diff --git "a/checkpoint-1450080/trainer_state.json" "b/checkpoint-1450080/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1450080/trainer_state.json" @@ -0,0 +1,17169 @@ +{ + "best_metric": 3.845747232437134, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/2/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1450080, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9575, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8163, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1923, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9769, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8209, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7141, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6128, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5406, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.459, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4141, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3519, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3101, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2647, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2178, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1785, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1386, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1091, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0779, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0521, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0219, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0079, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.98, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9504, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9376, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9266, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8884, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8712, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.859, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8438, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8202, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.804, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7996, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7845, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7783, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7637, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7439, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7372, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7037, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.711, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6823, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6828, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6697, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6727, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6507, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6475, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6369, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6209, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6323, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5989, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5909, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6016, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.598, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5725, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5671, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5663, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5485, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5686, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5298, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5394, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5305, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.515, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5236, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5041, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.5024, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4918, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5076, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4788, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4822, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4619, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4715, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4816, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4713, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4535, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4665, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4661, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4423, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4472, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4286, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4195, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.417, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4191, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4248, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4312, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4192, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3957, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4024, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4029, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3938, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3876, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.383, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3772, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3863, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3715, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3788, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3683, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.368, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.3522, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.3541, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3515, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.3581, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3588, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3347, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3427, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3336, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.337, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3251, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3227, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3279, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3178, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3161, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3094, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3053, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3189, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3045, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.305, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3091, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3136, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2986, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2873, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2933, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2994, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2851, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.284, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2826, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2827, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2755, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2801, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2719, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.2742, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2663, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2841, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2673, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2602, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2543, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2647, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2594, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.266, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2528, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2583, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2514, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2514, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2431, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2512, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2393, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2275, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2481, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2362, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2334, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2397, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2236, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.196439266204834, + "eval_runtime": 309.473, + "eval_samples_per_second": 1233.035, + "eval_steps_per_second": 38.533, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2129, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2179, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2222, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2174, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2258, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.2104, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.2133, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2036, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2189, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.1999, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.199, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2005, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1963, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1888, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.189, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1737, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1849, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1797, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1727, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.2005, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1775, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1798, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1756, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1893, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.162, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1664, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.169, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1677, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1568, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1577, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1647, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1673, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1675, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1581, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1516, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1619, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1349, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1557, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1332, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1436, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1384, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.148, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1409, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1353, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1402, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1325, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1446, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1184, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.1189, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1362, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1353, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.121, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1154, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1243, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1074, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1329, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1113, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1208, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1154, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1034, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1184, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.104, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.1039, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.0994, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1166, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.0986, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.0993, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.0893, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0989, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1119, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1059, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.0958, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.107, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1093, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.0949, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0996, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0892, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0808, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0827, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.086, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807198549755203e-05, + "loss": 4.0913, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.1052, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.095, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0718, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.8038458086313677e-05, + "loss": 4.0822, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.0873, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0833, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0743, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0733, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0748, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0787, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0708, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0804, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.073, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.0775, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0609, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0701, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0661, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0726, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.0729, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0603, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.0616, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0621, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.0639, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0503, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.0549, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0632, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0515, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.0513, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0477, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0453, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0653, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0457, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795363881330984e-05, + "loss": 4.0568, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0522, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0664, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777022241760315e-05, + "loss": 4.0522, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0384, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0475, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450645750716e-05, + "loss": 4.0526, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0372, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.0446, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0379, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.0496, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0348, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0468, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0389, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0422, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0327, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0555, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765286828886707e-05, + "loss": 4.0427, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0289, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0308, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0373, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761934087762872e-05, + "loss": 4.0389, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0461, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0297, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.0397, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758581346639037e-05, + "loss": 4.0307, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0368, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0298, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0345, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.0268, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0195, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.04, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0292, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0257, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0288, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0182, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.027224063873291, + "eval_runtime": 305.3242, + "eval_samples_per_second": 1249.789, + "eval_steps_per_second": 39.057, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0098, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.0111, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.0251, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0158, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0294, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.0134, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0152, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 4.0082, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0265, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0078, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0053, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0077, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0081, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0003, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 4.0039, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 3.9932, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 3.9976, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 3.9945, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9884, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0224, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 3.9986, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 3.9929, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 3.9999, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0076, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9851, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9938, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 3.9928, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9965, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9811, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9873, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9894, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.997, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722536513267159e-05, + "loss": 4.0023, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721697918516107e-05, + "loss": 3.9893, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720859323765055e-05, + "loss": 3.9825, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720020729014003e-05, + "loss": 3.9935, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719183772143324e-05, + "loss": 3.9746, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718345177392272e-05, + "loss": 3.9892, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.9705, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9765, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9787, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714992436268437e-05, + "loss": 3.9888, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714153841517385e-05, + "loss": 3.9801, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9762, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9791, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116396951446025e-05, + "loss": 3.9752, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7108011003935505e-05, + "loss": 3.984, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.9636, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9604, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082869540207674e-05, + "loss": 3.9823, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074483592697154e-05, + "loss": 3.9769, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9664, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9672, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704934212896932e-05, + "loss": 3.9708, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70409561814588e-05, + "loss": 3.9555, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703257023394828e-05, + "loss": 3.9779, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702418428643776e-05, + "loss": 3.9625, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701581471773098e-05, + "loss": 3.9699, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700742877022045e-05, + "loss": 3.9636, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699904282270993e-05, + "loss": 3.9611, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699065687519941e-05, + "loss": 3.9607, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698228730649263e-05, + "loss": 3.9604, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.69739013589821e-05, + "loss": 3.956, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696551541147158e-05, + "loss": 3.9535, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695712946396106e-05, + "loss": 3.9703, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694875989525428e-05, + "loss": 3.9555, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694037394774376e-05, + "loss": 3.955, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693198800023324e-05, + "loss": 3.9474, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692360205272272e-05, + "loss": 3.954, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915232484015926e-05, + "loss": 3.9702, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906846536505406e-05, + "loss": 3.9651, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898460588994886e-05, + "loss": 3.9573, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890074641484366e-05, + "loss": 3.9658, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881705072777575e-05, + "loss": 3.9692, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873319125267055e-05, + "loss": 3.9518, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864933177756535e-05, + "loss": 3.9608, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856547230246015e-05, + "loss": 3.9545, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684817766153923e-05, + "loss": 3.9457, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683979171402871e-05, + "loss": 3.9528, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683140576651819e-05, + "loss": 3.9461, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682301981900767e-05, + "loss": 3.9568, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681465025030088e-05, + "loss": 3.9639, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680626430279036e-05, + "loss": 3.9617, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679787835527984e-05, + "loss": 3.9356, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678949240776932e-05, + "loss": 3.9517, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678112283906253e-05, + "loss": 3.9515, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677273689155201e-05, + "loss": 3.9505, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676435094404149e-05, + "loss": 3.9458, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675596499653097e-05, + "loss": 3.9379, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747595427824184e-05, + "loss": 3.9477, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739209480313664e-05, + "loss": 3.9448, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730823532803144e-05, + "loss": 3.9417, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722437585292624e-05, + "loss": 3.9501, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671406801658583e-05, + "loss": 3.9414, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670568206907531e-05, + "loss": 3.9504, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669729612156479e-05, + "loss": 3.9367, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668891017405427e-05, + "loss": 3.9379, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668054060534748e-05, + "loss": 3.9386, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667215465783696e-05, + "loss": 3.949, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666376871032644e-05, + "loss": 3.9474, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665538276281592e-05, + "loss": 3.9359, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664701319410914e-05, + "loss": 3.9364, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663862724659862e-05, + "loss": 3.9363, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66302412990881e-05, + "loss": 3.9415, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662187173038131e-05, + "loss": 3.9242, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661348578287079e-05, + "loss": 3.9287, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660509983536027e-05, + "loss": 3.9433, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659671388784975e-05, + "loss": 3.9341, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588344319142956e-05, + "loss": 3.9266, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579958371632436e-05, + "loss": 3.9268, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571572424121916e-05, + "loss": 3.9248, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6563186476611396e-05, + "loss": 3.9405, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554800529100876e-05, + "loss": 3.9306, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546414581590356e-05, + "loss": 3.9319, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538028634079836e-05, + "loss": 3.9336, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652964268656932e-05, + "loss": 3.9483, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652127311786253e-05, + "loss": 3.9361, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651288717035201e-05, + "loss": 3.9203, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650450122284149e-05, + "loss": 3.9299, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649611527533097e-05, + "loss": 3.9321, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648774570662418e-05, + "loss": 3.9229, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647935975911366e-05, + "loss": 3.9252, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647097381160314e-05, + "loss": 3.9213, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646258786409262e-05, + "loss": 3.9332, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645421829538583e-05, + "loss": 3.9178, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644583234787531e-05, + "loss": 3.9335, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643744640036479e-05, + "loss": 3.9183, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429060452854276e-05, + "loss": 3.9283, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420690884147485e-05, + "loss": 3.9182, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412304936636965e-05, + "loss": 3.9396, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403918989126445e-05, + "loss": 3.9309, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395549420419654e-05, + "loss": 3.9203, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387163472909134e-05, + "loss": 3.9135, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378777525398614e-05, + "loss": 3.9265, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370391577888094e-05, + "loss": 3.9232, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6362005630377574e-05, + "loss": 3.9341, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635363606167078e-05, + "loss": 3.9164, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345266492964e-05, + "loss": 3.93, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633688054545348e-05, + "loss": 3.9227, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632849459794296e-05, + "loss": 3.9316, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632010865043244e-05, + "loss": 3.9156, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631172270292192e-05, + "loss": 3.9236, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.63033367554114e-05, + "loss": 3.9186, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629495080790088e-05, + "loss": 3.9105, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628656486039035e-05, + "loss": 3.9276, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627819529168357e-05, + "loss": 3.9248, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626980934417305e-05, + "loss": 3.9113, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626142339666253e-05, + "loss": 3.9212, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6253037449152e-05, + "loss": 3.91, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.953357696533203, + "eval_runtime": 301.6217, + "eval_samples_per_second": 1265.131, + "eval_steps_per_second": 39.536, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244667880445217e-05, + "loss": 3.9062, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236281932934697e-05, + "loss": 3.9047, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227895985424176e-05, + "loss": 3.9162, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219510037913656e-05, + "loss": 3.9135, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621114046920687e-05, + "loss": 3.9271, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620275452169635e-05, + "loss": 3.9031, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194368574185825e-05, + "loss": 3.9113, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185982626675305e-05, + "loss": 3.9041, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617761305796852e-05, + "loss": 3.925, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169227110458e-05, + "loss": 3.9036, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616085754175121e-05, + "loss": 3.8994, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615247159424069e-05, + "loss": 3.9092, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614408564673017e-05, + "loss": 3.9013, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613569969921965e-05, + "loss": 3.8995, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612731375170913e-05, + "loss": 3.9013, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118944183002346e-05, + "loss": 3.8948, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110558235491826e-05, + "loss": 3.8934, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.61021722879813e-05, + "loss": 3.8953, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609378634047078e-05, + "loss": 3.8902, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608540039296026e-05, + "loss": 3.92, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607701444544974e-05, + "loss": 3.8973, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606862849793922e-05, + "loss": 3.8964, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.60602425504287e-05, + "loss": 3.9002, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605187298172191e-05, + "loss": 3.9047, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604348703421139e-05, + "loss": 3.8897, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035101086700875e-05, + "loss": 3.897, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026715139190355e-05, + "loss": 3.893, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018345570483564e-05, + "loss": 3.8964, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009959622973044e-05, + "loss": 3.8854, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001573675462524e-05, + "loss": 3.8903, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993187727952004e-05, + "loss": 3.8954, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598481815924521e-05, + "loss": 3.899, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597643221173469e-05, + "loss": 3.9051, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.59680626430279e-05, + "loss": 3.8968, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595967669551738e-05, + "loss": 3.8849, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595129074800686e-05, + "loss": 3.8964, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594290480049634e-05, + "loss": 3.883, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593451885298583e-05, + "loss": 3.8916, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592613290547531e-05, + "loss": 3.8777, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591776333676852e-05, + "loss": 3.8825, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909377389258e-05, + "loss": 3.8812, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590099144174748e-05, + "loss": 3.898, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589260549423696e-05, + "loss": 3.8904, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588421954672644e-05, + "loss": 3.8821, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587583359921592e-05, + "loss": 3.886, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.58674476517054e-05, + "loss": 3.8833, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585906170419488e-05, + "loss": 3.8889, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850692135488086e-05, + "loss": 3.873, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842322566781295e-05, + "loss": 3.8667, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833936619270775e-05, + "loss": 3.8904, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582555067176026e-05, + "loss": 3.8861, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581716472424974e-05, + "loss": 3.8723, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580877877673922e-05, + "loss": 3.8786, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580040920803243e-05, + "loss": 3.8827, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579202326052191e-05, + "loss": 3.8661, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578363731301139e-05, + "loss": 3.8822, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577525136550087e-05, + "loss": 3.8713, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576688179679408e-05, + "loss": 3.8842, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575849584928356e-05, + "loss": 3.8719, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575010990177304e-05, + "loss": 3.8804, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574172395426252e-05, + "loss": 3.8679, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733338006752e-05, + "loss": 3.8745, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572495205924148e-05, + "loss": 3.8641, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716582490534696e-05, + "loss": 3.8689, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708196543024176e-05, + "loss": 3.8849, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699810595513656e-05, + "loss": 3.8659, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691424648003135e-05, + "loss": 3.8705, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568303870049261e-05, + "loss": 3.8608, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567465275298209e-05, + "loss": 3.8688, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566626680547157e-05, + "loss": 3.8824, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565789723676478e-05, + "loss": 3.8771, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649527668057994e-05, + "loss": 3.8752, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641141720547474e-05, + "loss": 3.8805, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632755773036953e-05, + "loss": 3.8786, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624369825526433e-05, + "loss": 3.8691, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561600025681965e-05, + "loss": 3.8746, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560761430930913e-05, + "loss": 3.8719, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559922836179861e-05, + "loss": 3.863, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559084241428808e-05, + "loss": 3.8651, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.55824728455813e-05, + "loss": 3.8636, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557408689807078e-05, + "loss": 3.8696, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556570095056025e-05, + "loss": 3.8793, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555731500304973e-05, + "loss": 3.8767, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554892905553921e-05, + "loss": 3.8517, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554055948683243e-05, + "loss": 3.8726, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553217353932191e-05, + "loss": 3.8671, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552378759181139e-05, + "loss": 3.8674, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551540164430087e-05, + "loss": 3.8622, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550701569679035e-05, + "loss": 3.8541, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498646128083556e-05, + "loss": 3.8689, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490260180573036e-05, + "loss": 3.861, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481874233062516e-05, + "loss": 3.8615, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473488285551996e-05, + "loss": 3.8657, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465102338041476e-05, + "loss": 3.8605, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456732769334685e-05, + "loss": 3.8724, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448346821824165e-05, + "loss": 3.8577, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439960874313645e-05, + "loss": 3.8544, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431574926803125e-05, + "loss": 3.8573, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542320535809634e-05, + "loss": 3.8709, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541481941058582e-05, + "loss": 3.8635, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.54064334630753e-05, + "loss": 3.8569, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539804751556478e-05, + "loss": 3.8548, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538966156805426e-05, + "loss": 3.8575, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538129199934747e-05, + "loss": 3.8659, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537290605183695e-05, + "loss": 3.8505, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536452010432643e-05, + "loss": 3.8445, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535613415681591e-05, + "loss": 3.8643, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534774820930539e-05, + "loss": 3.852, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.53393786405986e-05, + "loss": 3.8482, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533099269308808e-05, + "loss": 3.8463, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532260674557756e-05, + "loss": 3.8507, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314220798067045e-05, + "loss": 3.8642, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305834850556525e-05, + "loss": 3.8487, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297465281849734e-05, + "loss": 3.8543, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289079334339214e-05, + "loss": 3.8568, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280693386828694e-05, + "loss": 3.8679, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272307439318174e-05, + "loss": 3.8627, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526393787061138e-05, + "loss": 3.8415, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525555192310086e-05, + "loss": 3.8542, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524716597559034e-05, + "loss": 3.8508, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523878002807982e-05, + "loss": 3.8501, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.52303940805693e-05, + "loss": 3.8499, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522200813305878e-05, + "loss": 3.844, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213638564352e-05, + "loss": 3.8566, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520525261684148e-05, + "loss": 3.8446, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519686666933096e-05, + "loss": 3.8557, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518848072182044e-05, + "loss": 3.8461, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518009477430992e-05, + "loss": 3.8532, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517172520560313e-05, + "loss": 3.8416, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516333925809261e-05, + "loss": 3.8682, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515495331058209e-05, + "loss": 3.8497, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514656736307156e-05, + "loss": 3.8494, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513819779436478e-05, + "loss": 3.8377, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512981184685426e-05, + "loss": 3.8546, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512142589934374e-05, + "loss": 3.8474, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511303995183322e-05, + "loss": 3.8576, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510467038312643e-05, + "loss": 3.8435, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509628443561591e-05, + "loss": 3.8546, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508789848810539e-05, + "loss": 3.8506, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079512540594866e-05, + "loss": 3.8611, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507114297188808e-05, + "loss": 3.8391, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506275702437756e-05, + "loss": 3.8524, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054371076867035e-05, + "loss": 3.845, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045985129356515e-05, + "loss": 3.8419, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037599181845995e-05, + "loss": 3.8521, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029213234335474e-05, + "loss": 3.8522, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020827286824954e-05, + "loss": 3.842, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501245771811817e-05, + "loss": 3.8457, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500407177060765e-05, + "loss": 3.8414, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.911860942840576, + "eval_runtime": 302.0292, + "eval_samples_per_second": 1263.424, + "eval_steps_per_second": 39.483, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499568582309713e-05, + "loss": 3.8349, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498729987558661e-05, + "loss": 3.831, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497891392807609e-05, + "loss": 3.8433, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497052798056557e-05, + "loss": 3.842, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496215841185878e-05, + "loss": 3.8543, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495377246434826e-05, + "loss": 3.8353, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494538651683774e-05, + "loss": 3.8369, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493700056932722e-05, + "loss": 3.8346, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.49286146218167e-05, + "loss": 3.8518, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492022867430618e-05, + "loss": 3.8372, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491185910559939e-05, + "loss": 3.8278, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490347315808887e-05, + "loss": 3.8365, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895087210578355e-05, + "loss": 3.8304, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886701263067835e-05, + "loss": 3.8302, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878315315557315e-05, + "loss": 3.8351, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869945746850524e-05, + "loss": 3.8205, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861559799340004e-05, + "loss": 3.8269, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853173851829484e-05, + "loss": 3.8261, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844787904318964e-05, + "loss": 3.8217, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836401956808444e-05, + "loss": 3.8478, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482803238810165e-05, + "loss": 3.8333, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481964644059113e-05, + "loss": 3.8265, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481126049308061e-05, + "loss": 3.8317, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480287454557009e-05, + "loss": 3.8388, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479448859805957e-05, + "loss": 3.8223, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478611902935279e-05, + "loss": 3.8308, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477773308184227e-05, + "loss": 3.8242, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476934713433175e-05, + "loss": 3.8267, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476096118682122e-05, + "loss": 3.8183, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.47525752393107e-05, + "loss": 3.8253, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474418929180018e-05, + "loss": 3.8287, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47358197230934e-05, + "loss": 3.8319, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472743377558287e-05, + "loss": 3.8371, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471904782807235e-05, + "loss": 3.8315, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471066188056183e-05, + "loss": 3.8178, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702292311855046e-05, + "loss": 3.8291, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693906364344526e-05, + "loss": 3.8209, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685520416834006e-05, + "loss": 3.824, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677134469323486e-05, + "loss": 3.8136, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668764900616695e-05, + "loss": 3.818, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660378953106175e-05, + "loss": 3.8179, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651993005595655e-05, + "loss": 3.8309, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643607058085135e-05, + "loss": 3.8228, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635221110574615e-05, + "loss": 3.8183, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.8196, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618465594357304e-05, + "loss": 3.8202, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610079646846784e-05, + "loss": 3.8255, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601693699336264e-05, + "loss": 3.8105, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.7996, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458493818311896e-05, + "loss": 3.8249, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457655223560844e-05, + "loss": 3.8213, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456816628809792e-05, + "loss": 3.8074, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.45597803405874e-05, + "loss": 3.8142, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455141077188061e-05, + "loss": 3.8205, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.8004, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8193, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.81, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8203, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450949741313174e-05, + "loss": 3.8087, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450111146562122e-05, + "loss": 3.8149, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.44927255181107e-05, + "loss": 3.8045, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.8143, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.7994, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446758405438287e-05, + "loss": 3.8092, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445919810687235e-05, + "loss": 3.819, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8076, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8061, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.7989, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442565431683027e-05, + "loss": 3.8034, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441726836931975e-05, + "loss": 3.8155, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8187, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8136, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439212690559192e-05, + "loss": 3.8205, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43837409580814e-05, + "loss": 3.8195, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8058, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.811, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435859949435358e-05, + "loss": 3.8145, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435021354684306e-05, + "loss": 3.8009, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434182759933253e-05, + "loss": 3.8039, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8069, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432507208311523e-05, + "loss": 3.8067, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431668613560471e-05, + "loss": 3.8206, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430830018809418e-05, + "loss": 3.8162, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.792, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.8061, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283158724366356e-05, + "loss": 3.8104, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274772776855836e-05, + "loss": 3.8091, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.804, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.7925, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249631313128005e-05, + "loss": 3.8065, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.8014, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8024, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422448984940018e-05, + "loss": 3.8028, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216103901889654e-05, + "loss": 3.8051, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.8079, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.8056, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419096243816182e-05, + "loss": 3.791, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418257649065131e-05, + "loss": 3.7997, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.8066, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.8099, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.7962, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414904907941296e-05, + "loss": 3.7985, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414066313190244e-05, + "loss": 3.7995, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8069, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41238912368814e-05, + "loss": 3.7947, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411552166817461e-05, + "loss": 3.7915, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410713572066409e-05, + "loss": 3.7997, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409874977315357e-05, + "loss": 3.7957, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409036382564305e-05, + "loss": 3.7905, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408199425693626e-05, + "loss": 3.7916, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407360830942574e-05, + "loss": 3.7908, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406522236191522e-05, + "loss": 3.8077, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568364144047e-05, + "loss": 3.7952, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404846684569791e-05, + "loss": 3.7946, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404008089818739e-05, + "loss": 3.801, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403169495067687e-05, + "loss": 3.8133, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402330900316635e-05, + "loss": 3.8047, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401493943445956e-05, + "loss": 3.7874, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400655348694904e-05, + "loss": 3.7943, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399816753943852e-05, + "loss": 3.7948, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989781591928e-05, + "loss": 3.7897, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398141202322122e-05, + "loss": 3.7949, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39730260757107e-05, + "loss": 3.7865, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.799, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956254180689657e-05, + "loss": 3.793, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947884611982866e-05, + "loss": 3.7984, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939498664472346e-05, + "loss": 3.788, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931112716961826e-05, + "loss": 3.7929, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922726769451306e-05, + "loss": 3.7937, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914357200744515e-05, + "loss": 3.8066, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905971253233995e-05, + "loss": 3.7925, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.7981, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.7837, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388082978950617e-05, + "loss": 3.8004, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387244384199565e-05, + "loss": 3.7934, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386405789448513e-05, + "loss": 3.8012, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385567194697461e-05, + "loss": 3.788, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384730237826782e-05, + "loss": 3.8031, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.7907, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383053048324678e-05, + "loss": 3.8082, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382214453573626e-05, + "loss": 3.786, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381377496702947e-05, + "loss": 3.7955, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.7912, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.7843, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378861712449791e-05, + "loss": 3.7981, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378023117698739e-05, + "loss": 3.7974, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.7874, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763475660770084e-05, + "loss": 3.7891, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755089713259564e-05, + "loss": 3.7918, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8872928619384766, + "eval_runtime": 308.5774, + "eval_samples_per_second": 1236.614, + "eval_steps_per_second": 38.645, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746703765749044e-05, + "loss": 3.7814, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738317818238524e-05, + "loss": 3.7791, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729931870728004e-05, + "loss": 3.7898, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.7882, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371317635451069e-05, + "loss": 3.7981, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370479040700017e-05, + "loss": 3.7829, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369640445948965e-05, + "loss": 3.7835, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368801851197913e-05, + "loss": 3.783, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367964894327234e-05, + "loss": 3.7977, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367126299576182e-05, + "loss": 3.7811, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.36628770482513e-05, + "loss": 3.7785, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7823, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.3646121532034e-05, + "loss": 3.7792, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363773558452348e-05, + "loss": 3.7773, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362934963701296e-05, + "loss": 3.783, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362096368950243e-05, + "loss": 3.7693, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.3612594120795647e-05, + "loss": 3.7703, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.3604208173285126e-05, + "loss": 3.7767, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595822225774606e-05, + "loss": 3.7678, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358743627826408e-05, + "loss": 3.7933, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357905033075356e-05, + "loss": 3.7855, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357066438324304e-05, + "loss": 3.7775, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562294814536255e-05, + "loss": 3.7759, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553908867025735e-05, + "loss": 3.7864, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545522919515215e-05, + "loss": 3.771, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537136972004695e-05, + "loss": 3.7819, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528767403297904e-05, + "loss": 3.7708, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520381455787384e-05, + "loss": 3.7782, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.3511995508276864e-05, + "loss": 3.7697, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.3503609560766344e-05, + "loss": 3.7725, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.3495223613255824e-05, + "loss": 3.7783, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348685404454903e-05, + "loss": 3.7782, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347846809703851e-05, + "loss": 3.7848, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347008214952799e-05, + "loss": 3.7807, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346169620201748e-05, + "loss": 3.7662, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345332663331069e-05, + "loss": 3.7797, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344494068580017e-05, + "loss": 3.7709, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343655473828965e-05, + "loss": 3.7657, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342816879077913e-05, + "loss": 3.7687, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341979922207234e-05, + "loss": 3.767, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.341141327456182e-05, + "loss": 3.7689, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.34030273270513e-05, + "loss": 3.7829, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339464137954078e-05, + "loss": 3.7699, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338627181083399e-05, + "loss": 3.7692, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337788586332347e-05, + "loss": 3.7765, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336949991581295e-05, + "loss": 3.771, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361113968302434e-05, + "loss": 3.7707, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335274439959564e-05, + "loss": 3.761, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334435845208512e-05, + "loss": 3.7501, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.778, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.7688, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331921698835729e-05, + "loss": 3.7626, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331083104084677e-05, + "loss": 3.7626, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7692, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.7518, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328567319831521e-05, + "loss": 3.7683, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327730362960842e-05, + "loss": 3.7661, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.32689176820979e-05, + "loss": 3.7686, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326053173458739e-05, + "loss": 3.7638, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325214578707687e-05, + "loss": 3.7637, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243776218370076e-05, + "loss": 3.7546, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3235390270859556e-05, + "loss": 3.7674, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.3227004323349036e-05, + "loss": 3.7536, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7591, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.3210248807131725e-05, + "loss": 3.7706, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.3201862859621205e-05, + "loss": 3.7601, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.3193476912110685e-05, + "loss": 3.757, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.3185090964600165e-05, + "loss": 3.7546, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176705017089645e-05, + "loss": 3.755, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168335448382854e-05, + "loss": 3.7667, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315994950087234e-05, + "loss": 3.771, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315156355336182e-05, + "loss": 3.7637, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.31431776058513e-05, + "loss": 3.7736, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313480803714451e-05, + "loss": 3.7699, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312642208963399e-05, + "loss": 3.7657, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311803614212347e-05, + "loss": 3.7598, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310965019461295e-05, + "loss": 3.7643, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310128062590616e-05, + "loss": 3.759, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309289467839564e-05, + "loss": 3.7547, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308450873088512e-05, + "loss": 3.7646, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.30761227833746e-05, + "loss": 3.7579, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306775321466781e-05, + "loss": 3.7705, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305936726715729e-05, + "loss": 3.7716, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050981319646775e-05, + "loss": 3.7436, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042595372136254e-05, + "loss": 3.7628, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034225803429464e-05, + "loss": 3.7585, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025839855918944e-05, + "loss": 3.7626, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017453908408424e-05, + "loss": 3.7574, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7505, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000682013387383e-05, + "loss": 3.7599, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299231244468059e-05, + "loss": 3.7545, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298392649717007e-05, + "loss": 3.7589, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7543, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296715460214903e-05, + "loss": 3.7625, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295878503344224e-05, + "loss": 3.7614, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295039908593173e-05, + "loss": 3.7606, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7446, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293362719091069e-05, + "loss": 3.7576, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29252576222039e-05, + "loss": 3.7585, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291687167469338e-05, + "loss": 3.7668, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290848572718286e-05, + "loss": 3.7504, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290009977967234e-05, + "loss": 3.7549, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.2891730210965546e-05, + "loss": 3.7491, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.2883344263455026e-05, + "loss": 3.7622, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.2874958315944506e-05, + "loss": 3.7468, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286657236843398e-05, + "loss": 3.7489, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858202799727195e-05, + "loss": 3.7527, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284981685221668e-05, + "loss": 3.7519, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284143090470616e-05, + "loss": 3.7437, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2833044957195635e-05, + "loss": 3.7514, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282467538848885e-05, + "loss": 3.7466, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281628944097833e-05, + "loss": 3.7554, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280790349346781e-05, + "loss": 3.7554, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799517545957284e-05, + "loss": 3.7439, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.27911479772505e-05, + "loss": 3.7571, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278276202973998e-05, + "loss": 3.7676, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277437608222945e-05, + "loss": 3.7644, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276599013471893e-05, + "loss": 3.7403, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275760418720842e-05, + "loss": 3.7509, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749234618501636e-05, + "loss": 3.7503, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274084867099111e-05, + "loss": 3.7444, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273246272348059e-05, + "loss": 3.7508, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272407677597007e-05, + "loss": 3.7416, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715707207263285e-05, + "loss": 3.7547, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270732125975276e-05, + "loss": 3.7463, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269893531224224e-05, + "loss": 3.7572, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269054936473172e-05, + "loss": 3.7458, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268217979602493e-05, + "loss": 3.7448, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267379384851441e-05, + "loss": 3.7542, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2665407901003887e-05, + "loss": 3.7605, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265702195349337e-05, + "loss": 3.7503, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264865238478658e-05, + "loss": 3.7522, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264026643727606e-05, + "loss": 3.7408, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263188048976554e-05, + "loss": 3.7567, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262349454225502e-05, + "loss": 3.7483, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261512497354823e-05, + "loss": 3.7571, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260673902603771e-05, + "loss": 3.7449, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259835307852719e-05, + "loss": 3.7567, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258996713101667e-05, + "loss": 3.7463, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258159756230988e-05, + "loss": 3.7685, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257321161479936e-05, + "loss": 3.7414, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256482566728884e-05, + "loss": 3.7558, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255643971977833e-05, + "loss": 3.7456, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2548070151071536e-05, + "loss": 3.7447, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.2539684203561016e-05, + "loss": 3.7516, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.2531298256050496e-05, + "loss": 3.7503, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.2522912308539976e-05, + "loss": 3.7518, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.2514542739833185e-05, + "loss": 3.7417, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.2506156792322665e-05, + "loss": 3.7502, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8711609840393066, + "eval_runtime": 304.5353, + "eval_samples_per_second": 1253.027, + "eval_steps_per_second": 39.158, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2497770844812145e-05, + "loss": 3.7413, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.2489384897301625e-05, + "loss": 3.7345, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.2481015328594834e-05, + "loss": 3.7429, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.2472629381084314e-05, + "loss": 3.748, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.2464243433573794e-05, + "loss": 3.7528, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245585748606328e-05, + "loss": 3.7452, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.244747153855276e-05, + "loss": 3.7336, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243910196984597e-05, + "loss": 3.7429, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.243071602233545e-05, + "loss": 3.7525, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242233007482493e-05, + "loss": 3.7418, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.241394412731441e-05, + "loss": 3.7376, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240557455860762e-05, + "loss": 3.7391, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.23971886110971e-05, + "loss": 3.7398, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.238880266358658e-05, + "loss": 3.7334, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.238041671607606e-05, + "loss": 3.7423, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.237204714736927e-05, + "loss": 3.7266, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.236366119985875e-05, + "loss": 3.7289, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.2355275252348234e-05, + "loss": 3.734, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.2346889304837714e-05, + "loss": 3.7263, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7498, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.23301337886204e-05, + "loss": 3.7452, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232174784110988e-05, + "loss": 3.735, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.231336189359936e-05, + "loss": 3.7325, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230499232489257e-05, + "loss": 3.7413, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229660637738205e-05, + "loss": 3.7308, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.228822042987153e-05, + "loss": 3.7397, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227983448236101e-05, + "loss": 3.7291, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227146491365422e-05, + "loss": 3.7374, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.22630789661437e-05, + "loss": 3.7309, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225469301863319e-05, + "loss": 3.7302, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.224630707112267e-05, + "loss": 3.737, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223793750241588e-05, + "loss": 3.7399, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222955155490536e-05, + "loss": 3.7387, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222116560739484e-05, + "loss": 3.7423, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221277965988432e-05, + "loss": 3.7263, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.2204410091177526e-05, + "loss": 3.7435, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.2196024143667006e-05, + "loss": 3.7296, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.2187638196156486e-05, + "loss": 3.724, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.2179252248645966e-05, + "loss": 3.7281, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.2170882679939175e-05, + "loss": 3.7265, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.2162496732428655e-05, + "loss": 3.7281, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.2154110784918135e-05, + "loss": 3.7384, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.214572483740762e-05, + "loss": 3.73, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.213735526870083e-05, + "loss": 3.7323, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.212896932119031e-05, + "loss": 3.7342, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.212058337367979e-05, + "loss": 3.7306, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211219742616927e-05, + "loss": 3.7318, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210382785746248e-05, + "loss": 3.7206, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.209544190995196e-05, + "loss": 3.7103, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208705596244144e-05, + "loss": 3.7372, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.207867001493092e-05, + "loss": 3.7337, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.207030044622413e-05, + "loss": 3.7205, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.206191449871361e-05, + "loss": 3.7303, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.205352855120309e-05, + "loss": 3.727, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.2045142603692575e-05, + "loss": 3.7133, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.2036773034985784e-05, + "loss": 3.7248, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.2028387087475264e-05, + "loss": 3.7291, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.2020001139964744e-05, + "loss": 3.7274, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.2011615192454224e-05, + "loss": 3.723, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200324562374743e-05, + "loss": 3.7274, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.199485967623691e-05, + "loss": 3.7172, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.198647372872639e-05, + "loss": 3.7314, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197808778121587e-05, + "loss": 3.7139, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.196971821250908e-05, + "loss": 3.7184, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.196133226499856e-05, + "loss": 3.7313, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195294631748804e-05, + "loss": 3.7207, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194456036997753e-05, + "loss": 3.7203, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193619080127074e-05, + "loss": 3.7149, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192780485376022e-05, + "loss": 3.7142, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.19194189062497e-05, + "loss": 3.723, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191103295873918e-05, + "loss": 3.7356, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190266339003239e-05, + "loss": 3.724, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189427744252187e-05, + "loss": 3.7368, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188589149501135e-05, + "loss": 3.729, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187750554750083e-05, + "loss": 3.7308, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.1869135978794036e-05, + "loss": 3.7241, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.1860750031283516e-05, + "loss": 3.7223, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.1852364083772996e-05, + "loss": 3.7214, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184397813626248e-05, + "loss": 3.712, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183560856755569e-05, + "loss": 3.7268, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182722262004517e-05, + "loss": 3.7215, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181883667253465e-05, + "loss": 3.7321, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181045072502413e-05, + "loss": 3.7322, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180208115631734e-05, + "loss": 3.7051, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.179369520880682e-05, + "loss": 3.7269, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.17853092612963e-05, + "loss": 3.7186, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.1776923313785774e-05, + "loss": 3.7252, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.176855374507899e-05, + "loss": 3.7164, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.176016779756847e-05, + "loss": 3.7129, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.175178185005795e-05, + "loss": 3.7226, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174339590254743e-05, + "loss": 3.718, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.1735026333840645e-05, + "loss": 3.7198, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.1726640386330125e-05, + "loss": 3.7172, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.1718254438819605e-05, + "loss": 3.7231, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.170986849130908e-05, + "loss": 3.7284, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.1701498922602294e-05, + "loss": 3.714, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1693112975091774e-05, + "loss": 3.7122, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.168472702758125e-05, + "loss": 3.7174, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.167634108007073e-05, + "loss": 3.7194, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.166797151136394e-05, + "loss": 3.731, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165958556385342e-05, + "loss": 3.7149, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.16511996163429e-05, + "loss": 3.7168, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.164281366883238e-05, + "loss": 3.7137, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.16344441001256e-05, + "loss": 3.7268, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.162605815261508e-05, + "loss": 3.7051, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.161767220510455e-05, + "loss": 3.7137, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160928625759403e-05, + "loss": 3.7149, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160091668888725e-05, + "loss": 3.716, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159253074137672e-05, + "loss": 3.706, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.15841447938662e-05, + "loss": 3.714, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.157575884635568e-05, + "loss": 3.7084, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.15673892776489e-05, + "loss": 3.7188, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155900333013838e-05, + "loss": 3.7175, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155061738262786e-05, + "loss": 3.7101, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154223143511734e-05, + "loss": 3.7156, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153386186641055e-05, + "loss": 3.7298, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.1525475918900026e-05, + "loss": 3.7292, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.1517089971389506e-05, + "loss": 3.7063, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.1508704023878986e-05, + "loss": 3.7113, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.1500334455172195e-05, + "loss": 3.7139, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.1491948507661675e-05, + "loss": 3.7063, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.1483562560151155e-05, + "loss": 3.7182, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.1475176612640635e-05, + "loss": 3.7, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146680704393385e-05, + "loss": 3.7229, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145842109642333e-05, + "loss": 3.705, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.145003514891281e-05, + "loss": 3.7231, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144164920140229e-05, + "loss": 3.7097, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.14332796326955e-05, + "loss": 3.7114, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.142489368518498e-05, + "loss": 3.7153, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.141650773767446e-05, + "loss": 3.7239, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140812179016394e-05, + "loss": 3.7117, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139975222145715e-05, + "loss": 3.7175, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139136627394663e-05, + "loss": 3.7046, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138298032643611e-05, + "loss": 3.722, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137459437892559e-05, + "loss": 3.7117, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.1366224810218804e-05, + "loss": 3.718, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.1357838862708284e-05, + "loss": 3.7131, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1349452915197764e-05, + "loss": 3.7206, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1341066967687244e-05, + "loss": 3.7125, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133269739898045e-05, + "loss": 3.7311, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132431145146993e-05, + "loss": 3.7058, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131592550395941e-05, + "loss": 3.7186, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.130753955644889e-05, + "loss": 3.7123, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.12991699877421e-05, + "loss": 3.7118, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.129078404023158e-05, + "loss": 3.71, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128239809272106e-05, + "loss": 3.7157, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.127401214521054e-05, + "loss": 3.7149, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.126564257650376e-05, + "loss": 3.7066, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.125725662899324e-05, + "loss": 3.7204, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.8612208366394043, + "eval_runtime": 303.3015, + "eval_samples_per_second": 1258.124, + "eval_steps_per_second": 39.317, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124887068148272e-05, + "loss": 3.708, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.12404847339722e-05, + "loss": 3.6998, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123209878646168e-05, + "loss": 3.707, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122371283895116e-05, + "loss": 3.7104, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121534327024437e-05, + "loss": 3.7178, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120695732273385e-05, + "loss": 3.7115, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119857137522333e-05, + "loss": 3.705, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119018542771281e-05, + "loss": 3.706, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1181815859006016e-05, + "loss": 3.7182, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173429911495496e-05, + "loss": 3.7069, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1165043963984976e-05, + "loss": 3.7011, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156658016474456e-05, + "loss": 3.7055, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114828844776767e-05, + "loss": 3.7043, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113990250025715e-05, + "loss": 3.699, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113151655274663e-05, + "loss": 3.7061, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112313060523611e-05, + "loss": 3.6911, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111476103652932e-05, + "loss": 3.6954, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.11063750890188e-05, + "loss": 3.6997, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109798914150828e-05, + "loss": 3.6941, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108960319399776e-05, + "loss": 3.7137, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108123362529097e-05, + "loss": 3.7117, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107284767778045e-05, + "loss": 3.7013, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106446173026993e-05, + "loss": 3.6996, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105607578275941e-05, + "loss": 3.7069, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1047706214052625e-05, + "loss": 3.6976, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039320266542105e-05, + "loss": 3.7047, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030934319031585e-05, + "loss": 3.6924, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022548371521065e-05, + "loss": 3.7059, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014178802814274e-05, + "loss": 3.7035, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005792855303754e-05, + "loss": 3.694, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997406907793234e-05, + "loss": 3.7001, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0989020960282714e-05, + "loss": 3.7063, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098065139157592e-05, + "loss": 3.7022, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.09722654440654e-05, + "loss": 3.7122, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096387949655488e-05, + "loss": 3.6925, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095549354904436e-05, + "loss": 3.7034, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094712398033758e-05, + "loss": 3.6985, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093873803282706e-05, + "loss": 3.6921, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093035208531654e-05, + "loss": 3.6942, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092196613780602e-05, + "loss": 3.6918, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091359656909923e-05, + "loss": 3.6936, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090521062158871e-05, + "loss": 3.7064, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089682467407819e-05, + "loss": 3.6973, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088843872656767e-05, + "loss": 3.6987, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.088006915786088e-05, + "loss": 3.7027, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087168321035036e-05, + "loss": 3.6955, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086329726283984e-05, + "loss": 3.6946, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085491131532932e-05, + "loss": 3.6922, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084654174662253e-05, + "loss": 3.6699, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083815579911201e-05, + "loss": 3.7106, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082976985160149e-05, + "loss": 3.6944, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082138390409097e-05, + "loss": 3.6927, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081301433538418e-05, + "loss": 3.6944, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080462838787366e-05, + "loss": 3.6928, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079624244036314e-05, + "loss": 3.6808, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078785649285262e-05, + "loss": 3.6879, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.07794705453421e-05, + "loss": 3.6978, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077110097663531e-05, + "loss": 3.6934, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076271502912479e-05, + "loss": 3.6979, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075432908161427e-05, + "loss": 3.6863, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.0745959512907486e-05, + "loss": 3.6846, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737573565396966e-05, + "loss": 3.7025, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.0729187617886446e-05, + "loss": 3.6785, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.0720801670375926e-05, + "loss": 3.6862, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.07124157228654e-05, + "loss": 3.696, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.0704046154158615e-05, + "loss": 3.691, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695660206648095e-05, + "loss": 3.6851, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.0687274259137575e-05, + "loss": 3.6857, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067888831162705e-05, + "loss": 3.6789, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670518742920264e-05, + "loss": 3.6886, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662132795409744e-05, + "loss": 3.702, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653746847899224e-05, + "loss": 3.6911, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.0645360900388704e-05, + "loss": 3.7032, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063699133168192e-05, + "loss": 3.6965, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.06286053841714e-05, + "loss": 3.7022, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062021943666087e-05, + "loss": 3.6879, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061183348915035e-05, + "loss": 3.6926, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060346392044357e-05, + "loss": 3.6901, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059507797293305e-05, + "loss": 3.6767, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058669202542252e-05, + "loss": 3.6944, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578306077912e-05, + "loss": 3.6898, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056993650920522e-05, + "loss": 3.6975, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.05615505616947e-05, + "loss": 3.7023, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055316461418418e-05, + "loss": 3.6783, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054477866667366e-05, + "loss": 3.69, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053639271916314e-05, + "loss": 3.6867, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052802315045635e-05, + "loss": 3.6939, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051963720294583e-05, + "loss": 3.6862, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511251255435307e-05, + "loss": 3.6832, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502865307924787e-05, + "loss": 3.688, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494495739217996e-05, + "loss": 3.6841, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0486109791707476e-05, + "loss": 3.6883, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477723844196956e-05, + "loss": 3.6849, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469337896686436e-05, + "loss": 3.6957, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046096832797965e-05, + "loss": 3.6958, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045258238046913e-05, + "loss": 3.6826, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044419643295861e-05, + "loss": 3.6801, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043581048544809e-05, + "loss": 3.6851, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.04274409167413e-05, + "loss": 3.6926, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041905496923078e-05, + "loss": 3.6935, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041066902172026e-05, + "loss": 3.6866, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040228307420974e-05, + "loss": 3.6852, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039391350550295e-05, + "loss": 3.6809, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038552755799243e-05, + "loss": 3.698, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037714161048191e-05, + "loss": 3.6716, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036875566297139e-05, + "loss": 3.683, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.0360386094264605e-05, + "loss": 3.6785, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0352000146754085e-05, + "loss": 3.6864, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0343614199243565e-05, + "loss": 3.6745, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0335228251733045e-05, + "loss": 3.6884, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326858683026254e-05, + "loss": 3.6749, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318472735515734e-05, + "loss": 3.6881, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0310086788005214e-05, + "loss": 3.6881, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301700840494694e-05, + "loss": 3.6768, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.02933312717879e-05, + "loss": 3.6859, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028494532427738e-05, + "loss": 3.7015, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027655937676686e-05, + "loss": 3.6873, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026817342925634e-05, + "loss": 3.6834, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025980386054955e-05, + "loss": 3.675, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025141791303904e-05, + "loss": 3.6845, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024303196552852e-05, + "loss": 3.6833, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234646018018e-05, + "loss": 3.6817, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022626007050748e-05, + "loss": 3.6683, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021789050180069e-05, + "loss": 3.6891, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020950455429017e-05, + "loss": 3.6778, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020111860677965e-05, + "loss": 3.6897, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019273265926913e-05, + "loss": 3.6798, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018436309056234e-05, + "loss": 3.6836, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175977143051817e-05, + "loss": 3.6813, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167591195541297e-05, + "loss": 3.6946, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159205248030776e-05, + "loss": 3.6823, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015083567932399e-05, + "loss": 3.688, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014244973181347e-05, + "loss": 3.67, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013406378430295e-05, + "loss": 3.6926, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012567783679243e-05, + "loss": 3.681, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011730826808564e-05, + "loss": 3.6884, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010892232057512e-05, + "loss": 3.6834, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.01005363730646e-05, + "loss": 3.6872, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009215042555408e-05, + "loss": 3.678, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008378085684729e-05, + "loss": 3.7025, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007539490933677e-05, + "loss": 3.6776, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006700896182625e-05, + "loss": 3.6902, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005862301431573e-05, + "loss": 3.6846, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0050253445608946e-05, + "loss": 3.6805, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041867498098426e-05, + "loss": 3.6773, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.0033481550587906e-05, + "loss": 3.6874, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.0025095603077386e-05, + "loss": 3.6856, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016726034370595e-05, + "loss": 3.6767, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008340086860075e-05, + "loss": 3.6869, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.854868173599243, + "eval_runtime": 310.6755, + "eval_samples_per_second": 1228.262, + "eval_steps_per_second": 38.384, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.9999954139349555e-05, + "loss": 3.6694, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.9991568191839035e-05, + "loss": 3.6723, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.9983198623132244e-05, + "loss": 3.6758, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.9974812675621724e-05, + "loss": 3.6822, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.9966426728111204e-05, + "loss": 3.6884, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.9958040780600684e-05, + "loss": 3.6779, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.9949654833090164e-05, + "loss": 3.679, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994128526438338e-05, + "loss": 3.6753, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993289931687286e-05, + "loss": 3.6844, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992451336936234e-05, + "loss": 3.6818, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991612742185182e-05, + "loss": 3.671, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990775785314503e-05, + "loss": 3.6709, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989937190563451e-05, + "loss": 3.6799, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989098595812399e-05, + "loss": 3.6688, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988260001061347e-05, + "loss": 3.6719, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987423044190668e-05, + "loss": 3.6644, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986584449439616e-05, + "loss": 3.6645, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985745854688564e-05, + "loss": 3.6739, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984907259937512e-05, + "loss": 3.6639, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984070303066833e-05, + "loss": 3.6826, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983231708315781e-05, + "loss": 3.6831, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982393113564729e-05, + "loss": 3.6762, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981554518813677e-05, + "loss": 3.6697, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980717561942998e-05, + "loss": 3.6731, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979878967191946e-05, + "loss": 3.6723, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979040372440894e-05, + "loss": 3.6754, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978201777689842e-05, + "loss": 3.6651, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977364820819163e-05, + "loss": 3.6777, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976526226068111e-05, + "loss": 3.6671, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975687631317059e-05, + "loss": 3.6669, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974849036566007e-05, + "loss": 3.6677, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.974012079695329e-05, + "loss": 3.6782, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973173484944277e-05, + "loss": 3.6789, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972334890193225e-05, + "loss": 3.6806, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971496295442172e-05, + "loss": 3.6642, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.9706593385714936e-05, + "loss": 3.6696, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.9698207438204416e-05, + "loss": 3.6755, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.9689821490693896e-05, + "loss": 3.6628, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968143554318337e-05, + "loss": 3.6632, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.9673065974476585e-05, + "loss": 3.6638, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9664680026966065e-05, + "loss": 3.6664, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.9656294079455545e-05, + "loss": 3.6712, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.9647908131945025e-05, + "loss": 3.6757, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963953856323824e-05, + "loss": 3.6703, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963115261572772e-05, + "loss": 3.6685, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622766668217194e-05, + "loss": 3.6723, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614380720706674e-05, + "loss": 3.6631, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960601115199989e-05, + "loss": 3.6651, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959762520448937e-05, + "loss": 3.6399, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958923925697884e-05, + "loss": 3.6823, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958085330946832e-05, + "loss": 3.6638, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957248374076154e-05, + "loss": 3.6713, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956409779325101e-05, + "loss": 3.6653, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.95557118457405e-05, + "loss": 3.6645, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954732589822998e-05, + "loss": 3.6524, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.9538956329523194e-05, + "loss": 3.6588, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953057038201267e-05, + "loss": 3.6709, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952218443450215e-05, + "loss": 3.6628, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951379848699163e-05, + "loss": 3.6718, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950542891828484e-05, + "loss": 3.6615, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.9497042970774316e-05, + "loss": 3.6519, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.9488657023263796e-05, + "loss": 3.6759, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.9480271075753276e-05, + "loss": 3.6499, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.9471901507046485e-05, + "loss": 3.655, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.9463515559535965e-05, + "loss": 3.6695, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945512961202545e-05, + "loss": 3.6659, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944674366451493e-05, + "loss": 3.6527, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.943837409580814e-05, + "loss": 3.6627, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.942998814829762e-05, + "loss": 3.6467, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.94216022007871e-05, + "loss": 3.6654, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941321625327658e-05, + "loss": 3.6698, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940484668456979e-05, + "loss": 3.6682, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939646073705927e-05, + "loss": 3.6686, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938807478954875e-05, + "loss": 3.6692, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937968884203823e-05, + "loss": 3.6771, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937131927333144e-05, + "loss": 3.6577, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936293332582092e-05, + "loss": 3.6674, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.93545473783104e-05, + "loss": 3.6634, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.9346161430799886e-05, + "loss": 3.6439, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.9337791862093095e-05, + "loss": 3.668, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.9329405914582575e-05, + "loss": 3.6637, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.9321019967072055e-05, + "loss": 3.6671, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.9312634019561535e-05, + "loss": 3.679, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.9304264450854744e-05, + "loss": 3.6527, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.9295878503344224e-05, + "loss": 3.6564, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.9287492555833704e-05, + "loss": 3.6611, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9279106608323184e-05, + "loss": 3.6681, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927073703961639e-05, + "loss": 3.6546, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926235109210587e-05, + "loss": 3.6592, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925396514459535e-05, + "loss": 3.6593, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924557919708484e-05, + "loss": 3.6599, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923720962837805e-05, + "loss": 3.655, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922882368086753e-05, + "loss": 3.6615, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.922043773335701e-05, + "loss": 3.6681, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921205178584649e-05, + "loss": 3.6614, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920366583833597e-05, + "loss": 3.6641, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919529626962918e-05, + "loss": 3.6479, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918691032211866e-05, + "loss": 3.6597, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917852437460814e-05, + "loss": 3.6612, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.917013842709762e-05, + "loss": 3.6693, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9161768858390826e-05, + "loss": 3.66, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.9153382910880306e-05, + "loss": 3.655, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914499696336979e-05, + "loss": 3.6597, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913661101585927e-05, + "loss": 3.6635, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912824144715248e-05, + "loss": 3.6484, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911985549964196e-05, + "loss": 3.6569, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911146955213144e-05, + "loss": 3.6448, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910308360462092e-05, + "loss": 3.666, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909471403591413e-05, + "loss": 3.6492, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908632808840361e-05, + "loss": 3.6571, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907794214089309e-05, + "loss": 3.6494, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906955619338257e-05, + "loss": 3.6605, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906118662467578e-05, + "loss": 3.6631, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905280067716526e-05, + "loss": 3.6517, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904441472965475e-05, + "loss": 3.6576, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903602878214423e-05, + "loss": 3.6709, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9027659213437436e-05, + "loss": 3.6661, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.9019273265926916e-05, + "loss": 3.6546, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9010887318416396e-05, + "loss": 3.6487, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.9002501370905876e-05, + "loss": 3.655, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.8994131802199085e-05, + "loss": 3.6602, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.8985745854688565e-05, + "loss": 3.6504, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.8977359907178045e-05, + "loss": 3.6445, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.8968973959667525e-05, + "loss": 3.661, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.8960604390960734e-05, + "loss": 3.6544, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.8952218443450214e-05, + "loss": 3.6632, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.89438324959397e-05, + "loss": 3.6509, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893544654842918e-05, + "loss": 3.655, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892707697972239e-05, + "loss": 3.652, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891869103221187e-05, + "loss": 3.6664, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891030508470135e-05, + "loss": 3.6593, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890191913719083e-05, + "loss": 3.6581, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889354956848404e-05, + "loss": 3.6438, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.888516362097352e-05, + "loss": 3.6681, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8876777673463e-05, + "loss": 3.6544, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886839172595248e-05, + "loss": 3.6634, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.886002215724569e-05, + "loss": 3.654, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885163620973517e-05, + "loss": 3.6566, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.8843250262224654e-05, + "loss": 3.655, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.8834864314714134e-05, + "loss": 3.674, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882649474600734e-05, + "loss": 3.6487, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881810879849682e-05, + "loss": 3.6646, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.88097228509863e-05, + "loss": 3.6565, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880133690347578e-05, + "loss": 3.6518, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879296733476899e-05, + "loss": 3.6526, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878458138725847e-05, + "loss": 3.6594, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877619543974795e-05, + "loss": 3.6579, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876780949223743e-05, + "loss": 3.6559, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875943992353064e-05, + "loss": 3.6592, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.8506927490234375, + "eval_runtime": 306.5033, + "eval_samples_per_second": 1244.982, + "eval_steps_per_second": 38.907, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875105397602012e-05, + "loss": 3.6498, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874266802850961e-05, + "loss": 3.6436, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873428208099909e-05, + "loss": 3.6483, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872589613348857e-05, + "loss": 3.6574, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871752656478178e-05, + "loss": 3.6632, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870914061727126e-05, + "loss": 3.6512, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870075466976074e-05, + "loss": 3.6517, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869236872225022e-05, + "loss": 3.6524, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683999153543426e-05, + "loss": 3.6543, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675613206032906e-05, + "loss": 3.6603, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8667227258522386e-05, + "loss": 3.6442, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8658841311011866e-05, + "loss": 3.6439, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.8650471742305075e-05, + "loss": 3.6577, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.8642085794794555e-05, + "loss": 3.642, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863369984728404e-05, + "loss": 3.6466, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625313899773515e-05, + "loss": 3.6392, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8616927952262995e-05, + "loss": 3.6407, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608542004752474e-05, + "loss": 3.6436, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8600156057241954e-05, + "loss": 3.6394, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591770109731434e-05, + "loss": 3.6539, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8583400541024643e-05, + "loss": 3.6563, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8575014593514123e-05, + "loss": 3.6543, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8566628646003603e-05, + "loss": 3.6438, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855824269849308e-05, + "loss": 3.6465, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854987312978629e-05, + "loss": 3.6492, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854148718227578e-05, + "loss": 3.6461, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853310123476526e-05, + "loss": 3.6412, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852471528725474e-05, + "loss": 3.6575, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851632933974422e-05, + "loss": 3.6389, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850795977103743e-05, + "loss": 3.6408, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849957382352691e-05, + "loss": 3.6404, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849118787601639e-05, + "loss": 3.6526, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848280192850587e-05, + "loss": 3.6527, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847443235979908e-05, + "loss": 3.6602, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846604641228856e-05, + "loss": 3.6359, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845766046477804e-05, + "loss": 3.645, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844927451726752e-05, + "loss": 3.6527, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844090494856073e-05, + "loss": 3.6319, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843251900105021e-05, + "loss": 3.6404, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842413305353969e-05, + "loss": 3.6387, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841574710602917e-05, + "loss": 3.6416, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840737753732238e-05, + "loss": 3.6443, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839899158981186e-05, + "loss": 3.6469, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839060564230134e-05, + "loss": 3.6471, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838221969479082e-05, + "loss": 3.6425, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.83738337472803e-05, + "loss": 3.6462, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836546417857351e-05, + "loss": 3.6409, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835707823106299e-05, + "loss": 3.64, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834869228355247e-05, + "loss": 3.6117, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834030633604195e-05, + "loss": 3.6566, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331936767335166e-05, + "loss": 3.6372, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323550819824646e-05, + "loss": 3.6449, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8315164872314126e-05, + "loss": 3.6392, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306778924803606e-05, + "loss": 3.6414, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8298409356096815e-05, + "loss": 3.6277, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8290023408586295e-05, + "loss": 3.6327, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8281637461075775e-05, + "loss": 3.648, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8273251513565255e-05, + "loss": 3.6315, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264881944858464e-05, + "loss": 3.6454, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8256495997347944e-05, + "loss": 3.6382, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.8248110049837424e-05, + "loss": 3.6257, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8239724102326904e-05, + "loss": 3.6519, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823135453362012e-05, + "loss": 3.6255, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.82229685861096e-05, + "loss": 3.6317, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821458263859908e-05, + "loss": 3.6459, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820619669108856e-05, + "loss": 3.6387, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819782712238177e-05, + "loss": 3.627, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818944117487125e-05, + "loss": 3.6387, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818105522736073e-05, + "loss": 3.6221, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817266927985021e-05, + "loss": 3.6426, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816429971114342e-05, + "loss": 3.6465, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.81559137636329e-05, + "loss": 3.6389, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814752781612238e-05, + "loss": 3.6427, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813914186861186e-05, + "loss": 3.6445, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.8130772299905074e-05, + "loss": 3.6535, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8122386352394554e-05, + "loss": 3.6332, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8114000404884034e-05, + "loss": 3.6397, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.8105614457373514e-05, + "loss": 3.642, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809724488866672e-05, + "loss": 3.617, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.80888589411562e-05, + "loss": 3.6414, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808047299364568e-05, + "loss": 3.6423, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807208704613516e-05, + "loss": 3.6408, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806371747742837e-05, + "loss": 3.6535, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805533152991785e-05, + "loss": 3.6258, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804694558240733e-05, + "loss": 3.6322, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803855963489681e-05, + "loss": 3.6361, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.803019006619003e-05, + "loss": 3.6414, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802180411867951e-05, + "loss": 3.6356, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801341817116899e-05, + "loss": 3.6335, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800503222365847e-05, + "loss": 3.6318, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7996662654951676e-05, + "loss": 3.6389, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7988276707441156e-05, + "loss": 3.6315, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7979890759930636e-05, + "loss": 3.6347, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971504812420116e-05, + "loss": 3.644, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7963135243713325e-05, + "loss": 3.6349, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954749296202805e-05, + "loss": 3.6415, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.7946363348692285e-05, + "loss": 3.6265, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.7937977401181765e-05, + "loss": 3.6341, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792960783247498e-05, + "loss": 3.6339, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792122188496446e-05, + "loss": 3.6444, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791283593745394e-05, + "loss": 3.6341, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7904449989943414e-05, + "loss": 3.632, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789608042123663e-05, + "loss": 3.6352, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788769447372611e-05, + "loss": 3.6396, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787930852621559e-05, + "loss": 3.6241, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787092257870506e-05, + "loss": 3.6345, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786255300999828e-05, + "loss": 3.6208, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785416706248776e-05, + "loss": 3.6424, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784578111497724e-05, + "loss": 3.6287, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783739516746672e-05, + "loss": 3.6313, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7829025598759935e-05, + "loss": 3.6228, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7820639651249415e-05, + "loss": 3.6408, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781225370373889e-05, + "loss": 3.6347, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780386775622837e-05, + "loss": 3.6265, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7795498187521584e-05, + "loss": 3.6365, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7787112240011064e-05, + "loss": 3.6441, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777872629250054e-05, + "loss": 3.643, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777034034499002e-05, + "loss": 3.6283, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776197077628323e-05, + "loss": 3.6241, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775358482877271e-05, + "loss": 3.6333, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774519888126219e-05, + "loss": 3.6361, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.773681293375167e-05, + "loss": 3.6228, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772844336504489e-05, + "loss": 3.6227, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.772005741753436e-05, + "loss": 3.6376, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771167147002384e-05, + "loss": 3.6354, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770328552251332e-05, + "loss": 3.6356, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769491595380654e-05, + "loss": 3.63, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768653000629601e-05, + "loss": 3.6319, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767814405878549e-05, + "loss": 3.6293, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766975811127497e-05, + "loss": 3.645, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661388542568186e-05, + "loss": 3.632, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765300259505766e-05, + "loss": 3.6366, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764461664754714e-05, + "loss": 3.6199, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7636230700036626e-05, + "loss": 3.6447, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627861131329835e-05, + "loss": 3.625, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619475183819315e-05, + "loss": 3.6433, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7611089236308795e-05, + "loss": 3.6309, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7602703288798275e-05, + "loss": 3.6351, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7594333720091484e-05, + "loss": 3.6295, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.7585947772580964e-05, + "loss": 3.6529, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.7577561825070444e-05, + "loss": 3.6265, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7569175877559924e-05, + "loss": 3.6395, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756080630885313e-05, + "loss": 3.6356, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755242036134261e-05, + "loss": 3.6257, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754403441383209e-05, + "loss": 3.6325, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753564846632158e-05, + "loss": 3.6345, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752727889761479e-05, + "loss": 3.6351, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751889295010427e-05, + "loss": 3.6343, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751050700259375e-05, + "loss": 3.635, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8488142490386963, + "eval_runtime": 307.012, + "eval_samples_per_second": 1242.919, + "eval_steps_per_second": 38.842, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750212105508323e-05, + "loss": 3.621, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749373510757271e-05, + "loss": 3.621, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748536553886592e-05, + "loss": 3.6256, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.74769795913554e-05, + "loss": 3.6336, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746859364384488e-05, + "loss": 3.6417, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.746020769633436e-05, + "loss": 3.6292, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745183812762757e-05, + "loss": 3.6278, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744345218011705e-05, + "loss": 3.6267, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.7435066232606534e-05, + "loss": 3.6293, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.7426680285096014e-05, + "loss": 3.6358, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741831071638922e-05, + "loss": 3.6216, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.74099247688787e-05, + "loss": 3.6242, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740155520017191e-05, + "loss": 3.6341, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739316925266139e-05, + "loss": 3.6178, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738478330515087e-05, + "loss": 3.6253, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737639735764035e-05, + "loss": 3.6118, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736801141012983e-05, + "loss": 3.6198, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735962546261931e-05, + "loss": 3.622, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735123951510879e-05, + "loss": 3.613, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734285356759827e-05, + "loss": 3.6336, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733448399889149e-05, + "loss": 3.633, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732609805138097e-05, + "loss": 3.6276, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.731771210387045e-05, + "loss": 3.6237, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730932615635993e-05, + "loss": 3.6241, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300956587653136e-05, + "loss": 3.6298, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292570640142616e-05, + "loss": 3.6193, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7284184692632096e-05, + "loss": 3.6154, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7275798745121576e-05, + "loss": 3.6355, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7267429176414785e-05, + "loss": 3.6182, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7259043228904265e-05, + "loss": 3.6199, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7250657281393745e-05, + "loss": 3.6185, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.7242271333883225e-05, + "loss": 3.63, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723390176517644e-05, + "loss": 3.6228, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722551581766592e-05, + "loss": 3.6423, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.72171298701554e-05, + "loss": 3.6171, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720874392264488e-05, + "loss": 3.6183, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.720037435393809e-05, + "loss": 3.6321, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719198840642757e-05, + "loss": 3.6062, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718360245891705e-05, + "loss": 3.6176, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717521651140653e-05, + "loss": 3.6188, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716684694269974e-05, + "loss": 3.6133, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715846099518922e-05, + "loss": 3.6235, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.71500750476787e-05, + "loss": 3.6238, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714168910016818e-05, + "loss": 3.6256, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7133319531461395e-05, + "loss": 3.616, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124933583950875e-05, + "loss": 3.6264, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7116547636440355e-05, + "loss": 3.6117, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7108161688929834e-05, + "loss": 3.6238, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.7099775741419314e-05, + "loss": 3.5893, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.7091406172712524e-05, + "loss": 3.6313, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7083020225202003e-05, + "loss": 3.6152, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7074634277691483e-05, + "loss": 3.6239, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7066248330180963e-05, + "loss": 3.617, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705787876147417e-05, + "loss": 3.6197, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704949281396365e-05, + "loss": 3.6045, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704110686645313e-05, + "loss": 3.6095, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703272091894261e-05, + "loss": 3.6282, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702435135023583e-05, + "loss": 3.6074, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701596540272531e-05, + "loss": 3.6254, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700757945521479e-05, + "loss": 3.6221, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699919350770427e-05, + "loss": 3.5989, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699082393899748e-05, + "loss": 3.6285, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698243799148696e-05, + "loss": 3.6085, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697405204397644e-05, + "loss": 3.609, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696566609646591e-05, + "loss": 3.6218, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6957296527759126e-05, + "loss": 3.6156, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6948910580248606e-05, + "loss": 3.6071, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.6940524632738086e-05, + "loss": 3.6151, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.6932138685227566e-05, + "loss": 3.6029, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692376911652078e-05, + "loss": 3.6176, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691538316901026e-05, + "loss": 3.6217, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690699722149974e-05, + "loss": 3.618, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898611273989215e-05, + "loss": 3.6228, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.689024170528243e-05, + "loss": 3.6207, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688185575777191e-05, + "loss": 3.6293, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6873469810261384e-05, + "loss": 3.6121, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.68651002415546e-05, + "loss": 3.6217, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685671429404408e-05, + "loss": 3.6185, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684832834653356e-05, + "loss": 3.5996, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683994239902303e-05, + "loss": 3.6184, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683157283031625e-05, + "loss": 3.6229, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6823186882805736e-05, + "loss": 3.6162, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814800935295216e-05, + "loss": 3.6346, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680641498778469e-05, + "loss": 3.6013, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679802904027417e-05, + "loss": 3.6091, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.6789659471567385e-05, + "loss": 3.6162, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678127352405686e-05, + "loss": 3.6206, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677288757654634e-05, + "loss": 3.6156, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676450162903582e-05, + "loss": 3.6118, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.6756132060329033e-05, + "loss": 3.6074, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674774611281851e-05, + "loss": 3.6175, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673936016530799e-05, + "loss": 3.6132, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673097421779747e-05, + "loss": 3.6109, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672260464909069e-05, + "loss": 3.6206, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671421870158016e-05, + "loss": 3.6203, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670583275406964e-05, + "loss": 3.6135, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669744680655912e-05, + "loss": 3.6053, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668907723785233e-05, + "loss": 3.6121, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668069129034181e-05, + "loss": 3.609, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667230534283129e-05, + "loss": 3.6251, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666391939532077e-05, + "loss": 3.6151, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665554982661398e-05, + "loss": 3.6103, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664716387910346e-05, + "loss": 3.6118, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663877793159294e-05, + "loss": 3.6126, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.663039198408243e-05, + "loss": 3.6107, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.6622022415375636e-05, + "loss": 3.6108, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6613636467865116e-05, + "loss": 3.6001, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6605250520354596e-05, + "loss": 3.6214, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.6596864572844076e-05, + "loss": 3.6084, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6588495004137285e-05, + "loss": 3.6044, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6580109056626765e-05, + "loss": 3.6014, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571723109116245e-05, + "loss": 3.6167, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.6563337161605725e-05, + "loss": 3.6156, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6554951214095205e-05, + "loss": 3.6041, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6546581645388414e-05, + "loss": 3.6167, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6538195697877894e-05, + "loss": 3.6255, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652980975036738e-05, + "loss": 3.6182, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652144018166059e-05, + "loss": 3.609, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651305423415007e-05, + "loss": 3.6061, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650466828663955e-05, + "loss": 3.6102, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649628233912903e-05, + "loss": 3.6173, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648791277042224e-05, + "loss": 3.6004, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647952682291172e-05, + "loss": 3.6018, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.64711408754012e-05, + "loss": 3.6155, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646275492789068e-05, + "loss": 3.6097, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645438535918389e-05, + "loss": 3.6128, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644599941167337e-05, + "loss": 3.6115, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643761346416285e-05, + "loss": 3.6094, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6429227516652334e-05, + "loss": 3.6089, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6420857947945543e-05, + "loss": 3.6222, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6412472000435023e-05, + "loss": 3.6097, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.64040860529245e-05, + "loss": 3.6183, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639570010541398e-05, + "loss": 3.5977, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638733053670719e-05, + "loss": 3.6168, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637894458919667e-05, + "loss": 3.611, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637055864168615e-05, + "loss": 3.6175, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636217269417563e-05, + "loss": 3.6129, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635380312546884e-05, + "loss": 3.6109, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634541717795832e-05, + "loss": 3.6138, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.63370312304478e-05, + "loss": 3.6259, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632864528293729e-05, + "loss": 3.6087, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.63202757142305e-05, + "loss": 3.615, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631188976671998e-05, + "loss": 3.6178, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630350381920946e-05, + "loss": 3.6063, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629511787169894e-05, + "loss": 3.6084, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6286748302992146e-05, + "loss": 3.6152, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6278362355481626e-05, + "loss": 3.6131, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6269976407971106e-05, + "loss": 3.6133, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6261590460460586e-05, + "loss": 3.6105, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.846524477005005, + "eval_runtime": 307.3346, + "eval_samples_per_second": 1241.614, + "eval_steps_per_second": 38.801, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.6253204512950066e-05, + "loss": 3.6006, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.6244818565439546e-05, + "loss": 3.6033, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.6236432617929026e-05, + "loss": 3.6048, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.6228046670418506e-05, + "loss": 3.6122, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621967710171172e-05, + "loss": 3.6172, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.62112911542012e-05, + "loss": 3.6096, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620290520669068e-05, + "loss": 3.6087, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619451925918016e-05, + "loss": 3.607, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618614969047337e-05, + "loss": 3.6093, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617776374296285e-05, + "loss": 3.6124, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616937779545233e-05, + "loss": 3.6055, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616099184794181e-05, + "loss": 3.6, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615262227923502e-05, + "loss": 3.6125, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.61442363317245e-05, + "loss": 3.5978, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613585038421398e-05, + "loss": 3.6043, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612746443670346e-05, + "loss": 3.5898, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611907848919294e-05, + "loss": 3.602, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.611069254168242e-05, + "loss": 3.6016, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.61023065941719e-05, + "loss": 3.5929, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609392064666138e-05, + "loss": 3.6117, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608555107795459e-05, + "loss": 3.6097, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607716513044407e-05, + "loss": 3.6051, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606877918293355e-05, + "loss": 3.6034, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.606039323542303e-05, + "loss": 3.6044, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605202366671624e-05, + "loss": 3.6098, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604363771920572e-05, + "loss": 3.6027, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.60352517716952e-05, + "loss": 3.5888, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602686582418468e-05, + "loss": 3.6144, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601849625547789e-05, + "loss": 3.5978, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.601011030796737e-05, + "loss": 3.5982, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600172436045685e-05, + "loss": 3.6036, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599333841294633e-05, + "loss": 3.6065, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598496884423954e-05, + "loss": 3.6022, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597658289672902e-05, + "loss": 3.6218, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.59681969492185e-05, + "loss": 3.5955, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595981100170798e-05, + "loss": 3.599, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595144143300119e-05, + "loss": 3.6129, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594305548549067e-05, + "loss": 3.5847, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593466953798015e-05, + "loss": 3.5985, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592628359046963e-05, + "loss": 3.6011, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591791402176285e-05, + "loss": 3.5931, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590952807425233e-05, + "loss": 3.6037, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590114212674181e-05, + "loss": 3.6036, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5892756179231287e-05, + "loss": 3.6025, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5884386610524496e-05, + "loss": 3.5999, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5876000663013976e-05, + "loss": 3.6048, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5867614715503456e-05, + "loss": 3.5922, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5859228767992936e-05, + "loss": 3.6051, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5850859199286145e-05, + "loss": 3.5712, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5842473251775625e-05, + "loss": 3.6061, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.5834087304265105e-05, + "loss": 3.5979, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.5825701356754585e-05, + "loss": 3.6064, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.58173317880478e-05, + "loss": 3.5935, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580894584053728e-05, + "loss": 3.6006, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580055989302676e-05, + "loss": 3.587, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579217394551624e-05, + "loss": 3.5894, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578380437680945e-05, + "loss": 3.6104, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577541842929893e-05, + "loss": 3.5833, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576703248178841e-05, + "loss": 3.605, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575864653427789e-05, + "loss": 3.6039, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.57502769655711e-05, + "loss": 3.577, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574189101806058e-05, + "loss": 3.6116, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573350507055006e-05, + "loss": 3.5885, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572511912303954e-05, + "loss": 3.5876, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.571673317552902e-05, + "loss": 3.6004, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5708363606822234e-05, + "loss": 3.5988, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699977659311714e-05, + "loss": 3.5868, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5691591711801194e-05, + "loss": 3.5954, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.56832221430944e-05, + "loss": 3.583, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567483619558388e-05, + "loss": 3.5998, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566645024807336e-05, + "loss": 3.6025, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565806430056284e-05, + "loss": 3.5985, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564967835305232e-05, + "loss": 3.6003, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564130878434553e-05, + "loss": 3.5986, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563292283683501e-05, + "loss": 3.6118, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562453688932449e-05, + "loss": 3.5915, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561615094181397e-05, + "loss": 3.6055, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560778137310719e-05, + "loss": 3.593, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559939542559667e-05, + "loss": 3.5838, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559100947808615e-05, + "loss": 3.5964, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558262353057563e-05, + "loss": 3.6021, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557425396186884e-05, + "loss": 3.5979, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556586801435832e-05, + "loss": 3.616, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.5557482066847797e-05, + "loss": 3.581, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.5549096119337277e-05, + "loss": 3.5918, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5540726550630486e-05, + "loss": 3.5956, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.5532340603119966e-05, + "loss": 3.6012, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.5523954655609446e-05, + "loss": 3.5937, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5515568708098925e-05, + "loss": 3.5899, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550719913939214e-05, + "loss": 3.5917, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549881319188162e-05, + "loss": 3.5964, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.54904272443711e-05, + "loss": 3.5951, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548204129686058e-05, + "loss": 3.5908, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547367172815379e-05, + "loss": 3.6028, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546528578064327e-05, + "loss": 3.6002, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545689983313275e-05, + "loss": 3.5956, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544851388562223e-05, + "loss": 3.5873, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.544014431691544e-05, + "loss": 3.5935, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543175836940492e-05, + "loss": 3.5913, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.54233724218944e-05, + "loss": 3.6022, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541498647438388e-05, + "loss": 3.5945, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5406616905677095e-05, + "loss": 3.5876, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5398230958166575e-05, + "loss": 3.5933, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389845010656055e-05, + "loss": 3.5951, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.5381459063145535e-05, + "loss": 3.5917, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5373089494438744e-05, + "loss": 3.5871, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5364703546928224e-05, + "loss": 3.5829, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5356317599417704e-05, + "loss": 3.5993, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.5347931651907184e-05, + "loss": 3.5931, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533956208320039e-05, + "loss": 3.5853, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533117613568987e-05, + "loss": 3.5817, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532279018817935e-05, + "loss": 3.5968, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531440424066883e-05, + "loss": 3.5963, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530603467196205e-05, + "loss": 3.5841, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529764872445153e-05, + "loss": 3.5972, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528926277694101e-05, + "loss": 3.6065, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528087682943049e-05, + "loss": 3.5953, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.52725072607237e-05, + "loss": 3.5927, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526412131321318e-05, + "loss": 3.5882, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525573536570266e-05, + "loss": 3.589, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524734941819214e-05, + "loss": 3.5988, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523897984948535e-05, + "loss": 3.583, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230593901974827e-05, + "loss": 3.5796, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5222207954464307e-05, + "loss": 3.5947, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.5213822006953786e-05, + "loss": 3.5892, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5205452438247e-05, + "loss": 3.5954, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519706649073648e-05, + "loss": 3.5941, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518868054322596e-05, + "loss": 3.5866, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.5180294595715435e-05, + "loss": 3.5884, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517192502700865e-05, + "loss": 3.6021, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516353907949813e-05, + "loss": 3.5901, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515515313198761e-05, + "loss": 3.6006, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146767184477084e-05, + "loss": 3.5809, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.51383976157703e-05, + "loss": 3.5941, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.513001166825978e-05, + "loss": 3.5946, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512162572074926e-05, + "loss": 3.5945, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511323977323874e-05, + "loss": 3.596, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104870204531956e-05, + "loss": 3.5897, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5096484257021436e-05, + "loss": 3.5951, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508809830951091e-05, + "loss": 3.6058, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507971236200039e-05, + "loss": 3.59, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5071342793293605e-05, + "loss": 3.5936, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062956845783085e-05, + "loss": 3.5976, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505457089827256e-05, + "loss": 3.5872, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504618495076204e-05, + "loss": 3.5901, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5037815382055254e-05, + "loss": 3.5997, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502942943454473e-05, + "loss": 3.59, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.5021043487034214e-05, + "loss": 3.5944, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.5012657539523694e-05, + "loss": 3.5921, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.845747232437134, + "eval_runtime": 307.9623, + "eval_samples_per_second": 1239.084, + "eval_steps_per_second": 38.722, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500428797081691e-05, + "loss": 3.5876, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499590202330638e-05, + "loss": 3.5809, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498751607579586e-05, + "loss": 3.5846, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497913012828534e-05, + "loss": 3.5954, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497076055957856e-05, + "loss": 3.5919, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496237461206803e-05, + "loss": 3.5925, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495398866455751e-05, + "loss": 3.592, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494560271704699e-05, + "loss": 3.5877, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.49372331483402e-05, + "loss": 3.5867, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492884720082968e-05, + "loss": 3.5924, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.492046125331917e-05, + "loss": 3.5883, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491207530580865e-05, + "loss": 3.5793, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903705737101857e-05, + "loss": 3.5968, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4895319789591337e-05, + "loss": 3.5811, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.4886933842080816e-05, + "loss": 3.5816, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4878547894570296e-05, + "loss": 3.5734, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4870178325863506e-05, + "loss": 3.5853, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861792378352986e-05, + "loss": 3.5808, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4853406430842465e-05, + "loss": 3.577, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4845020483331945e-05, + "loss": 3.5867, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.4836650914625155e-05, + "loss": 3.5964, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.4828264967114634e-05, + "loss": 3.5864, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481987901960412e-05, + "loss": 3.5822, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.48114930720936e-05, + "loss": 3.5875, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480312350338681e-05, + "loss": 3.5926, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479473755587629e-05, + "loss": 3.5792, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478635160836577e-05, + "loss": 3.5742, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477796566085525e-05, + "loss": 3.595, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476957971334473e-05, + "loss": 3.5822, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476121014463794e-05, + "loss": 3.574, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475282419712742e-05, + "loss": 3.5832, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.47444382496169e-05, + "loss": 3.583, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473605230210638e-05, + "loss": 3.5883, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472768273339959e-05, + "loss": 3.6007, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4719296785889075e-05, + "loss": 3.5739, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710910838378555e-05, + "loss": 3.5871, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4702524890868035e-05, + "loss": 3.5921, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4694138943357515e-05, + "loss": 3.5625, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685769374650724e-05, + "loss": 3.5811, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.4677383427140204e-05, + "loss": 3.582, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4668997479629684e-05, + "loss": 3.5702, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4660611532119164e-05, + "loss": 3.5901, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465224196341237e-05, + "loss": 3.581, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464385601590185e-05, + "loss": 3.5886, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463547006839133e-05, + "loss": 3.5804, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462708412088081e-05, + "loss": 3.5849, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461871455217403e-05, + "loss": 3.5724, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.461032860466351e-05, + "loss": 3.5897, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460194265715299e-05, + "loss": 3.5561, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459355670964247e-05, + "loss": 3.5868, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458518714093568e-05, + "loss": 3.5773, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457680119342516e-05, + "loss": 3.589, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456841524591464e-05, + "loss": 3.5732, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.456002929840412e-05, + "loss": 3.5795, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.4551659729697326e-05, + "loss": 3.5722, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.4543273782186806e-05, + "loss": 3.5727, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534887834676286e-05, + "loss": 3.5925, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.4526501887165766e-05, + "loss": 3.5642, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451813231845898e-05, + "loss": 3.588, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450974637094846e-05, + "loss": 3.5844, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450136042343794e-05, + "loss": 3.5578, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449297447592742e-05, + "loss": 3.5916, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.44845885284169e-05, + "loss": 3.5692, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447621895971011e-05, + "loss": 3.5693, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446783301219959e-05, + "loss": 3.5817, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445944706468907e-05, + "loss": 3.5808, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445106111717855e-05, + "loss": 3.5672, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444269154847176e-05, + "loss": 3.5778, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443430560096124e-05, + "loss": 3.5622, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442591965345072e-05, + "loss": 3.5796, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.44175337059402e-05, + "loss": 3.5873, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4409164137233416e-05, + "loss": 3.5771, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.4400778189722896e-05, + "loss": 3.5842, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.4392392242212376e-05, + "loss": 3.5789, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.4384006294701856e-05, + "loss": 3.5935, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4375636725995065e-05, + "loss": 3.5765, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4367250778484545e-05, + "loss": 3.5852, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358864830974025e-05, + "loss": 3.5736, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4350478883463505e-05, + "loss": 3.5638, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4342109314756714e-05, + "loss": 3.5781, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.4333723367246194e-05, + "loss": 3.5836, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.4325337419735674e-05, + "loss": 3.5829, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4316951472225154e-05, + "loss": 3.5954, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430858190351837e-05, + "loss": 3.5662, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.430019595600785e-05, + "loss": 3.568, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.429181000849733e-05, + "loss": 3.5756, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428342406098681e-05, + "loss": 3.5874, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427505449228002e-05, + "loss": 3.5734, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.42666685447695e-05, + "loss": 3.5733, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425828259725898e-05, + "loss": 3.5744, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424989664974846e-05, + "loss": 3.5765, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424152708104167e-05, + "loss": 3.5759, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423314113353115e-05, + "loss": 3.5741, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422475518602063e-05, + "loss": 3.5842, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421636923851011e-05, + "loss": 3.5816, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420799966980332e-05, + "loss": 3.5787, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.41996137222928e-05, + "loss": 3.568, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419122777478228e-05, + "loss": 3.5751, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182841827271756e-05, + "loss": 3.5731, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417447225856497e-05, + "loss": 3.5901, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416608631105445e-05, + "loss": 3.5743, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415770036354393e-05, + "loss": 3.5704, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4149314416033405e-05, + "loss": 3.5756, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414094484732662e-05, + "loss": 3.5758, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.41325588998161e-05, + "loss": 3.5765, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412417295230558e-05, + "loss": 3.5727, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411578700479506e-05, + "loss": 3.5608, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410740105728454e-05, + "loss": 3.582, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409903148857776e-05, + "loss": 3.5722, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409064554106723e-05, + "loss": 3.5704, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408225959355671e-05, + "loss": 3.5629, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407387364604619e-05, + "loss": 3.5777, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.4065504077339406e-05, + "loss": 3.5817, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405711812982888e-05, + "loss": 3.5637, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404873218231836e-05, + "loss": 3.5782, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.404034623480784e-05, + "loss": 3.5856, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403197666610105e-05, + "loss": 3.5841, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402359071859053e-05, + "loss": 3.5739, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4015204771080015e-05, + "loss": 3.5693, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.4006818823569495e-05, + "loss": 3.5688, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.3998449254862704e-05, + "loss": 3.5832, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.3990063307352184e-05, + "loss": 3.5628, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3981677359841664e-05, + "loss": 3.5678, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3973291412331144e-05, + "loss": 3.5682, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396492184362435e-05, + "loss": 3.5756, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395653589611383e-05, + "loss": 3.5765, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394814994860331e-05, + "loss": 3.5769, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393976400109279e-05, + "loss": 3.5664, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3931394432386e-05, + "loss": 3.5715, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392300848487548e-05, + "loss": 3.5878, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391462253736497e-05, + "loss": 3.5724, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390623658985445e-05, + "loss": 3.585, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389786702114766e-05, + "loss": 3.5592, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388948107363714e-05, + "loss": 3.579, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388109512612662e-05, + "loss": 3.5761, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.38727091786161e-05, + "loss": 3.5744, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3864339609909306e-05, + "loss": 3.5787, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3855953662398786e-05, + "loss": 3.5703, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.3847567714888266e-05, + "loss": 3.5794, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3839181767377746e-05, + "loss": 3.5861, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3830795819867226e-05, + "loss": 3.5751, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.3822426251160435e-05, + "loss": 3.5747, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381404030364992e-05, + "loss": 3.5797, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.38056543561394e-05, + "loss": 3.5687, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379726840862888e-05, + "loss": 3.5705, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378889883992209e-05, + "loss": 3.5844, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378051289241157e-05, + "loss": 3.5726, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377212694490105e-05, + "loss": 3.5782, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376374099739053e-05, + "loss": 3.571, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8462741374969482, + "eval_runtime": 305.5361, + "eval_samples_per_second": 1248.923, + "eval_steps_per_second": 39.03, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375537142868374e-05, + "loss": 3.578, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374698548117322e-05, + "loss": 3.5614, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.37385995336627e-05, + "loss": 3.5687, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.373021358615218e-05, + "loss": 3.577, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372184401744539e-05, + "loss": 3.5756, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3713458069934876e-05, + "loss": 3.5754, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3705072122424356e-05, + "loss": 3.5696, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3696686174913836e-05, + "loss": 3.5749, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3688300227403315e-05, + "loss": 3.5679, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3679930658696525e-05, + "loss": 3.5813, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3671544711186005e-05, + "loss": 3.5659, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3663158763675484e-05, + "loss": 3.5659, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654789194968694e-05, + "loss": 3.58, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3646403247458174e-05, + "loss": 3.5581, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3638017299947654e-05, + "loss": 3.5657, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629631352437133e-05, + "loss": 3.5579, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3621245404926613e-05, + "loss": 3.5668, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361285945741609e-05, + "loss": 3.5627, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360447350990557e-05, + "loss": 3.5601, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359608756239505e-05, + "loss": 3.5629, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358771799368827e-05, + "loss": 3.581, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357933204617775e-05, + "loss": 3.5671, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357094609866723e-05, + "loss": 3.5644, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356256015115671e-05, + "loss": 3.5723, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355419058244992e-05, + "loss": 3.5786, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.35458046349394e-05, + "loss": 3.5595, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353741868742888e-05, + "loss": 3.5583, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352903273991836e-05, + "loss": 3.5776, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352064679240783e-05, + "loss": 3.5615, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351227722370105e-05, + "loss": 3.5576, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350389127619053e-05, + "loss": 3.5659, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349550532868001e-05, + "loss": 3.5631, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348711938116949e-05, + "loss": 3.5758, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.34787498124627e-05, + "loss": 3.5809, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.347036386495218e-05, + "loss": 3.5615, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346197791744166e-05, + "loss": 3.5655, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453591969931136e-05, + "loss": 3.5757, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344522240122435e-05, + "loss": 3.547, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343683645371383e-05, + "loss": 3.5705, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3428450506203305e-05, + "loss": 3.559, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3420064558692785e-05, + "loss": 3.5526, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411678611182265e-05, + "loss": 3.5693, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340330904247548e-05, + "loss": 3.5699, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339492309496496e-05, + "loss": 3.5672, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338653714745444e-05, + "loss": 3.5606, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337815119994392e-05, + "loss": 3.5657, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336978163123713e-05, + "loss": 3.5591, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336139568372661e-05, + "loss": 3.5681, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335300973621609e-05, + "loss": 3.5413, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334462378870557e-05, + "loss": 3.5678, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333625421999878e-05, + "loss": 3.5638, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332786827248826e-05, + "loss": 3.5699, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331948232497774e-05, + "loss": 3.5574, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331109637746722e-05, + "loss": 3.5596, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3302726808760434e-05, + "loss": 3.5527, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.3294340861249914e-05, + "loss": 3.5539, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.3285954913739394e-05, + "loss": 3.5746, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.3277568966228874e-05, + "loss": 3.5425, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326919939752208e-05, + "loss": 3.5744, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326081345001156e-05, + "loss": 3.5658, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325242750250104e-05, + "loss": 3.546, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324404155499052e-05, + "loss": 3.5747, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323567198628373e-05, + "loss": 3.548, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322728603877321e-05, + "loss": 3.5523, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321890009126269e-05, + "loss": 3.5627, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.321051414375217e-05, + "loss": 3.5655, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320214457504539e-05, + "loss": 3.5472, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319375862753487e-05, + "loss": 3.5691, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318537268002435e-05, + "loss": 3.5442, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317698673251383e-05, + "loss": 3.5586, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316861716380704e-05, + "loss": 3.5715, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.316023121629652e-05, + "loss": 3.5612, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3151845268786e-05, + "loss": 3.5665, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314345932127548e-05, + "loss": 3.5642, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3135089752568686e-05, + "loss": 3.5759, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3126703805058166e-05, + "loss": 3.559, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.3118317857547646e-05, + "loss": 3.5691, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.3109931910037126e-05, + "loss": 3.5511, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310156234133034e-05, + "loss": 3.549, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309317639381982e-05, + "loss": 3.5633, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.30847904463093e-05, + "loss": 3.5625, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307640449879878e-05, + "loss": 3.5648, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306803493009199e-05, + "loss": 3.5801, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305964898258147e-05, + "loss": 3.556, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305126303507095e-05, + "loss": 3.5497, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304287708756043e-05, + "loss": 3.5565, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303450751885364e-05, + "loss": 3.5696, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302612157134312e-05, + "loss": 3.5556, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.30177356238326e-05, + "loss": 3.5543, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300934967632208e-05, + "loss": 3.5584, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000980107615295e-05, + "loss": 3.5554, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2992594160104775e-05, + "loss": 3.5637, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2984208212594255e-05, + "loss": 3.5549, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975822265083735e-05, + "loss": 3.5649, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2967452696376944e-05, + "loss": 3.5679, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2959066748866424e-05, + "loss": 3.5591, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2950680801355904e-05, + "loss": 3.5538, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2942294853845384e-05, + "loss": 3.5569, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293392528513859e-05, + "loss": 3.5589, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292553933762807e-05, + "loss": 3.57, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291715339011755e-05, + "loss": 3.5581, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290876744260703e-05, + "loss": 3.5518, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.290039787390025e-05, + "loss": 3.561, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289201192638973e-05, + "loss": 3.5568, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288362597887921e-05, + "loss": 3.5569, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287524003136869e-05, + "loss": 3.5551, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.28668704626619e-05, + "loss": 3.5484, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285848451515138e-05, + "loss": 3.5633, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.285009856764086e-05, + "loss": 3.5563, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284171262013034e-05, + "loss": 3.5498, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283334305142355e-05, + "loss": 3.5457, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282495710391303e-05, + "loss": 3.5573, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281657115640251e-05, + "loss": 3.5653, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280818520889199e-05, + "loss": 3.5508, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.27998156401852e-05, + "loss": 3.5598, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279142969267468e-05, + "loss": 3.5648, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278304374516416e-05, + "loss": 3.5689, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277465779765364e-05, + "loss": 3.5596, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276628822894685e-05, + "loss": 3.5507, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275790228143633e-05, + "loss": 3.5534, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274951633392581e-05, + "loss": 3.5664, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274113038641529e-05, + "loss": 3.5449, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273274443890477e-05, + "loss": 3.5523, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272437487019798e-05, + "loss": 3.5534, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271598892268746e-05, + "loss": 3.5565, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270760297517694e-05, + "loss": 3.5593, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2699233406470156e-05, + "loss": 3.5646, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690847458959636e-05, + "loss": 3.5473, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2682461511449116e-05, + "loss": 3.5542, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2674075563938596e-05, + "loss": 3.5688, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.2665689616428076e-05, + "loss": 3.5586, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2657320047721285e-05, + "loss": 3.5642, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648934100210765e-05, + "loss": 3.5448, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2640548152700245e-05, + "loss": 3.5613, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2632162205189725e-05, + "loss": 3.5595, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623792636482934e-05, + "loss": 3.558, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.2615406688972414e-05, + "loss": 3.5564, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.2607020741461894e-05, + "loss": 3.5561, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2598634793951374e-05, + "loss": 3.5672, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.259026522524459e-05, + "loss": 3.5627, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258187927773407e-05, + "loss": 3.5618, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257349333022355e-05, + "loss": 3.5551, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256510738271303e-05, + "loss": 3.564, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255673781400624e-05, + "loss": 3.5547, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254835186649572e-05, + "loss": 3.5495, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.25399659189852e-05, + "loss": 3.5707, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253157997147468e-05, + "loss": 3.5525, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252321040276789e-05, + "loss": 3.567, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251482445525737e-05, + "loss": 3.5534, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.846177339553833, + "eval_runtime": 302.8487, + "eval_samples_per_second": 1260.005, + "eval_steps_per_second": 39.376, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250643850774685e-05, + "loss": 3.5517, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249805256023633e-05, + "loss": 3.5494, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489682991529544e-05, + "loss": 3.5547, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.2481297044019024e-05, + "loss": 3.5574, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.2472911096508504e-05, + "loss": 3.5592, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.2464525148997983e-05, + "loss": 3.5604, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245615558029119e-05, + "loss": 3.5519, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244776963278067e-05, + "loss": 3.5551, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243938368527015e-05, + "loss": 3.5514, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2430997737759626e-05, + "loss": 3.5644, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2422611790249106e-05, + "loss": 3.5505, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241424222154232e-05, + "loss": 3.5519, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240587265283553e-05, + "loss": 3.5645, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239748670532502e-05, + "loss": 3.5434, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.23891007578145e-05, + "loss": 3.5476, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238071481030398e-05, + "loss": 3.5433, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237232886279346e-05, + "loss": 3.5514, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236394291528293e-05, + "loss": 3.5411, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235555696777241e-05, + "loss": 3.5449, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234717102026189e-05, + "loss": 3.5495, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.23388014515551e-05, + "loss": 3.5627, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.233041550404458e-05, + "loss": 3.5529, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232202955653406e-05, + "loss": 3.5442, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231364360902354e-05, + "loss": 3.5571, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2305274040316755e-05, + "loss": 3.5627, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2296888092806235e-05, + "loss": 3.5455, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2288502145295715e-05, + "loss": 3.5405, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2280116197785195e-05, + "loss": 3.5609, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2271746629078404e-05, + "loss": 3.5433, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2263360681567884e-05, + "loss": 3.5451, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.2254974734057364e-05, + "loss": 3.5477, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.2246588786546844e-05, + "loss": 3.5496, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223821921784005e-05, + "loss": 3.5564, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222983327032953e-05, + "loss": 3.5645, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222144732281901e-05, + "loss": 3.5486, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221306137530849e-05, + "loss": 3.5478, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220469180660171e-05, + "loss": 3.559, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219630585909119e-05, + "loss": 3.5325, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218791991158067e-05, + "loss": 3.5547, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217953396407015e-05, + "loss": 3.5417, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217114801655963e-05, + "loss": 3.5413, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216277844785284e-05, + "loss": 3.5513, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215439250034232e-05, + "loss": 3.5579, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.21460065528318e-05, + "loss": 3.5461, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213762060532128e-05, + "loss": 3.5481, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212925103661449e-05, + "loss": 3.549, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212086508910397e-05, + "loss": 3.5437, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2112479141593447e-05, + "loss": 3.5515, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2104093194082927e-05, + "loss": 3.525, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209572362537614e-05, + "loss": 3.5508, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208733767786562e-05, + "loss": 3.5479, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.20789517303551e-05, + "loss": 3.5546, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.207056578284458e-05, + "loss": 3.54, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206219621413779e-05, + "loss": 3.5391, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205381026662727e-05, + "loss": 3.5389, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204542431911675e-05, + "loss": 3.5345, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203703837160623e-05, + "loss": 3.5602, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202866880289944e-05, + "loss": 3.5317, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.202028285538892e-05, + "loss": 3.5537, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.20118969078784e-05, + "loss": 3.5476, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200351096036788e-05, + "loss": 3.5334, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.1995141391661096e-05, + "loss": 3.5557, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.1986755444150576e-05, + "loss": 3.533, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.1978369496640056e-05, + "loss": 3.5362, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.1969983549129536e-05, + "loss": 3.5451, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.1961613980422745e-05, + "loss": 3.5525, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.1953228032912225e-05, + "loss": 3.5313, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.1944842085401705e-05, + "loss": 3.5513, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1936456137891185e-05, + "loss": 3.5258, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1928086569184394e-05, + "loss": 3.5421, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1919700621673874e-05, + "loss": 3.5555, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.1911314674163354e-05, + "loss": 3.5498, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.1902928726652834e-05, + "loss": 3.5481, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189455915794605e-05, + "loss": 3.5489, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188617321043553e-05, + "loss": 3.5584, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187778726292501e-05, + "loss": 3.5458, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186940131541449e-05, + "loss": 3.5577, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.18610317467077e-05, + "loss": 3.5352, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185264579919718e-05, + "loss": 3.5327, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184425985168666e-05, + "loss": 3.5446, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183587390417614e-05, + "loss": 3.5466, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182750433546935e-05, + "loss": 3.5484, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181911838795883e-05, + "loss": 3.5653, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181073244044831e-05, + "loss": 3.5431, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180234649293779e-05, + "loss": 3.5289, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1793976924231003e-05, + "loss": 3.5433, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178559097672048e-05, + "loss": 3.5499, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177720502920996e-05, + "loss": 3.542, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176881908169944e-05, + "loss": 3.5393, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.176044951299265e-05, + "loss": 3.5454, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175206356548213e-05, + "loss": 3.5389, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174367761797161e-05, + "loss": 3.5493, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173529167046109e-05, + "loss": 3.5367, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.17269221017543e-05, + "loss": 3.5491, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171853615424378e-05, + "loss": 3.5541, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.171015020673326e-05, + "loss": 3.5448, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170176425922274e-05, + "loss": 3.5359, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.169339469051596e-05, + "loss": 3.5424, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.168500874300544e-05, + "loss": 3.5397, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167662279549492e-05, + "loss": 3.5525, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.16682368479844e-05, + "loss": 3.5455, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1659867279277606e-05, + "loss": 3.5381, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.1651481331767086e-05, + "loss": 3.542, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.1643095384256566e-05, + "loss": 3.5425, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.1634709436746046e-05, + "loss": 3.544, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1626323489235526e-05, + "loss": 3.5404, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.1617953920528735e-05, + "loss": 3.5359, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.1609567973018215e-05, + "loss": 3.5449, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.1601182025507695e-05, + "loss": 3.5423, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.1592796077997175e-05, + "loss": 3.532, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158442650929039e-05, + "loss": 3.5324, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157604056177987e-05, + "loss": 3.5367, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156765461426935e-05, + "loss": 3.5541, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155926866675883e-05, + "loss": 3.5363, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155089909805204e-05, + "loss": 3.5429, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154251315054152e-05, + "loss": 3.544, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1534127203031e-05, + "loss": 3.559, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152574125552048e-05, + "loss": 3.5435, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151737168681369e-05, + "loss": 3.5342, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150898573930317e-05, + "loss": 3.5392, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.150059979179265e-05, + "loss": 3.5471, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149221384428213e-05, + "loss": 3.53, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1483844275575344e-05, + "loss": 3.5377, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1475458328064824e-05, + "loss": 3.5378, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1467072380554304e-05, + "loss": 3.5423, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145868643304378e-05, + "loss": 3.538, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.145031686433699e-05, + "loss": 3.5498, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144193091682647e-05, + "loss": 3.5388, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1433544969315946e-05, + "loss": 3.5395, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1425159021805426e-05, + "loss": 3.5527, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141678945309864e-05, + "loss": 3.545, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140840350558812e-05, + "loss": 3.548, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.14000175580776e-05, + "loss": 3.5322, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.139163161056708e-05, + "loss": 3.5411, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.13832620418603e-05, + "loss": 3.5478, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137487609434978e-05, + "loss": 3.5399, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136649014683925e-05, + "loss": 3.5439, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135810419932873e-05, + "loss": 3.5404, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134973463062195e-05, + "loss": 3.5529, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134134868311142e-05, + "loss": 3.5475, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.13329627356009e-05, + "loss": 3.547, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132457678809038e-05, + "loss": 3.5421, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.1316207219383596e-05, + "loss": 3.5473, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130782127187307e-05, + "loss": 3.5363, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.1299435324362556e-05, + "loss": 3.5362, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.1291049376852036e-05, + "loss": 3.5559, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128267980814525e-05, + "loss": 3.5375, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1274293860634725e-05, + "loss": 3.5499, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.1265907913124205e-05, + "loss": 3.5396, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.8480913639068604, + "eval_runtime": 302.5865, + "eval_samples_per_second": 1261.097, + "eval_steps_per_second": 39.41, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.1257521965613685e-05, + "loss": 3.5232, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.1249136018103165e-05, + "loss": 3.5335, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.1240750070592645e-05, + "loss": 3.5363, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.1232364123082125e-05, + "loss": 3.5428, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.1223978175571605e-05, + "loss": 3.5438, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.1215608606864814e-05, + "loss": 3.5471, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.1207222659354294e-05, + "loss": 3.5362, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.1198836711843774e-05, + "loss": 3.5381, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1190450764333254e-05, + "loss": 3.5405, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118208119562647e-05, + "loss": 3.5513, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117369524811595e-05, + "loss": 3.5286, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116530930060543e-05, + "loss": 3.5389, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115693973189864e-05, + "loss": 3.5462, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114855378438812e-05, + "loss": 3.5334, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.11401678368776e-05, + "loss": 3.5301, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113178188936708e-05, + "loss": 3.5314, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112339594185656e-05, + "loss": 3.5304, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111500999434604e-05, + "loss": 3.5294, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110662404683552e-05, + "loss": 3.5311, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1098238099325e-05, + "loss": 3.5313, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108986853061821e-05, + "loss": 3.55, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108148258310769e-05, + "loss": 3.536, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1073096635597174e-05, + "loss": 3.5315, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064710688086654e-05, + "loss": 3.5389, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105634111937986e-05, + "loss": 3.5512, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104795517186934e-05, + "loss": 3.5262, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103956922435882e-05, + "loss": 3.528, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.10311832768483e-05, + "loss": 3.5425, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102281370814151e-05, + "loss": 3.5314, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101442776063099e-05, + "loss": 3.5287, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100604181312047e-05, + "loss": 3.5298, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.099765586560995e-05, + "loss": 3.538, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098928629690316e-05, + "loss": 3.5397, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098090034939264e-05, + "loss": 3.5458, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097251440188213e-05, + "loss": 3.5378, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096412845437161e-05, + "loss": 3.5316, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095575888566482e-05, + "loss": 3.5415, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0947372938154297e-05, + "loss": 3.52, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0938986990643777e-05, + "loss": 3.5422, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0930601043133257e-05, + "loss": 3.5254, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0922231474426466e-05, + "loss": 3.526, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0913845526915946e-05, + "loss": 3.5328, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.0905459579405426e-05, + "loss": 3.5416, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0897073631894905e-05, + "loss": 3.5322, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.0888704063188115e-05, + "loss": 3.5341, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.0880318115677595e-05, + "loss": 3.5325, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087193216816708e-05, + "loss": 3.5298, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863546220656554e-05, + "loss": 3.5405, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085517665194977e-05, + "loss": 3.507, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084679070443925e-05, + "loss": 3.5306, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083840475692873e-05, + "loss": 3.5416, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.0830018809418203e-05, + "loss": 3.5343, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082164924071142e-05, + "loss": 3.5222, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.08132632932009e-05, + "loss": 3.5286, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080487734569038e-05, + "loss": 3.5255, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079649139817985e-05, + "loss": 3.5196, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078812182947307e-05, + "loss": 3.5482, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077973588196255e-05, + "loss": 3.5152, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077134993445203e-05, + "loss": 3.5375, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076296398694151e-05, + "loss": 3.5306, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.0754594418234724e-05, + "loss": 3.5231, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0746208470724204e-05, + "loss": 3.5363, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073782252321368e-05, + "loss": 3.5204, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072943657570316e-05, + "loss": 3.5247, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072106700699637e-05, + "loss": 3.5237, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071268105948585e-05, + "loss": 3.5431, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0704295111975326e-05, + "loss": 3.5167, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0695909164464806e-05, + "loss": 3.5354, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068753959575802e-05, + "loss": 3.5134, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.06791536482475e-05, + "loss": 3.5251, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.067076770073698e-05, + "loss": 3.5391, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066238175322646e-05, + "loss": 3.5371, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065401218451968e-05, + "loss": 3.5313, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064562623700915e-05, + "loss": 3.534, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063724028949863e-05, + "loss": 3.5442, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062885434198811e-05, + "loss": 3.5273, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062048477328133e-05, + "loss": 3.5409, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.06120988257708e-05, + "loss": 3.5228, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060371287826028e-05, + "loss": 3.519, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059532693074976e-05, + "loss": 3.5276, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.0586957362042976e-05, + "loss": 3.5303, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.0578571414532456e-05, + "loss": 3.5345, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0570185467021935e-05, + "loss": 3.5467, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0561799519511415e-05, + "loss": 3.5356, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0553429950804625e-05, + "loss": 3.5165, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0545044003294105e-05, + "loss": 3.5236, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0536658055783584e-05, + "loss": 3.5369, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0528272108273064e-05, + "loss": 3.5285, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0519902539566274e-05, + "loss": 3.5247, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511516592055757e-05, + "loss": 3.5297, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0503130644545237e-05, + "loss": 3.5227, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494744697034717e-05, + "loss": 3.5339, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0486375128327926e-05, + "loss": 3.5251, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477989180817406e-05, + "loss": 3.5331, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469603233306886e-05, + "loss": 3.5346, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0461217285796366e-05, + "loss": 3.5325, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045283133828585e-05, + "loss": 3.5223, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0444461769579058e-05, + "loss": 3.5278, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0436075822068538e-05, + "loss": 3.526, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427689874558018e-05, + "loss": 3.537, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0419303927047498e-05, + "loss": 3.5289, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.041093435834071e-05, + "loss": 3.5206, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.040254841083019e-05, + "loss": 3.5255, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.039416246331967e-05, + "loss": 3.5295, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.038577651580915e-05, + "loss": 3.5298, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037740694710236e-05, + "loss": 3.5251, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036902099959184e-05, + "loss": 3.5178, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.036063505208132e-05, + "loss": 3.5329, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0352249104570803e-05, + "loss": 3.5293, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343879535864012e-05, + "loss": 3.5144, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0335493588353492e-05, + "loss": 3.5195, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0327107640842972e-05, + "loss": 3.5187, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318721693332452e-05, + "loss": 3.5364, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0310352124625664e-05, + "loss": 3.5247, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0301966177115144e-05, + "loss": 3.5273, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293580229604624e-05, + "loss": 3.531, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0285194282094104e-05, + "loss": 3.544, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276824713387313e-05, + "loss": 3.5268, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0268438765876793e-05, + "loss": 3.5173, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0260052818366273e-05, + "loss": 3.5309, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251666870855756e-05, + "loss": 3.5297, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0243297302148966e-05, + "loss": 3.5188, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234911354638445e-05, + "loss": 3.52, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226525407127925e-05, + "loss": 3.5256, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0218139459617405e-05, + "loss": 3.5276, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209769890910618e-05, + "loss": 3.5236, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0201383943400098e-05, + "loss": 3.5355, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0192997995889578e-05, + "loss": 3.5218, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184612048379058e-05, + "loss": 3.5271, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0176242479672267e-05, + "loss": 3.5285, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167856532161747e-05, + "loss": 3.5356, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0159470584651227e-05, + "loss": 3.5344, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.015108463714071e-05, + "loss": 3.5135, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014271506843392e-05, + "loss": 3.5243, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.01343291209234e-05, + "loss": 3.5349, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.012594317341288e-05, + "loss": 3.5241, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011755722590236e-05, + "loss": 3.531, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010918765719557e-05, + "loss": 3.5233, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010080170968505e-05, + "loss": 3.539, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009241576217453e-05, + "loss": 3.5294, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008402981466401e-05, + "loss": 3.5318, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007566024595722e-05, + "loss": 3.5255, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.00672742984467e-05, + "loss": 3.5323, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005888835093618e-05, + "loss": 3.5225, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0050502403425664e-05, + "loss": 3.5178, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0042132834718873e-05, + "loss": 3.5405, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033746887208353e-05, + "loss": 3.5276, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0025360939697833e-05, + "loss": 3.5333, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016974992187313e-05, + "loss": 3.526, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008605423480525e-05, + "loss": 3.5192, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.849181652069092, + "eval_runtime": 304.2322, + "eval_samples_per_second": 1254.276, + "eval_steps_per_second": 39.197, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 3.0000219475970005e-05, + "loss": 3.5196, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991833528459485e-05, + "loss": 3.5212, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9983447580948965e-05, + "loss": 3.5294, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9975078012242174e-05, + "loss": 3.5275, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966692064731654e-05, + "loss": 3.5335, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9958306117221134e-05, + "loss": 3.5205, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949920169710617e-05, + "loss": 3.5236, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941550601003827e-05, + "loss": 3.5191, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9933164653493306e-05, + "loss": 3.5409, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924778705982786e-05, + "loss": 3.5162, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9916392758472266e-05, + "loss": 3.5231, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990802318976548e-05, + "loss": 3.5317, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.989963724225496e-05, + "loss": 3.5231, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989125129474444e-05, + "loss": 3.515, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988286534723392e-05, + "loss": 3.5145, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874495778527128e-05, + "loss": 3.5141, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9866109831016608e-05, + "loss": 3.5158, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857723883506088e-05, + "loss": 3.5193, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984933793599557e-05, + "loss": 3.5136, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.984096836728878e-05, + "loss": 3.5388, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.983258241977826e-05, + "loss": 3.5223, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.982419647226774e-05, + "loss": 3.5152, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.981581052475722e-05, + "loss": 3.5253, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9807440956050433e-05, + "loss": 3.5338, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9799055008539912e-05, + "loss": 3.5108, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790669061029392e-05, + "loss": 3.5176, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9782283113518872e-05, + "loss": 3.5229, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.977391354481208e-05, + "loss": 3.5252, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.976552759730156e-05, + "loss": 3.5103, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975714164979104e-05, + "loss": 3.5139, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.974875570228052e-05, + "loss": 3.5244, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9740386133573734e-05, + "loss": 3.5268, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9732000186063214e-05, + "loss": 3.5289, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723614238552694e-05, + "loss": 3.5239, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9715228291042174e-05, + "loss": 3.5186, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706858722335383e-05, + "loss": 3.5236, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698472774824866e-05, + "loss": 3.5075, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9690086827314346e-05, + "loss": 3.5269, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681700879803826e-05, + "loss": 3.5113, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9673331311097035e-05, + "loss": 3.5129, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664945363586515e-05, + "loss": 3.5162, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656559416075995e-05, + "loss": 3.5307, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.964817346856547e-05, + "loss": 3.5171, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639803899858688e-05, + "loss": 3.5187, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9631417952348167e-05, + "loss": 3.5215, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9623032004837647e-05, + "loss": 3.5103, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961464605732712e-05, + "loss": 3.5285, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9606276488620336e-05, + "loss": 3.4951, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959789054110982e-05, + "loss": 3.5116, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.95895045935993e-05, + "loss": 3.5228, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9581118646088773e-05, + "loss": 3.5239, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.957274907738199e-05, + "loss": 3.5109, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956436312987147e-05, + "loss": 3.5109, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555977182360945e-05, + "loss": 3.5148, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547591234850425e-05, + "loss": 3.5012, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.953922166614364e-05, + "loss": 3.5329, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.953083571863312e-05, + "loss": 3.508, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522449771122594e-05, + "loss": 3.5208, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9514063823612074e-05, + "loss": 3.5157, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.950569425490529e-05, + "loss": 3.5074, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9497308307394767e-05, + "loss": 3.518, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488922359884247e-05, + "loss": 3.5094, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480536412373727e-05, + "loss": 3.5127, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9472166843666942e-05, + "loss": 3.5065, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946378089615642e-05, + "loss": 3.5287, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.94553949486459e-05, + "loss": 3.5068, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944700900113538e-05, + "loss": 3.5156, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438639432428595e-05, + "loss": 3.5007, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9430253484918068e-05, + "loss": 3.5146, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421867537407548e-05, + "loss": 3.5251, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413481589897028e-05, + "loss": 3.5218, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.940511202119024e-05, + "loss": 3.5139, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.939672607367972e-05, + "loss": 3.5236, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.93883401261692e-05, + "loss": 3.5288, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937995417865868e-05, + "loss": 3.5131, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.937158460995189e-05, + "loss": 3.5241, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9363198662441373e-05, + "loss": 3.5124, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354812714930853e-05, + "loss": 3.5048, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9346426767420333e-05, + "loss": 3.5143, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9338057198713542e-05, + "loss": 3.5131, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.932967125120302e-05, + "loss": 3.5251, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.93212853036925e-05, + "loss": 3.5328, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.931289935618198e-05, + "loss": 3.5223, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304529787475194e-05, + "loss": 3.4996, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9296143839964674e-05, + "loss": 3.5124, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287757892454154e-05, + "loss": 3.5194, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9279371944943634e-05, + "loss": 3.5158, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9271002376236843e-05, + "loss": 3.5099, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262616428726326e-05, + "loss": 3.515, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9254230481215806e-05, + "loss": 3.5099, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245844533705286e-05, + "loss": 3.5167, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9237474964998495e-05, + "loss": 3.511, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9229089017487975e-05, + "loss": 3.5228, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220703069977455e-05, + "loss": 3.5171, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9212317122466935e-05, + "loss": 3.5212, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203947553760148e-05, + "loss": 3.5027, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195561606249628e-05, + "loss": 3.5127, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9187175658739108e-05, + "loss": 3.5148, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178789711228588e-05, + "loss": 3.5221, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9170420142521797e-05, + "loss": 3.521, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.916203419501128e-05, + "loss": 3.5059, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915364824750076e-05, + "loss": 3.5114, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914526229999024e-05, + "loss": 3.5117, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913689273128345e-05, + "loss": 3.5195, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.912850678377293e-05, + "loss": 3.509, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.912012083626241e-05, + "loss": 3.5071, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911173488875189e-05, + "loss": 3.5204, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.91033653200451e-05, + "loss": 3.5108, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909499575133831e-05, + "loss": 3.5051, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908660980382779e-05, + "loss": 3.506, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.907822385631727e-05, + "loss": 3.5054, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906983790880675e-05, + "loss": 3.5214, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9061451961296234e-05, + "loss": 3.5107, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9053066013785714e-05, + "loss": 3.5129, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044680066275194e-05, + "loss": 3.5196, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9036294118764674e-05, + "loss": 3.5285, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9027924550057883e-05, + "loss": 3.5113, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019538602547363e-05, + "loss": 3.5066, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9011152655036843e-05, + "loss": 3.5126, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9002766707526326e-05, + "loss": 3.5161, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8994397138819535e-05, + "loss": 3.5052, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8986011191309015e-05, + "loss": 3.5071, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977625243798495e-05, + "loss": 3.508, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8969239296287975e-05, + "loss": 3.5159, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960869727581187e-05, + "loss": 3.5124, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8952483780070667e-05, + "loss": 3.519, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8944097832560147e-05, + "loss": 3.5098, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935711885049627e-05, + "loss": 3.5107, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8927342316342836e-05, + "loss": 3.5112, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8918956368832316e-05, + "loss": 3.5265, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910570421321796e-05, + "loss": 3.5167, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.890218447381128e-05, + "loss": 3.5092, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.889381490510449e-05, + "loss": 3.5048, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888542895759397e-05, + "loss": 3.5218, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887704301008345e-05, + "loss": 3.5096, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.886865706257293e-05, + "loss": 3.5183, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.886028749386614e-05, + "loss": 3.5097, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885190154635562e-05, + "loss": 3.5237, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.88435155988451e-05, + "loss": 3.513, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883512965133458e-05, + "loss": 3.5175, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.882676008262779e-05, + "loss": 3.5146, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.881837413511727e-05, + "loss": 3.5222, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.880998818760675e-05, + "loss": 3.5136, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.880160224009623e-05, + "loss": 3.5003, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8793232671389442e-05, + "loss": 3.526, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784846723878922e-05, + "loss": 3.5156, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776460776368402e-05, + "loss": 3.5175, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8768074828857882e-05, + "loss": 3.5142, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875970526015109e-05, + "loss": 3.5044, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.849909782409668, + "eval_runtime": 304.1238, + "eval_samples_per_second": 1254.723, + "eval_steps_per_second": 39.211, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751319312640575e-05, + "loss": 3.5032, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742933365130055e-05, + "loss": 3.5101, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734547417619535e-05, + "loss": 3.5173, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8726177848912744e-05, + "loss": 3.5096, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717791901402224e-05, + "loss": 3.5243, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709405953891704e-05, + "loss": 3.5056, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8701020006381184e-05, + "loss": 3.5116, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692650437674396e-05, + "loss": 3.5059, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8684264490163876e-05, + "loss": 3.5253, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675878542653356e-05, + "loss": 3.5058, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8667492595142836e-05, + "loss": 3.5067, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8659123026436045e-05, + "loss": 3.5122, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650753457729257e-05, + "loss": 3.511, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642367510218737e-05, + "loss": 3.5009, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633981562708217e-05, + "loss": 3.5073, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625595615197697e-05, + "loss": 3.4944, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8617209667687177e-05, + "loss": 3.5042, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608823720176657e-05, + "loss": 3.5048, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8600437772666137e-05, + "loss": 3.4975, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859206820395935e-05, + "loss": 3.5307, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858368225644883e-05, + "loss": 3.5017, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857529630893831e-05, + "loss": 3.5087, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856691036142779e-05, + "loss": 3.5075, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558540792721e-05, + "loss": 3.5223, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8550154845210482e-05, + "loss": 3.4984, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541768897699962e-05, + "loss": 3.5051, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8533382950189442e-05, + "loss": 3.5096, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852501338148265e-05, + "loss": 3.5119, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851662743397213e-05, + "loss": 3.4994, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850824148646161e-05, + "loss": 3.5003, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849985553895109e-05, + "loss": 3.5129, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491485970244303e-05, + "loss": 3.5124, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8483100022733783e-05, + "loss": 3.5151, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474714075223263e-05, + "loss": 3.5089, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8466328127712736e-05, + "loss": 3.5003, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457958559005952e-05, + "loss": 3.5135, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449572611495436e-05, + "loss": 3.49, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8441186663984916e-05, + "loss": 3.5144, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843280071647439e-05, + "loss": 3.4967, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424431147767605e-05, + "loss": 3.5004, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8416045200257085e-05, + "loss": 3.5008, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407659252746565e-05, + "loss": 3.516, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.839927330523604e-05, + "loss": 3.5056, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390903736529257e-05, + "loss": 3.5033, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382517789018737e-05, + "loss": 3.5096, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837413184150821e-05, + "loss": 3.5032, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836574589399769e-05, + "loss": 3.51, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8357376325290906e-05, + "loss": 3.4867, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834899037778039e-05, + "loss": 3.4972, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340604430269863e-05, + "loss": 3.5109, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8332218482759342e-05, + "loss": 3.5101, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832384891405256e-05, + "loss": 3.4981, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831546296654204e-05, + "loss": 3.4956, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8307077019031515e-05, + "loss": 3.5044, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298691071520995e-05, + "loss": 3.4852, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.829032150281421e-05, + "loss": 3.5165, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281935555303684e-05, + "loss": 3.5001, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273549607793164e-05, + "loss": 3.5061, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8265163660282644e-05, + "loss": 3.5027, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256777712772127e-05, + "loss": 3.4926, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248408144065336e-05, + "loss": 3.5066, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8240022196554816e-05, + "loss": 3.4965, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231636249044296e-05, + "loss": 3.4964, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8223250301533776e-05, + "loss": 3.4931, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821488073282699e-05, + "loss": 3.5138, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.820649478531647e-05, + "loss": 3.4975, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819810883780595e-05, + "loss": 3.4974, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189739269099158e-05, + "loss": 3.4901, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8181353321588638e-05, + "loss": 3.5011, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172967374078118e-05, + "loss": 3.5085, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164581426567597e-05, + "loss": 3.5101, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815621185786081e-05, + "loss": 3.5004, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814782591035029e-05, + "loss": 3.5096, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813943996283977e-05, + "loss": 3.511, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813105401532925e-05, + "loss": 3.5049, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812268444662246e-05, + "loss": 3.5115, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8114298499111942e-05, + "loss": 3.5001, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105912551601422e-05, + "loss": 3.4908, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8097526604090902e-05, + "loss": 3.5003, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808915703538411e-05, + "loss": 3.5022, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808077108787359e-05, + "loss": 3.5066, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807238514036307e-05, + "loss": 3.5188, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806399919285255e-05, + "loss": 3.5083, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055629624145764e-05, + "loss": 3.486, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047243676635244e-05, + "loss": 3.4973, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038857729124724e-05, + "loss": 3.5061, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8030471781614203e-05, + "loss": 3.5056, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8022085834103683e-05, + "loss": 3.4959, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013716265396896e-05, + "loss": 3.5004, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005330317886376e-05, + "loss": 3.4979, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996944370375856e-05, + "loss": 3.5022, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988558422865336e-05, + "loss": 3.4957, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7980188854158545e-05, + "loss": 3.5092, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971802906648025e-05, + "loss": 3.5041, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963416959137505e-05, + "loss": 3.5075, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7955031011626988e-05, + "loss": 3.4908, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946661442920197e-05, + "loss": 3.5016, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938275495409677e-05, + "loss": 3.5025, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929889547899157e-05, + "loss": 3.5056, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921503600388637e-05, + "loss": 3.5044, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.791313403168185e-05, + "loss": 3.4975, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790474808417133e-05, + "loss": 3.4955, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789636213666081e-05, + "loss": 3.5032, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788797618915029e-05, + "loss": 3.5043, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.78796066204435e-05, + "loss": 3.492, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787122067293298e-05, + "loss": 3.4936, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786283472542246e-05, + "loss": 3.5077, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785444877791194e-05, + "loss": 3.4965, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784607920920515e-05, + "loss": 3.4933, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783769326169463e-05, + "loss": 3.4939, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782930731418411e-05, + "loss": 3.492, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.782092136667359e-05, + "loss": 3.5094, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.78125517979668e-05, + "loss": 3.4936, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7804165850456283e-05, + "loss": 3.5043, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795779902945763e-05, + "loss": 3.501, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787393955435243e-05, + "loss": 3.5173, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7779024386728452e-05, + "loss": 3.5005, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770638439217932e-05, + "loss": 3.4919, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7762252491707412e-05, + "loss": 3.5008, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753866544196892e-05, + "loss": 3.503, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745496975490105e-05, + "loss": 3.4902, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7737111027979585e-05, + "loss": 3.4964, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728725080469064e-05, + "loss": 3.4945, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7720339132958544e-05, + "loss": 3.5064, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711969564251754e-05, + "loss": 3.495, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703583616741237e-05, + "loss": 3.5075, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7695197669230717e-05, + "loss": 3.4973, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686811721720197e-05, + "loss": 3.4987, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7678425774209677e-05, + "loss": 3.498, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7670056205502886e-05, + "loss": 3.5138, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661670257992366e-05, + "loss": 3.5061, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7653284310481846e-05, + "loss": 3.4913, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644914741775058e-05, + "loss": 3.4913, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636528794264538e-05, + "loss": 3.5053, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7628142846754018e-05, + "loss": 3.5005, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619756899243498e-05, + "loss": 3.5067, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7611387330536707e-05, + "loss": 3.4981, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760300138302619e-05, + "loss": 3.5088, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759461543551567e-05, + "loss": 3.4993, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758622948800515e-05, + "loss": 3.5051, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757785991929836e-05, + "loss": 3.5003, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756947397178784e-05, + "loss": 3.5038, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.756108802427732e-05, + "loss": 3.5003, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.75527020767668e-05, + "loss": 3.4909, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7544332508060012e-05, + "loss": 3.5132, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535946560549492e-05, + "loss": 3.5053, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527560613038972e-05, + "loss": 3.5037, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7519174665528452e-05, + "loss": 3.497, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751080509682166e-05, + "loss": 3.4927, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.851712703704834, + "eval_runtime": 306.0629, + "eval_samples_per_second": 1246.773, + "eval_steps_per_second": 38.963, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502419149311144e-05, + "loss": 3.4931, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7494033201800624e-05, + "loss": 3.4943, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485647254290104e-05, + "loss": 3.505, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7477277685583313e-05, + "loss": 3.4943, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468891738072793e-05, + "loss": 3.5139, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460505790562273e-05, + "loss": 3.4939, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7452119843051753e-05, + "loss": 3.4962, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443750274344966e-05, + "loss": 3.4934, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7435364326834446e-05, + "loss": 3.5109, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426978379323925e-05, + "loss": 3.4934, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7418592431813405e-05, + "loss": 3.4912, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7410222863106615e-05, + "loss": 3.4958, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401853294399827e-05, + "loss": 3.4993, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393467346889307e-05, + "loss": 3.488, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7385081399378787e-05, + "loss": 3.4955, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376695451868267e-05, + "loss": 3.4836, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7368309504357747e-05, + "loss": 3.4877, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359923556847227e-05, + "loss": 3.492, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7351537609336707e-05, + "loss": 3.4833, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734316804062992e-05, + "loss": 3.5206, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.73347820931194e-05, + "loss": 3.4929, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.732639614560888e-05, + "loss": 3.4897, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.731801019809836e-05, + "loss": 3.4983, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309624250587836e-05, + "loss": 3.5056, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730125468188105e-05, + "loss": 3.4868, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729286873437053e-05, + "loss": 3.4918, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284482786860005e-05, + "loss": 3.4947, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7276096839349485e-05, + "loss": 3.4999, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.72677272706427e-05, + "loss": 3.4817, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725934132313218e-05, + "loss": 3.4895, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250955375621657e-05, + "loss": 3.4962, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242569428111137e-05, + "loss": 3.4976, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7234199859404353e-05, + "loss": 3.5087, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225813911893833e-05, + "loss": 3.4969, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217427964383306e-05, + "loss": 3.4851, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720904201687279e-05, + "loss": 3.4984, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200672448166005e-05, + "loss": 3.4806, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.719228650065548e-05, + "loss": 3.4998, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718390055314496e-05, + "loss": 3.4839, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175514605634438e-05, + "loss": 3.4864, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7167145036927654e-05, + "loss": 3.4908, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715875908941713e-05, + "loss": 3.5044, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.715037314190661e-05, + "loss": 3.4935, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714198719439609e-05, + "loss": 3.4875, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133617625689307e-05, + "loss": 3.4943, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712523167817878e-05, + "loss": 3.4911, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711684573066826e-05, + "loss": 3.4977, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7108459783157743e-05, + "loss": 3.4774, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7100090214450952e-05, + "loss": 3.4808, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091704266940432e-05, + "loss": 3.4979, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7083318319429912e-05, + "loss": 3.4931, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074932371919392e-05, + "loss": 3.4835, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066562803212604e-05, + "loss": 3.4863, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7058176855702084e-05, + "loss": 3.49, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049790908191564e-05, + "loss": 3.4739, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7041404960681044e-05, + "loss": 3.4992, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7033035391974253e-05, + "loss": 3.4871, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024649444463733e-05, + "loss": 3.4934, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7016263496953213e-05, + "loss": 3.4874, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007893928246426e-05, + "loss": 3.4872, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999507980735906e-05, + "loss": 3.4864, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6991122033225386e-05, + "loss": 3.4869, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982736085714866e-05, + "loss": 3.484, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6974366517008075e-05, + "loss": 3.481, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965980569497558e-05, + "loss": 3.4998, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957594621987038e-05, + "loss": 3.4871, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6949208674476518e-05, + "loss": 3.4847, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940839105769727e-05, + "loss": 3.4778, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932453158259207e-05, + "loss": 3.4856, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6924067210748687e-05, + "loss": 3.4969, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915681263238167e-05, + "loss": 3.4946, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.690731169453138e-05, + "loss": 3.4902, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.689892574702086e-05, + "loss": 3.4973, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.689053979951034e-05, + "loss": 3.4981, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688215385199982e-05, + "loss": 3.4871, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.687378428329303e-05, + "loss": 3.4979, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686539833578251e-05, + "loss": 3.4895, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6857012388271992e-05, + "loss": 3.4816, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848626440761472e-05, + "loss": 3.4908, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.684025687205468e-05, + "loss": 3.4862, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683187092454416e-05, + "loss": 3.4931, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.682348497703364e-05, + "loss": 3.5015, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681509902952312e-05, + "loss": 3.4994, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.68067130820126e-05, + "loss": 3.4715, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6798343513305813e-05, + "loss": 3.4883, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789957565795293e-05, + "loss": 3.4912, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781571618284773e-05, + "loss": 3.4927, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6773185670774253e-05, + "loss": 3.4857, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764816102067462e-05, + "loss": 3.4828, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756430154556945e-05, + "loss": 3.4909, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6748044207046425e-05, + "loss": 3.4857, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739658259535905e-05, + "loss": 3.484, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6731288690829114e-05, + "loss": 3.495, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722902743318594e-05, + "loss": 3.4897, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714516795808074e-05, + "loss": 3.4981, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6706130848297554e-05, + "loss": 3.4824, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697761279590767e-05, + "loss": 3.4881, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6689375332080247e-05, + "loss": 3.4884, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680989384569727e-05, + "loss": 3.4945, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672603437059207e-05, + "loss": 3.4921, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6664233868352416e-05, + "loss": 3.4837, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.66558479208419e-05, + "loss": 3.4832, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664746197333138e-05, + "loss": 3.4879, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663907602582086e-05, + "loss": 3.4945, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630706457114068e-05, + "loss": 3.4773, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6622320509603548e-05, + "loss": 3.4783, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613934562093028e-05, + "loss": 3.4942, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605548614582508e-05, + "loss": 3.4871, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659717904587572e-05, + "loss": 3.4754, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.65887930983652e-05, + "loss": 3.4836, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.658040715085468e-05, + "loss": 3.4796, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657202120334416e-05, + "loss": 3.494, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656365163463737e-05, + "loss": 3.4876, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6555265687126853e-05, + "loss": 3.4874, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546879739616333e-05, + "loss": 3.4885, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538493792105813e-05, + "loss": 3.5027, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6530124223399022e-05, + "loss": 3.4894, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521738275888502e-05, + "loss": 3.4817, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651335232837798e-05, + "loss": 3.4878, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.650496638086746e-05, + "loss": 3.489, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496596812160674e-05, + "loss": 3.4815, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6488210864650154e-05, + "loss": 3.4835, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479824917139634e-05, + "loss": 3.4807, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471438969629114e-05, + "loss": 3.4928, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6463069400922323e-05, + "loss": 3.4803, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454683453411806e-05, + "loss": 3.4969, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6446297505901286e-05, + "loss": 3.4805, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437911558390766e-05, + "loss": 3.4861, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6429541989683975e-05, + "loss": 3.4819, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6421156042173455e-05, + "loss": 3.5004, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412770094662935e-05, + "loss": 3.4957, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404384147152415e-05, + "loss": 3.4823, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6396014578445628e-05, + "loss": 3.4772, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387628630935108e-05, + "loss": 3.4925, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6379242683424588e-05, + "loss": 3.4846, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370856735914068e-05, + "loss": 3.4939, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6362487167207277e-05, + "loss": 3.4836, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635410121969676e-05, + "loss": 3.4971, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634571527218624e-05, + "loss": 3.488, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.633732932467572e-05, + "loss": 3.4981, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.632895975596893e-05, + "loss": 3.485, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.632057380845841e-05, + "loss": 3.49, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.631218786094789e-05, + "loss": 3.489, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630380191343737e-05, + "loss": 3.4783, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629543234473058e-05, + "loss": 3.4963, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628704639722006e-05, + "loss": 3.4958, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627866044970954e-05, + "loss": 3.4868, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.627027450219902e-05, + "loss": 3.4888, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626190493349223e-05, + "loss": 3.4786, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.853783130645752, + "eval_runtime": 303.486, + "eval_samples_per_second": 1257.359, + "eval_steps_per_second": 39.293, + "step": 1450080 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0022392838238843e+18, + "trial_name": null, + "trial_params": null +}