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3201364943987767e-05, + "loss": 3.3729, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3192978996477249e-05, + "loss": 3.3617, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3184593048966729e-05, + "loss": 3.3749, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176207101456206e-05, + "loss": 3.3795, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.316783753274942e-05, + "loss": 3.375, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.31594515852389e-05, + "loss": 3.3759, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.315106563772838e-05, + "loss": 3.3779, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3142679690217858e-05, + "loss": 3.389, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.313431012151107e-05, + "loss": 3.3705, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.312592417400055e-05, + "loss": 3.3821, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3117538226490029e-05, + "loss": 3.3779, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3109152278979509e-05, + "loss": 3.3699, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3100766331468989e-05, + "loss": 3.3805, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3092396762762201e-05, + "loss": 3.3724, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.308401081525168e-05, + "loss": 3.383, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.307562486774116e-05, + "loss": 3.3844, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.306723892023064e-05, + "loss": 3.3722, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3058869351523853e-05, + "loss": 3.3562, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.305048340401333e-05, + "loss": 3.3664, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3042097456502812e-05, + "loss": 3.3789, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3033711508992292e-05, + "loss": 3.3725, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.30253419402855e-05, + "loss": 3.371, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3016955992774982e-05, + "loss": 3.3738, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3008570045264462e-05, + "loss": 3.3665, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3000184097753942e-05, + "loss": 3.3683, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2991798150243422e-05, + "loss": 3.3709, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2983428581536633e-05, + "loss": 3.3743, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975042634026113e-05, + "loss": 3.3835, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2966656686515593e-05, + "loss": 3.3869, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2958270739005075e-05, + "loss": 3.3658, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2949884791494554e-05, + "loss": 3.3737, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2941498843984034e-05, + "loss": 3.3761, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933129275277245e-05, + "loss": 3.3726, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2924743327766725e-05, + "loss": 3.3774, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2916357380256205e-05, + "loss": 3.3729, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2907971432745683e-05, + "loss": 3.3666, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2899585485235163e-05, + "loss": 3.3654, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2891215916528376e-05, + "loss": 3.377, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2882829969017857e-05, + "loss": 3.3696, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2874444021507334e-05, + "loss": 3.3544, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866058073996814e-05, + "loss": 3.3742, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2857688505290028e-05, + "loss": 3.3759, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2849302557779508e-05, + "loss": 3.3661, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2840916610268985e-05, + "loss": 3.3675, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2832530662758466e-05, + "loss": 3.3654, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2824161094051679e-05, + "loss": 3.3767, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2815775146541157e-05, + "loss": 3.3687, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2807389199030637e-05, + "loss": 3.3732, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2799003251520117e-05, + "loss": 3.3801, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2790617304009597e-05, + "loss": 3.3773, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2782231356499077e-05, + "loss": 3.3742, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2773861787792288e-05, + "loss": 3.3677, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2765475840281768e-05, + "loss": 3.3748, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2757089892771248e-05, + "loss": 3.3737, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.274870394526073e-05, + "loss": 3.3659, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2740334376553938e-05, + "loss": 3.3696, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.273194842904342e-05, + "loss": 3.3682, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.27235624815329e-05, + "loss": 3.3745, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.271517653402238e-05, + "loss": 3.3644, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.270680696531559e-05, + "loss": 3.3706, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.269842101780507e-05, + "loss": 3.3604, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.269003507029455e-05, + "loss": 3.3676, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.268164912278403e-05, + "loss": 3.382, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2673279554077241e-05, + "loss": 3.3705, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2664893606566721e-05, + "loss": 3.3851, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656507659056201e-05, + "loss": 3.3561, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648121711545683e-05, + "loss": 3.3763, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2639735764035163e-05, + "loss": 3.38, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2631366195328374e-05, + "loss": 3.3746, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2622980247817854e-05, + "loss": 3.3718, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2614594300307334e-05, + "loss": 3.3618, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606208352796812e-05, + "loss": 3.3793, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2597838784090024e-05, + "loss": 3.3903, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589452836579504e-05, + "loss": 3.3638, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2581066889068984e-05, + "loss": 3.3691, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2572680941558463e-05, + "loss": 3.3753, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2564294994047942e-05, + "loss": 3.3692, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2555925425341155e-05, + "loss": 3.369, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2547539477830633e-05, + "loss": 3.3755, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2539153530320113e-05, + "loss": 3.3639, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2530767582809593e-05, + "loss": 3.3792, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2522381635299075e-05, + "loss": 3.3644, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.866408348083496, + "eval_runtime": 310.4277, + "eval_samples_per_second": 1229.243, + "eval_steps_per_second": 38.415, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514028445396016e-05, + "loss": 3.3739, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2505642497885498e-05, + "loss": 3.3658, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2497256550374976e-05, + "loss": 3.3751, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2488870602864456e-05, + "loss": 3.3836, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2480484655353936e-05, + "loss": 3.3711, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472098707843416e-05, + "loss": 3.3728, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2463729139136627e-05, + "loss": 3.3704, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2455343191626109e-05, + "loss": 3.3693, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2446957244115589e-05, + "loss": 3.3625, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2438571296605067e-05, + "loss": 3.3828, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2430185349094547e-05, + "loss": 3.3764, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.242181578038776e-05, + "loss": 3.3776, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.241342983287724e-05, + "loss": 3.3839, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.240504388536672e-05, + "loss": 3.3512, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2396657937856199e-05, + "loss": 3.374, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2388271990345679e-05, + "loss": 3.3608, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.237990242163889e-05, + "loss": 3.3684, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.237151647412837e-05, + "loss": 3.3595, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.236313052661785e-05, + "loss": 3.3658, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.235474457910733e-05, + "loss": 3.3627, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.234635863159681e-05, + "loss": 3.3855, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.233798906289002e-05, + "loss": 3.3753, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.23296031153795e-05, + "loss": 3.3683, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.232121716786898e-05, + "loss": 3.3688, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.231283122035846e-05, + "loss": 3.3786, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2304461651651671e-05, + "loss": 3.3606, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2296075704141153e-05, + "loss": 3.3578, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2287689756630631e-05, + "loss": 3.3775, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2279303809120111e-05, + "loss": 3.3635, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2270934240413324e-05, + "loss": 3.3604, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2262548292902803e-05, + "loss": 3.3655, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2254162345392282e-05, + "loss": 3.3685, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2245776397881763e-05, + "loss": 3.3719, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2237406829174974e-05, + "loss": 3.3656, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229020881664454e-05, + "loss": 3.363, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2220634934153934e-05, + "loss": 3.3748, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2212248986643414e-05, + "loss": 3.3724, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2203863039132894e-05, + "loss": 3.3507, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2195493470426105e-05, + "loss": 3.3639, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2187107522915585e-05, + "loss": 3.3568, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2178721575405065e-05, + "loss": 3.3594, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2170335627894545e-05, + "loss": 3.3659, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2161966059187755e-05, + "loss": 3.3715, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2153580111677235e-05, + "loss": 3.3606, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2145194164166717e-05, + "loss": 3.3651, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2136808216656195e-05, + "loss": 3.3711, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2128438647949406e-05, + "loss": 3.3707, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2120052700438888e-05, + "loss": 3.3666, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2111666752928368e-05, + "loss": 3.3465, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2103280805417846e-05, + "loss": 3.3724, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2094911236711058e-05, + "loss": 3.3709, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2086525289200538e-05, + "loss": 3.3634, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078139341690017e-05, + "loss": 3.3627, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2069753394179498e-05, + "loss": 3.3657, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2061383825472709e-05, + "loss": 3.3483, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2052997877962189e-05, + "loss": 3.3581, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2044611930451669e-05, + "loss": 3.3763, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2036225982941149e-05, + "loss": 3.3641, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.202785641423436e-05, + "loss": 3.3791, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2019470466723841e-05, + "loss": 3.3696, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.201108451921332e-05, + "loss": 3.3489, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.20026985717028e-05, + "loss": 3.373, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1994329002996012e-05, + "loss": 3.3549, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.198594305548549e-05, + "loss": 3.3538, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.197755710797497e-05, + "loss": 3.3555, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969171160464452e-05, + "loss": 3.3653, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1960785212953932e-05, + "loss": 3.3571, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1952415644247143e-05, + "loss": 3.3579, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.1944029696736623e-05, + "loss": 3.3516, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1935643749226103e-05, + "loss": 3.3685, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.1927257801715581e-05, + "loss": 3.3687, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.1918888233008793e-05, + "loss": 3.3676, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.1910502285498273e-05, + "loss": 3.3649, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1902116337987753e-05, + "loss": 3.3693, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1893730390477233e-05, + "loss": 3.3756, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1885344442966713e-05, + "loss": 3.3676, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1876974874259924e-05, + "loss": 3.3675, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1868588926749404e-05, + "loss": 3.3664, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.1860202979238884e-05, + "loss": 3.3643, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.1851817031728364e-05, + "loss": 3.3694, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.1843447463021576e-05, + "loss": 3.3637, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835061515511055e-05, + "loss": 3.3703, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1826675568000535e-05, + "loss": 3.3777, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1818289620490015e-05, + "loss": 3.3637, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1809903672979494e-05, + "loss": 3.3432, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1801534104272705e-05, + "loss": 3.3606, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1793148156762187e-05, + "loss": 3.3697, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1784762209251667e-05, + "loss": 3.3614, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1776376261741145e-05, + "loss": 3.3633, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1767990314230625e-05, + "loss": 3.367, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1759620745523838e-05, + "loss": 3.3529, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1751234798013318e-05, + "loss": 3.3595, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1742848850502797e-05, + "loss": 3.3596, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1734462902992277e-05, + "loss": 3.3684, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1726093334285488e-05, + "loss": 3.3687, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1717707386774968e-05, + "loss": 3.3784, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1709321439264448e-05, + "loss": 3.3536, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1700935491753928e-05, + "loss": 3.3638, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1692549544243408e-05, + "loss": 3.3678, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684179975536619e-05, + "loss": 3.3644, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1675794028026099e-05, + "loss": 3.3728, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1667408080515579e-05, + "loss": 3.3574, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659022133005059e-05, + "loss": 3.3566, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1650636185494539e-05, + "loss": 3.3559, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1642266616787751e-05, + "loss": 3.3703, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1633880669277231e-05, + "loss": 3.3584, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.162549472176671e-05, + "loss": 3.3487, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.161710877425619e-05, + "loss": 3.361, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1608722826745671e-05, + "loss": 3.3637, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1600353258038882e-05, + "loss": 3.3579, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.159196731052836e-05, + "loss": 3.3628, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1583581363017842e-05, + "loss": 3.3502, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1575195415507322e-05, + "loss": 3.3702, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1566825846800532e-05, + "loss": 3.3587, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1558439899290012e-05, + "loss": 3.3616, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1550053951779492e-05, + "loss": 3.3709, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1541668004268972e-05, + "loss": 3.3711, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1533282056758452e-05, + "loss": 3.3616, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1524912488051663e-05, + "loss": 3.3583, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1516526540541143e-05, + "loss": 3.3643, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1508140593030623e-05, + "loss": 3.3623, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1499754645520103e-05, + "loss": 3.3555, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1491385076813314e-05, + "loss": 3.3639, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1482999129302795e-05, + "loss": 3.3576, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1474613181792274e-05, + "loss": 3.361, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1466227234281754e-05, + "loss": 3.3562, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1457841286771234e-05, + "loss": 3.3609, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1449455339260713e-05, + "loss": 3.3552, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1441085770553924e-05, + "loss": 3.357, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1432699823043406e-05, + "loss": 3.3721, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1424313875532886e-05, + "loss": 3.3645, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1415927928022364e-05, + "loss": 3.3731, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1407558359315577e-05, + "loss": 3.3508, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1399172411805057e-05, + "loss": 3.3654, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1390786464294537e-05, + "loss": 3.3706, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1382400516784015e-05, + "loss": 3.3659, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374030948077227e-05, + "loss": 3.3562, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1365645000566707e-05, + "loss": 3.3524, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1357259053056187e-05, + "loss": 3.3705, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1348873105545667e-05, + "loss": 3.3813, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1340503536838878e-05, + "loss": 3.3556, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.133211758932836e-05, + "loss": 3.3586, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1323731641817838e-05, + "loss": 3.3646, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1315345694307318e-05, + "loss": 3.3583, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.130697612560053e-05, + "loss": 3.358, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1298590178090009e-05, + "loss": 3.366, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1290204230579489e-05, + "loss": 3.3533, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1281818283068968e-05, + "loss": 3.3727, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.127343233555845e-05, + "loss": 3.3534, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8687448501586914, + "eval_runtime": 305.4777, + "eval_samples_per_second": 1249.161, + "eval_steps_per_second": 39.037, + "step": 2365920 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.65353729543177e+18, + "trial_name": null, + "trial_params": null +}